1774 lines
61 KiB
Go
Raw Normal View History

2014-08-10 16:35:08 -07:00
package consensus
import (
"bytes"
2014-10-18 01:42:33 -07:00
"fmt"
"reflect"
2017-10-02 15:24:30 -04:00
"runtime/debug"
2014-08-10 16:35:08 -07:00
"sync"
"time"
"github.com/pkg/errors"
2018-07-01 22:36:49 -04:00
cmn "github.com/tendermint/tendermint/libs/common"
"github.com/tendermint/tendermint/libs/fail"
2018-07-01 22:36:49 -04:00
"github.com/tendermint/tendermint/libs/log"
tmtime "github.com/tendermint/tendermint/types/time"
2018-04-05 17:54:26 +03:00
cfg "github.com/tendermint/tendermint/config"
cstypes "github.com/tendermint/tendermint/consensus/types"
tmevents "github.com/tendermint/tendermint/libs/events"
2018-01-01 21:27:38 -05:00
"github.com/tendermint/tendermint/p2p"
2015-04-01 17:30:16 -07:00
sm "github.com/tendermint/tendermint/state"
"github.com/tendermint/tendermint/types"
2014-08-10 16:35:08 -07:00
)
//-----------------------------------------------------------------------------
// Errors
2014-12-30 17:14:54 -08:00
var (
ErrInvalidProposalSignature = errors.New("Error invalid proposal signature")
2015-06-22 19:04:31 -07:00
ErrInvalidProposalPOLRound = errors.New("Error invalid proposal POL round")
2015-08-12 14:00:23 -04:00
ErrAddingVote = errors.New("Error adding vote")
2015-08-26 18:56:34 -04:00
ErrVoteHeightMismatch = errors.New("Error vote height mismatch")
2014-12-30 17:14:54 -08:00
)
2014-10-30 03:32:09 -07:00
//-----------------------------------------------------------------------------
2014-09-14 15:37:32 -07:00
2015-12-05 14:58:12 -05:00
var (
2016-12-23 11:11:22 -05:00
msgQueueSize = 1000
2015-12-05 14:58:12 -05:00
)
// msgs from the reactor which may update the state
2015-12-08 16:00:59 -05:00
type msgInfo struct {
2018-01-01 21:27:38 -05:00
Msg ConsensusMessage `json:"msg"`
PeerID p2p.ID `json:"peer_key"`
2015-12-08 16:00:59 -05:00
}
// internally generated messages which may update the state
2015-12-08 16:00:59 -05:00
type timeoutInfo struct {
Duration time.Duration `json:"duration"`
Height int64 `json:"height"`
Round int `json:"round"`
Step cstypes.RoundStepType `json:"step"`
2015-12-08 16:00:59 -05:00
}
func (ti *timeoutInfo) String() string {
2015-12-22 15:23:22 -05:00
return fmt.Sprintf("%v ; %d/%d %v", ti.Duration, ti.Height, ti.Round, ti.Step)
2015-12-08 16:00:59 -05:00
}
// interface to the mempool
type txNotifier interface {
TxsAvailable() <-chan struct{}
}
// interface to the evidence pool
type evidencePool interface {
AddEvidence(types.Evidence) error
}
2017-07-20 00:05:33 -04:00
// ConsensusState handles execution of the consensus algorithm.
// It processes votes and proposals, and upon reaching agreement,
// commits blocks to the chain and executes them against the application.
// The internal state machine receives input from peers, the internal validator, and from a timer.
type ConsensusState struct {
cmn.BaseService
2014-10-30 03:32:09 -07:00
// config details
config *cfg.ConsensusConfig
2017-09-18 18:12:31 -04:00
privValidator types.PrivValidator // for signing votes
// store blocks and commits
blockStore sm.BlockStore
// create and execute blocks
blockExec *sm.BlockExecutor
// notify us if txs are available
txNotifier txNotifier
// add evidence to the pool
// when it's detected
evpool evidencePool
2016-11-16 20:52:08 -05:00
// internal state
mtx sync.RWMutex
cstypes.RoundState
state sm.State // State until height-1.
2018-01-23 21:41:13 -05:00
// state changes may be triggered by: msgs from peers,
// msgs from ourself, or by timeouts
peerMsgQueue chan msgInfo
internalMsgQueue chan msgInfo
timeoutTicker TimeoutTicker
2015-12-05 14:58:12 -05:00
// information about about added votes and block parts are written on this channel
// so statistics can be computed by reactor
statsMsgQueue chan msgInfo
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
// we use eventBus to trigger msg broadcasts in the reactor,
// and to notify external subscribers, eg. through a websocket
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
eventBus *types.EventBus
// a Write-Ahead Log ensures we can recover from any kind of crash
// and helps us avoid signing conflicting votes
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
wal WAL
replayMode bool // so we don't log signing errors during replay
doWALCatchup bool // determines if we even try to do the catchup
2015-12-22 15:23:22 -05:00
// for tests where we want to limit the number of transitions the state makes
nSteps int
2016-06-26 15:33:11 -04:00
// some functions can be overwritten for testing
decideProposal func(height int64, round int)
doPrevote func(height int64, round int)
2016-06-26 15:33:11 -04:00
setProposal func(proposal *types.Proposal) error
2017-01-12 14:44:42 -05:00
// closed when we finish shutting down
2017-01-12 14:44:42 -05:00
done chan struct{}
2018-05-16 10:28:58 +04:00
// synchronous pubsub between consensus state and reactor.
// state only emits EventNewRoundStep and EventVote
2018-05-16 10:28:58 +04:00
evsw tmevents.EventSwitch
// for reporting metrics
metrics *Metrics
}
// StateOption sets an optional parameter on the ConsensusState.
type StateOption func(*ConsensusState)
2017-07-20 00:05:33 -04:00
// NewConsensusState returns a new ConsensusState.
func NewConsensusState(
config *cfg.ConsensusConfig,
state sm.State,
blockExec *sm.BlockExecutor,
blockStore sm.BlockStore,
txNotifier txNotifier,
evpool evidencePool,
options ...StateOption,
) *ConsensusState {
2014-09-14 15:37:32 -07:00
cs := &ConsensusState{
2016-05-08 15:00:58 -07:00
config: config,
2017-12-27 22:09:48 -05:00
blockExec: blockExec,
blockStore: blockStore,
txNotifier: txNotifier,
peerMsgQueue: make(chan msgInfo, msgQueueSize),
internalMsgQueue: make(chan msgInfo, msgQueueSize),
timeoutTicker: NewTimeoutTicker(),
statsMsgQueue: make(chan msgInfo, msgQueueSize),
2017-01-12 14:44:42 -05:00
done: make(chan struct{}),
doWALCatchup: true,
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
wal: nilWAL{},
evpool: evpool,
2018-05-16 10:28:58 +04:00
evsw: tmevents.NewEventSwitch(),
2018-06-16 11:44:03 +04:00
metrics: NopMetrics(),
2014-09-14 15:37:32 -07:00
}
2016-06-26 15:33:11 -04:00
// set function defaults (may be overwritten before calling Start)
cs.decideProposal = cs.defaultDecideProposal
cs.doPrevote = cs.defaultDoPrevote
cs.setProposal = cs.defaultSetProposal
2015-09-15 16:13:39 -04:00
cs.updateToState(state)
2015-06-24 14:04:40 -07:00
// Don't call scheduleRound0 yet.
// We do that upon Start().
2015-06-19 15:30:10 -07:00
cs.reconstructLastCommit(state)
2017-05-02 11:53:32 +04:00
cs.BaseService = *cmn.NewBaseService(nil, "ConsensusState", cs)
2018-06-16 11:44:03 +04:00
for _, option := range options {
option(cs)
}
return cs
2014-08-10 16:35:08 -07:00
}
//----------------------------------------
// Public interface
2017-05-12 23:07:53 +02:00
// SetLogger implements Service.
func (cs *ConsensusState) SetLogger(l log.Logger) {
cs.BaseService.Logger = l
cs.timeoutTicker.SetLogger(l)
}
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
// SetEventBus sets event bus.
func (cs *ConsensusState) SetEventBus(b *types.EventBus) {
cs.eventBus = b
2017-12-28 19:35:56 -05:00
cs.blockExec.SetEventBus(b)
}
// StateMetrics sets the metrics.
func StateMetrics(metrics *Metrics) StateOption {
return func(cs *ConsensusState) { cs.metrics = metrics }
2018-06-16 11:44:03 +04:00
}
2017-07-20 00:05:33 -04:00
// String returns a string.
func (cs *ConsensusState) String() string {
// better not to access shared variables
return fmt.Sprintf("ConsensusState") //(H:%v R:%v S:%v", cs.Height, cs.Round, cs.Step)
}
2017-07-20 00:05:33 -04:00
// GetState returns a copy of the chain state.
2017-12-27 22:09:48 -05:00
func (cs *ConsensusState) GetState() sm.State {
cs.mtx.RLock()
defer cs.mtx.RUnlock()
2015-01-11 14:27:46 -08:00
return cs.state.Copy()
}
// GetLastHeight returns the last height committed.
// If there were no blocks, returns 0.
func (cs *ConsensusState) GetLastHeight() int64 {
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
2018-11-13 20:32:51 +04:00
cs.mtx.RLock()
defer cs.mtx.RUnlock()
return cs.RoundState.Height - 1
}
fix data race Closes #1442 ``` WARNING: DATA RACE Write at 0x00c4209de7c8 by goroutine 23: github.com/tendermint/tendermint/types.(*Block).fillHeader() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:88 +0x157 github.com/tendermint/tendermint/types.(*Block).Hash() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:104 +0x121 github.com/tendermint/tendermint/types.(*Block).HashesTo() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:135 +0x4f github.com/tendermint/tendermint/consensus.(*ConsensusState).enterPrecommit() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1037 +0x182d github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1425 +0x1a6c github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1318 +0x77 github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:581 +0x7a9 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:539 +0x6c3 Previous read at 0x00c4209de7c8 by goroutine 47: github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*HexBytes).MarshalJSON() <autogenerated>:1 +0x52 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.invokeMarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:433 +0x88 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:82 +0x8d2 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).MarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/amino.go:296 +0x182 github.com/tendermint/tendermint/rpc/lib/types.NewRPCSuccessResponse() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/types/types.go:100 +0x12c github.com/tendermint/tendermint/rpc/lib/server.makeJSONRPCHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:152 +0xab7 net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.(*ServeMux).ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2254 +0xa2 github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:138 +0x4fa net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.serverHandler.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2619 +0xbc net/http.(*conn).serve() /usr/lib/go-1.9/src/net/http/server.go:1801 +0x83b Goroutine 23 (running) created at: github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:250 +0x35b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/reactor.go:69 +0x1b4 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).Start() <autogenerated>:1 +0x43 github.com/tendermint/tendermint/p2p.(*Switch).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/p2p/switch.go:177 +0x124 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/node.(*Node).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/node/node.go:416 +0xa1b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/rpc/test.StartTendermint() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/test/helpers.go:100 +0x5b github.com/tendermint/tendermint/rpc/client_test.TestMain() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/client/main_test.go:17 +0x4c main.main() github.com/tendermint/tendermint/rpc/client/_test/_testmain.go:76 +0x1cd Goroutine 47 (running) created at: net/http.(*Server).Serve() /usr/lib/go-1.9/src/net/http/server.go:2720 +0x37c net/http.Serve() /usr/lib/go-1.9/src/net/http/server.go:2323 +0xe2 github.com/tendermint/tendermint/rpc/lib/server.StartHTTPServer.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:35 +0xb3 ```
2018-04-10 11:15:16 +02:00
// GetRoundState returns a shallow copy of the internal consensus state.
func (cs *ConsensusState) GetRoundState() *cstypes.RoundState {
cs.mtx.RLock()
2014-09-14 15:37:32 -07:00
rs := cs.RoundState // copy
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
2018-11-13 20:32:51 +04:00
cs.mtx.RUnlock()
2014-09-14 15:37:32 -07:00
return &rs
2014-08-10 16:35:08 -07:00
}
fix data race Closes #1442 ``` WARNING: DATA RACE Write at 0x00c4209de7c8 by goroutine 23: github.com/tendermint/tendermint/types.(*Block).fillHeader() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:88 +0x157 github.com/tendermint/tendermint/types.(*Block).Hash() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:104 +0x121 github.com/tendermint/tendermint/types.(*Block).HashesTo() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:135 +0x4f github.com/tendermint/tendermint/consensus.(*ConsensusState).enterPrecommit() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1037 +0x182d github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1425 +0x1a6c github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1318 +0x77 github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:581 +0x7a9 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:539 +0x6c3 Previous read at 0x00c4209de7c8 by goroutine 47: github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*HexBytes).MarshalJSON() <autogenerated>:1 +0x52 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.invokeMarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:433 +0x88 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:82 +0x8d2 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).MarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/amino.go:296 +0x182 github.com/tendermint/tendermint/rpc/lib/types.NewRPCSuccessResponse() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/types/types.go:100 +0x12c github.com/tendermint/tendermint/rpc/lib/server.makeJSONRPCHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:152 +0xab7 net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.(*ServeMux).ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2254 +0xa2 github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:138 +0x4fa net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.serverHandler.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2619 +0xbc net/http.(*conn).serve() /usr/lib/go-1.9/src/net/http/server.go:1801 +0x83b Goroutine 23 (running) created at: github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:250 +0x35b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/reactor.go:69 +0x1b4 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).Start() <autogenerated>:1 +0x43 github.com/tendermint/tendermint/p2p.(*Switch).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/p2p/switch.go:177 +0x124 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/node.(*Node).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/node/node.go:416 +0xa1b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/rpc/test.StartTendermint() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/test/helpers.go:100 +0x5b github.com/tendermint/tendermint/rpc/client_test.TestMain() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/client/main_test.go:17 +0x4c main.main() github.com/tendermint/tendermint/rpc/client/_test/_testmain.go:76 +0x1cd Goroutine 47 (running) created at: net/http.(*Server).Serve() /usr/lib/go-1.9/src/net/http/server.go:2720 +0x37c net/http.Serve() /usr/lib/go-1.9/src/net/http/server.go:2323 +0xe2 github.com/tendermint/tendermint/rpc/lib/server.StartHTTPServer.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:35 +0xb3 ```
2018-04-10 11:15:16 +02:00
// GetRoundStateJSON returns a json of RoundState, marshalled using go-amino.
func (cs *ConsensusState) GetRoundStateJSON() ([]byte, error) {
cs.mtx.RLock()
defer cs.mtx.RUnlock()
fix data race Closes #1442 ``` WARNING: DATA RACE Write at 0x00c4209de7c8 by goroutine 23: github.com/tendermint/tendermint/types.(*Block).fillHeader() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:88 +0x157 github.com/tendermint/tendermint/types.(*Block).Hash() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:104 +0x121 github.com/tendermint/tendermint/types.(*Block).HashesTo() /home/vagrant/go/src/github.com/tendermint/tendermint/types/block.go:135 +0x4f github.com/tendermint/tendermint/consensus.(*ConsensusState).enterPrecommit() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1037 +0x182d github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1425 +0x1a6c github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:1318 +0x77 github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:581 +0x7a9 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:539 +0x6c3 Previous read at 0x00c4209de7c8 by goroutine 47: github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*HexBytes).MarshalJSON() <autogenerated>:1 +0x52 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.invokeMarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:433 +0x88 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:82 +0x8d2 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSONStruct() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:348 +0x539 github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec)._encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:119 +0x83f github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).encodeReflectJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/json-encode.go:50 +0x10e github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino.(*Codec).MarshalJSON() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/go-amino/amino.go:296 +0x182 github.com/tendermint/tendermint/rpc/lib/types.NewRPCSuccessResponse() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/types/types.go:100 +0x12c github.com/tendermint/tendermint/rpc/lib/server.makeJSONRPCHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:152 +0xab7 net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.(*ServeMux).ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2254 +0xa2 github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:138 +0x4fa net/http.HandlerFunc.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:1918 +0x51 net/http.serverHandler.ServeHTTP() /usr/lib/go-1.9/src/net/http/server.go:2619 +0xbc net/http.(*conn).serve() /usr/lib/go-1.9/src/net/http/server.go:1801 +0x83b Goroutine 23 (running) created at: github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/state.go:250 +0x35b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/consensus/reactor.go:69 +0x1b4 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/consensus.(*ConsensusReactor).Start() <autogenerated>:1 +0x43 github.com/tendermint/tendermint/p2p.(*Switch).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/p2p/switch.go:177 +0x124 github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/node.(*Node).OnStart() /home/vagrant/go/src/github.com/tendermint/tendermint/node/node.go:416 +0xa1b github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common.(*BaseService).Start() /home/vagrant/go/src/github.com/tendermint/tendermint/vendor/github.com/tendermint/tmlibs/common/service.go:130 +0x5fc github.com/tendermint/tendermint/rpc/test.StartTendermint() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/test/helpers.go:100 +0x5b github.com/tendermint/tendermint/rpc/client_test.TestMain() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/client/main_test.go:17 +0x4c main.main() github.com/tendermint/tendermint/rpc/client/_test/_testmain.go:76 +0x1cd Goroutine 47 (running) created at: net/http.(*Server).Serve() /usr/lib/go-1.9/src/net/http/server.go:2720 +0x37c net/http.Serve() /usr/lib/go-1.9/src/net/http/server.go:2323 +0xe2 github.com/tendermint/tendermint/rpc/lib/server.StartHTTPServer.func1() /home/vagrant/go/src/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:35 +0xb3 ```
2018-04-10 11:15:16 +02:00
return cdc.MarshalJSON(cs.RoundState)
}
// GetRoundStateSimpleJSON returns a json of RoundStateSimple, marshalled using go-amino.
func (cs *ConsensusState) GetRoundStateSimpleJSON() ([]byte, error) {
cs.mtx.RLock()
defer cs.mtx.RUnlock()
return cdc.MarshalJSON(cs.RoundState.RoundStateSimple())
}
2017-07-20 00:05:33 -04:00
// GetValidators returns a copy of the current validators.
func (cs *ConsensusState) GetValidators() (int64, []*types.Validator) {
cs.mtx.RLock()
defer cs.mtx.RUnlock()
2016-10-14 21:36:42 -04:00
return cs.state.LastBlockHeight, cs.state.Validators.Copy().Validators
}
2017-07-20 00:05:33 -04:00
// SetPrivValidator sets the private validator account for signing votes.
2017-09-18 18:12:31 -04:00
func (cs *ConsensusState) SetPrivValidator(priv types.PrivValidator) {
cs.mtx.Lock()
cs.privValidator = priv
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
2018-11-13 20:32:51 +04:00
cs.mtx.Unlock()
2016-11-16 20:52:08 -05:00
}
2017-07-20 00:05:33 -04:00
// SetTimeoutTicker sets the local timer. It may be useful to overwrite for testing.
func (cs *ConsensusState) SetTimeoutTicker(timeoutTicker TimeoutTicker) {
cs.mtx.Lock()
cs.timeoutTicker = timeoutTicker
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
2018-11-13 20:32:51 +04:00
cs.mtx.Unlock()
}
2017-07-20 00:05:33 -04:00
// LoadCommit loads the commit for a given height.
func (cs *ConsensusState) LoadCommit(height int64) *types.Commit {
cs.mtx.RLock()
defer cs.mtx.RUnlock()
2016-11-16 16:47:31 -05:00
if height == cs.blockStore.Height() {
return cs.blockStore.LoadSeenCommit(height)
}
return cs.blockStore.LoadBlockCommit(height)
}
2017-07-20 00:05:33 -04:00
// OnStart implements cmn.Service.
// It loads the latest state via the WAL, and starts the timeout and receive routines.
func (cs *ConsensusState) OnStart() error {
2018-05-16 10:28:58 +04:00
if err := cs.evsw.Start(); err != nil {
return err
}
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
// we may set the WAL in testing before calling Start,
// so only OpenWAL if its still the nilWAL
if _, ok := cs.wal.(nilWAL); ok {
walFile := cs.config.WalFile()
wal, err := cs.OpenWAL(walFile)
if err != nil {
cs.Logger.Error("Error loading ConsensusState wal", "err", err.Error())
return err
}
cs.wal = wal
}
// we need the timeoutRoutine for replay so
2017-09-06 13:11:47 -04:00
// we don't block on the tick chan.
// NOTE: we will get a build up of garbage go routines
2017-09-06 13:11:47 -04:00
// firing on the tockChan until the receiveRoutine is started
// to deal with them (by that point, at most one will be valid)
2018-05-16 10:28:58 +04:00
if err := cs.timeoutTicker.Start(); err != nil {
2017-09-06 13:11:47 -04:00
return err
}
// we may have lost some votes if the process crashed
// reload from consensus log to catchup
if cs.doWALCatchup {
if err := cs.catchupReplay(cs.Height); err != nil {
WAL: better errors and new fail point (#3246) * privval: more info in errors * wal: change Debug logs to Info * wal: log and return error on corrupted wal instead of panicing * fail: Exit right away instead of sending interupt * consensus: FAIL before handling our own vote allows to replicate #3089: - run using `FAIL_TEST_INDEX=0` - delete some bytes from the end of the WAL - start normally Results in logs like: ``` I[2019-02-03|18:12:58.225] Searching for height module=consensus wal=/Users/ethanbuchman/.tendermint/data/cs.wal/wal height=1 min=0 max=0 E[2019-02-03|18:12:58.225] Error on catchup replay. Proceeding to start ConsensusState anyway module=consensus err="failed to read data: EOF" I[2019-02-03|18:12:58.225] Started node module=main nodeInfo="{ProtocolVersion:{P2P:6 Block:9 App:1} ID_:35e87e93f2e31f305b65a5517fd2102331b56002 ListenAddr:tcp://0.0.0.0:26656 Network:test-chain-J8JvJH Version:0.29.1 Channels:4020212223303800 Moniker:Ethans-MacBook-Pro.local Other:{TxIndex:on RPCAddress:tcp://0.0.0.0:26657}}" E[2019-02-03|18:12:58.226] Couldn't connect to any seeds module=p2p I[2019-02-03|18:12:59.229] Timed out module=consensus dur=998.568ms height=1 round=0 step=RoundStepNewHeight I[2019-02-03|18:12:59.230] enterNewRound(1/0). Current: 1/0/RoundStepNewHeight module=consensus height=1 round=0 I[2019-02-03|18:12:59.230] enterPropose(1/0). Current: 1/0/RoundStepNewRound module=consensus height=1 round=0 I[2019-02-03|18:12:59.230] enterPropose: Our turn to propose module=consensus height=1 round=0 proposer=AD278B7767B05D7FBEB76207024C650988FA77D5 privValidator="PrivValidator{AD278B7767B05D7FBEB76207024C650988FA77D5 LH:1, LR:0, LS:2}" E[2019-02-03|18:12:59.230] enterPropose: Error signing proposal module=consensus height=1 round=0 err="Error signing proposal: Step regression at height 1 round 0. Got 1, last step 2" I[2019-02-03|18:13:02.233] Timed out module=consensus dur=3s height=1 round=0 step=RoundStepPropose I[2019-02-03|18:13:02.233] enterPrevote(1/0). Current: 1/0/RoundStepPropose module=consensus I[2019-02-03|18:13:02.233] enterPrevote: ProposalBlock is nil module=consensus height=1 round=0 E[2019-02-03|18:13:02.234] Error signing vote module=consensus height=1 round=0 vote="Vote{0:AD278B7767B0 1/00/1(Prevote) 000000000000 000000000000 @ 2019-02-04T02:13:02.233897Z}" err="Error signing vote: Conflicting data" ``` Notice the EOF, the step regression, and the conflicting data. * wal: change errors to be DataCorruptionError * exit on corrupt WAL * fix log * fix new line
2019-02-04 13:00:06 -05:00
// don't try to recover from data corruption error
if IsDataCorruptionError(err) {
cs.Logger.Error("Encountered corrupt WAL file", "err", err.Error())
cs.Logger.Error("Please repair the WAL file before restarting")
fmt.Println(`You can attempt to repair the WAL as follows:
----
WALFILE=~/.tendermint/data/cs.wal/wal
cp $WALFILE ${WALFILE}.bak # backup the file
go run scripts/wal2json/main.go $WALFILE > wal.json # this will panic, but can be ignored
rm $WALFILE # remove the corrupt file
go run scripts/json2wal/main.go wal.json $WALFILE # rebuild the file without corruption
----`)
return err
}
cs.Logger.Error("Error on catchup replay. Proceeding to start ConsensusState anyway", "err", err.Error())
// NOTE: if we ever do return an error here,
// make sure to stop the timeoutTicker
}
}
2016-09-09 23:10:23 -04:00
// now start the receiveRoutine
go cs.receiveRoutine(0)
2016-09-09 23:10:23 -04:00
// schedule the first round!
// use GetRoundState so we don't race the receiveRoutine for access
cs.scheduleRound0(cs.GetRoundState())
return nil
}
2015-12-12 17:22:48 -05:00
// timeoutRoutine: receive requests for timeouts on tickChan and fire timeouts on tockChan
// receiveRoutine: serializes processing of proposoals, block parts, votes; coordinates state transitions
func (cs *ConsensusState) startRoutines(maxSteps int) {
err := cs.timeoutTicker.Start()
2017-09-06 13:11:47 -04:00
if err != nil {
2017-09-21 10:56:42 -04:00
cs.Logger.Error("Error starting timeout ticker", "err", err)
2017-10-03 18:12:17 -04:00
return
2017-09-06 13:11:47 -04:00
}
2015-12-12 17:22:48 -05:00
go cs.receiveRoutine(maxSteps)
}
// OnStop implements cmn.Service.
2015-07-21 18:31:01 -07:00
func (cs *ConsensusState) OnStop() {
2018-05-16 10:28:58 +04:00
cs.evsw.Stop()
cs.timeoutTicker.Stop()
// WAL is stopped in receiveRoutine.
2014-10-30 03:32:09 -07:00
}
2017-07-20 00:05:33 -04:00
// Wait waits for the the main routine to return.
2017-01-12 14:44:42 -05:00
// NOTE: be sure to Stop() the event switch and drain
// any event channels or this may deadlock
func (cs *ConsensusState) Wait() {
<-cs.done
}
2017-07-20 00:05:33 -04:00
// OpenWAL opens a file to log all consensus messages and timeouts for deterministic accountability
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
func (cs *ConsensusState) OpenWAL(walFile string) (WAL, error) {
2018-04-09 16:32:43 +02:00
wal, err := NewWAL(walFile)
2016-01-18 14:10:05 -05:00
if err != nil {
cs.Logger.Error("Failed to open WAL for consensus state", "wal", walFile, "err", err)
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
return nil, err
}
2017-05-12 23:07:53 +02:00
wal.SetLogger(cs.Logger.With("wal", walFile))
if err := wal.Start(); err != nil {
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
return nil, err
2017-05-12 23:07:53 +02:00
}
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
return wal, nil
}
2015-12-12 17:22:48 -05:00
//------------------------------------------------------------
2017-07-20 00:05:33 -04:00
// Public interface for passing messages into the consensus state, possibly causing a state transition.
2018-01-01 21:27:38 -05:00
// If peerID == "", the msg is considered internal.
2017-07-20 00:05:33 -04:00
// Messages are added to the appropriate queue (peer or internal).
// If the queue is full, the function may block.
2015-12-12 17:22:48 -05:00
// TODO: should these return anything or let callers just use events?
2017-07-20 00:05:33 -04:00
// AddVote inputs a vote.
2018-01-01 21:27:38 -05:00
func (cs *ConsensusState) AddVote(vote *types.Vote, peerID p2p.ID) (added bool, err error) {
if peerID == "" {
cs.internalMsgQueue <- msgInfo{&VoteMessage{vote}, ""}
} else {
2018-01-01 21:27:38 -05:00
cs.peerMsgQueue <- msgInfo{&VoteMessage{vote}, peerID}
}
// TODO: wait for event?!
return false, nil
}
2017-07-20 00:05:33 -04:00
// SetProposal inputs a proposal.
2018-01-01 21:27:38 -05:00
func (cs *ConsensusState) SetProposal(proposal *types.Proposal, peerID p2p.ID) error {
2018-01-01 21:27:38 -05:00
if peerID == "" {
cs.internalMsgQueue <- msgInfo{&ProposalMessage{proposal}, ""}
} else {
2018-01-01 21:27:38 -05:00
cs.peerMsgQueue <- msgInfo{&ProposalMessage{proposal}, peerID}
}
// TODO: wait for event?!
return nil
}
2017-07-20 00:05:33 -04:00
// AddProposalBlockPart inputs a part of the proposal block.
2018-01-01 21:27:38 -05:00
func (cs *ConsensusState) AddProposalBlockPart(height int64, round int, part *types.Part, peerID p2p.ID) error {
2018-01-01 21:27:38 -05:00
if peerID == "" {
cs.internalMsgQueue <- msgInfo{&BlockPartMessage{height, round, part}, ""}
} else {
2018-01-01 21:27:38 -05:00
cs.peerMsgQueue <- msgInfo{&BlockPartMessage{height, round, part}, peerID}
}
// TODO: wait for event?!
return nil
}
2017-07-20 00:05:33 -04:00
// SetProposalAndBlock inputs the proposal and all block parts.
2018-01-01 21:27:38 -05:00
func (cs *ConsensusState) SetProposalAndBlock(proposal *types.Proposal, block *types.Block, parts *types.PartSet, peerID p2p.ID) error {
if err := cs.SetProposal(proposal, peerID); err != nil {
2017-09-06 13:11:47 -04:00
return err
}
for i := 0; i < parts.Total(); i++ {
part := parts.GetPart(i)
2018-01-01 21:27:38 -05:00
if err := cs.AddProposalBlockPart(proposal.Height, proposal.Round, part, peerID); err != nil {
2017-09-06 13:11:47 -04:00
return err
}
}
2017-09-06 13:11:47 -04:00
return nil
}
2015-12-12 17:22:48 -05:00
//------------------------------------------------------------
// internal functions for managing the state
func (cs *ConsensusState) updateHeight(height int64) {
cs.metrics.Height.Set(float64(height))
2018-06-13 22:40:55 +04:00
cs.Height = height
2015-12-08 16:00:59 -05:00
}
func (cs *ConsensusState) updateRoundStep(round int, step cstypes.RoundStepType) {
2015-12-08 16:00:59 -05:00
cs.Round = round
cs.Step = step
}
// enterNewRound(height, 0) at cs.StartTime.
func (cs *ConsensusState) scheduleRound0(rs *cstypes.RoundState) {
//cs.Logger.Info("scheduleRound0", "now", tmtime.Now(), "startTime", cs.StartTime)
sleepDuration := rs.StartTime.Sub(tmtime.Now())
cs.scheduleTimeout(sleepDuration, rs.Height, 0, cstypes.RoundStepNewHeight)
2015-12-08 16:00:59 -05:00
}
// Attempt to schedule a timeout (by sending timeoutInfo on the tickChan)
func (cs *ConsensusState) scheduleTimeout(duration time.Duration, height int64, round int, step cstypes.RoundStepType) {
cs.timeoutTicker.ScheduleTimeout(timeoutInfo{duration, height, round, step})
2015-06-05 14:15:40 -07:00
}
// send a msg into the receiveRoutine regarding our own proposal, block part, or vote
func (cs *ConsensusState) sendInternalMessage(mi msgInfo) {
select {
case cs.internalMsgQueue <- mi:
default:
// NOTE: using the go-routine means our votes can
// be processed out of order.
// TODO: use CList here for strict determinism and
// attempt push to internalMsgQueue in receiveRoutine
2017-05-02 11:53:32 +04:00
cs.Logger.Info("Internal msg queue is full. Using a go-routine")
go func() { cs.internalMsgQueue <- mi }()
}
}
2016-04-02 09:10:16 -07:00
// Reconstruct LastCommit from SeenCommit, which we saved along with the block,
// (which happens even before saving the state)
2017-12-27 22:09:48 -05:00
func (cs *ConsensusState) reconstructLastCommit(state sm.State) {
if state.LastBlockHeight == 0 {
return
}
2016-04-02 09:10:16 -07:00
seenCommit := cs.blockStore.LoadSeenCommit(state.LastBlockHeight)
lastPrecommits := types.CommitToVoteSet(state.ChainID, seenCommit, state.LastValidators)
if !lastPrecommits.HasTwoThirdsMajority() {
panic("Failed to reconstruct LastCommit: Does not have +2/3 maj")
}
cs.LastCommit = lastPrecommits
}
// Updates ConsensusState and increments height to match that of state.
// The round becomes 0 and cs.Step becomes cstypes.RoundStepNewHeight.
2017-12-27 22:09:48 -05:00
func (cs *ConsensusState) updateToState(state sm.State) {
if cs.CommitRound > -1 && 0 < cs.Height && cs.Height != state.LastBlockHeight {
panic(fmt.Sprintf("updateToState() expected state height of %v but found %v",
cs.Height, state.LastBlockHeight))
}
2017-12-27 22:09:48 -05:00
if !cs.state.IsEmpty() && cs.state.LastBlockHeight+1 != cs.Height {
// This might happen when someone else is mutating cs.state.
// Someone forgot to pass in state.Copy() somewhere?!
panic(fmt.Sprintf("Inconsistent cs.state.LastBlockHeight+1 %v vs cs.Height %v",
cs.state.LastBlockHeight+1, cs.Height))
}
// If state isn't further out than cs.state, just ignore.
// This happens when SwitchToConsensus() is called in the reactor.
// We don't want to reset e.g. the Votes, but we still want to
// signal the new round step, because other services (eg. txNotifier)
// depend on having an up-to-date peer state!
2017-12-27 22:09:48 -05:00
if !cs.state.IsEmpty() && (state.LastBlockHeight <= cs.state.LastBlockHeight) {
2017-05-02 11:53:32 +04:00
cs.Logger.Info("Ignoring updateToState()", "newHeight", state.LastBlockHeight+1, "oldHeight", cs.state.LastBlockHeight+1)
cs.newStep()
return
}
// Reset fields based on state.
validators := state.Validators
lastPrecommits := (*types.VoteSet)(nil)
if cs.CommitRound > -1 && cs.Votes != nil {
if !cs.Votes.Precommits(cs.CommitRound).HasTwoThirdsMajority() {
panic("updateToState(state) called but last Precommit round didn't have +2/3")
}
lastPrecommits = cs.Votes.Precommits(cs.CommitRound)
}
// Next desired block height
height := state.LastBlockHeight + 1
// RoundState fields
cs.updateHeight(height)
cs.updateRoundStep(0, cstypes.RoundStepNewHeight)
if cs.CommitTime.IsZero() {
// "Now" makes it easier to sync up dev nodes.
// We add timeoutCommit to allow transactions
// to be gathered for the first block.
// And alternative solution that relies on clocks:
cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable (#3928) * cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable Previously, if create_empty_blocks was set to false, TM sometimes could create 2 consecutive blocks without actually waiting for timeoutCommit (1 sec. by default). ``` I[2019-08-29|07:32:43.874] Executed block module=state height=47 validTxs=10 invalidTxs=0 I[2019-08-29|07:32:43.876] Committed state module=state height=47 txs=10 appHash=F88C010000000000 I[2019-08-29|07:32:44.885] Executed block module=state height=48 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:44.887] Committed state module=state height=48 txs=2 appHash=FC8C010000000000 I[2019-08-29|07:32:44.908] Executed block module=state height=49 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:44.909] Committed state module=state height=49 txs=8 appHash=8C8D010000000000 I[2019-08-29|07:32:45.886] Executed block module=state height=50 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:45.895] Committed state module=state height=50 txs=2 appHash=908D010000000000 I[2019-08-29|07:32:45.908] Executed block module=state height=51 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:45.909] Committed state module=state height=51 txs=8 appHash=A08D010000000000 ``` This commit fixes that by adding a check to handleTxsAvailable. Fixes #3908 * update changelog * schedule timeoutCommit if StartTime is in the future or SkipTimeoutCommit=true && we DON'T have all the votes * fix TestReactorCreatesBlockWhenEmptyBlocksFalse by checking if we have LastCommit or not * address Ethan's comments
2019-09-10 16:38:37 +04:00
// cs.StartTime = state.LastBlockTime.Add(timeoutCommit)
cs.StartTime = cs.config.Commit(tmtime.Now())
} else {
cs.StartTime = cs.config.Commit(cs.CommitTime)
}
cs.Validators = validators
cs.Proposal = nil
cs.ProposalBlock = nil
cs.ProposalBlockParts = nil
2018-10-15 22:05:13 +02:00
cs.LockedRound = -1
cs.LockedBlock = nil
cs.LockedBlockParts = nil
2018-10-15 22:05:13 +02:00
cs.ValidRound = -1
cs.ValidBlock = nil
cs.ValidBlockParts = nil
cs.Votes = cstypes.NewHeightVoteSet(state.ChainID, height, validators)
cs.CommitRound = -1
cs.LastCommit = lastPrecommits
cs.LastValidators = state.LastValidators
cs: reset triggered timeout precommit (#3310) * Reset TriggeredTimeoutPrecommit as part of updateToState * Add failing test and fix * fix DATA RACE in TestResetTimeoutPrecommitUponNewHeight ``` WARNING: DATA RACE Read at 0x00c001691d28 by goroutine 691: github.com/tendermint/tendermint/consensus.decideProposal() /go/src/github.com/tendermint/tendermint/consensus/common_test.go:133 +0x121 github.com/tendermint/tendermint/consensus.TestResetTimeoutPrecommitUponNewHeight() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:1389 +0x958 testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 Previous write at 0x00c001691d28 by goroutine 931: github.com/tendermint/tendermint/consensus.(*ConsensusState).updateToState() /go/src/github.com/tendermint/tendermint/consensus/state.go:562 +0x5b2 github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1340 +0x141e github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1255 +0x66e github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1() /go/src/github.com/tendermint/tendermint/consensus/state.go:1201 +0x135 github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1232 +0x94b github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1657 +0x132e github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1503 +0x8f github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /go/src/github.com/tendermint/tendermint/consensus/state.go:694 +0xa1e github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:655 +0x7dd github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:655 +0x7dd Goroutine 691 (running) created at: testing.(*T).Run() /usr/local/go/src/testing/testing.go:878 +0x659 testing.runTests.func1() /usr/local/go/src/testing/testing.go:1119 +0xa8 testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 testing.runTests() testing.(*M).Run() /usr/local/go/src/testing/testing.go:1034 +0x2ee main.main() _testmain.go:216 +0x332 ``` * fix another DATA RACE by locking consensus ``` WARNING: DATA RACE Read at 0x00c009b835a8 by goroutine 871: github.com/tendermint/tendermint/consensus.(*ConsensusState).createProposalBlock() /go/src/github.com/tendermint/tendermint/consensus/state.go:955 +0x7c github.com/tendermint/tendermint/consensus.decideProposal() /go/src/github.com/tendermint/tendermint/consensus/common_test.go:127 +0x53 github.com/tendermint/tendermint/consensus.TestResetTimeoutPrecommitUponNewHeight() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:1389 +0x958 testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 Previous write at 0x00c009b835a8 by goroutine 931: github.com/tendermint/tendermint/consensus.(*ConsensusState).updateHeight() /go/src/github.com/tendermint/tendermint/consensus/state.go:446 +0xb7 github.com/tendermint/tendermint/consensus.(*ConsensusState).updateToState() /go/src/github.com/tendermint/tendermint/consensus/state.go:542 +0x22f github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1340 +0x141e github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1255 +0x66e github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1() /go/src/github.com/tendermint/tendermint/consensus/state.go:1201 +0x135 github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit() /go/src/github.com/tendermint/tendermint/consensus/state.go:1232 +0x94b github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1657 +0x132e github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1503 +0x8f github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /go/src/github.com/tendermint/tendermint/consensus/state.go:694 +0xa1e github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:655 +0x7dd github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:642 +0x948 github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:655 +0x7dd ``` * Fix failing test * Delete profile.out * fix data races
2019-02-18 08:29:41 +01:00
cs.TriggeredTimeoutPrecommit = false
cs.state = state
// Finally, broadcast RoundState
cs.newStep()
}
func (cs *ConsensusState) newStep() {
2015-12-22 15:23:22 -05:00
rs := cs.RoundStateEvent()
cs.wal.Write(rs)
cs.nSteps++
// newStep is called by updateToState in NewConsensusState before the eventBus is set!
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
if cs.eventBus != nil {
cs.eventBus.PublishEventNewRoundStep(rs)
2018-05-16 10:28:58 +04:00
cs.evsw.FireEvent(types.EventNewRoundStep, &cs.RoundState)
}
}
//-----------------------------------------
// the main go routines
// receiveRoutine handles messages which may cause state transitions.
// it's argument (n) is the number of messages to process before exiting - use 0 to run forever
// It keeps the RoundState and is the only thing that updates it.
2017-07-25 10:52:14 -04:00
// Updates (state transitions) happen on timeouts, complete proposals, and 2/3 majorities.
// ConsensusState must be locked before any internal state is updated.
func (cs *ConsensusState) receiveRoutine(maxSteps int) {
onExit := func(cs *ConsensusState) {
// NOTE: the internalMsgQueue may have signed messages from our
// priv_val that haven't hit the WAL, but its ok because
// priv_val tracks LastSig
// close wal now that we're done writing to it
cs.wal.Stop()
cs.wal.Wait()
close(cs.done)
}
defer func() {
if r := recover(); r != nil {
2017-10-02 15:24:30 -04:00
cs.Logger.Error("CONSENSUS FAILURE!!!", "err", r, "stack", string(debug.Stack()))
// stop gracefully
//
// NOTE: We most probably shouldn't be running any further when there is
// some unexpected panic. Some unknown error happened, and so we don't
// know if that will result in the validator signing an invalid thing. It
// might be worthwhile to explore a mechanism for manual resuming via
// some console or secure RPC system, but for now, halting the chain upon
// unexpected consensus bugs sounds like the better option.
onExit(cs)
}
}()
for {
if maxSteps > 0 {
if cs.nSteps >= maxSteps {
2017-05-12 23:07:53 +02:00
cs.Logger.Info("reached max steps. exiting receive routine")
cs.nSteps = 0
return
}
}
rs := cs.RoundState
var mi msgInfo
select {
case <-cs.txNotifier.TxsAvailable():
cs.handleTxsAvailable()
case mi = <-cs.peerMsgQueue:
cs.wal.Write(mi)
// handles proposals, block parts, votes
// may generate internal events (votes, complete proposals, 2/3 majorities)
2017-07-25 10:52:14 -04:00
cs.handleMsg(mi)
case mi = <-cs.internalMsgQueue:
cs.wal.WriteSync(mi) // NOTE: fsync
WAL: better errors and new fail point (#3246) * privval: more info in errors * wal: change Debug logs to Info * wal: log and return error on corrupted wal instead of panicing * fail: Exit right away instead of sending interupt * consensus: FAIL before handling our own vote allows to replicate #3089: - run using `FAIL_TEST_INDEX=0` - delete some bytes from the end of the WAL - start normally Results in logs like: ``` I[2019-02-03|18:12:58.225] Searching for height module=consensus wal=/Users/ethanbuchman/.tendermint/data/cs.wal/wal height=1 min=0 max=0 E[2019-02-03|18:12:58.225] Error on catchup replay. Proceeding to start ConsensusState anyway module=consensus err="failed to read data: EOF" I[2019-02-03|18:12:58.225] Started node module=main nodeInfo="{ProtocolVersion:{P2P:6 Block:9 App:1} ID_:35e87e93f2e31f305b65a5517fd2102331b56002 ListenAddr:tcp://0.0.0.0:26656 Network:test-chain-J8JvJH Version:0.29.1 Channels:4020212223303800 Moniker:Ethans-MacBook-Pro.local Other:{TxIndex:on RPCAddress:tcp://0.0.0.0:26657}}" E[2019-02-03|18:12:58.226] Couldn't connect to any seeds module=p2p I[2019-02-03|18:12:59.229] Timed out module=consensus dur=998.568ms height=1 round=0 step=RoundStepNewHeight I[2019-02-03|18:12:59.230] enterNewRound(1/0). Current: 1/0/RoundStepNewHeight module=consensus height=1 round=0 I[2019-02-03|18:12:59.230] enterPropose(1/0). Current: 1/0/RoundStepNewRound module=consensus height=1 round=0 I[2019-02-03|18:12:59.230] enterPropose: Our turn to propose module=consensus height=1 round=0 proposer=AD278B7767B05D7FBEB76207024C650988FA77D5 privValidator="PrivValidator{AD278B7767B05D7FBEB76207024C650988FA77D5 LH:1, LR:0, LS:2}" E[2019-02-03|18:12:59.230] enterPropose: Error signing proposal module=consensus height=1 round=0 err="Error signing proposal: Step regression at height 1 round 0. Got 1, last step 2" I[2019-02-03|18:13:02.233] Timed out module=consensus dur=3s height=1 round=0 step=RoundStepPropose I[2019-02-03|18:13:02.233] enterPrevote(1/0). Current: 1/0/RoundStepPropose module=consensus I[2019-02-03|18:13:02.233] enterPrevote: ProposalBlock is nil module=consensus height=1 round=0 E[2019-02-03|18:13:02.234] Error signing vote module=consensus height=1 round=0 vote="Vote{0:AD278B7767B0 1/00/1(Prevote) 000000000000 000000000000 @ 2019-02-04T02:13:02.233897Z}" err="Error signing vote: Conflicting data" ``` Notice the EOF, the step regression, and the conflicting data. * wal: change errors to be DataCorruptionError * exit on corrupt WAL * fix log * fix new line
2019-02-04 13:00:06 -05:00
if _, ok := mi.Msg.(*VoteMessage); ok {
// we actually want to simulate failing during
// the previous WriteSync, but this isn't easy to do.
// Equivalent would be to fail here and manually remove
// some bytes from the end of the wal.
fail.Fail() // XXX
}
// handles proposals, block parts, votes
2017-07-25 10:52:14 -04:00
cs.handleMsg(mi)
case ti := <-cs.timeoutTicker.Chan(): // tockChan:
cs.wal.Write(ti)
// if the timeout is relevant to the rs
// go to the next step
cs.handleTimeout(ti, rs)
case <-cs.Quit():
onExit(cs)
return
}
}
}
// state transitions on complete-proposal, 2/3-any, 2/3-one
2017-07-25 10:52:14 -04:00
func (cs *ConsensusState) handleMsg(mi msgInfo) {
cs.mtx.Lock()
defer cs.mtx.Unlock()
var (
added bool
err error
)
2018-01-01 21:27:38 -05:00
msg, peerID := mi.Msg, mi.PeerID
switch msg := msg.(type) {
case *ProposalMessage:
// will not cause transition.
// once proposal is set, we can receive block parts
err = cs.setProposal(msg.Proposal)
case *BlockPartMessage:
// if the proposal is complete, we'll enterPrevote or tryFinalizeCommit
added, err = cs.addProposalBlockPart(msg, peerID)
if added {
cs.statsMsgQueue <- mi
}
if err != nil && msg.Round != cs.Round {
2018-05-17 13:59:41 -04:00
cs.Logger.Debug("Received block part from wrong round", "height", cs.Height, "csRound", cs.Round, "blockRound", msg.Round)
err = nil
}
case *VoteMessage:
// attempt to add the vote and dupeout the validator if its a duplicate signature
// if the vote gives us a 2/3-any or 2/3-one, we transition
added, err = cs.tryAddVote(msg.Vote, peerID)
if added {
cs.statsMsgQueue <- mi
}
// if err == ErrAddingVote {
// TODO: punish peer
// We probably don't want to stop the peer here. The vote does not
// necessarily comes from a malicious peer but can be just broadcasted by
// a typical peer.
// https://github.com/tendermint/tendermint/issues/1281
// }
// NOTE: the vote is broadcast to peers by the reactor listening
// for vote events
// TODO: If rs.Height == vote.Height && rs.Round < vote.Round,
// the peer is sending us CatchupCommit precommits.
// We could make note of this and help filter in broadcastHasVoteMessage().
default:
cs.Logger.Error("Unknown msg type", "type", reflect.TypeOf(msg))
return
}
if err != nil { // nolint:staticcheck
// Causes TestReactorValidatorSetChanges to timeout
// https://github.com/tendermint/tendermint/issues/3406
// cs.Logger.Error("Error with msg", "height", cs.Height, "round", cs.Round,
// "peer", peerID, "err", err, "msg", msg)
}
}
func (cs *ConsensusState) handleTimeout(ti timeoutInfo, rs cstypes.RoundState) {
2017-05-02 11:53:32 +04:00
cs.Logger.Debug("Received tock", "timeout", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
// timeouts must be for current height, round, step
2015-12-22 15:23:22 -05:00
if ti.Height != rs.Height || ti.Round < rs.Round || (ti.Round == rs.Round && ti.Step < rs.Step) {
2017-05-02 11:53:32 +04:00
cs.Logger.Debug("Ignoring tock because we're ahead", "height", rs.Height, "round", rs.Round, "step", rs.Step)
return
}
// the timeout will now cause a state transition
cs.mtx.Lock()
defer cs.mtx.Unlock()
2015-12-22 15:23:22 -05:00
switch ti.Step {
case cstypes.RoundStepNewHeight:
// NewRound event fired from enterNewRound.
// XXX: should we fire timeout here (for timeout commit)?
2015-12-22 15:23:22 -05:00
cs.enterNewRound(ti.Height, 0)
case cstypes.RoundStepNewRound:
cs.enterPropose(ti.Height, 0)
case cstypes.RoundStepPropose:
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventTimeoutPropose(cs.RoundStateEvent())
2015-12-22 15:23:22 -05:00
cs.enterPrevote(ti.Height, ti.Round)
case cstypes.RoundStepPrevoteWait:
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventTimeoutWait(cs.RoundStateEvent())
2015-12-22 15:23:22 -05:00
cs.enterPrecommit(ti.Height, ti.Round)
case cstypes.RoundStepPrecommitWait:
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventTimeoutWait(cs.RoundStateEvent())
cs.enterPrecommit(ti.Height, ti.Round)
2015-12-22 15:23:22 -05:00
cs.enterNewRound(ti.Height, ti.Round+1)
default:
panic(fmt.Sprintf("Invalid timeout step: %v", ti.Step))
}
}
func (cs *ConsensusState) handleTxsAvailable() {
cs.mtx.Lock()
defer cs.mtx.Unlock()
cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable (#3928) * cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable Previously, if create_empty_blocks was set to false, TM sometimes could create 2 consecutive blocks without actually waiting for timeoutCommit (1 sec. by default). ``` I[2019-08-29|07:32:43.874] Executed block module=state height=47 validTxs=10 invalidTxs=0 I[2019-08-29|07:32:43.876] Committed state module=state height=47 txs=10 appHash=F88C010000000000 I[2019-08-29|07:32:44.885] Executed block module=state height=48 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:44.887] Committed state module=state height=48 txs=2 appHash=FC8C010000000000 I[2019-08-29|07:32:44.908] Executed block module=state height=49 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:44.909] Committed state module=state height=49 txs=8 appHash=8C8D010000000000 I[2019-08-29|07:32:45.886] Executed block module=state height=50 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:45.895] Committed state module=state height=50 txs=2 appHash=908D010000000000 I[2019-08-29|07:32:45.908] Executed block module=state height=51 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:45.909] Committed state module=state height=51 txs=8 appHash=A08D010000000000 ``` This commit fixes that by adding a check to handleTxsAvailable. Fixes #3908 * update changelog * schedule timeoutCommit if StartTime is in the future or SkipTimeoutCommit=true && we DON'T have all the votes * fix TestReactorCreatesBlockWhenEmptyBlocksFalse by checking if we have LastCommit or not * address Ethan's comments
2019-09-10 16:38:37 +04:00
// We only need to do this for round 0.
if cs.Round != 0 {
return
}
switch cs.Step {
case cstypes.RoundStepNewHeight: // timeoutCommit phase
if cs.needProofBlock(cs.Height) {
// enterPropose will be called by enterNewRound
return
}
// +1ms to ensure RoundStepNewRound timeout always happens after RoundStepNewHeight
timeoutCommit := cs.StartTime.Sub(tmtime.Now()) + 1*time.Millisecond
cs.scheduleTimeout(timeoutCommit, cs.Height, 0, cstypes.RoundStepNewRound)
case cstypes.RoundStepNewRound: // after timeoutCommit
cs.enterPropose(cs.Height, 0)
}
}
2014-10-21 23:30:18 -07:00
//-----------------------------------------------------------------------------
// State functions
// Used internally by handleTimeout and handleMsg to make state transitions
2014-08-10 16:35:08 -07:00
2017-07-20 00:05:33 -04:00
// Enter: `timeoutNewHeight` by startTime (commitTime+timeoutCommit),
cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable (#3928) * cs: check for SkipTimeoutCommit or wait timeout in handleTxsAvailable Previously, if create_empty_blocks was set to false, TM sometimes could create 2 consecutive blocks without actually waiting for timeoutCommit (1 sec. by default). ``` I[2019-08-29|07:32:43.874] Executed block module=state height=47 validTxs=10 invalidTxs=0 I[2019-08-29|07:32:43.876] Committed state module=state height=47 txs=10 appHash=F88C010000000000 I[2019-08-29|07:32:44.885] Executed block module=state height=48 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:44.887] Committed state module=state height=48 txs=2 appHash=FC8C010000000000 I[2019-08-29|07:32:44.908] Executed block module=state height=49 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:44.909] Committed state module=state height=49 txs=8 appHash=8C8D010000000000 I[2019-08-29|07:32:45.886] Executed block module=state height=50 validTxs=2 invalidTxs=0 I[2019-08-29|07:32:45.895] Committed state module=state height=50 txs=2 appHash=908D010000000000 I[2019-08-29|07:32:45.908] Executed block module=state height=51 validTxs=8 invalidTxs=0 I[2019-08-29|07:32:45.909] Committed state module=state height=51 txs=8 appHash=A08D010000000000 ``` This commit fixes that by adding a check to handleTxsAvailable. Fixes #3908 * update changelog * schedule timeoutCommit if StartTime is in the future or SkipTimeoutCommit=true && we DON'T have all the votes * fix TestReactorCreatesBlockWhenEmptyBlocksFalse by checking if we have LastCommit or not * address Ethan's comments
2019-09-10 16:38:37 +04:00
// or, if SkipTimeoutCommit==true, after receiving all precommits from (height,round-1)
// Enter: `timeoutPrecommits` after any +2/3 precommits from (height,round-1)
2017-07-20 00:05:33 -04:00
// Enter: +2/3 precommits for nil at (height,round-1)
// Enter: +2/3 prevotes any or +2/3 precommits for block or any from (height, round)
2015-06-05 14:15:40 -07:00
// NOTE: cs.StartTime was already set for height.
func (cs *ConsensusState) enterNewRound(height int64, round int) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height, "round", round)
if cs.Height != height || round < cs.Round || (cs.Round == round && cs.Step != cstypes.RoundStepNewHeight) {
logger.Debug(fmt.Sprintf("enterNewRound(%v/%v): Invalid args. Current step: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
2014-10-30 03:32:09 -07:00
}
2015-09-09 16:45:53 -04:00
if now := tmtime.Now(); cs.StartTime.After(now) {
2018-05-17 13:59:41 -04:00
logger.Info("Need to set a buffer and log message here for sanity.", "startTime", cs.StartTime, "now", now)
2014-10-30 03:32:09 -07:00
}
logger.Info(fmt.Sprintf("enterNewRound(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
// Increment validators if necessary
2015-06-24 14:04:40 -07:00
validators := cs.Validators
2015-06-05 14:15:40 -07:00
if cs.Round < round {
2015-06-24 14:04:40 -07:00
validators = validators.Copy()
validators.IncrementProposerPriority(round - cs.Round)
2015-06-05 14:15:40 -07:00
}
// Setup new round
2015-12-12 16:25:49 -05:00
// we don't fire newStep for this step,
// but we fire an event, so update the round step first
cs.updateRoundStep(round, cstypes.RoundStepNewRound)
2015-06-05 14:15:40 -07:00
cs.Validators = validators
if round == 0 {
// We've already reset these upon new height,
// and meanwhile we might have received a proposal
// for round 0.
} else {
2018-05-17 13:59:41 -04:00
logger.Info("Resetting Proposal info")
cs.Proposal = nil
cs.ProposalBlock = nil
cs.ProposalBlockParts = nil
}
cs.Votes.SetRound(round + 1) // also track next round (round+1) to allow round-skipping
cs.TriggeredTimeoutPrecommit = false
2015-06-05 14:15:40 -07:00
cs.eventBus.PublishEventNewRound(cs.NewRoundEvent())
cs.metrics.Rounds.Set(float64(round))
2015-09-09 16:45:53 -04:00
2017-07-12 01:02:16 -04:00
// Wait for txs to be available in the mempool
// before we enterPropose in round 0. If the last block changed the app hash,
// we may need an empty "proof" block, and enterPropose immediately.
waitForTxs := cs.config.WaitForTxs() && round == 0 && !cs.needProofBlock(height)
if waitForTxs {
if cs.config.CreateEmptyBlocksInterval > 0 {
cs.scheduleTimeout(cs.config.CreateEmptyBlocksInterval, height, round,
cstypes.RoundStepNewRound)
}
2017-07-13 13:19:44 -04:00
} else {
cs.enterPropose(height, round)
}
2017-07-12 01:02:16 -04:00
}
// needProofBlock returns true on the first height (so the genesis app hash is signed right away)
// and where the last block (height-1) caused the app hash to change
func (cs *ConsensusState) needProofBlock(height int64) bool {
if height == 1 {
return true
}
lastBlockMeta := cs.blockStore.LoadBlockMeta(height - 1)
return !bytes.Equal(cs.state.AppHash, lastBlockMeta.Header.AppHash)
}
// Enter (CreateEmptyBlocks): from enterNewRound(height,round)
// Enter (CreateEmptyBlocks, CreateEmptyBlocksInterval > 0 ): after enterNewRound(height,round), after timeout of CreateEmptyBlocksInterval
// Enter (!CreateEmptyBlocks) : after enterNewRound(height,round), once txs are in the mempool
func (cs *ConsensusState) enterPropose(height int64, round int) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height, "round", round)
if cs.Height != height || round < cs.Round || (cs.Round == round && cstypes.RoundStepPropose <= cs.Step) {
logger.Debug(fmt.Sprintf("enterPropose(%v/%v): Invalid args. Current step: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2014-10-21 01:18:46 -07:00
return
}
logger.Info(fmt.Sprintf("enterPropose(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
2015-12-12 16:25:49 -05:00
defer func() {
// Done enterPropose:
cs.updateRoundStep(round, cstypes.RoundStepPropose)
2015-12-12 16:25:49 -05:00
cs.newStep()
// If we have the whole proposal + POL, then goto Prevote now.
// else, we'll enterPrevote when the rest of the proposal is received (in AddProposalBlockPart),
// or else after timeoutPropose
if cs.isProposalComplete() {
cs.enterPrevote(height, cs.Round)
}
2015-12-12 16:25:49 -05:00
}()
// If we don't get the proposal and all block parts quick enough, enterPrevote
cs.scheduleTimeout(cs.config.Propose(round), height, round, cstypes.RoundStepPropose)
2014-09-14 15:37:32 -07:00
// Nothing more to do if we're not a validator
if cs.privValidator == nil {
2018-05-17 13:59:41 -04:00
logger.Debug("This node is not a validator")
return
}
2015-06-05 14:15:40 -07:00
2018-01-23 21:41:13 -05:00
// if not a validator, we're done
address := cs.privValidator.GetPubKey().Address()
if !cs.Validators.HasAddress(address) {
logger.Debug("This node is not a validator", "addr", address, "vals", cs.Validators)
2018-01-23 21:41:13 -05:00
return
}
2018-05-17 13:59:41 -04:00
logger.Debug("This node is a validator")
if cs.isProposer(address) {
2018-05-17 13:59:41 -04:00
logger.Info("enterPropose: Our turn to propose", "proposer", cs.Validators.GetProposer().Address, "privValidator", cs.privValidator)
2015-08-26 18:56:34 -04:00
cs.decideProposal(height, round)
} else {
2018-05-17 13:59:41 -04:00
logger.Info("enterPropose: Not our turn to propose", "proposer", cs.Validators.GetProposer().Address, "privValidator", cs.privValidator)
2016-06-26 15:33:11 -04:00
}
}
2014-08-10 16:35:08 -07:00
func (cs *ConsensusState) isProposer(address []byte) bool {
return bytes.Equal(cs.Validators.GetProposer().Address, address)
2017-07-11 19:18:15 -04:00
}
func (cs *ConsensusState) defaultDecideProposal(height int64, round int) {
var block *types.Block
var blockParts *types.PartSet
2014-09-14 15:37:32 -07:00
2015-06-05 14:15:40 -07:00
// Decide on block
2018-10-15 22:05:13 +02:00
if cs.ValidBlock != nil {
// If there is valid block, choose that.
block, blockParts = cs.ValidBlock, cs.ValidBlockParts
2014-08-10 16:35:08 -07:00
} else {
2015-06-05 14:15:40 -07:00
// Create a new proposal block from state/txs from the mempool.
block, blockParts = cs.createProposalBlock()
2015-12-01 20:12:01 -08:00
if block == nil { // on error
return
}
2014-08-10 16:35:08 -07:00
}
cs: sync WAL more frequently (#3300) As per #3043, this adds a ticker to sync the WAL every 2s while the WAL is running. * Flush WAL every 2s This adds a ticker that flushes the WAL every 2s while the WAL is running. This is related to #3043. * Fix spelling * Increase timeout to 2mins for slower build environments * Make WAL sync interval configurable * Add TODO to replace testChan with more comprehensive testBus * Remove extraneous debug statement * Remove testChan in favour of using system time As per https://github.com/tendermint/tendermint/pull/3300#discussion_r255886586, this removes the `testChan` WAL member and replaces the approach with a system time-oriented one. In this new approach, we keep track of the system time at which each flush and periodic flush successfully occurred. The naming of the various functions is also updated here to be more consistent with "flushing" as opposed to "sync'ing". * Update naming convention and ensure lock for timestamp update * Add Flush method as part of WAL interface Adds a `Flush` method as part of the WAL interface to enforce the idea that we can manually trigger a WAL flush from outside of the WAL. This is employed in the consensus state management to flush the WAL prior to signing votes/proposals, as per https://github.com/tendermint/tendermint/issues/3043#issuecomment-453853630 * Update CHANGELOG_PENDING * Remove mutex approach and replace with DI The dependency injection approach to dealing with testing concerns could allow similar effects to some kind of "testing bus"-based approach. This commit introduces an example of this, where instead of relying on (potentially fragile) timing of things between the code and the test, we inject code into the function under test that can signal the test through a channel. This allows us to avoid the `time.Sleep()`-based approach previously employed. * Update comment on WAL flushing during vote signing Co-Authored-By: thanethomson <connect@thanethomson.com> * Simplify flush interval definition Co-Authored-By: thanethomson <connect@thanethomson.com> * Expand commentary on WAL disk flushing Co-Authored-By: thanethomson <connect@thanethomson.com> * Add broken test to illustrate WAL sync test problem Removes test-related state (dependency injection code) from the WAL data structure and adds test code to illustrate the problem with using `WALGenerateNBlocks` and `wal.SearchForEndHeight` to test periodic sync'ing. * Fix test error messages * Use WAL group buffer size to check for flush A function is added to `libs/autofile/group.go#Group` in order to return the size of the buffered data (i.e. data that has not yet been flushed to disk). The test now checks that, prior to a `time.Sleep`, the group buffer has data in it. After the `time.Sleep` (during which time the periodic flush should have been called), the buffer should be empty. * Remove config root dir removal from #3291 * Add godoc for NewWAL mentioning periodic sync
2019-02-20 07:45:18 +02:00
// Flush the WAL. Otherwise, we may not recompute the same proposal to sign, and the privValidator will refuse to sign anything.
cs.wal.FlushAndSync()
cs: sync WAL more frequently (#3300) As per #3043, this adds a ticker to sync the WAL every 2s while the WAL is running. * Flush WAL every 2s This adds a ticker that flushes the WAL every 2s while the WAL is running. This is related to #3043. * Fix spelling * Increase timeout to 2mins for slower build environments * Make WAL sync interval configurable * Add TODO to replace testChan with more comprehensive testBus * Remove extraneous debug statement * Remove testChan in favour of using system time As per https://github.com/tendermint/tendermint/pull/3300#discussion_r255886586, this removes the `testChan` WAL member and replaces the approach with a system time-oriented one. In this new approach, we keep track of the system time at which each flush and periodic flush successfully occurred. The naming of the various functions is also updated here to be more consistent with "flushing" as opposed to "sync'ing". * Update naming convention and ensure lock for timestamp update * Add Flush method as part of WAL interface Adds a `Flush` method as part of the WAL interface to enforce the idea that we can manually trigger a WAL flush from outside of the WAL. This is employed in the consensus state management to flush the WAL prior to signing votes/proposals, as per https://github.com/tendermint/tendermint/issues/3043#issuecomment-453853630 * Update CHANGELOG_PENDING * Remove mutex approach and replace with DI The dependency injection approach to dealing with testing concerns could allow similar effects to some kind of "testing bus"-based approach. This commit introduces an example of this, where instead of relying on (potentially fragile) timing of things between the code and the test, we inject code into the function under test that can signal the test through a channel. This allows us to avoid the `time.Sleep()`-based approach previously employed. * Update comment on WAL flushing during vote signing Co-Authored-By: thanethomson <connect@thanethomson.com> * Simplify flush interval definition Co-Authored-By: thanethomson <connect@thanethomson.com> * Expand commentary on WAL disk flushing Co-Authored-By: thanethomson <connect@thanethomson.com> * Add broken test to illustrate WAL sync test problem Removes test-related state (dependency injection code) from the WAL data structure and adds test code to illustrate the problem with using `WALGenerateNBlocks` and `wal.SearchForEndHeight` to test periodic sync'ing. * Fix test error messages * Use WAL group buffer size to check for flush A function is added to `libs/autofile/group.go#Group` in order to return the size of the buffered data (i.e. data that has not yet been flushed to disk). The test now checks that, prior to a `time.Sleep`, the group buffer has data in it. After the `time.Sleep` (during which time the periodic flush should have been called), the buffer should be empty. * Remove config root dir removal from #3291 * Add godoc for NewWAL mentioning periodic sync
2019-02-20 07:45:18 +02:00
2014-09-14 15:37:32 -07:00
// Make proposal
propBlockId := types.BlockID{Hash: block.Hash(), PartsHeader: blockParts.Header()}
proposal := types.NewProposal(height, round, cs.ValidRound, propBlockId)
if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal); err == nil {
2015-12-05 14:58:12 -05:00
// send proposal and block parts on internal msg queue
cs.sendInternalMessage(msgInfo{&ProposalMessage{proposal}, ""})
for i := 0; i < blockParts.Total(); i++ {
part := blockParts.GetPart(i)
cs.sendInternalMessage(msgInfo{&BlockPartMessage{cs.Height, cs.Round, part}, ""})
}
2017-05-02 11:53:32 +04:00
cs.Logger.Info("Signed proposal", "height", height, "round", round, "proposal", proposal)
cs.Logger.Debug(fmt.Sprintf("Signed proposal block: %v", block))
} else if !cs.replayMode {
cs.Logger.Error("enterPropose: Error signing proposal", "height", height, "round", round, "err", err)
2015-06-05 14:15:40 -07:00
}
}
// Returns true if the proposal block is complete &&
// (if POLRound was proposed, we have +2/3 prevotes from there).
2015-06-05 14:15:40 -07:00
func (cs *ConsensusState) isProposalComplete() bool {
if cs.Proposal == nil || cs.ProposalBlock == nil {
return false
}
2015-08-12 14:00:23 -04:00
// we have the proposal. if there's a POLRound,
// make sure we have the prevotes from it too
2015-06-24 14:04:40 -07:00
if cs.Proposal.POLRound < 0 {
return true
}
// if this is false the proposer is lying or we haven't received the POL yet
return cs.Votes.Prevotes(cs.Proposal.POLRound).HasTwoThirdsMajority()
2015-06-05 14:15:40 -07:00
}
// Create the next block to propose and return it.
// We really only need to return the parts, but the block
// is returned for convenience so we can log the proposal block.
2015-12-01 20:12:01 -08:00
// Returns nil block upon error.
2015-08-26 18:56:34 -04:00
// NOTE: keep it side-effect free for clarity.
2015-06-24 14:04:40 -07:00
func (cs *ConsensusState) createProposalBlock() (block *types.Block, blockParts *types.PartSet) {
2016-04-02 09:10:16 -07:00
var commit *types.Commit
2019-08-02 08:53:52 +02:00
switch {
case cs.Height == 1:
2015-06-05 14:15:40 -07:00
// We're creating a proposal for the first block.
2016-04-02 09:10:16 -07:00
// The commit is empty, but not nil.
commit = types.NewCommit(types.BlockID{}, nil)
2019-08-02 08:53:52 +02:00
case cs.LastCommit.HasTwoThirdsMajority():
2016-04-02 09:10:16 -07:00
// Make the commit from LastCommit
commit = cs.LastCommit.MakeCommit()
2019-08-02 08:53:52 +02:00
default:
2015-06-05 14:15:40 -07:00
// This shouldn't happen.
2017-05-02 11:53:32 +04:00
cs.Logger.Error("enterPropose: Cannot propose anything: No commit for the previous block.")
2015-06-05 14:15:40 -07:00
return
}
2015-12-01 20:12:01 -08:00
proposerAddr := cs.privValidator.GetPubKey().Address()
return cs.blockExec.CreateProposalBlock(cs.Height, cs.state, commit, proposerAddr)
2014-08-10 16:35:08 -07:00
}
// Enter: `timeoutPropose` after entering Propose.
2015-06-05 14:15:40 -07:00
// Enter: proposal block and POL is ready.
// Prevote for LockedBlock if we're locked, or ProposalBlock if valid.
2014-10-30 03:32:09 -07:00
// Otherwise vote nil.
func (cs *ConsensusState) enterPrevote(height int64, round int) {
if cs.Height != height || round < cs.Round || (cs.Round == round && cstypes.RoundStepPrevote <= cs.Step) {
cs.Logger.Debug(fmt.Sprintf("enterPrevote(%v/%v): Invalid args. Current step: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
2014-10-21 01:18:46 -07:00
}
2015-09-09 16:45:53 -04:00
2015-12-12 16:25:49 -05:00
defer func() {
// Done enterPrevote:
cs.updateRoundStep(round, cstypes.RoundStepPrevote)
2015-12-12 16:25:49 -05:00
cs.newStep()
}()
cs.Logger.Info(fmt.Sprintf("enterPrevote(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
// Sign and broadcast vote as necessary
cs.doPrevote(height, round)
2015-09-09 16:45:53 -04:00
// Once `addVote` hits any +2/3 prevotes, we will go to PrevoteWait
// (so we have more time to try and collect +2/3 prevotes for a single block)
2015-06-05 14:15:40 -07:00
}
func (cs *ConsensusState) defaultDoPrevote(height int64, round int) {
2017-07-07 16:58:16 -04:00
logger := cs.Logger.With("height", height, "round", round)
2014-10-21 01:18:46 -07:00
// If a block is locked, prevote that.
if cs.LockedBlock != nil {
2017-07-07 16:58:16 -04:00
logger.Info("enterPrevote: Block was locked")
cs.signAddVote(types.PrevoteType, cs.LockedBlock.Hash(), cs.LockedBlockParts.Header())
2014-10-30 03:32:09 -07:00
return
}
2014-10-30 03:32:09 -07:00
// If ProposalBlock is nil, prevote nil.
if cs.ProposalBlock == nil {
2017-07-07 16:58:16 -04:00
logger.Info("enterPrevote: ProposalBlock is nil")
cs.signAddVote(types.PrevoteType, nil, types.PartSetHeader{})
2014-10-30 03:32:09 -07:00
return
2014-10-21 01:18:46 -07:00
}
2014-10-30 03:32:09 -07:00
2017-07-20 00:05:33 -04:00
// Validate proposal block
2017-12-28 19:35:56 -05:00
err := cs.blockExec.ValidateBlock(cs.state, cs.ProposalBlock)
2014-10-21 01:18:46 -07:00
if err != nil {
2014-10-30 03:32:09 -07:00
// ProposalBlock is invalid, prevote nil.
2017-07-07 16:58:16 -04:00
logger.Error("enterPrevote: ProposalBlock is invalid", "err", err)
cs.signAddVote(types.PrevoteType, nil, types.PartSetHeader{})
2014-10-30 03:32:09 -07:00
return
2014-10-21 01:18:46 -07:00
}
2014-10-30 03:32:09 -07:00
// Prevote cs.ProposalBlock
2015-08-12 14:00:23 -04:00
// NOTE: the proposal signature is validated when it is received,
// and the proposal block parts are validated as they are received (against the merkle hash in the proposal)
2017-07-09 18:01:25 -04:00
logger.Info("enterPrevote: ProposalBlock is valid")
cs.signAddVote(types.PrevoteType, cs.ProposalBlock.Hash(), cs.ProposalBlockParts.Header())
2014-10-21 01:18:46 -07:00
}
2015-06-24 18:51:14 -07:00
// Enter: any +2/3 prevotes at next round.
func (cs *ConsensusState) enterPrevoteWait(height int64, round int) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height, "round", round)
if cs.Height != height || round < cs.Round || (cs.Round == round && cstypes.RoundStepPrevoteWait <= cs.Step) {
logger.Debug(fmt.Sprintf("enterPrevoteWait(%v/%v): Invalid args. Current step: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
}
if !cs.Votes.Prevotes(round).HasTwoThirdsAny() {
panic(fmt.Sprintf("enterPrevoteWait(%v/%v), but Prevotes does not have any +2/3 votes", height, round))
}
logger.Info(fmt.Sprintf("enterPrevoteWait(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
2015-12-12 16:25:49 -05:00
defer func() {
// Done enterPrevoteWait:
cs.updateRoundStep(round, cstypes.RoundStepPrevoteWait)
2015-12-12 16:25:49 -05:00
cs.newStep()
}()
2015-06-05 14:15:40 -07:00
// Wait for some more prevotes; enterPrecommit
cs.scheduleTimeout(cs.config.Prevote(round), height, round, cstypes.RoundStepPrevoteWait)
2015-06-05 14:15:40 -07:00
}
// Enter: `timeoutPrevote` after any +2/3 prevotes.
2018-10-15 22:05:13 +02:00
// Enter: `timeoutPrecommit` after any +2/3 precommits.
2017-07-20 00:05:33 -04:00
// Enter: +2/3 precomits for block or nil.
2015-08-26 18:56:34 -04:00
// Lock & precommit the ProposalBlock if we have enough prevotes for it (a POL in this round)
2015-06-05 14:15:40 -07:00
// else, unlock an existing lock and precommit nil if +2/3 of prevotes were nil,
2015-08-12 14:00:23 -04:00
// else, precommit nil otherwise.
func (cs *ConsensusState) enterPrecommit(height int64, round int) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height, "round", round)
if cs.Height != height || round < cs.Round || (cs.Round == round && cstypes.RoundStepPrecommit <= cs.Step) {
logger.Debug(fmt.Sprintf("enterPrecommit(%v/%v): Invalid args. Current step: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
2014-09-14 15:37:32 -07:00
}
2015-09-09 16:45:53 -04:00
logger.Info(fmt.Sprintf("enterPrecommit(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
defer func() {
// Done enterPrecommit:
cs.updateRoundStep(round, cstypes.RoundStepPrecommit)
cs.newStep()
}()
2014-09-14 15:37:32 -07:00
// check for a polka
2016-08-16 14:59:19 -07:00
blockID, ok := cs.Votes.Prevotes(round).TwoThirdsMajority()
2015-06-05 14:15:40 -07:00
2018-05-12 17:36:05 -07:00
// If we don't have a polka, we must precommit nil.
2014-10-30 03:32:09 -07:00
if !ok {
2015-06-05 14:15:40 -07:00
if cs.LockedBlock != nil {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: No +2/3 prevotes during enterPrecommit while we're locked. Precommitting nil")
2015-06-05 14:15:40 -07:00
} else {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: No +2/3 prevotes during enterPrecommit. Precommitting nil.")
2015-06-05 14:15:40 -07:00
}
cs.signAddVote(types.PrecommitType, nil, types.PartSetHeader{})
2014-10-30 03:32:09 -07:00
return
2014-09-14 15:37:32 -07:00
}
2014-08-10 16:35:08 -07:00
2018-05-12 17:36:05 -07:00
// At this point +2/3 prevoted for a particular block or nil.
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventPolka(cs.RoundStateEvent())
2015-09-09 16:45:53 -04:00
2018-05-12 17:36:05 -07:00
// the latest POLRound should be this round.
polRound, _ := cs.Votes.POLInfo()
if polRound < round {
panic(fmt.Sprintf("This POLRound should be %v but got %v", round, polRound))
2015-09-09 16:45:53 -04:00
}
2015-08-12 14:00:23 -04:00
2015-06-05 14:15:40 -07:00
// +2/3 prevoted nil. Unlock and precommit nil.
2016-08-16 14:59:19 -07:00
if len(blockID.Hash) == 0 {
2015-05-04 10:15:58 -07:00
if cs.LockedBlock == nil {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: +2/3 prevoted for nil.")
2015-05-04 10:15:58 -07:00
} else {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: +2/3 prevoted for nil. Unlocking")
2018-10-15 22:05:13 +02:00
cs.LockedRound = -1
2015-05-04 10:15:58 -07:00
cs.LockedBlock = nil
cs.LockedBlockParts = nil
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventUnlock(cs.RoundStateEvent())
2015-05-04 10:15:58 -07:00
}
cs.signAddVote(types.PrecommitType, nil, types.PartSetHeader{})
2014-10-30 03:32:09 -07:00
return
}
2014-09-14 15:37:32 -07:00
2015-06-05 14:15:40 -07:00
// At this point, +2/3 prevoted for a particular block.
2015-08-12 14:00:23 -04:00
// If we're already locked on that block, precommit it, and update the LockedRound
2016-08-16 14:59:19 -07:00
if cs.LockedBlock.HashesTo(blockID.Hash) {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: +2/3 prevoted locked block. Relocking")
2015-08-12 14:00:23 -04:00
cs.LockedRound = round
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventRelock(cs.RoundStateEvent())
cs.signAddVote(types.PrecommitType, blockID.Hash, blockID.PartsHeader)
2014-10-30 03:32:09 -07:00
return
}
2014-09-14 15:37:32 -07:00
2015-06-05 14:15:40 -07:00
// If +2/3 prevoted for proposal block, stage and precommit it
2016-08-16 14:59:19 -07:00
if cs.ProposalBlock.HashesTo(blockID.Hash) {
2018-05-17 13:59:41 -04:00
logger.Info("enterPrecommit: +2/3 prevoted proposal block. Locking", "hash", blockID.Hash)
2015-06-05 14:15:40 -07:00
// Validate the block.
2017-12-28 19:35:56 -05:00
if err := cs.blockExec.ValidateBlock(cs.state, cs.ProposalBlock); err != nil {
panic(fmt.Sprintf("enterPrecommit: +2/3 prevoted for an invalid block: %v", err))
2015-06-05 14:15:40 -07:00
}
2015-06-24 18:51:14 -07:00
cs.LockedRound = round
2015-06-05 14:15:40 -07:00
cs.LockedBlock = cs.ProposalBlock
cs.LockedBlockParts = cs.ProposalBlockParts
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventLock(cs.RoundStateEvent())
cs.signAddVote(types.PrecommitType, blockID.Hash, blockID.PartsHeader)
2014-10-30 03:32:09 -07:00
return
2014-09-14 15:37:32 -07:00
}
2015-09-09 16:45:53 -04:00
// There was a polka in this round for a block we don't have.
// Fetch that block, unlock, and precommit nil.
// The +2/3 prevotes for this round is the POL for our unlock.
// TODO: In the future save the POL prevotes for justification.
2018-10-15 22:05:13 +02:00
cs.LockedRound = -1
2015-06-05 14:15:40 -07:00
cs.LockedBlock = nil
cs.LockedBlockParts = nil
2016-08-16 14:59:19 -07:00
if !cs.ProposalBlockParts.HasHeader(blockID.PartsHeader) {
2015-06-05 14:15:40 -07:00
cs.ProposalBlock = nil
2016-08-16 14:59:19 -07:00
cs.ProposalBlockParts = types.NewPartSetFromHeader(blockID.PartsHeader)
2015-06-05 14:15:40 -07:00
}
new pubsub package comment out failing consensus tests for now rewrite rpc httpclient to use new pubsub package import pubsub as tmpubsub, query as tmquery make event IDs constants EventKey -> EventTypeKey rename EventsPubsub to PubSub mempool does not use pubsub rename eventsSub to pubsub new subscribe API fix channel size issues and consensus tests bugs refactor rpc client add missing discardFromChan method add mutex rename pubsub to eventBus remove IsRunning from WSRPCConnection interface (not needed) add a comment in broadcastNewRoundStepsAndVotes rename registerEventCallbacks to broadcastNewRoundStepsAndVotes See https://dave.cheney.net/2014/03/19/channel-axioms stop eventBuses after reactor tests remove unnecessary Unsubscribe return subscribe helper function move discardFromChan to where it is used subscribe now returns an err this gives us ability to refuse to subscribe if pubsub is at its max capacity. use context for control overflow cache queries handle err when subscribing in replay_test rename testClientID to testSubscriber extract var set channel buffer capacity to 1 in replay_file fix byzantine_test unsubscribe from single event, not all events refactor httpclient to return events to appropriate channels return failing testReplayCrashBeforeWriteVote test fix TestValidatorSetChanges refactor code a bit fix testReplayCrashBeforeWriteVote add comment fix TestValidatorSetChanges fixes from Bucky's review update comment [ci skip] test TxEventBuffer update changelog fix TestValidatorSetChanges (2nd attempt) only do wg.Done when no errors benchmark event bus create pubsub server inside NewEventBus only expose config params (later if needed) set buffer capacity to 0 so we are not testing cache new tx event format: key = "Tx" plus a tag {"tx.hash": XYZ} This should allow to subscribe to all transactions! or a specific one using a query: "tm.events.type = Tx and tx.hash = '013ABF99434...'" use TimeoutCommit instead of afterPublishEventNewBlockTimeout TimeoutCommit is the time a node waits after committing a block, before it goes into the next height. So it will finish everything from the last block, but then wait a bit. The idea is this gives it time to hear more votes from other validators, to strengthen the commit it includes in the next block. But it also gives it time to hear about new transactions. waitForBlockWithUpdatedVals rewrite WAL crash tests Task: test that we can recover from any WAL crash. Solution: the old tests were relying on event hub being run in the same thread (we were injecting the private validator's last signature). when considering a rewrite, we considered two possible solutions: write a "fuzzy" testing system where WAL is crashing upon receiving a new message, or inject failures and trigger them in tests using something like https://github.com/coreos/gofail. remove sleep no cs.Lock around wal.Save test different cases (empty block, non-empty block, ...) comments add comments test 4 cases: empty block, non-empty block, non-empty block with smaller part size, many blocks fixes as per Bucky's last review reset subscriptions on UnsubscribeAll use a simple counter to track message for which we panicked also, set a smaller part size for all test cases
2017-06-26 19:00:30 +04:00
cs.eventBus.PublishEventUnlock(cs.RoundStateEvent())
cs.signAddVote(types.PrecommitType, nil, types.PartSetHeader{})
2015-06-05 14:15:40 -07:00
}
// Enter: any +2/3 precommits for next round.
func (cs *ConsensusState) enterPrecommitWait(height int64, round int) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height, "round", round)
if cs.Height != height || round < cs.Round || (cs.Round == round && cs.TriggeredTimeoutPrecommit) {
logger.Debug(
fmt.Sprintf(
"enterPrecommitWait(%v/%v): Invalid args. "+
"Current state is Height/Round: %v/%v/, TriggeredTimeoutPrecommit:%v",
height, round, cs.Height, cs.Round, cs.TriggeredTimeoutPrecommit))
2015-05-04 10:15:58 -07:00
return
}
2015-06-05 14:15:40 -07:00
if !cs.Votes.Precommits(round).HasTwoThirdsAny() {
panic(fmt.Sprintf("enterPrecommitWait(%v/%v), but Precommits does not have any +2/3 votes", height, round))
2015-06-05 14:15:40 -07:00
}
logger.Info(fmt.Sprintf("enterPrecommitWait(%v/%v). Current: %v/%v/%v", height, round, cs.Height, cs.Round, cs.Step))
2015-05-04 10:15:58 -07:00
2015-12-12 16:25:49 -05:00
defer func() {
// Done enterPrecommitWait:
cs.TriggeredTimeoutPrecommit = true
2015-12-12 16:25:49 -05:00
cs.newStep()
}()
2015-06-05 14:15:40 -07:00
// Wait for some more precommits; enterNewRound
cs.scheduleTimeout(cs.config.Precommit(round), height, round, cstypes.RoundStepPrecommitWait)
2015-12-08 16:00:59 -05:00
2014-08-10 16:35:08 -07:00
}
2015-06-05 14:15:40 -07:00
// Enter: +2/3 precommits for block
func (cs *ConsensusState) enterCommit(height int64, commitRound int) {
2018-05-17 14:06:58 -04:00
logger := cs.Logger.With("height", height, "commitRound", commitRound)
2018-05-17 13:59:41 -04:00
if cs.Height != height || cstypes.RoundStepCommit <= cs.Step {
logger.Debug(fmt.Sprintf("enterCommit(%v/%v): Invalid args. Current step: %v/%v/%v", height, commitRound, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
2014-10-30 03:32:09 -07:00
}
logger.Info(fmt.Sprintf("enterCommit(%v/%v). Current: %v/%v/%v", height, commitRound, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
defer func() {
// Done enterCommit:
// keep cs.Round the same, commitRound points to the right Precommits set.
cs.updateRoundStep(cs.Round, cstypes.RoundStepCommit)
2015-09-15 16:13:39 -04:00
cs.CommitRound = commitRound
cs.CommitTime = tmtime.Now()
cs.newStep()
2015-06-05 14:15:40 -07:00
// Maybe finalize immediately.
2015-09-15 16:13:39 -04:00
cs.tryFinalizeCommit(height)
}()
2016-08-16 14:59:19 -07:00
blockID, ok := cs.Votes.Precommits(commitRound).TwoThirdsMajority()
2014-10-30 03:32:09 -07:00
if !ok {
panic("RunActionCommit() expects +2/3 precommits")
2014-10-30 03:32:09 -07:00
}
2015-06-05 14:15:40 -07:00
// The Locked* fields no longer matter.
// Move them over to ProposalBlock if they match the commit hash,
2015-08-26 18:56:34 -04:00
// otherwise they'll be cleared in updateToState.
2016-08-16 14:59:19 -07:00
if cs.LockedBlock.HashesTo(blockID.Hash) {
2018-05-17 14:06:58 -04:00
logger.Info("Commit is for locked block. Set ProposalBlock=LockedBlock", "blockHash", blockID.Hash)
2014-10-30 03:32:09 -07:00
cs.ProposalBlock = cs.LockedBlock
cs.ProposalBlockParts = cs.LockedBlockParts
}
// If we don't have the block being committed, set up to get it.
2016-08-16 14:59:19 -07:00
if !cs.ProposalBlock.HashesTo(blockID.Hash) {
if !cs.ProposalBlockParts.HasHeader(blockID.PartsHeader) {
2018-05-17 14:06:58 -04:00
logger.Info("Commit is for a block we don't know about. Set ProposalBlock=nil", "proposal", cs.ProposalBlock.Hash(), "commit", blockID.Hash)
2014-10-30 03:32:09 -07:00
// We're getting the wrong block.
// Set up ProposalBlockParts and keep waiting.
cs.ProposalBlock = nil
2016-08-16 14:59:19 -07:00
cs.ProposalBlockParts = types.NewPartSetFromHeader(blockID.PartsHeader)
cs.eventBus.PublishEventValidBlock(cs.RoundStateEvent())
cs.evsw.FireEvent(types.EventValidBlock, &cs.RoundState)
2014-10-30 03:32:09 -07:00
}
// else {
// We just need to keep waiting.
// }
}
2015-06-05 14:15:40 -07:00
}
2015-06-05 14:15:40 -07:00
// If we have the block AND +2/3 commits for it, finalize.
func (cs *ConsensusState) tryFinalizeCommit(height int64) {
2018-05-17 13:59:41 -04:00
logger := cs.Logger.With("height", height)
2015-06-24 14:04:40 -07:00
if cs.Height != height {
panic(fmt.Sprintf("tryFinalizeCommit() cs.Height: %v vs height: %v", cs.Height, height))
}
2015-06-24 14:04:40 -07:00
2016-08-16 14:59:19 -07:00
blockID, ok := cs.Votes.Precommits(cs.CommitRound).TwoThirdsMajority()
if !ok || len(blockID.Hash) == 0 {
2018-05-17 13:59:41 -04:00
logger.Error("Attempt to finalize failed. There was no +2/3 majority, or +2/3 was for <nil>.")
return
2015-06-24 14:04:40 -07:00
}
2016-08-16 14:59:19 -07:00
if !cs.ProposalBlock.HashesTo(blockID.Hash) {
// TODO: this happens every time if we're not a validator (ugly logs)
// TODO: ^^ wait, why does it matter that we're a validator?
2018-05-17 13:59:41 -04:00
logger.Info("Attempt to finalize failed. We don't have the commit block.", "proposal-block", cs.ProposalBlock.Hash(), "commit-block", blockID.Hash)
return
2015-06-24 14:04:40 -07:00
}
// go
cs.finalizeCommit(height)
}
// Increment height and goto cstypes.RoundStepNewHeight
func (cs *ConsensusState) finalizeCommit(height int64) {
if cs.Height != height || cs.Step != cstypes.RoundStepCommit {
cs.Logger.Debug(fmt.Sprintf("finalizeCommit(%v): Invalid args. Current step: %v/%v/%v", height, cs.Height, cs.Round, cs.Step))
2015-06-05 14:15:40 -07:00
return
2014-10-21 01:18:46 -07:00
}
2016-08-16 14:59:19 -07:00
blockID, ok := cs.Votes.Precommits(cs.CommitRound).TwoThirdsMajority()
block, blockParts := cs.ProposalBlock, cs.ProposalBlockParts
2014-10-30 03:32:09 -07:00
2015-06-05 14:15:40 -07:00
if !ok {
panic(fmt.Sprintf("Cannot finalizeCommit, commit does not have two thirds majority"))
2015-06-05 14:15:40 -07:00
}
2016-08-16 14:59:19 -07:00
if !blockParts.HasHeader(blockID.PartsHeader) {
panic(fmt.Sprintf("Expected ProposalBlockParts header to be commit header"))
2015-06-05 14:15:40 -07:00
}
2016-08-16 14:59:19 -07:00
if !block.HashesTo(blockID.Hash) {
panic(fmt.Sprintf("Cannot finalizeCommit, ProposalBlock does not hash to commit hash"))
2015-06-05 14:15:40 -07:00
}
2017-12-28 19:35:56 -05:00
if err := cs.blockExec.ValidateBlock(cs.state, block); err != nil {
panic(fmt.Sprintf("+2/3 committed an invalid block: %v", err))
2014-10-30 03:32:09 -07:00
}
2015-06-05 14:15:40 -07:00
cs.Logger.Info(fmt.Sprintf("Finalizing commit of block with %d txs", block.NumTxs),
2016-08-25 01:39:03 -04:00
"height", block.Height, "hash", block.Hash(), "root", block.AppHash)
cs.Logger.Info(fmt.Sprintf("%v", block))
2016-09-11 15:32:33 -04:00
fail.Fail() // XXX
// Save to blockStore.
if cs.blockStore.Height() < block.Height {
2016-11-19 19:32:35 -05:00
// NOTE: the seenCommit is local justification to commit this block,
// but may differ from the LastCommit included in the next block
precommits := cs.Votes.Precommits(cs.CommitRound)
seenCommit := precommits.MakeCommit()
cs.blockStore.SaveBlock(block, blockParts, seenCommit)
} else {
// Happens during replay if we already saved the block but didn't commit
2017-05-02 11:53:32 +04:00
cs.Logger.Info("Calling finalizeCommit on already stored block", "height", block.Height)
}
2016-09-11 15:32:33 -04:00
fail.Fail() // XXX
2018-05-15 08:48:27 -07:00
// Write EndHeightMessage{} for this height, implying that the blockstore
// has saved the block.
//
// If we crash before writing this EndHeightMessage{}, we will recover by
// running ApplyBlock during the ABCI handshake when we restart. If we
// didn't save the block to the blockstore before writing
// EndHeightMessage{}, we'd have to change WAL replay -- currently it
// complains about replaying for heights where an #ENDHEIGHT entry already
// exists.
//
// Either way, the ConsensusState should not be resumed until we
// successfully call ApplyBlock (ie. later here, or in Handshake after
// restart).
cs.wal.WriteSync(EndHeightMessage{height}) // NOTE: fsync
fail.Fail() // XXX
2018-05-15 08:48:27 -07:00
// Create a copy of the state for staging and an event cache for txs.
stateCopy := cs.state.Copy()
// Execute and commit the block, update and save the state, and update the mempool.
2018-05-15 08:48:27 -07:00
// NOTE The block.AppHash wont reflect these txs until the next block.
2017-12-27 22:09:48 -05:00
var err error
stateCopy, err = cs.blockExec.ApplyBlock(stateCopy, types.BlockID{Hash: block.Hash(), PartsHeader: blockParts.Header()}, block)
2016-11-30 17:28:41 -05:00
if err != nil {
cs.Logger.Error("Error on ApplyBlock. Did the application crash? Please restart tendermint", "err", err)
2017-10-27 10:55:20 -04:00
err := cmn.Kill()
if err != nil {
cs.Logger.Error("Failed to kill this process - please do so manually", "err", err)
}
return
2016-11-30 17:28:41 -05:00
}
2016-09-11 15:32:33 -04:00
fail.Fail() // XXX
// must be called before we update state
2018-06-14 16:09:32 +04:00
cs.recordMetrics(height, block)
2018-06-13 20:38:19 +04:00
2015-12-12 17:22:48 -05:00
// NewHeightStep!
cs.updateToState(stateCopy)
2017-04-15 01:33:30 -04:00
fail.Fail() // XXX
2015-06-24 14:04:40 -07:00
// cs.StartTime is already set.
// Schedule Round0 to start soon.
2016-09-09 23:10:23 -04:00
cs.scheduleRound0(&cs.RoundState)
2015-06-05 14:15:40 -07:00
// By here,
// * cs.Height has been increment to height+1
// * cs.Step is now cstypes.RoundStepNewHeight
2015-06-24 14:04:40 -07:00
// * cs.StartTime is set to when we will start round0.
}
2018-06-14 16:09:32 +04:00
func (cs *ConsensusState) recordMetrics(height int64, block *types.Block) {
cs.metrics.Validators.Set(float64(cs.Validators.Size()))
2018-06-15 14:35:36 +04:00
cs.metrics.ValidatorsPower.Set(float64(cs.Validators.TotalVotingPower()))
2018-06-13 20:38:19 +04:00
missingValidators := 0
2018-06-15 14:35:36 +04:00
missingValidatorsPower := int64(0)
for i, val := range cs.Validators.Validators {
var vote *types.CommitSig
2018-06-13 20:38:19 +04:00
if i < len(block.LastCommit.Precommits) {
vote = block.LastCommit.Precommits[i]
}
if vote == nil {
missingValidators++
2018-06-15 14:35:36 +04:00
missingValidatorsPower += val.VotingPower
2018-06-13 20:38:19 +04:00
}
}
cs.metrics.MissingValidators.Set(float64(missingValidators))
2018-06-15 14:35:36 +04:00
cs.metrics.MissingValidatorsPower.Set(float64(missingValidatorsPower))
cs.metrics.ByzantineValidators.Set(float64(len(block.Evidence.Evidence)))
2018-06-15 14:35:36 +04:00
byzantineValidatorsPower := int64(0)
for _, ev := range block.Evidence.Evidence {
if _, val := cs.Validators.GetByAddress(ev.Address()); val != nil {
byzantineValidatorsPower += val.VotingPower
}
}
cs.metrics.ByzantineValidatorsPower.Set(float64(byzantineValidatorsPower))
if height > 1 {
lastBlockMeta := cs.blockStore.LoadBlockMeta(height - 1)
cs.metrics.BlockIntervalSeconds.Set(
block.Time.Sub(lastBlockMeta.Header.Time).Seconds(),
)
}
2018-06-14 16:09:32 +04:00
cs.metrics.NumTxs.Set(float64(block.NumTxs))
cs.metrics.BlockSizeBytes.Set(float64(block.Size()))
cs.metrics.TotalTxs.Set(float64(block.TotalTxs))
cs.metrics.CommittedHeight.Set(float64(block.Height))
2018-06-13 20:38:19 +04:00
}
2014-10-21 23:30:18 -07:00
//-----------------------------------------------------------------------------
2016-06-26 15:33:11 -04:00
func (cs *ConsensusState) defaultSetProposal(proposal *types.Proposal) error {
2014-10-21 23:30:18 -07:00
// Already have one
2016-06-26 15:33:11 -04:00
// TODO: possibly catch double proposals
2014-10-21 23:30:18 -07:00
if cs.Proposal != nil {
return nil
}
2014-10-30 03:32:09 -07:00
// Does not apply
2014-10-21 23:30:18 -07:00
if proposal.Height != cs.Height || proposal.Round != cs.Round {
return nil
}
// Verify POLRound, which must be -1 or in range [0, proposal.Round).
if proposal.POLRound < -1 ||
(proposal.POLRound >= 0 && proposal.POLRound >= proposal.Round) {
2015-06-22 19:04:31 -07:00
return ErrInvalidProposalPOLRound
}
2014-10-21 23:30:18 -07:00
// Verify signature
2018-03-02 01:50:17 -05:00
if !cs.Validators.GetProposer().PubKey.VerifyBytes(proposal.SignBytes(cs.state.ChainID), proposal.Signature) {
2014-10-21 23:30:18 -07:00
return ErrInvalidProposalSignature
}
cs.Proposal = proposal
// We don't update cs.ProposalBlockParts if it is already set.
// This happens if we're already in cstypes.RoundStepCommit or if there is a valid block in the current round.
// TODO: We can check if Proposal is for a different block as this is a sign of misbehavior!
if cs.ProposalBlockParts == nil {
cs.ProposalBlockParts = types.NewPartSetFromHeader(proposal.BlockID.PartsHeader)
}
cs.Logger.Info("Received proposal", "proposal", proposal)
2014-10-21 23:30:18 -07:00
return nil
}
// NOTE: block is not necessarily valid.
// Asynchronously triggers either enterPrevote (before we timeout of propose) or tryFinalizeCommit, once we have the full block.
func (cs *ConsensusState) addProposalBlockPart(msg *BlockPartMessage, peerID p2p.ID) (added bool, err error) {
height, round, part := msg.Height, msg.Round, msg.Part
2014-10-21 23:30:18 -07:00
// Blocks might be reused, so round mismatch is OK
if cs.Height != height {
cs.Logger.Debug("Received block part from wrong height", "height", height, "round", round)
2014-10-21 23:30:18 -07:00
return false, nil
}
// We're not expecting a block part.
2014-10-30 03:32:09 -07:00
if cs.ProposalBlockParts == nil {
// NOTE: this can happen when we've gone to a higher round and
// then receive parts from the previous round - not necessarily a bad peer.
cs.Logger.Info("Received a block part when we're not expecting any",
"height", height, "round", round, "index", part.Index, "peer", peerID)
return false, nil
2014-10-21 23:30:18 -07:00
}
2018-05-17 13:17:50 -04:00
added, err = cs.ProposalBlockParts.AddPart(part)
2014-10-21 23:30:18 -07:00
if err != nil {
return added, err
}
2014-10-26 13:26:27 -07:00
if added && cs.ProposalBlockParts.IsComplete() {
2015-06-24 18:51:14 -07:00
// Added and completed!
_, err = cdc.UnmarshalBinaryLengthPrefixedReader(
cs.ProposalBlockParts.GetReader(),
&cs.ProposalBlock,
cs.state.ConsensusParams.Block.MaxBytes,
)
2018-04-03 07:03:08 -07:00
if err != nil {
return added, err
2018-04-03 07:03:08 -07:00
}
// NOTE: it's possible to receive complete proposal blocks for future rounds without having the proposal
2017-05-12 23:07:53 +02:00
cs.Logger.Info("Received complete proposal block", "height", cs.ProposalBlock.Height, "hash", cs.ProposalBlock.Hash())
cs.eventBus.PublishEventCompleteProposal(cs.CompleteProposalEvent())
2018-04-17 15:43:40 +02:00
2018-05-12 17:42:37 -07:00
// Update Valid* if we can.
2018-04-17 15:43:40 +02:00
prevotes := cs.Votes.Prevotes(cs.Round)
2018-05-12 17:42:37 -07:00
blockID, hasTwoThirds := prevotes.TwoThirdsMajority()
if hasTwoThirds && !blockID.IsZero() && (cs.ValidRound < cs.Round) {
2018-04-25 16:12:25 +02:00
if cs.ProposalBlock.HashesTo(blockID.Hash) {
2018-05-17 13:59:41 -04:00
cs.Logger.Info("Updating valid block to new proposal block",
"valid-round", cs.Round, "valid-block-hash", cs.ProposalBlock.Hash())
2018-04-17 15:43:40 +02:00
cs.ValidRound = cs.Round
cs.ValidBlock = cs.ProposalBlock
cs.ValidBlockParts = cs.ProposalBlockParts
}
2018-05-12 17:42:37 -07:00
// TODO: In case there is +2/3 majority in Prevotes set for some
// block and cs.ProposalBlock contains different block, either
// proposer is faulty or voting power of faulty processes is more
// than 1/3. We should trigger in the future accountability
// procedure at this point.
2018-04-17 15:43:40 +02:00
}
if cs.Step <= cstypes.RoundStepPropose && cs.isProposalComplete() {
2015-06-24 18:51:14 -07:00
// Move onto the next step
cs.enterPrevote(height, cs.Round)
if hasTwoThirds { // this is optimisation as this will be triggered when prevote is added
cs.enterPrecommit(height, cs.Round)
}
} else if cs.Step == cstypes.RoundStepCommit {
2015-06-24 18:51:14 -07:00
// If we're waiting on the proposal block...
2015-09-15 16:13:39 -04:00
cs.tryFinalizeCommit(height)
}
return added, nil
2014-10-21 23:30:18 -07:00
}
2015-06-24 18:51:14 -07:00
return added, nil
2014-10-21 23:30:18 -07:00
}
2015-08-12 14:00:23 -04:00
// Attempt to add the vote. if its a duplicate signature, dupeout the validator
func (cs *ConsensusState) tryAddVote(vote *types.Vote, peerID p2p.ID) (bool, error) {
added, err := cs.addVote(vote, peerID)
2015-08-12 14:00:23 -04:00
if err != nil {
2015-08-26 18:56:34 -04:00
// If the vote height is off, we'll just ignore it,
2017-11-19 00:57:55 +00:00
// But if it's a conflicting sig, add it to the cs.evpool.
2015-09-09 16:45:53 -04:00
// If it's otherwise invalid, punish peer.
2015-08-26 18:56:34 -04:00
if err == ErrVoteHeightMismatch {
return added, err
2017-07-09 14:10:00 -04:00
} else if voteErr, ok := err.(*types.ErrVoteConflictingVotes); ok {
addr := cs.privValidator.GetPubKey().Address()
if bytes.Equal(vote.ValidatorAddress, addr) {
2017-05-02 11:53:32 +04:00
cs.Logger.Error("Found conflicting vote from ourselves. Did you unsafe_reset a validator?", "height", vote.Height, "round", vote.Round, "type", vote.Type)
return added, err
2016-02-07 16:56:59 -08:00
}
2017-11-02 12:06:48 -06:00
cs.evpool.AddEvidence(voteErr.DuplicateVoteEvidence)
return added, err
2015-08-12 14:00:23 -04:00
} else {
// Either
// 1) bad peer OR
// 2) not a bad peer? this can also err sometimes with "Unexpected step" OR
// 3) tmkms use with multiple validators connecting to a single tmkms instance (https://github.com/tendermint/tendermint/issues/3839).
cs.Logger.Info("Error attempting to add vote", "err", err)
return added, ErrAddingVote
2015-08-12 14:00:23 -04:00
}
}
return added, nil
2015-08-12 14:00:23 -04:00
}
//-----------------------------------------------------------------------------
2018-01-01 21:27:38 -05:00
func (cs *ConsensusState) addVote(vote *types.Vote, peerID p2p.ID) (added bool, err error) {
2017-06-28 11:12:45 -04:00
cs.Logger.Debug("addVote", "voteHeight", vote.Height, "voteType", vote.Type, "valIndex", vote.ValidatorIndex, "csHeight", cs.Height)
2015-06-05 14:15:40 -07:00
// A precommit for the previous height?
// These come in while we wait timeoutCommit
2015-08-26 18:56:34 -04:00
if vote.Height+1 == cs.Height {
if !(cs.Step == cstypes.RoundStepNewHeight && vote.Type == types.PrecommitType) {
2015-08-26 18:56:34 -04:00
// TODO: give the reason ..
// fmt.Errorf("tryAddVote: Wrong height, not a LastCommit straggler commit.")
return added, ErrVoteHeightMismatch
2015-08-26 18:56:34 -04:00
}
added, err = cs.LastCommit.AddVote(vote)
if !added {
return added, err
}
cs.Logger.Info(fmt.Sprintf("Added to lastPrecommits: %v", cs.LastCommit.StringShort()))
cs.eventBus.PublishEventVote(types.EventDataVote{Vote: vote})
2018-05-16 10:28:58 +04:00
cs.evsw.FireEvent(types.EventVote, vote)
// if we can skip timeoutCommit and have all the votes now,
if cs.config.SkipTimeoutCommit && cs.LastCommit.HasAll() {
// go straight to new round (skip timeout commit)
// cs.scheduleTimeout(time.Duration(0), cs.Height, 0, cstypes.RoundStepNewHeight)
cs.enterNewRound(cs.Height, 0)
2015-05-04 11:18:21 -07:00
}
2015-05-04 11:18:21 -07:00
return
2015-06-05 14:15:40 -07:00
}
// Height mismatch is ignored.
// Not necessarily a bad peer, but not favourable behaviour.
if vote.Height != cs.Height {
err = ErrVoteHeightMismatch
cs.Logger.Info("Vote ignored and not added", "voteHeight", vote.Height, "csHeight", cs.Height, "peerID", peerID)
return
}
height := cs.Height
added, err = cs.Votes.AddVote(vote, peerID)
if !added {
// Either duplicate, or error upon cs.Votes.AddByIndex()
return
}
cs.eventBus.PublishEventVote(types.EventDataVote{Vote: vote})
2018-05-16 10:28:58 +04:00
cs.evsw.FireEvent(types.EventVote, vote)
switch vote.Type {
case types.PrevoteType:
prevotes := cs.Votes.Prevotes(vote.Round)
cs.Logger.Info("Added to prevote", "vote", vote, "prevotes", prevotes.StringShort())
2018-05-12 17:36:05 -07:00
// If +2/3 prevotes for a block or nil for *any* round:
if blockID, ok := prevotes.TwoThirdsMajority(); ok {
2018-05-14 16:32:19 -04:00
// There was a polka!
// If we're locked but this is a recent polka, unlock.
// If it matches our ProposalBlock, update the ValidBlock
// Unlock if `cs.LockedRound < vote.Round <= cs.Round`
// NOTE: If vote.Round > cs.Round, we'll deal with it when we get to vote.Round
2018-05-12 17:36:05 -07:00
if (cs.LockedBlock != nil) &&
(cs.LockedRound < vote.Round) &&
(vote.Round <= cs.Round) &&
!cs.LockedBlock.HashesTo(blockID.Hash) {
cs.Logger.Info("Unlocking because of POL.", "lockedRound", cs.LockedRound, "POLRound", vote.Round)
2018-10-15 22:05:13 +02:00
cs.LockedRound = -1
cs.LockedBlock = nil
cs.LockedBlockParts = nil
cs.eventBus.PublishEventUnlock(cs.RoundStateEvent())
}
2018-05-12 17:36:05 -07:00
// Update Valid* if we can.
2018-05-14 16:32:19 -04:00
// NOTE: our proposal block may be nil or not what received a polka..
if len(blockID.Hash) != 0 && (cs.ValidRound < vote.Round) && (vote.Round == cs.Round) {
if cs.ProposalBlock.HashesTo(blockID.Hash) {
cs.Logger.Info(
"Updating ValidBlock because of POL.", "validRound", cs.ValidRound, "POLRound", vote.Round)
cs.ValidRound = vote.Round
cs.ValidBlock = cs.ProposalBlock
cs.ValidBlockParts = cs.ProposalBlockParts
} else {
cs.Logger.Info(
"Valid block we don't know about. Set ProposalBlock=nil",
"proposal", cs.ProposalBlock.Hash(), "blockId", blockID.Hash)
// We're getting the wrong block.
cs.ProposalBlock = nil
}
if !cs.ProposalBlockParts.HasHeader(blockID.PartsHeader) {
cs.ProposalBlockParts = types.NewPartSetFromHeader(blockID.PartsHeader)
}
cs.evsw.FireEvent(types.EventValidBlock, &cs.RoundState)
cs.eventBus.PublishEventValidBlock(cs.RoundStateEvent())
}
}
// If +2/3 prevotes for *anything* for future round:
2019-08-02 08:53:52 +02:00
switch {
case cs.Round < vote.Round && prevotes.HasTwoThirdsAny():
// Round-skip if there is any 2/3+ of votes ahead of us
cs.enterNewRound(height, vote.Round)
2019-08-02 08:53:52 +02:00
case cs.Round == vote.Round && cstypes.RoundStepPrevote <= cs.Step: // current round
blockID, ok := prevotes.TwoThirdsMajority()
if ok && (cs.isProposalComplete() || len(blockID.Hash) == 0) {
cs.enterPrecommit(height, vote.Round)
} else if prevotes.HasTwoThirdsAny() {
cs.enterPrevoteWait(height, vote.Round)
}
2019-08-02 08:53:52 +02:00
case cs.Proposal != nil && 0 <= cs.Proposal.POLRound && cs.Proposal.POLRound == vote.Round:
// If the proposal is now complete, enter prevote of cs.Round.
if cs.isProposalComplete() {
cs.enterPrevote(height, cs.Round)
}
}
2018-05-12 17:36:05 -07:00
case types.PrecommitType:
precommits := cs.Votes.Precommits(vote.Round)
cs.Logger.Info("Added to precommit", "vote", vote, "precommits", precommits.StringShort())
blockID, ok := precommits.TwoThirdsMajority()
if ok {
// Executed as TwoThirdsMajority could be from a higher round
cs.enterNewRound(height, vote.Round)
cs.enterPrecommit(height, vote.Round)
if len(blockID.Hash) != 0 {
cs.enterCommit(height, vote.Round)
if cs.config.SkipTimeoutCommit && precommits.HasAll() {
cs.enterNewRound(cs.Height, 0)
}
} else {
cs.enterPrecommitWait(height, vote.Round)
}
} else if cs.Round <= vote.Round && precommits.HasTwoThirdsAny() {
cs.enterNewRound(height, vote.Round)
cs.enterPrecommitWait(height, vote.Round)
2014-10-30 03:32:09 -07:00
}
default:
panic(fmt.Sprintf("Unexpected vote type %X", vote.Type)) // go-amino should prevent this.
2014-10-21 23:30:18 -07:00
}
2015-06-05 14:15:40 -07:00
return added, err
2014-10-21 23:30:18 -07:00
}
func (cs *ConsensusState) signVote(type_ types.SignedMsgType, hash []byte, header types.PartSetHeader) (*types.Vote, error) {
cs: sync WAL more frequently (#3300) As per #3043, this adds a ticker to sync the WAL every 2s while the WAL is running. * Flush WAL every 2s This adds a ticker that flushes the WAL every 2s while the WAL is running. This is related to #3043. * Fix spelling * Increase timeout to 2mins for slower build environments * Make WAL sync interval configurable * Add TODO to replace testChan with more comprehensive testBus * Remove extraneous debug statement * Remove testChan in favour of using system time As per https://github.com/tendermint/tendermint/pull/3300#discussion_r255886586, this removes the `testChan` WAL member and replaces the approach with a system time-oriented one. In this new approach, we keep track of the system time at which each flush and periodic flush successfully occurred. The naming of the various functions is also updated here to be more consistent with "flushing" as opposed to "sync'ing". * Update naming convention and ensure lock for timestamp update * Add Flush method as part of WAL interface Adds a `Flush` method as part of the WAL interface to enforce the idea that we can manually trigger a WAL flush from outside of the WAL. This is employed in the consensus state management to flush the WAL prior to signing votes/proposals, as per https://github.com/tendermint/tendermint/issues/3043#issuecomment-453853630 * Update CHANGELOG_PENDING * Remove mutex approach and replace with DI The dependency injection approach to dealing with testing concerns could allow similar effects to some kind of "testing bus"-based approach. This commit introduces an example of this, where instead of relying on (potentially fragile) timing of things between the code and the test, we inject code into the function under test that can signal the test through a channel. This allows us to avoid the `time.Sleep()`-based approach previously employed. * Update comment on WAL flushing during vote signing Co-Authored-By: thanethomson <connect@thanethomson.com> * Simplify flush interval definition Co-Authored-By: thanethomson <connect@thanethomson.com> * Expand commentary on WAL disk flushing Co-Authored-By: thanethomson <connect@thanethomson.com> * Add broken test to illustrate WAL sync test problem Removes test-related state (dependency injection code) from the WAL data structure and adds test code to illustrate the problem with using `WALGenerateNBlocks` and `wal.SearchForEndHeight` to test periodic sync'ing. * Fix test error messages * Use WAL group buffer size to check for flush A function is added to `libs/autofile/group.go#Group` in order to return the size of the buffered data (i.e. data that has not yet been flushed to disk). The test now checks that, prior to a `time.Sleep`, the group buffer has data in it. After the `time.Sleep` (during which time the periodic flush should have been called), the buffer should be empty. * Remove config root dir removal from #3291 * Add godoc for NewWAL mentioning periodic sync
2019-02-20 07:45:18 +02:00
// Flush the WAL. Otherwise, we may not recompute the same vote to sign, and the privValidator will refuse to sign anything.
cs.wal.FlushAndSync()
cs: sync WAL more frequently (#3300) As per #3043, this adds a ticker to sync the WAL every 2s while the WAL is running. * Flush WAL every 2s This adds a ticker that flushes the WAL every 2s while the WAL is running. This is related to #3043. * Fix spelling * Increase timeout to 2mins for slower build environments * Make WAL sync interval configurable * Add TODO to replace testChan with more comprehensive testBus * Remove extraneous debug statement * Remove testChan in favour of using system time As per https://github.com/tendermint/tendermint/pull/3300#discussion_r255886586, this removes the `testChan` WAL member and replaces the approach with a system time-oriented one. In this new approach, we keep track of the system time at which each flush and periodic flush successfully occurred. The naming of the various functions is also updated here to be more consistent with "flushing" as opposed to "sync'ing". * Update naming convention and ensure lock for timestamp update * Add Flush method as part of WAL interface Adds a `Flush` method as part of the WAL interface to enforce the idea that we can manually trigger a WAL flush from outside of the WAL. This is employed in the consensus state management to flush the WAL prior to signing votes/proposals, as per https://github.com/tendermint/tendermint/issues/3043#issuecomment-453853630 * Update CHANGELOG_PENDING * Remove mutex approach and replace with DI The dependency injection approach to dealing with testing concerns could allow similar effects to some kind of "testing bus"-based approach. This commit introduces an example of this, where instead of relying on (potentially fragile) timing of things between the code and the test, we inject code into the function under test that can signal the test through a channel. This allows us to avoid the `time.Sleep()`-based approach previously employed. * Update comment on WAL flushing during vote signing Co-Authored-By: thanethomson <connect@thanethomson.com> * Simplify flush interval definition Co-Authored-By: thanethomson <connect@thanethomson.com> * Expand commentary on WAL disk flushing Co-Authored-By: thanethomson <connect@thanethomson.com> * Add broken test to illustrate WAL sync test problem Removes test-related state (dependency injection code) from the WAL data structure and adds test code to illustrate the problem with using `WALGenerateNBlocks` and `wal.SearchForEndHeight` to test periodic sync'ing. * Fix test error messages * Use WAL group buffer size to check for flush A function is added to `libs/autofile/group.go#Group` in order to return the size of the buffered data (i.e. data that has not yet been flushed to disk). The test now checks that, prior to a `time.Sleep`, the group buffer has data in it. After the `time.Sleep` (during which time the periodic flush should have been called), the buffer should be empty. * Remove config root dir removal from #3291 * Add godoc for NewWAL mentioning periodic sync
2019-02-20 07:45:18 +02:00
addr := cs.privValidator.GetPubKey().Address()
valIndex, _ := cs.Validators.GetByAddress(addr)
vote := &types.Vote{
ValidatorAddress: addr,
ValidatorIndex: valIndex,
Height: cs.Height,
Round: cs.Round,
Timestamp: cs.voteTime(),
Type: type_,
BlockID: types.BlockID{Hash: hash, PartsHeader: header},
}
err := cs.privValidator.SignVote(cs.state.ChainID, vote)
2015-08-12 14:00:23 -04:00
return vote, err
}
func (cs *ConsensusState) voteTime() time.Time {
now := tmtime.Now()
minVoteTime := now
// TODO: We should remove next line in case we don't vote for v in case cs.ProposalBlock == nil,
// even if cs.LockedBlock != nil. See https://github.com/tendermint/spec.
timeIotaMs := time.Duration(cs.state.ConsensusParams.Block.TimeIotaMs) * time.Millisecond
if cs.LockedBlock != nil {
// See the BFT time spec https://tendermint.com/docs/spec/consensus/bft-time.html
minVoteTime = cs.LockedBlock.Time.Add(timeIotaMs)
} else if cs.ProposalBlock != nil {
minVoteTime = cs.ProposalBlock.Time.Add(timeIotaMs)
}
if now.After(minVoteTime) {
return now
}
return minVoteTime
}
// sign the vote and publish on internalMsgQueue
func (cs *ConsensusState) signAddVote(type_ types.SignedMsgType, hash []byte, header types.PartSetHeader) *types.Vote {
2016-11-16 20:58:53 -05:00
// if we don't have a key or we're not in the validator set, do nothing
if cs.privValidator == nil || !cs.Validators.HasAddress(cs.privValidator.GetPubKey().Address()) {
2015-08-12 14:00:23 -04:00
return nil
}
vote, err := cs.signVote(type_, hash, header)
if err == nil {
cs.sendInternalMessage(msgInfo{&VoteMessage{vote}, ""})
cs.Logger.Info("Signed and pushed vote", "height", cs.Height, "round", cs.Round, "vote", vote, "err", err)
return vote
}
//if !cs.replayMode {
cs.Logger.Error("Error signing vote", "height", cs.Height, "round", cs.Round, "vote", vote, "err", err)
//}
return nil
}
2014-10-30 03:32:09 -07:00
//---------------------------------------------------------
2015-12-01 20:12:01 -08:00
func CompareHRS(h1 int64, r1 int, s1 cstypes.RoundStepType, h2 int64, r2 int, s2 cstypes.RoundStepType) int {
2015-12-01 20:12:01 -08:00
if h1 < h2 {
return -1
} else if h1 > h2 {
return 1
}
if r1 < r2 {
return -1
} else if r1 > r2 {
return 1
}
if s1 < s2 {
return -1
} else if s1 > s2 {
return 1
}
return 0
}