340 lines
9.3 KiB
Go
Raw Normal View History

2016-01-18 14:10:05 -05:00
package consensus
import (
2017-10-09 23:10:58 +04:00
"encoding/binary"
"fmt"
"hash/crc32"
2017-10-09 23:10:58 +04:00
"io"
"path/filepath"
2016-01-18 14:10:05 -05:00
"time"
"github.com/pkg/errors"
2018-04-09 16:32:43 +02:00
amino "github.com/tendermint/go-amino"
2018-07-01 22:36:49 -04:00
auto "github.com/tendermint/tendermint/libs/autofile"
cmn "github.com/tendermint/tendermint/libs/common"
2018-11-06 13:12:12 +01:00
"github.com/tendermint/tendermint/libs/log"
"github.com/tendermint/tendermint/types"
tmtime "github.com/tendermint/tendermint/types/time"
2016-01-18 14:10:05 -05:00
)
const (
// must be greater than types.BlockPartSizeBytes + a few bytes
2017-12-15 11:42:53 -06:00
maxMsgSizeBytes = 1024 * 1024 // 1MB
)
2016-01-18 14:10:05 -05:00
//--------------------------------------------------------
// types and functions for savings consensus messages
2016-10-28 15:01:14 -07:00
type TimedWALMessage struct {
2017-10-09 23:10:58 +04:00
Time time.Time `json:"time"` // for debugging purposes
Msg WALMessage `json:"msg"`
}
// EndHeightMessage marks the end of the given height inside WAL.
2017-12-06 15:57:00 -06:00
// @internal used by scripts/wal2json util.
2017-10-09 23:10:58 +04:00
type EndHeightMessage struct {
Height int64 `json:"height"`
2016-01-18 14:10:05 -05:00
}
2016-10-28 15:01:14 -07:00
type WALMessage interface{}
2016-01-18 14:10:05 -05:00
2018-04-05 07:05:45 -07:00
func RegisterWALMessages(cdc *amino.Codec) {
cdc.RegisterInterface((*WALMessage)(nil), nil)
cdc.RegisterConcrete(types.EventDataRoundState{}, "tendermint/wal/EventDataRoundState", nil)
cdc.RegisterConcrete(msgInfo{}, "tendermint/wal/MsgInfo", nil)
cdc.RegisterConcrete(timeoutInfo{}, "tendermint/wal/TimeoutInfo", nil)
2018-04-06 13:46:40 -07:00
cdc.RegisterConcrete(EndHeightMessage{}, "tendermint/wal/EndHeightMessage", nil)
2018-04-05 07:05:45 -07:00
}
2016-01-18 14:10:05 -05:00
//--------------------------------------------------------
// Simple write-ahead logger
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 is an interface for any write-ahead logger.
type WAL interface {
Write(WALMessage)
WriteSync(WALMessage)
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
Group() *auto.Group
SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
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
Start() error
Stop() error
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
Wait()
}
2016-01-18 14:10:05 -05:00
// Write ahead logger writes msgs to disk before they are processed.
// Can be used for crash-recovery and deterministic replay
2016-01-18 15:57:57 -05:00
// TODO: currently the wal is overwritten during replay catchup
// give it a mode so it's either reading or appending - must read to end to start appending again
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
type baseWAL struct {
2017-10-04 16:40:45 -04:00
cmn.BaseService
2016-10-28 15:01:14 -07:00
group *auto.Group
2017-10-09 23:10:58 +04:00
enc *WALEncoder
2016-01-18 14:10:05 -05:00
}
func NewWAL(walFile string, groupOptions ...func(*auto.Group)) (*baseWAL, error) {
err := cmn.EnsureDir(filepath.Dir(walFile), 0700)
if err != nil {
return nil, errors.Wrap(err, "failed to ensure WAL directory is in place")
}
group, err := auto.OpenGroup(walFile, groupOptions...)
2016-01-18 14:10:05 -05:00
if err != nil {
return nil, 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
wal := &baseWAL{
2016-10-28 15:01:14 -07:00
group: group,
2017-10-09 23:10:58 +04:00
enc: NewWALEncoder(group),
2016-10-28 15:01:14 -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
wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
2017-05-12 23:07:53 +02:00
return wal, nil
2016-11-16 01:15:39 -05:00
}
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
func (wal *baseWAL) Group() *auto.Group {
return wal.group
}
2018-11-06 13:12:12 +01:00
func (wal *baseWAL) SetLogger(l log.Logger) {
wal.BaseService.Logger = l
wal.group.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
func (wal *baseWAL) OnStart() error {
2016-11-16 01:15:39 -05:00
size, err := wal.group.Head.Size()
if err != nil {
return err
} else if size == 0 {
wal.WriteSync(EndHeightMessage{0})
2016-11-16 01:15:39 -05:00
}
err = wal.group.Start()
2016-11-21 19:16:19 -08:00
return err
2016-01-18 14:10:05 -05:00
}
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
2019-02-06 10:24:43 -05:00
// Stop the underlying autofile group.
// Use Wait() to ensure it's finished shutting down
// before cleaning up files.
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 (wal *baseWAL) OnStop() {
2016-11-21 19:16:19 -08:00
wal.group.Stop()
wal.group.Close()
2016-08-17 23:08:43 -04:00
}
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
2019-02-06 10:24:43 -05:00
// Wait for the underlying autofile group to finish shutting down
// so it's safe to cleanup files.
func (wal *baseWAL) Wait() {
wal.group.Wait()
}
2018-05-20 16:44:08 -04:00
// Write is called in newStep and for each receive on the
2018-05-22 15:39:27 +04:00
// peerMsgQueue and the timeoutTicker.
2018-05-20 16:44:08 -04:00
// NOTE: does not call fsync()
func (wal *baseWAL) Write(msg WALMessage) {
if wal == nil {
return
}
// Write the wal message
if err := wal.enc.Encode(&TimedWALMessage{tmtime.Now(), msg}); err != nil {
panic(fmt.Sprintf("Error writing msg to consensus wal: %v \n\nMessage: %v", err, msg))
}
}
2018-05-20 16:44:08 -04:00
// WriteSync is called when we receive a msg from ourselves
// so that we write to disk before sending signed messages.
// NOTE: calls fsync()
func (wal *baseWAL) WriteSync(msg WALMessage) {
2016-10-28 11:58:09 -07:00
if wal == nil {
return
}
2017-10-09 23:10:58 +04:00
2018-05-20 16:44:08 -04:00
wal.Write(msg)
if err := wal.group.Flush(); err != nil {
panic(fmt.Sprintf("Error flushing consensus wal buf to file. Error: %v \n", err))
}
2016-01-18 14:10:05 -05:00
}
2016-11-16 01:15:39 -05:00
// WALSearchOptions are optional arguments to SearchForEndHeight.
type WALSearchOptions struct {
2017-12-12 13:02:40 -06:00
// IgnoreDataCorruptionErrors set to true will result in skipping data corruption errors.
IgnoreDataCorruptionErrors bool
}
// SearchForEndHeight searches for the EndHeightMessage with the given height
// and returns an auto.GroupReader, whenever it was found or not and an error.
2017-10-09 23:10:58 +04:00
// Group reader will be nil if found equals false.
//
// CONTRACT: caller must close group reader.
func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
2017-10-09 23:10:58 +04:00
var msg *TimedWALMessage
lastHeightFound := int64(-1)
2016-12-22 15:01:02 -05:00
2017-10-09 23:10:58 +04:00
// NOTE: starting from the last file in the group because we're usually
// searching for the last height. See replay.go
min, max := wal.group.MinIndex(), wal.group.MaxIndex()
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
wal.Logger.Info("Searching for height", "height", height, "min", min, "max", max)
2017-10-09 23:10:58 +04:00
for index := max; index >= min; index-- {
gr, err = wal.group.NewReader(index)
if err != nil {
return nil, false, err
}
dec := NewWALDecoder(gr)
for {
msg, err = dec.Decode()
if err == io.EOF {
// OPTIMISATION: no need to look for height in older files if we've seen h < height
if lastHeightFound > 0 && lastHeightFound < height {
gr.Close()
return nil, false, nil
}
2017-10-25 21:54:56 -04:00
// check next file
2017-10-09 23:10:58 +04:00
break
}
if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
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
wal.Logger.Error("Corrupted entry. Skipping...", "err", err)
// do nothing
continue
} else if err != nil {
2017-10-09 23:10:58 +04:00
gr.Close()
return nil, false, err
}
if m, ok := msg.Msg.(EndHeightMessage); ok {
lastHeightFound = m.Height
2017-10-09 23:10:58 +04:00
if m.Height == height { // found
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
wal.Logger.Info("Found", "height", height, "index", index)
2017-10-09 23:10:58 +04:00
return gr, true, nil
}
}
}
gr.Close()
}
return nil, false, nil
}
///////////////////////////////////////////////////////////////////////////////
// A WALEncoder writes custom-encoded WAL messages to an output stream.
//
2018-04-05 07:05:45 -07:00
// Format: 4 bytes CRC sum + 4 bytes length + arbitrary-length value (go-amino encoded)
2017-10-09 23:10:58 +04:00
type WALEncoder struct {
wr io.Writer
}
// NewWALEncoder returns a new encoder that writes to wr.
func NewWALEncoder(wr io.Writer) *WALEncoder {
return &WALEncoder{wr}
}
// Encode writes the custom encoding of v to the stream.
func (enc *WALEncoder) Encode(v *TimedWALMessage) error {
2018-04-05 07:05:45 -07:00
data := cdc.MustMarshalBinaryBare(v)
2017-10-09 23:10:58 +04:00
crc := crc32.Checksum(data, crc32c)
length := uint32(len(data))
totalLength := 8 + int(length)
msg := make([]byte, totalLength)
binary.BigEndian.PutUint32(msg[0:4], crc)
binary.BigEndian.PutUint32(msg[4:8], length)
copy(msg[8:], data)
_, err := enc.wr.Write(msg)
return err
}
///////////////////////////////////////////////////////////////////////////////
// IsDataCorruptionError returns true if data has been corrupted inside WAL.
func IsDataCorruptionError(err error) bool {
_, ok := err.(DataCorruptionError)
return ok
}
2017-12-12 13:02:40 -06:00
// DataCorruptionError is an error that occures if data on disk was corrupted.
type DataCorruptionError struct {
cause error
}
func (e DataCorruptionError) Error() string {
return fmt.Sprintf("DataCorruptionError[%v]", e.cause)
}
func (e DataCorruptionError) Cause() error {
return e.cause
}
2017-10-09 23:10:58 +04:00
// A WALDecoder reads and decodes custom-encoded WAL messages from an input
// stream. See WALEncoder for the format used.
//
// It will also compare the checksums and make sure data size is equal to the
// length from the header. If that is not the case, error will be returned.
type WALDecoder struct {
rd io.Reader
}
// NewWALDecoder returns a new decoder that reads from rd.
func NewWALDecoder(rd io.Reader) *WALDecoder {
return &WALDecoder{rd}
}
2017-10-25 21:54:56 -04:00
// Decode reads the next custom-encoded value from its reader and returns it.
2017-10-09 23:10:58 +04:00
func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
b := make([]byte, 4)
2017-12-11 19:50:05 -06:00
_, err := dec.rd.Read(b)
2017-10-09 23:10:58 +04:00
if err == io.EOF {
return nil, err
}
if 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
return nil, DataCorruptionError{fmt.Errorf("failed to read checksum: %v", err)}
2017-10-09 23:10:58 +04:00
}
crc := binary.BigEndian.Uint32(b)
b = make([]byte, 4)
2017-12-11 19:50:05 -06:00
_, err = dec.rd.Read(b)
2017-10-09 23:10:58 +04:00
if 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
return nil, DataCorruptionError{fmt.Errorf("failed to read length: %v", err)}
2017-10-09 23:10:58 +04:00
}
length := binary.BigEndian.Uint32(b)
if length > maxMsgSizeBytes {
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
return nil, DataCorruptionError{fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)}
}
2017-10-09 23:10:58 +04:00
data := make([]byte, length)
2017-12-11 19:50:05 -06:00
_, err = dec.rd.Read(data)
2017-10-09 23:10:58 +04:00
if 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
return nil, DataCorruptionError{fmt.Errorf("failed to read data: %v", err)}
2017-10-09 23:10:58 +04:00
}
// check checksum before decoding data
actualCRC := crc32.Checksum(data, crc32c)
if actualCRC != crc {
return nil, DataCorruptionError{fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)}
2017-10-09 23:10:58 +04:00
}
2018-04-05 07:05:45 -07:00
var res = new(TimedWALMessage) // nolint: gosimple
err = cdc.UnmarshalBinaryBare(data, res)
2017-10-09 23:10:58 +04:00
if err != nil {
return nil, DataCorruptionError{fmt.Errorf("failed to decode data: %v", err)}
2017-10-09 23:10:58 +04:00
}
return res, 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
type nilWAL struct{}
func (nilWAL) Write(m WALMessage) {}
func (nilWAL) WriteSync(m WALMessage) {}
func (nilWAL) Group() *auto.Group { return nil }
func (nilWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
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, false, nil
}
func (nilWAL) Start() error { return nil }
func (nilWAL) Stop() error { return nil }
func (nilWAL) Wait() {}