tendermint/node/node_test.go

311 lines
8.1 KiB
Go
Raw Normal View History

2015-07-21 18:15:40 -04:00
package node
import (
2017-11-08 13:12:48 -05:00
"context"
2018-07-14 14:50:56 +01:00
"fmt"
"net"
2018-07-14 14:50:56 +01:00
"os"
"syscall"
2015-07-21 18:15:40 -04:00
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/tendermint/tendermint/abci/example/kvstore"
cfg "github.com/tendermint/tendermint/config"
"github.com/tendermint/tendermint/crypto/ed25519"
"github.com/tendermint/tendermint/evidence"
cmn "github.com/tendermint/tendermint/libs/common"
dbm "github.com/tendermint/tendermint/libs/db"
2018-07-01 22:36:49 -04:00
"github.com/tendermint/tendermint/libs/log"
mempl "github.com/tendermint/tendermint/mempool"
"github.com/tendermint/tendermint/p2p"
"github.com/tendermint/tendermint/privval"
"github.com/tendermint/tendermint/proxy"
sm "github.com/tendermint/tendermint/state"
2017-11-07 18:08:45 -05:00
"github.com/tendermint/tendermint/types"
tmtime "github.com/tendermint/tendermint/types/time"
"github.com/tendermint/tendermint/version"
2015-07-21 18:15:40 -04:00
)
func TestNodeStartStop(t *testing.T) {
2017-05-04 22:33:08 -04:00
config := cfg.ResetTestRoot("node_node_test")
defer os.RemoveAll(config.RootDir)
2015-12-01 20:12:01 -08:00
2017-11-07 18:08:45 -05:00
// create & start node
2017-09-21 17:08:17 -04:00
n, err := DefaultNewNode(config, log.TestingLogger())
require.NoError(t, err)
err = n.Start()
require.NoError(t, err)
2017-05-02 11:53:32 +04:00
t.Logf("Started node %v", n.sw.NodeInfo())
2017-11-07 18:08:45 -05:00
// wait for the node to produce a block
pubsub 2.0 (#3227) * green pubsub tests :OK: * get rid of clientToQueryMap * Subscribe and SubscribeUnbuffered * start adapting other pkgs to new pubsub * nope * rename MsgAndTags to Message * remove TagMap it does not bring any additional benefits * bring back EventSubscriber * fix test * fix data race in TestStartNextHeightCorrectly ``` Write at 0x00c0001c7418 by goroutine 796: github.com/tendermint/tendermint/consensus.TestStartNextHeightCorrectly() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:1296 +0xad testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 Previous read at 0x00c0001c7418 by goroutine 858: github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1631 +0x1366 github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1476 +0x8f github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /go/src/github.com/tendermint/tendermint/consensus/state.go:667 +0xa1e github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:628 +0x794 Goroutine 796 (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() /usr/local/go/src/testing/testing.go:1117 +0x4ee testing.(*M).Run() /usr/local/go/src/testing/testing.go:1034 +0x2ee main.main() _testmain.go:214 +0x332 Goroutine 858 (running) created at: github.com/tendermint/tendermint/consensus.(*ConsensusState).startRoutines() /go/src/github.com/tendermint/tendermint/consensus/state.go:334 +0x221 github.com/tendermint/tendermint/consensus.startTestRound() /go/src/github.com/tendermint/tendermint/consensus/common_test.go:122 +0x63 github.com/tendermint/tendermint/consensus.TestStateFullRound1() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:255 +0x397 testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 ``` * fixes after my own review * fix formatting * wait 100ms before kicking a subscriber out + a test for indexer_service * fixes after my second review * no timeout * add changelog entries * fix merge conflicts * fix typos after Thane's review Co-Authored-By: melekes <anton.kalyaev@gmail.com> * reformat code * rewrite indexer service in the attempt to fix failing test https://github.com/tendermint/tendermint/pull/3227/#issuecomment-462316527 * Revert "rewrite indexer service in the attempt to fix failing test" This reverts commit 0d9107a098230de7138abb1c201877c246e89ed1. * another attempt to fix indexer * fixes after Ethan's review * use unbuffered channel when indexing transactions Refs https://github.com/tendermint/tendermint/pull/3227#discussion_r258786716 * add a comment for EventBus#SubscribeUnbuffered * format code
2019-02-23 08:11:27 +04:00
blocksSub, err := n.EventBus().Subscribe(context.Background(), "node_test", types.EventQueryNewBlock)
require.NoError(t, err)
select {
pubsub 2.0 (#3227) * green pubsub tests :OK: * get rid of clientToQueryMap * Subscribe and SubscribeUnbuffered * start adapting other pkgs to new pubsub * nope * rename MsgAndTags to Message * remove TagMap it does not bring any additional benefits * bring back EventSubscriber * fix test * fix data race in TestStartNextHeightCorrectly ``` Write at 0x00c0001c7418 by goroutine 796: github.com/tendermint/tendermint/consensus.TestStartNextHeightCorrectly() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:1296 +0xad testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 Previous read at 0x00c0001c7418 by goroutine 858: github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1631 +0x1366 github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote() /go/src/github.com/tendermint/tendermint/consensus/state.go:1476 +0x8f github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg() /go/src/github.com/tendermint/tendermint/consensus/state.go:667 +0xa1e github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine() /go/src/github.com/tendermint/tendermint/consensus/state.go:628 +0x794 Goroutine 796 (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() /usr/local/go/src/testing/testing.go:1117 +0x4ee testing.(*M).Run() /usr/local/go/src/testing/testing.go:1034 +0x2ee main.main() _testmain.go:214 +0x332 Goroutine 858 (running) created at: github.com/tendermint/tendermint/consensus.(*ConsensusState).startRoutines() /go/src/github.com/tendermint/tendermint/consensus/state.go:334 +0x221 github.com/tendermint/tendermint/consensus.startTestRound() /go/src/github.com/tendermint/tendermint/consensus/common_test.go:122 +0x63 github.com/tendermint/tendermint/consensus.TestStateFullRound1() /go/src/github.com/tendermint/tendermint/consensus/state_test.go:255 +0x397 testing.tRunner() /usr/local/go/src/testing/testing.go:827 +0x162 ``` * fixes after my own review * fix formatting * wait 100ms before kicking a subscriber out + a test for indexer_service * fixes after my second review * no timeout * add changelog entries * fix merge conflicts * fix typos after Thane's review Co-Authored-By: melekes <anton.kalyaev@gmail.com> * reformat code * rewrite indexer service in the attempt to fix failing test https://github.com/tendermint/tendermint/pull/3227/#issuecomment-462316527 * Revert "rewrite indexer service in the attempt to fix failing test" This reverts commit 0d9107a098230de7138abb1c201877c246e89ed1. * another attempt to fix indexer * fixes after Ethan's review * use unbuffered channel when indexing transactions Refs https://github.com/tendermint/tendermint/pull/3227#discussion_r258786716 * add a comment for EventBus#SubscribeUnbuffered * format code
2019-02-23 08:11:27 +04:00
case <-blocksSub.Out():
case <-blocksSub.Cancelled():
t.Fatal("blocksSub was cancelled")
2018-05-20 16:44:08 -04:00
case <-time.After(10 * time.Second):
2017-11-07 18:08:45 -05:00
t.Fatal("timed out waiting for the node to produce a block")
}
2017-11-07 18:08:45 -05:00
// stop the node
2015-07-21 18:15:40 -04:00
go func() {
n.Stop()
}()
2015-07-21 18:15:40 -04:00
select {
case <-n.Quit():
case <-time.After(5 * time.Second):
2018-07-14 14:50:56 +01:00
pid := os.Getpid()
p, err := os.FindProcess(pid)
if err != nil {
panic(err)
}
err = p.Signal(syscall.SIGABRT)
fmt.Println(err)
2015-07-21 18:15:40 -04:00
t.Fatal("timed out waiting for shutdown")
}
}
func TestSplitAndTrimEmpty(t *testing.T) {
testCases := []struct {
s string
sep string
cutset string
expected []string
}{
{"a,b,c", ",", " ", []string{"a", "b", "c"}},
{" a , b , c ", ",", " ", []string{"a", "b", "c"}},
{" a, b, c ", ",", " ", []string{"a", "b", "c"}},
{" a, ", ",", " ", []string{"a"}},
{" ", ",", " ", []string{}},
}
for _, tc := range testCases {
assert.Equal(t, tc.expected, splitAndTrimEmpty(tc.s, tc.sep, tc.cutset), "%s", tc.s)
}
}
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
func TestNodeDelayedStart(t *testing.T) {
config := cfg.ResetTestRoot("node_delayed_start_test")
defer os.RemoveAll(config.RootDir)
now := tmtime.Now()
// create & start node
n, err := DefaultNewNode(config, log.TestingLogger())
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
n.GenesisDoc().GenesisTime = now.Add(2 * time.Second)
require.NoError(t, err)
n.Start()
startTime := tmtime.Now()
assert.Equal(t, true, startTime.After(n.GenesisDoc().GenesisTime))
}
func TestNodeSetAppVersion(t *testing.T) {
config := cfg.ResetTestRoot("node_app_version_test")
defer os.RemoveAll(config.RootDir)
// create & start node
n, err := DefaultNewNode(config, log.TestingLogger())
require.NoError(t, err)
// default config uses the kvstore app
var appVersion version.Protocol = kvstore.ProtocolVersion
// check version is set in state
state := sm.LoadState(n.stateDB)
assert.Equal(t, state.Version.Consensus.App, appVersion)
// check version is set in node info
assert.Equal(t, n.nodeInfo.(p2p.DefaultNodeInfo).ProtocolVersion.App, appVersion)
}
func TestNodeSetPrivValTCP(t *testing.T) {
addr := "tcp://" + testFreeAddr(t)
config := cfg.ResetTestRoot("node_priv_val_tcp_test")
defer os.RemoveAll(config.RootDir)
config.BaseConfig.PrivValidatorListenAddr = addr
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
dialer := privval.DialTCPFn(addr, 100*time.Millisecond, ed25519.GenPrivKey())
pvsc := privval.NewRemoteSigner(
log.TestingLogger(),
config.ChainID(),
types.NewMockPV(),
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
dialer,
)
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
privval.RemoteSignerConnDeadline(100 * time.Millisecond)(pvsc)
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
go func() {
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
err := pvsc.Start()
if err != nil {
panic(err)
}
}()
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
defer pvsc.Stop()
n, err := DefaultNewNode(config, log.TestingLogger())
require.NoError(t, err)
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
assert.IsType(t, &privval.SocketVal{}, n.PrivValidator())
}
// address without a protocol must result in error
func TestPrivValidatorListenAddrNoProtocol(t *testing.T) {
addrNoPrefix := testFreeAddr(t)
config := cfg.ResetTestRoot("node_priv_val_tcp_test")
defer os.RemoveAll(config.RootDir)
config.BaseConfig.PrivValidatorListenAddr = addrNoPrefix
_, err := DefaultNewNode(config, log.TestingLogger())
assert.Error(t, err)
}
func TestNodeSetPrivValIPC(t *testing.T) {
tmpfile := "/tmp/kms." + cmn.RandStr(6) + ".sock"
defer os.Remove(tmpfile) // clean up
config := cfg.ResetTestRoot("node_priv_val_tcp_test")
defer os.RemoveAll(config.RootDir)
config.BaseConfig.PrivValidatorListenAddr = "unix://" + tmpfile
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
dialer := privval.DialUnixFn(tmpfile)
pvsc := privval.NewRemoteSigner(
log.TestingLogger(),
config.ChainID(),
types.NewMockPV(),
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
2019-01-13 20:31:31 +01:00
dialer,
)
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
privval.RemoteSignerConnDeadline(100 * time.Millisecond)(pvsc)
go func() {
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
err := pvsc.Start()
require.NoError(t, err)
}()
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
defer pvsc.Stop()
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
n, err := DefaultNewNode(config, log.TestingLogger())
require.NoError(t, err)
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
assert.IsType(t, &privval.SocketVal{}, n.PrivValidator())
}
// testFreeAddr claims a free port so we don't block on listener being ready.
func testFreeAddr(t *testing.T) string {
ln, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
defer ln.Close()
return fmt.Sprintf("127.0.0.1:%d", ln.Addr().(*net.TCPAddr).Port)
}
// create a proposal block using real and full
// mempool and evidence pool and validate it.
func TestCreateProposalBlock(t *testing.T) {
config := cfg.ResetTestRoot("node_create_proposal")
defer os.RemoveAll(config.RootDir)
cc := proxy.NewLocalClientCreator(kvstore.NewKVStoreApplication())
proxyApp := proxy.NewAppConns(cc)
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop()
logger := log.TestingLogger()
var height int64 = 1
state, stateDB := state(1, height)
maxBytes := 16384
state.ConsensusParams.BlockSize.MaxBytes = int64(maxBytes)
proposerAddr, _ := state.Validators.GetByIndex(0)
// Make Mempool
memplMetrics := mempl.PrometheusMetrics("node_test")
mempool := mempl.NewMempool(
config.Mempool,
proxyApp.Mempool(),
state.LastBlockHeight,
mempl.WithMetrics(memplMetrics),
mempl.WithPreCheck(sm.TxPreCheck(state)),
mempl.WithPostCheck(sm.TxPostCheck(state)),
)
mempool.SetLogger(logger)
// Make EvidencePool
types.RegisterMockEvidencesGlobal() // XXX!
evidence.RegisterMockEvidences()
evidenceDB := dbm.NewMemDB()
evidencePool := evidence.NewEvidencePool(stateDB, evidenceDB)
evidencePool.SetLogger(logger)
// fill the evidence pool with more evidence
// than can fit in a block
minEvSize := 12
numEv := (maxBytes / types.MaxEvidenceBytesDenominator) / minEvSize
for i := 0; i < numEv; i++ {
ev := types.NewMockRandomGoodEvidence(1, proposerAddr, cmn.RandBytes(minEvSize))
err := evidencePool.AddEvidence(ev)
assert.NoError(t, err)
}
// fill the mempool with more txs
// than can fit in a block
txLength := 1000
for i := 0; i < maxBytes/txLength; i++ {
tx := cmn.RandBytes(txLength)
err := mempool.CheckTx(tx, nil)
assert.NoError(t, err)
}
blockExec := sm.NewBlockExecutor(
stateDB,
logger,
proxyApp.Consensus(),
mempool,
evidencePool,
)
commit := types.NewCommit(types.BlockID{}, nil)
block, _ := blockExec.CreateProposalBlock(
height,
state, commit,
proposerAddr,
)
err = blockExec.ValidateBlock(state, block)
assert.NoError(t, err)
}
func state(nVals int, height int64) (sm.State, dbm.DB) {
vals := make([]types.GenesisValidator, nVals)
for i := 0; i < nVals; i++ {
secret := []byte(fmt.Sprintf("test%d", i))
pk := ed25519.GenPrivKeyFromSecret(secret)
vals[i] = types.GenesisValidator{
pk.PubKey().Address(),
pk.PubKey(),
1000,
fmt.Sprintf("test%d", i),
}
}
s, _ := sm.MakeGenesisState(&types.GenesisDoc{
ChainID: "test-chain",
Validators: vals,
AppHash: nil,
})
// save validators to db for 2 heights
stateDB := dbm.NewMemDB()
sm.SaveState(stateDB, s)
for i := 1; i < int(height); i++ {
s.LastBlockHeight++
s.LastValidators = s.Validators.Copy()
sm.SaveState(stateDB, s)
}
return s, stateDB
}