You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

327 lines
8.4 KiB

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
8 years ago
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
8 years ago
blockchain: Reorg reactor (#3561) * go routines in blockchain reactor * Added reference to the go routine diagram * Initial commit * cleanup * Undo testing_logger change, committed by mistake * Fix the test loggers * pulled some fsm code into pool.go * added pool tests * changes to the design added block requests under peer moved the request trigger in the reactor poolRoutine, triggered now by a ticker in general moved everything required for making block requests smarter in the poolRoutine added a simple map of heights to keep track of what will need to be requested next added a few more tests * send errors to FSM in a different channel than blocks send errors (RemovePeer) from switch on a different channel than the one receiving blocks renamed channels added more pool tests * more pool tests * lint errors * more tests * more tests * switch fast sync to new implementation * fixed data race in tests * cleanup * finished fsm tests * address golangci comments :) * address golangci comments :) * Added timeout on next block needed to advance * updating docs and cleanup * fix issue in test from previous cleanup * cleanup * Added termination scenarios, tests and more cleanup * small fixes to adr, comments and cleanup * Fix bug in sendRequest() If we tried to send a request to a peer not present in the switch, a missing continue statement caused the request to be blackholed in a peer that was removed and never retried. While this bug was manifesting, the reactor kept asking for other blocks that would be stored and never consumed. Added the number of unconsumed blocks in the math for requesting blocks ahead of current processing height so eventually there will be no more blocks requested until the already received ones are consumed. * remove bpPeer's didTimeout field * Use distinct err codes for peer timeout and FSM timeouts * Don't allow peers to update with lower height * review comments from Ethan and Zarko * some cleanup, renaming, comments * Move block execution in separate goroutine * Remove pool's numPending * review comments * fix lint, remove old blockchain reactor and duplicates in fsm tests * small reorg around peer after review comments * add the reactor spec * verify block only once * review comments * change to int for max number of pending requests * cleanup and godoc * Add configuration flag fast sync version * golangci fixes * fix config template * move both reactor versions under blockchain * cleanup, golint, renaming stuff * updated documentation, fixed more golint warnings * integrate with behavior package * sync with master * gofmt * add changelog_pending entry * move to improvments * suggestion to changelog entry
5 years ago
8 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
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
8 years ago
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
6 years ago
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
8 years ago
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
8 years ago
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
6 years ago
7 years ago
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
6 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
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
6 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
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
8 years ago
7 years ago
8 years ago
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
6 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
8 years ago
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
8 years ago
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
8 years ago
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
6 years ago
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
8 years ago
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
8 years ago
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
6 years ago
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
8 years ago
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
6 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
blockchain: Reorg reactor (#3561) * go routines in blockchain reactor * Added reference to the go routine diagram * Initial commit * cleanup * Undo testing_logger change, committed by mistake * Fix the test loggers * pulled some fsm code into pool.go * added pool tests * changes to the design added block requests under peer moved the request trigger in the reactor poolRoutine, triggered now by a ticker in general moved everything required for making block requests smarter in the poolRoutine added a simple map of heights to keep track of what will need to be requested next added a few more tests * send errors to FSM in a different channel than blocks send errors (RemovePeer) from switch on a different channel than the one receiving blocks renamed channels added more pool tests * more pool tests * lint errors * more tests * more tests * switch fast sync to new implementation * fixed data race in tests * cleanup * finished fsm tests * address golangci comments :) * address golangci comments :) * Added timeout on next block needed to advance * updating docs and cleanup * fix issue in test from previous cleanup * cleanup * Added termination scenarios, tests and more cleanup * small fixes to adr, comments and cleanup * Fix bug in sendRequest() If we tried to send a request to a peer not present in the switch, a missing continue statement caused the request to be blackholed in a peer that was removed and never retried. While this bug was manifesting, the reactor kept asking for other blocks that would be stored and never consumed. Added the number of unconsumed blocks in the math for requesting blocks ahead of current processing height so eventually there will be no more blocks requested until the already received ones are consumed. * remove bpPeer's didTimeout field * Use distinct err codes for peer timeout and FSM timeouts * Don't allow peers to update with lower height * review comments from Ethan and Zarko * some cleanup, renaming, comments * Move block execution in separate goroutine * Remove pool's numPending * review comments * fix lint, remove old blockchain reactor and duplicates in fsm tests * small reorg around peer after review comments * add the reactor spec * verify block only once * review comments * change to int for max number of pending requests * cleanup and godoc * Add configuration flag fast sync version * golangci fixes * fix config template * move both reactor versions under blockchain * cleanup, golint, renaming stuff * updated documentation, fixed more golint warnings * integrate with behavior package * sync with master * gofmt * add changelog_pending entry * move to improvments * suggestion to changelog entry
5 years ago
lint: Enable Golint (#4212) * Fix many golint errors * Fix golint errors in the 'lite' package * Don't export Pool.store * Fix typo * Revert unwanted changes * Fix errors in counter package * Fix linter errors in kvstore package * Fix linter error in example package * Fix error in tests package * Fix linter errors in v2 package * Fix linter errors in consensus package * Fix linter errors in evidence package * Fix linter error in fail package * Fix linter errors in query package * Fix linter errors in core package * Fix linter errors in node package * Fix linter errors in mempool package * Fix linter error in conn package * Fix linter errors in pex package * Rename PEXReactor export to Reactor * Fix linter errors in trust package * Fix linter errors in upnp package * Fix linter errors in p2p package * Fix linter errors in proxy package * Fix linter errors in mock_test package * Fix linter error in client_test package * Fix linter errors in coretypes package * Fix linter errors in coregrpc package * Fix linter errors in rpcserver package * Fix linter errors in rpctypes package * Fix linter errors in rpctest package * Fix linter error in json2wal script * Fix linter error in wal2json script * Fix linter errors in kv package * Fix linter error in state package * Fix linter error in grpc_client * Fix linter errors in types package * Fix linter error in version package * Fix remaining errors * Address review comments * Fix broken tests * Reconcile package coregrpc * Fix golangci bot error * Fix new golint errors * Fix broken reference * Enable golint linter * minor changes to bring golint into line * fix failing test * fix pex reactor naming * address PR comments
5 years ago
8 years ago
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
8 years ago
  1. package consensus
  2. import (
  3. "bufio"
  4. "context"
  5. "errors"
  6. "fmt"
  7. "io"
  8. "os"
  9. "strconv"
  10. "strings"
  11. dbm "github.com/tendermint/tm-db"
  12. cfg "github.com/tendermint/tendermint/config"
  13. "github.com/tendermint/tendermint/libs/log"
  14. tmos "github.com/tendermint/tendermint/libs/os"
  15. "github.com/tendermint/tendermint/proxy"
  16. sm "github.com/tendermint/tendermint/state"
  17. "github.com/tendermint/tendermint/store"
  18. "github.com/tendermint/tendermint/types"
  19. )
  20. const (
  21. // event bus subscriber
  22. subscriber = "replay-file"
  23. )
  24. //--------------------------------------------------------
  25. // replay messages interactively or all at once
  26. // replay the wal file
  27. func RunReplayFile(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig, console bool) {
  28. consensusState := newConsensusStateForReplay(config, csConfig)
  29. if err := consensusState.ReplayFile(csConfig.WalFile(), console); err != nil {
  30. tmos.Exit(fmt.Sprintf("Error during consensus replay: %v", err))
  31. }
  32. }
  33. // Replay msgs in file or start the console
  34. func (cs *State) ReplayFile(file string, console bool) error {
  35. if cs.IsRunning() {
  36. return errors.New("cs is already running, cannot replay")
  37. }
  38. if cs.wal != nil {
  39. return errors.New("cs wal is open, cannot replay")
  40. }
  41. cs.startForReplay()
  42. // ensure all new step events are regenerated as expected
  43. ctx := context.Background()
  44. newStepSub, err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  45. if err != nil {
  46. return fmt.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
  47. }
  48. defer cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  49. // just open the file for reading, no need to use wal
  50. fp, err := os.OpenFile(file, os.O_RDONLY, 0600)
  51. if err != nil {
  52. return err
  53. }
  54. pb := newPlayback(file, fp, cs, cs.state.Copy())
  55. defer pb.fp.Close() // nolint: errcheck
  56. var nextN int // apply N msgs in a row
  57. var msg *TimedWALMessage
  58. for {
  59. if nextN == 0 && console {
  60. nextN = pb.replayConsoleLoop()
  61. }
  62. msg, err = pb.dec.Decode()
  63. if err == io.EOF {
  64. return nil
  65. } else if err != nil {
  66. return err
  67. }
  68. if err := pb.cs.readReplayMessage(msg, newStepSub); err != nil {
  69. return err
  70. }
  71. if nextN > 0 {
  72. nextN--
  73. }
  74. pb.count++
  75. }
  76. }
  77. //------------------------------------------------
  78. // playback manager
  79. type playback struct {
  80. cs *State
  81. fp *os.File
  82. dec *WALDecoder
  83. count int // how many lines/msgs into the file are we
  84. // replays can be reset to beginning
  85. fileName string // so we can close/reopen the file
  86. genesisState sm.State // so the replay session knows where to restart from
  87. }
  88. func newPlayback(fileName string, fp *os.File, cs *State, genState sm.State) *playback {
  89. return &playback{
  90. cs: cs,
  91. fp: fp,
  92. fileName: fileName,
  93. genesisState: genState,
  94. dec: NewWALDecoder(fp),
  95. }
  96. }
  97. // go back count steps by resetting the state and running (pb.count - count) steps
  98. func (pb *playback) replayReset(count int, newStepSub types.Subscription) error {
  99. pb.cs.Stop()
  100. pb.cs.Wait()
  101. newCS := NewState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
  102. pb.cs.blockStore, pb.cs.txNotifier, pb.cs.evpool)
  103. newCS.SetEventBus(pb.cs.eventBus)
  104. newCS.startForReplay()
  105. if err := pb.fp.Close(); err != nil {
  106. return err
  107. }
  108. fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0600)
  109. if err != nil {
  110. return err
  111. }
  112. pb.fp = fp
  113. pb.dec = NewWALDecoder(fp)
  114. count = pb.count - count
  115. fmt.Printf("Reseting from %d to %d\n", pb.count, count)
  116. pb.count = 0
  117. pb.cs = newCS
  118. var msg *TimedWALMessage
  119. for i := 0; i < count; i++ {
  120. msg, err = pb.dec.Decode()
  121. if err == io.EOF {
  122. return nil
  123. } else if err != nil {
  124. return err
  125. }
  126. if err := pb.cs.readReplayMessage(msg, newStepSub); err != nil {
  127. return err
  128. }
  129. pb.count++
  130. }
  131. return nil
  132. }
  133. func (cs *State) startForReplay() {
  134. cs.Logger.Error("Replay commands are disabled until someone updates them and writes tests")
  135. /* TODO:!
  136. // since we replay tocks we just ignore ticks
  137. go func() {
  138. for {
  139. select {
  140. case <-cs.tickChan:
  141. case <-cs.Quit:
  142. return
  143. }
  144. }
  145. }()*/
  146. }
  147. // console function for parsing input and running commands
  148. func (pb *playback) replayConsoleLoop() int {
  149. for {
  150. fmt.Printf("> ")
  151. bufReader := bufio.NewReader(os.Stdin)
  152. line, more, err := bufReader.ReadLine()
  153. if more {
  154. tmos.Exit("input is too long")
  155. } else if err != nil {
  156. tmos.Exit(err.Error())
  157. }
  158. tokens := strings.Split(string(line), " ")
  159. if len(tokens) == 0 {
  160. continue
  161. }
  162. switch tokens[0] {
  163. case "next":
  164. // "next" -> replay next message
  165. // "next N" -> replay next N messages
  166. if len(tokens) == 1 {
  167. return 0
  168. }
  169. i, err := strconv.Atoi(tokens[1])
  170. if err != nil {
  171. fmt.Println("next takes an integer argument")
  172. } else {
  173. return i
  174. }
  175. case "back":
  176. // "back" -> go back one message
  177. // "back N" -> go back N messages
  178. // NOTE: "back" is not supported in the state machine design,
  179. // so we restart and replay up to
  180. ctx := context.Background()
  181. // ensure all new step events are regenerated as expected
  182. newStepSub, err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  183. if err != nil {
  184. tmos.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
  185. }
  186. defer pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  187. if len(tokens) == 1 {
  188. if err := pb.replayReset(1, newStepSub); err != nil {
  189. pb.cs.Logger.Error("Replay reset error", "err", err)
  190. }
  191. } else {
  192. i, err := strconv.Atoi(tokens[1])
  193. if err != nil {
  194. fmt.Println("back takes an integer argument")
  195. } else if i > pb.count {
  196. fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
  197. } else if err := pb.replayReset(i, newStepSub); err != nil {
  198. pb.cs.Logger.Error("Replay reset error", "err", err)
  199. }
  200. }
  201. case "rs":
  202. // "rs" -> print entire round state
  203. // "rs short" -> print height/round/step
  204. // "rs <field>" -> print another field of the round state
  205. rs := pb.cs.RoundState
  206. if len(tokens) == 1 {
  207. fmt.Println(rs)
  208. } else {
  209. switch tokens[1] {
  210. case "short":
  211. fmt.Printf("%v/%v/%v\n", rs.Height, rs.Round, rs.Step)
  212. case "validators":
  213. fmt.Println(rs.Validators)
  214. case "proposal":
  215. fmt.Println(rs.Proposal)
  216. case "proposal_block":
  217. fmt.Printf("%v %v\n", rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort())
  218. case "locked_round":
  219. fmt.Println(rs.LockedRound)
  220. case "locked_block":
  221. fmt.Printf("%v %v\n", rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort())
  222. case "votes":
  223. fmt.Println(rs.Votes.StringIndented(" "))
  224. default:
  225. fmt.Println("Unknown option", tokens[1])
  226. }
  227. }
  228. case "n":
  229. fmt.Println(pb.count)
  230. }
  231. }
  232. }
  233. //--------------------------------------------------------------------------------
  234. // convenience for replay mode
  235. func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig) *State {
  236. dbType := dbm.BackendType(config.DBBackend)
  237. // Get BlockStore
  238. blockStoreDB, err := dbm.NewDB("blockstore", dbType, config.DBDir())
  239. if err != nil {
  240. tmos.Exit(err.Error())
  241. }
  242. blockStore := store.NewBlockStore(blockStoreDB)
  243. // Get State
  244. stateDB, err := dbm.NewDB("state", dbType, config.DBDir())
  245. if err != nil {
  246. tmos.Exit(err.Error())
  247. }
  248. gdoc, err := sm.MakeGenesisDocFromFile(config.GenesisFile())
  249. if err != nil {
  250. tmos.Exit(err.Error())
  251. }
  252. state, err := sm.MakeGenesisState(gdoc)
  253. if err != nil {
  254. tmos.Exit(err.Error())
  255. }
  256. // Create proxyAppConn connection (consensus, mempool, query)
  257. clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
  258. proxyApp := proxy.NewAppConns(clientCreator)
  259. err = proxyApp.Start()
  260. if err != nil {
  261. tmos.Exit(fmt.Sprintf("Error starting proxy app conns: %v", err))
  262. }
  263. eventBus := types.NewEventBus()
  264. if err := eventBus.Start(); err != nil {
  265. tmos.Exit(fmt.Sprintf("Failed to start event bus: %v", err))
  266. }
  267. handshaker := NewHandshaker(stateDB, state, blockStore, gdoc)
  268. handshaker.SetEventBus(eventBus)
  269. err = handshaker.Handshake(proxyApp)
  270. if err != nil {
  271. tmos.Exit(fmt.Sprintf("Error on handshake: %v", err))
  272. }
  273. mempool, evpool := emptyMempool{}, emptyEvidencePool{}
  274. blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
  275. consensusState := NewState(csConfig, state.Copy(), blockExec,
  276. blockStore, mempool, evpool)
  277. consensusState.SetEventBus(eventBus)
  278. return consensusState
  279. }