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.

348 lines
8.8 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
7 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
7 years ago
7 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
7 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
7 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
7 years ago
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
6 years ago
7 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
7 years ago
7 years ago
7 years ago
7 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
7 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
7 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
7 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
7 years ago
abci: localClient improvements & bugfixes & pubsub Unsubscribe issues (#2748) * use READ lock/unlock in ConsensusState#GetLastHeight Refs #2721 * do not use defers when there's no need * fix peer formatting (output its address instead of the pointer) ``` [54310]: E[11-02|11:59:39.851] Connection failed @ sendRoutine module=p2p peer=0xb78f00 conn=MConn{74.207.236.148:26656} err="pong timeout" ``` https://github.com/tendermint/tendermint/issues/2721#issuecomment-435326581 * panic if peer has no state https://github.com/tendermint/tendermint/issues/2721#issuecomment-435347165 It's confusing that sometimes we check if peer has a state, but most of the times we expect it to be there 1. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/mempool/reactor.go#L138 2. https://github.com/tendermint/tendermint/blob/add79700b5fe84417538202b6c927c8cc5383672/rpc/core/consensus.go#L196 (edited) I will change everything to always assume peer has a state and panic otherwise that should help identify issues earlier * abci/localclient: extend lock on app callback App callback should be protected by lock as well (note this was already done for InitChainAsync, why not for others???). Otherwise, when we execute the block, tx might come in and call the callback in the same time we're updating it in execBlockOnProxyApp => DATA RACE Fixes #2721 Consensus state is locked ``` goroutine 113333 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00180009c, 0xc0000c7e00) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*RWMutex).RLock(0xc001800090) /usr/local/go/src/sync/rwmutex.go:50 +0x4e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).GetRoundState(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:218 +0x46 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).queryMaj23Routine(0xc0017def80, 0x11104a0, 0xc0072488f0, 0xc007248 9c0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:735 +0x16d created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusReactor).AddPeer /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/reactor.go:172 +0x236 ``` because localClient is locked ``` goroutine 1899 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0xc0000cb500) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).SetResponseCallback(0xc0001fb560, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:32 +0x33 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnConsensus).SetResponseCallback(0xc00002f750, 0xc007868540) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:57 +0x40 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.execBlockOnProxyApp(0x1104e20, 0xc002ca0ba0, 0x11092a0, 0xc00002f750, 0xc0001fe960, 0xc000bfc660, 0x110cfe0, 0xc000090330, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:230 +0x1fd github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state.(*BlockExecutor).ApplyBlock(0xc002c2a230, 0x7, 0x0, 0xc000eae880, 0x6, 0xc002e52c60, 0x16, 0x1f927, 0xc9d12, 0xc000d9d5a0, ...) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/state/execution.go:96 +0x142 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).finalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1339 +0xa3e github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryFinalizeCommit(0xc001800000, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1270 +0x451 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit.func1(0xc001800000, 0x0, 0x1f928) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1218 +0x90 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).enterCommit(0xc001800000, 0x1f928, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1247 +0x6b8 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).addVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xc003bc7ad0, 0xc003bc7b10) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1659 +0xbad github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).tryAddVote(0xc001800000, 0xc003d8dea0, 0xc000cf4cc0, 0x28, 0xf1, 0xf1, 0xf1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:1517 +0x59 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).handleMsg(0xc001800000, 0xd98200, 0xc0070dbed0, 0xc000cf4cc0, 0x28) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:660 +0x64b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).receiveRoutine(0xc001800000, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:617 +0x670 created by github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus.(*ConsensusState).OnStart /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/consensus/state.go:311 +0x132 ``` tx comes in and CheckTx is executed right when we execute the block ``` goroutine 111044 [semacquire, 309 minutes]: sync.runtime_SemacquireMutex(0xc00003363c, 0x0) /usr/local/go/src/runtime/sema.go:71 +0x3d sync.(*Mutex).Lock(0xc000033638) /usr/local/go/src/sync/mutex.go:134 +0xff github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client.(*localClient).CheckTxAsync(0xc0001fb0e0, 0xc002d94500, 0x13f, 0x280, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/abci/client/local_client.go:85 +0x47 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy.(*appConnMempool).CheckTxAsync(0xc00002f720, 0xc002d94500, 0x13f, 0x280, 0x1) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/proxy/app_conn.go:114 +0x51 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool.(*Mempool).CheckTx(0xc002d3a320, 0xc002d94500, 0x13f, 0x280, 0xc0072355f0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/mempool/mempool.go:316 +0x17b github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core.BroadcastTxSync(0xc002d94500, 0x13f, 0x280, 0x0, 0x0, 0x0) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/core/mempool.go:93 +0xb8 reflect.Value.call(0xd85560, 0x10326c0, 0x13, 0xec7b8b, 0x4, 0xc00663f180, 0x1, 0x1, 0xc00663f180, 0xc00663f188, ...) /usr/local/go/src/reflect/value.go:447 +0x449 reflect.Value.Call(0xd85560, 0x10326c0, 0x13, 0xc00663f180, 0x1, 0x1, 0x0, 0x0, 0xc005cc9344) /usr/local/go/src/reflect/value.go:308 +0xa4 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.makeHTTPHandler.func2(0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/handlers.go:269 +0x188 net/http.HandlerFunc.ServeHTTP(0xc002c81f20, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.(*ServeMux).ServeHTTP(0xc002c81b60, 0x1102060, 0xc00663f100, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2361 +0x127 github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.maxBytesHandler.ServeHTTP(0x10f8a40, 0xc002c81b60, 0xf4240, 0x1102060, 0xc00663f100, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:219 +0xcf github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server.RecoverAndLogHandler.func1(0x1103220, 0xc00121e620, 0xc0082d7900) /root/go/src/github.com/MinterTeam/minter-go-node/vendor/github.com/tendermint/tendermint/rpc/lib/server/http_server.go:192 +0x394 net/http.HandlerFunc.ServeHTTP(0xc002c06ea0, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:1964 +0x44 net/http.serverHandler.ServeHTTP(0xc001a1aa90, 0x1103220, 0xc00121e620, 0xc0082d7900) /usr/local/go/src/net/http/server.go:2741 +0xab net/http.(*conn).serve(0xc00785a3c0, 0x11041a0, 0xc000f844c0) /usr/local/go/src/net/http/server.go:1847 +0x646 created by net/http.(*Server).Serve /usr/local/go/src/net/http/server.go:2851 +0x2f5 ``` * consensus: use read lock in Receive#VoteMessage * use defer to unlock mutex because application might panic * use defer in every method of the localClient * add a changelog entry * drain channels before Unsubscribe(All) Read https://github.com/tendermint/tendermint/blob/55362ed76630f3e1ebec159a598f6a9fb5892cb1/libs/pubsub/pubsub.go#L13 for the detailed explanation of the issue. We'll need to fix it someday. Make sure to keep an eye on https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-033-pubsub.md * retry instead of panic when peer has no state in reactors other than consensus in /dump_consensus_state RPC endpoint, skip a peer with no state * rpc/core/mempool: simplify error messages * rpc/core/mempool: use time.After instead of timer also, do not log DeliverTx result (to be consistent with other memthods) * unlock before calling the callback in reqRes#SetCallback
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
7 years ago
7 years ago
7 years ago
7 years ago
7 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
7 years ago
7 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
7 years ago
  1. package consensus
  2. import (
  3. "bufio"
  4. "context"
  5. "fmt"
  6. "io"
  7. "os"
  8. "strconv"
  9. "strings"
  10. "github.com/pkg/errors"
  11. bc "github.com/tendermint/tendermint/blockchain"
  12. cfg "github.com/tendermint/tendermint/config"
  13. cmn "github.com/tendermint/tendermint/libs/common"
  14. dbm "github.com/tendermint/tendermint/libs/db"
  15. "github.com/tendermint/tendermint/libs/log"
  16. "github.com/tendermint/tendermint/proxy"
  17. sm "github.com/tendermint/tendermint/state"
  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. cmn.Exit(fmt.Sprintf("Error during consensus replay: %v", err))
  31. }
  32. }
  33. // Replay msgs in file or start the console
  34. func (cs *ConsensusState) 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. newStepCh := make(chan interface{}, 1)
  44. ctx := context.Background()
  45. err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
  46. if err != nil {
  47. return errors.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
  48. }
  49. defer func() {
  50. // drain newStepCh to make sure we don't block
  51. LOOP:
  52. for {
  53. select {
  54. case <-newStepCh:
  55. default:
  56. break LOOP
  57. }
  58. }
  59. cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  60. }()
  61. // just open the file for reading, no need to use wal
  62. fp, err := os.OpenFile(file, os.O_RDONLY, 0600)
  63. if err != nil {
  64. return err
  65. }
  66. pb := newPlayback(file, fp, cs, cs.state.Copy())
  67. defer pb.fp.Close() // nolint: errcheck
  68. var nextN int // apply N msgs in a row
  69. var msg *TimedWALMessage
  70. for {
  71. if nextN == 0 && console {
  72. nextN = pb.replayConsoleLoop()
  73. }
  74. msg, err = pb.dec.Decode()
  75. if err == io.EOF {
  76. return nil
  77. } else if err != nil {
  78. return err
  79. }
  80. if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
  81. return err
  82. }
  83. if nextN > 0 {
  84. nextN--
  85. }
  86. pb.count++
  87. }
  88. return nil
  89. }
  90. //------------------------------------------------
  91. // playback manager
  92. type playback struct {
  93. cs *ConsensusState
  94. fp *os.File
  95. dec *WALDecoder
  96. count int // how many lines/msgs into the file are we
  97. // replays can be reset to beginning
  98. fileName string // so we can close/reopen the file
  99. genesisState sm.State // so the replay session knows where to restart from
  100. }
  101. func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState sm.State) *playback {
  102. return &playback{
  103. cs: cs,
  104. fp: fp,
  105. fileName: fileName,
  106. genesisState: genState,
  107. dec: NewWALDecoder(fp),
  108. }
  109. }
  110. // go back count steps by resetting the state and running (pb.count - count) steps
  111. func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
  112. pb.cs.Stop()
  113. pb.cs.Wait()
  114. newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
  115. pb.cs.blockStore, pb.cs.txNotifier, pb.cs.evpool)
  116. newCS.SetEventBus(pb.cs.eventBus)
  117. newCS.startForReplay()
  118. if err := pb.fp.Close(); err != nil {
  119. return err
  120. }
  121. fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0600)
  122. if err != nil {
  123. return err
  124. }
  125. pb.fp = fp
  126. pb.dec = NewWALDecoder(fp)
  127. count = pb.count - count
  128. fmt.Printf("Reseting from %d to %d\n", pb.count, count)
  129. pb.count = 0
  130. pb.cs = newCS
  131. var msg *TimedWALMessage
  132. for i := 0; i < count; i++ {
  133. msg, err = pb.dec.Decode()
  134. if err == io.EOF {
  135. return nil
  136. } else if err != nil {
  137. return err
  138. }
  139. if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
  140. return err
  141. }
  142. pb.count++
  143. }
  144. return nil
  145. }
  146. func (cs *ConsensusState) startForReplay() {
  147. cs.Logger.Error("Replay commands are disabled until someone updates them and writes tests")
  148. /* TODO:!
  149. // since we replay tocks we just ignore ticks
  150. go func() {
  151. for {
  152. select {
  153. case <-cs.tickChan:
  154. case <-cs.Quit:
  155. return
  156. }
  157. }
  158. }()*/
  159. }
  160. // console function for parsing input and running commands
  161. func (pb *playback) replayConsoleLoop() int {
  162. for {
  163. fmt.Printf("> ")
  164. bufReader := bufio.NewReader(os.Stdin)
  165. line, more, err := bufReader.ReadLine()
  166. if more {
  167. cmn.Exit("input is too long")
  168. } else if err != nil {
  169. cmn.Exit(err.Error())
  170. }
  171. tokens := strings.Split(string(line), " ")
  172. if len(tokens) == 0 {
  173. continue
  174. }
  175. switch tokens[0] {
  176. case "next":
  177. // "next" -> replay next message
  178. // "next N" -> replay next N messages
  179. if len(tokens) == 1 {
  180. return 0
  181. }
  182. i, err := strconv.Atoi(tokens[1])
  183. if err != nil {
  184. fmt.Println("next takes an integer argument")
  185. } else {
  186. return i
  187. }
  188. case "back":
  189. // "back" -> go back one message
  190. // "back N" -> go back N messages
  191. // NOTE: "back" is not supported in the state machine design,
  192. // so we restart and replay up to
  193. ctx := context.Background()
  194. // ensure all new step events are regenerated as expected
  195. newStepCh := make(chan interface{}, 1)
  196. err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
  197. if err != nil {
  198. cmn.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
  199. }
  200. defer func() {
  201. // drain newStepCh to make sure we don't block
  202. LOOP:
  203. for {
  204. select {
  205. case <-newStepCh:
  206. default:
  207. break LOOP
  208. }
  209. }
  210. pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
  211. }()
  212. if len(tokens) == 1 {
  213. if err := pb.replayReset(1, newStepCh); err != nil {
  214. pb.cs.Logger.Error("Replay reset error", "err", err)
  215. }
  216. } else {
  217. i, err := strconv.Atoi(tokens[1])
  218. if err != nil {
  219. fmt.Println("back takes an integer argument")
  220. } else if i > pb.count {
  221. fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
  222. } else {
  223. if err := pb.replayReset(i, newStepCh); err != nil {
  224. pb.cs.Logger.Error("Replay reset error", "err", err)
  225. }
  226. }
  227. }
  228. case "rs":
  229. // "rs" -> print entire round state
  230. // "rs short" -> print height/round/step
  231. // "rs <field>" -> print another field of the round state
  232. rs := pb.cs.RoundState
  233. if len(tokens) == 1 {
  234. fmt.Println(rs)
  235. } else {
  236. switch tokens[1] {
  237. case "short":
  238. fmt.Printf("%v/%v/%v\n", rs.Height, rs.Round, rs.Step)
  239. case "validators":
  240. fmt.Println(rs.Validators)
  241. case "proposal":
  242. fmt.Println(rs.Proposal)
  243. case "proposal_block":
  244. fmt.Printf("%v %v\n", rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort())
  245. case "locked_round":
  246. fmt.Println(rs.LockedRound)
  247. case "locked_block":
  248. fmt.Printf("%v %v\n", rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort())
  249. case "votes":
  250. fmt.Println(rs.Votes.StringIndented(" "))
  251. default:
  252. fmt.Println("Unknown option", tokens[1])
  253. }
  254. }
  255. case "n":
  256. fmt.Println(pb.count)
  257. }
  258. }
  259. return 0
  260. }
  261. //--------------------------------------------------------------------------------
  262. // convenience for replay mode
  263. func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig) *ConsensusState {
  264. dbType := dbm.DBBackendType(config.DBBackend)
  265. // Get BlockStore
  266. blockStoreDB := dbm.NewDB("blockstore", dbType, config.DBDir())
  267. blockStore := bc.NewBlockStore(blockStoreDB)
  268. // Get State
  269. stateDB := dbm.NewDB("state", dbType, config.DBDir())
  270. gdoc, err := sm.MakeGenesisDocFromFile(config.GenesisFile())
  271. if err != nil {
  272. cmn.Exit(err.Error())
  273. }
  274. state, err := sm.MakeGenesisState(gdoc)
  275. if err != nil {
  276. cmn.Exit(err.Error())
  277. }
  278. // Create proxyAppConn connection (consensus, mempool, query)
  279. clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
  280. proxyApp := proxy.NewAppConns(clientCreator)
  281. err = proxyApp.Start()
  282. if err != nil {
  283. cmn.Exit(fmt.Sprintf("Error starting proxy app conns: %v", err))
  284. }
  285. handshaker := NewHandshaker(stateDB, state, blockStore, gdoc)
  286. err = handshaker.Handshake(proxyApp)
  287. if err != nil {
  288. cmn.Exit(fmt.Sprintf("Error on handshake: %v", err))
  289. }
  290. eventBus := types.NewEventBus()
  291. if err := eventBus.Start(); err != nil {
  292. cmn.Exit(fmt.Sprintf("Failed to start event bus: %v", err))
  293. }
  294. mempool, evpool := sm.MockMempool{}, sm.MockEvidencePool{}
  295. blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
  296. consensusState := NewConsensusState(csConfig, state.Copy(), blockExec,
  297. blockStore, mempool, evpool)
  298. consensusState.SetEventBus(eventBus)
  299. return consensusState
  300. }