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.

310 lines
8.1 KiB

8 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
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
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
6 years ago
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
privval: improve Remote Signer implementation (#3351) This issue is related to #3107 This is a first renaming/refactoring step before reworking and removing heartbeats. As discussed with @Liamsi , we preferred to go for a couple of independent and separate PRs to simplify review work. The changes: Help to clarify the relation between the validator and remote signer endpoints Differentiate between timeouts and deadlines Prepare to encapsulate networking related code behind RemoteSigner in the next PR My intention is to separate and encapsulate the "network related" code from the actual signer. SignerRemote ---(uses/contains)--> SignerValidatorEndpoint <--(connects to)--> SignerServiceEndpoint ---> SignerService (future.. not here yet but would like to decouple too) All reconnection/heartbeat/whatever code goes in the endpoints. Signer[Remote/Service] do not need to know about that. I agree Endpoint may not be the perfect name. I tried to find something "Go-ish" enough. It is a common name in go-kit, kubernetes, etc. Right now: SignerValidatorEndpoint: handles the listener contains SignerRemote Implements the PrivValidator interface connects and sets a connection object in a contained SignerRemote delegates PrivValidator some calls to SignerRemote which in turn uses the conn object that was set externally SignerRemote: Implements the PrivValidator interface read/writes from a connection object directly handles heartbeats SignerServiceEndpoint: Does most things in a single place delegates to a PrivValidator IIRC. * cleanup * Refactoring step 1 * Refactoring step 2 * move messages to another file * mark for future work / next steps * mark deprecated classes in docs * Fix linter problems * additional linter fixes
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
Close and retry a RemoteSigner on err (#2923) * Close and recreate a RemoteSigner on err * Update changelog * Address Anton's comments / suggestions: - update changelog - restart TCPVal - shut down on `ErrUnexpectedResponse` * re-init remote signer client with fresh connection if Ping fails - add/update TODOs in secret connection - rename tcp.go -> tcp_client.go, same with ipc to clarify their purpose * account for `conn returned by waitConnection can be `nil` - also add TODO about RemoteSigner conn field * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn * Tests for retrying: IPC / TCP - shorter info log on success - set conn and use it in tests to close conn - add rwmutex for conn field in IPC * comments and doc.go * fix ipc tests. fixes #2677 * use constants for tests * cleanup some error statements * fixes #2784, race in tests * remove print statement * minor fixes from review * update comment on sts spec * cosmetics * p2p/conn: add failing tests * p2p/conn: make SecretConnection thread safe * changelog * IPCVal signer refactor - use a .reset() method - don't use embedded RemoteSignerClient - guard RemoteSignerClient with mutex - drop the .conn - expose Close() on RemoteSignerClient * apply IPCVal refactor to TCPVal * remove mtx from RemoteSignerClient * consolidate IPCVal and TCPVal, fixes #3104 - done in tcp_client.go - now called SocketVal - takes a listener in the constructor - make tcpListener and unixListener contain all the differences * delete ipc files * introduce unix and tcp dialer for RemoteSigner * rename files - drop tcp_ prefix - rename priv_validator.go to file.go * bring back listener options * fix node * fix priv_val_server * fix node test * minor cleanup and comments
6 years ago
privval: improve Remote Signer implementation (#3351) This issue is related to #3107 This is a first renaming/refactoring step before reworking and removing heartbeats. As discussed with @Liamsi , we preferred to go for a couple of independent and separate PRs to simplify review work. The changes: Help to clarify the relation between the validator and remote signer endpoints Differentiate between timeouts and deadlines Prepare to encapsulate networking related code behind RemoteSigner in the next PR My intention is to separate and encapsulate the "network related" code from the actual signer. SignerRemote ---(uses/contains)--> SignerValidatorEndpoint <--(connects to)--> SignerServiceEndpoint ---> SignerService (future.. not here yet but would like to decouple too) All reconnection/heartbeat/whatever code goes in the endpoints. Signer[Remote/Service] do not need to know about that. I agree Endpoint may not be the perfect name. I tried to find something "Go-ish" enough. It is a common name in go-kit, kubernetes, etc. Right now: SignerValidatorEndpoint: handles the listener contains SignerRemote Implements the PrivValidator interface connects and sets a connection object in a contained SignerRemote delegates PrivValidator some calls to SignerRemote which in turn uses the conn object that was set externally SignerRemote: Implements the PrivValidator interface read/writes from a connection object directly handles heartbeats SignerServiceEndpoint: Does most things in a single place delegates to a PrivValidator IIRC. * cleanup * Refactoring step 1 * Refactoring step 2 * move messages to another file * mark for future work / next steps * mark deprecated classes in docs * Fix linter problems * additional linter fixes
6 years ago
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
6 years ago
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
6 years ago
fix non deterministic test failures and race in privval socket (#3258) * node: decrease retry conn timeout in test Should fix #3256 The retry timeout was set to the default, which is the same as the accept timeout, so it's no wonder this would fail. Here we decrease the retry timeout so we can try many times before the accept timeout. * p2p: increase handshake timeout in test This fails sometimes, presumably because the handshake timeout is so low (only 50ms). So increase it to 1s. Should fix #3187 * privval: fix race with ping. closes #3237 Pings happen in a go-routine and can happen concurrently with other messages. Since we use a request/response protocol, we expect to send a request and get back the corresponding response. But with pings happening concurrently, this assumption could be violated. We were using a mutex, but only a RWMutex, where the RLock was being held for sending messages - this was to allow the underlying connection to be replaced if it fails. Turns out we actually need to use a full lock (not just a read lock) to prevent multiple requests from happening concurrently. * node: fix test name. DelayedStop -> DelayedStart * autofile: Wait() method In the TestWALTruncate in consensus/wal_test.go we remove the WAL directory at the end of the test. However the wal.Stop() does not properly wait for the autofile group to finish shutting down. Hence it was possible that the group's go-routine is still running when the cleanup happens, which causes a panic since the directory disappeared. Here we add a Wait() method to properly wait until the go-routine exits so we can safely clean up. This fixes #2852.
6 years ago
6 years ago
  1. package node
  2. import (
  3. "context"
  4. "fmt"
  5. "net"
  6. "os"
  7. "syscall"
  8. "testing"
  9. "time"
  10. "github.com/stretchr/testify/assert"
  11. "github.com/stretchr/testify/require"
  12. "github.com/tendermint/tendermint/abci/example/kvstore"
  13. cfg "github.com/tendermint/tendermint/config"
  14. "github.com/tendermint/tendermint/crypto/ed25519"
  15. "github.com/tendermint/tendermint/evidence"
  16. cmn "github.com/tendermint/tendermint/libs/common"
  17. dbm "github.com/tendermint/tendermint/libs/db"
  18. "github.com/tendermint/tendermint/libs/log"
  19. mempl "github.com/tendermint/tendermint/mempool"
  20. "github.com/tendermint/tendermint/p2p"
  21. "github.com/tendermint/tendermint/privval"
  22. "github.com/tendermint/tendermint/proxy"
  23. sm "github.com/tendermint/tendermint/state"
  24. "github.com/tendermint/tendermint/types"
  25. tmtime "github.com/tendermint/tendermint/types/time"
  26. "github.com/tendermint/tendermint/version"
  27. )
  28. func TestNodeStartStop(t *testing.T) {
  29. config := cfg.ResetTestRoot("node_node_test")
  30. defer os.RemoveAll(config.RootDir)
  31. // create & start node
  32. n, err := DefaultNewNode(config, log.TestingLogger())
  33. require.NoError(t, err)
  34. err = n.Start()
  35. require.NoError(t, err)
  36. t.Logf("Started node %v", n.sw.NodeInfo())
  37. // wait for the node to produce a block
  38. blocksSub, err := n.EventBus().Subscribe(context.Background(), "node_test", types.EventQueryNewBlock)
  39. require.NoError(t, err)
  40. select {
  41. case <-blocksSub.Out():
  42. case <-blocksSub.Cancelled():
  43. t.Fatal("blocksSub was cancelled")
  44. case <-time.After(10 * time.Second):
  45. t.Fatal("timed out waiting for the node to produce a block")
  46. }
  47. // stop the node
  48. go func() {
  49. n.Stop()
  50. }()
  51. select {
  52. case <-n.Quit():
  53. case <-time.After(5 * time.Second):
  54. pid := os.Getpid()
  55. p, err := os.FindProcess(pid)
  56. if err != nil {
  57. panic(err)
  58. }
  59. err = p.Signal(syscall.SIGABRT)
  60. fmt.Println(err)
  61. t.Fatal("timed out waiting for shutdown")
  62. }
  63. }
  64. func TestSplitAndTrimEmpty(t *testing.T) {
  65. testCases := []struct {
  66. s string
  67. sep string
  68. cutset string
  69. expected []string
  70. }{
  71. {"a,b,c", ",", " ", []string{"a", "b", "c"}},
  72. {" a , b , c ", ",", " ", []string{"a", "b", "c"}},
  73. {" a, b, c ", ",", " ", []string{"a", "b", "c"}},
  74. {" a, ", ",", " ", []string{"a"}},
  75. {" ", ",", " ", []string{}},
  76. }
  77. for _, tc := range testCases {
  78. assert.Equal(t, tc.expected, splitAndTrimEmpty(tc.s, tc.sep, tc.cutset), "%s", tc.s)
  79. }
  80. }
  81. func TestNodeDelayedStart(t *testing.T) {
  82. config := cfg.ResetTestRoot("node_delayed_start_test")
  83. defer os.RemoveAll(config.RootDir)
  84. now := tmtime.Now()
  85. // create & start node
  86. n, err := DefaultNewNode(config, log.TestingLogger())
  87. n.GenesisDoc().GenesisTime = now.Add(2 * time.Second)
  88. require.NoError(t, err)
  89. n.Start()
  90. startTime := tmtime.Now()
  91. assert.Equal(t, true, startTime.After(n.GenesisDoc().GenesisTime))
  92. }
  93. func TestNodeSetAppVersion(t *testing.T) {
  94. config := cfg.ResetTestRoot("node_app_version_test")
  95. defer os.RemoveAll(config.RootDir)
  96. // create & start node
  97. n, err := DefaultNewNode(config, log.TestingLogger())
  98. require.NoError(t, err)
  99. // default config uses the kvstore app
  100. var appVersion version.Protocol = kvstore.ProtocolVersion
  101. // check version is set in state
  102. state := sm.LoadState(n.stateDB)
  103. assert.Equal(t, state.Version.Consensus.App, appVersion)
  104. // check version is set in node info
  105. assert.Equal(t, n.nodeInfo.(p2p.DefaultNodeInfo).ProtocolVersion.App, appVersion)
  106. }
  107. func TestNodeSetPrivValTCP(t *testing.T) {
  108. addr := "tcp://" + testFreeAddr(t)
  109. config := cfg.ResetTestRoot("node_priv_val_tcp_test")
  110. defer os.RemoveAll(config.RootDir)
  111. config.BaseConfig.PrivValidatorListenAddr = addr
  112. dialer := privval.DialTCPFn(addr, 100*time.Millisecond, ed25519.GenPrivKey())
  113. pvsc := privval.NewSignerDialerEndpoint(
  114. log.TestingLogger(),
  115. config.ChainID(),
  116. types.NewMockPV(),
  117. dialer,
  118. )
  119. privval.SignerServiceEndpointTimeoutReadWrite(100 * time.Millisecond)(pvsc)
  120. go func() {
  121. err := pvsc.Start()
  122. if err != nil {
  123. panic(err)
  124. }
  125. }()
  126. defer pvsc.Stop()
  127. n, err := DefaultNewNode(config, log.TestingLogger())
  128. require.NoError(t, err)
  129. assert.IsType(t, &privval.SignerClient{}, n.PrivValidator())
  130. }
  131. // address without a protocol must result in error
  132. func TestPrivValidatorListenAddrNoProtocol(t *testing.T) {
  133. addrNoPrefix := testFreeAddr(t)
  134. config := cfg.ResetTestRoot("node_priv_val_tcp_test")
  135. defer os.RemoveAll(config.RootDir)
  136. config.BaseConfig.PrivValidatorListenAddr = addrNoPrefix
  137. _, err := DefaultNewNode(config, log.TestingLogger())
  138. assert.Error(t, err)
  139. }
  140. func TestNodeSetPrivValIPC(t *testing.T) {
  141. tmpfile := "/tmp/kms." + cmn.RandStr(6) + ".sock"
  142. defer os.Remove(tmpfile) // clean up
  143. config := cfg.ResetTestRoot("node_priv_val_tcp_test")
  144. defer os.RemoveAll(config.RootDir)
  145. config.BaseConfig.PrivValidatorListenAddr = "unix://" + tmpfile
  146. dialer := privval.DialUnixFn(tmpfile)
  147. pvsc := privval.NewSignerDialerEndpoint(
  148. log.TestingLogger(),
  149. config.ChainID(),
  150. types.NewMockPV(),
  151. dialer,
  152. )
  153. privval.SignerServiceEndpointTimeoutReadWrite(100 * time.Millisecond)(pvsc)
  154. go func() {
  155. err := pvsc.Start()
  156. require.NoError(t, err)
  157. }()
  158. defer pvsc.Stop()
  159. n, err := DefaultNewNode(config, log.TestingLogger())
  160. require.NoError(t, err)
  161. assert.IsType(t, &privval.SignerClient{}, n.PrivValidator())
  162. }
  163. // testFreeAddr claims a free port so we don't block on listener being ready.
  164. func testFreeAddr(t *testing.T) string {
  165. ln, err := net.Listen("tcp", "127.0.0.1:0")
  166. require.NoError(t, err)
  167. defer ln.Close()
  168. return fmt.Sprintf("127.0.0.1:%d", ln.Addr().(*net.TCPAddr).Port)
  169. }
  170. // create a proposal block using real and full
  171. // mempool and evidence pool and validate it.
  172. func TestCreateProposalBlock(t *testing.T) {
  173. config := cfg.ResetTestRoot("node_create_proposal")
  174. defer os.RemoveAll(config.RootDir)
  175. cc := proxy.NewLocalClientCreator(kvstore.NewKVStoreApplication())
  176. proxyApp := proxy.NewAppConns(cc)
  177. err := proxyApp.Start()
  178. require.Nil(t, err)
  179. defer proxyApp.Stop()
  180. logger := log.TestingLogger()
  181. var height int64 = 1
  182. state, stateDB := state(1, height)
  183. maxBytes := 16384
  184. state.ConsensusParams.Block.MaxBytes = int64(maxBytes)
  185. proposerAddr, _ := state.Validators.GetByIndex(0)
  186. // Make Mempool
  187. memplMetrics := mempl.PrometheusMetrics("node_test")
  188. mempool := mempl.NewMempool(
  189. config.Mempool,
  190. proxyApp.Mempool(),
  191. state.LastBlockHeight,
  192. mempl.WithMetrics(memplMetrics),
  193. mempl.WithPreCheck(sm.TxPreCheck(state)),
  194. mempl.WithPostCheck(sm.TxPostCheck(state)),
  195. )
  196. mempool.SetLogger(logger)
  197. // Make EvidencePool
  198. types.RegisterMockEvidencesGlobal() // XXX!
  199. evidence.RegisterMockEvidences()
  200. evidenceDB := dbm.NewMemDB()
  201. evidencePool := evidence.NewEvidencePool(stateDB, evidenceDB)
  202. evidencePool.SetLogger(logger)
  203. // fill the evidence pool with more evidence
  204. // than can fit in a block
  205. minEvSize := 12
  206. numEv := (maxBytes / types.MaxEvidenceBytesDenominator) / minEvSize
  207. for i := 0; i < numEv; i++ {
  208. ev := types.NewMockRandomGoodEvidence(1, proposerAddr, cmn.RandBytes(minEvSize))
  209. err := evidencePool.AddEvidence(ev)
  210. assert.NoError(t, err)
  211. }
  212. // fill the mempool with more txs
  213. // than can fit in a block
  214. txLength := 1000
  215. for i := 0; i < maxBytes/txLength; i++ {
  216. tx := cmn.RandBytes(txLength)
  217. err := mempool.CheckTx(tx, nil)
  218. assert.NoError(t, err)
  219. }
  220. blockExec := sm.NewBlockExecutor(
  221. stateDB,
  222. logger,
  223. proxyApp.Consensus(),
  224. mempool,
  225. evidencePool,
  226. )
  227. commit := types.NewCommit(types.BlockID{}, nil)
  228. block, _ := blockExec.CreateProposalBlock(
  229. height,
  230. state, commit,
  231. proposerAddr,
  232. )
  233. err = blockExec.ValidateBlock(state, block)
  234. assert.NoError(t, err)
  235. }
  236. func state(nVals int, height int64) (sm.State, dbm.DB) {
  237. vals := make([]types.GenesisValidator, nVals)
  238. for i := 0; i < nVals; i++ {
  239. secret := []byte(fmt.Sprintf("test%d", i))
  240. pk := ed25519.GenPrivKeyFromSecret(secret)
  241. vals[i] = types.GenesisValidator{
  242. pk.PubKey().Address(),
  243. pk.PubKey(),
  244. 1000,
  245. fmt.Sprintf("test%d", i),
  246. }
  247. }
  248. s, _ := sm.MakeGenesisState(&types.GenesisDoc{
  249. ChainID: "test-chain",
  250. Validators: vals,
  251. AppHash: nil,
  252. })
  253. // save validators to db for 2 heights
  254. stateDB := dbm.NewMemDB()
  255. sm.SaveState(stateDB, s)
  256. for i := 1; i < int(height); i++ {
  257. s.LastBlockHeight++
  258. s.LastValidators = s.Validators.Copy()
  259. sm.SaveState(stateDB, s)
  260. }
  261. return s, stateDB
  262. }