As per #3043, this adds a ticker to sync the WAL every 2s while the WAL is running.
* Flush WAL every 2s
This adds a ticker that flushes the WAL every 2s while the WAL is
running. This is related to #3043.
* Fix spelling
* Increase timeout to 2mins for slower build environments
* Make WAL sync interval configurable
* Add TODO to replace testChan with more comprehensive testBus
* Remove extraneous debug statement
* Remove testChan in favour of using system time
As per
https://github.com/tendermint/tendermint/pull/3300#discussion_r255886586,
this removes the `testChan` WAL member and replaces the approach with a
system time-oriented one. In this new approach, we keep track of the
system time at which each flush and periodic flush successfully
occurred.
The naming of the various functions is also updated here to be more
consistent with "flushing" as opposed to "sync'ing".
* Update naming convention and ensure lock for timestamp update
* Add Flush method as part of WAL interface
Adds a `Flush` method as part of the WAL interface to enforce the idea
that we can manually trigger a WAL flush from outside of the WAL. This
is employed in the consensus state management to flush the WAL prior to
signing votes/proposals, as per https://github.com/tendermint/tendermint/issues/3043#issuecomment-453853630
* Update CHANGELOG_PENDING
* Remove mutex approach and replace with DI
The dependency injection approach to dealing with testing concerns could
allow similar effects to some kind of "testing bus"-based approach. This
commit introduces an example of this, where instead of relying on
(potentially fragile) timing of things between the code and the test, we
inject code into the function under test that can signal the test
through a channel.
This allows us to avoid the `time.Sleep()`-based approach previously
employed.
* Update comment on WAL flushing during vote signing
Co-Authored-By: thanethomson <connect@thanethomson.com>
* Simplify flush interval definition
Co-Authored-By: thanethomson <connect@thanethomson.com>
* Expand commentary on WAL disk flushing
Co-Authored-By: thanethomson <connect@thanethomson.com>
* Add broken test to illustrate WAL sync test problem
Removes test-related state (dependency injection code) from the WAL data
structure and adds test code to illustrate the problem with using
`WALGenerateNBlocks` and `wal.SearchForEndHeight` to test periodic
sync'ing.
* Fix test error messages
* Use WAL group buffer size to check for flush
A function is added to `libs/autofile/group.go#Group` in order to return
the size of the buffered data (i.e. data that has not yet been flushed
to disk). The test now checks that, prior to a `time.Sleep`, the group
buffer has data in it. After the `time.Sleep` (during which time the
periodic flush should have been called), the buffer should be empty.
* Remove config root dir removal from #3291
* Add godoc for NewWAL mentioning periodic sync
Earlier this week somebody posted this in GoS Riot chat:
```
E[2019-02-12|10:38:37.596] Corrupted entry. Skipping... module=consensus wal=/home/gaia/.gaiad/data/cs.wal/wal err="DataCorruptionError[length 878916964 exceeded maximum possible value of 1048576 bytes]"
E[2019-02-12|10:38:37.596] Corrupted entry. Skipping... module=consensus wal=/home/gaia/.gaiad/data/cs.wal/wal err="DataCorruptionError[length 825701731 exceeded maximum possible value of 1048576 bytes]"
E[2019-02-12|10:38:37.596] Corrupted entry. Skipping... module=consensus wal=/home/gaia/.gaiad/data/cs.wal/wal err="DataCorruptionError[length 1631073634 exceeded maximum possible value of 1048576 bytes]"
E[2019-02-12|10:38:37.596] Corrupted entry. Skipping... module=consensus wal=/home/gaia/.gaiad/data/cs.wal/wal err="DataCorruptionError[length 912418148 exceeded maximum possible value of 1048576 bytes]"
E[2019-02-12|10:38:37.600] Corrupted entry. Skipping... module=consensus wal=/home/gaia/.gaiad/data/cs.wal/wal err="DataCorruptionError[failed to read data: EOF]"
E[2019-02-12|10:38:37.600] Error on catchup replay. Proceeding to start ConsensusState anyway module=consensus err="Cannot replay height 7242. WAL does not contain #ENDHEIGHT for 7241"
E[2019-02-12|10:38:37.861] Error dialing peer module=p2p err="dial tcp 35.183.126.181:26656: i/o timeout
```
Note the length error messages. What has happened is the length field got corrupted probably. I've looked at the code and noticed that we don't check the msg size during encoding. This PR fixes that. It also improves a few error messages in WALDecoder.
* 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.
* fix Group.RotateFile need call Flush() before rename. #2428
* fix some review issue. #2428
refactor Group's config: replace setting member with initial option
* fix a handwriting mistake
* fix a time window error between rename and write.
* fix a syntax mistake.
* change option name Get_ to With_
* fix review issue
* fix review issue
* remove ConsensusParams.TxSize and ConsensusParams.BlockGossip
Refs #2347
* block part size is now fixed
Refs #2347
* use max data size, not max bytes for tx limit
Refs #2347
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
