3abf4d7fdf
Merge branch 'master' into feature-remote-logs
2018-03-09 14:50:04 -08:00
91bb8faa45
Merge commit 'f773b9460d31d31b7d421860fc647936f31aa1fa'
...
# Conflicts:
# tests/fast/SidebandWithStatus.txt
# tests/rare/LargeApiCorrectnessStatus.txt
# tests/slow/DDBalanceAndRemoveStatus.txt
2018-03-09 14:47:03 -08:00
28ea983487
Merge branch 'release-5.1' into release-5.2
...
# Conflicts:
# flow/Trace.cpp
# versions.target
2018-03-09 14:40:31 -08:00
bb9f51bb5c
Don't try to extract attributes from the program start trace events if they couldn't be collected.
2018-03-09 11:55:57 -08:00
cf6dd1437b
suppress spammy trace events
2018-03-09 10:16:34 -08:00
ae7d8e90b2
Merge branch 'release-5.1' of github.com:apple/foundationdb into release-5.1
2018-03-09 09:56:09 -08:00
5390af8be4
suppress spammy logs
2018-03-09 09:40:36 -08:00
1bf9f0ec6b
Merge pull request #54 from etschannen/release-5.1
...
fix: new cluster controllers should not consider anything failed unti…
2018-03-09 09:28:21 -08:00
f9625f5b2f
fix: new cluster controllers should not consider anything failed until they have time to get failure monitoring updates
...
fix: storage and log class machines wait 100MS before attempting to become the cluster controller
2018-03-08 18:08:41 -08:00
e7309a3535
Add trace events to print the ranges in ConsistencyCheck.
2018-03-08 13:53:59 -08:00
cf9d02cdbd
Merge pull request #48 from apple/release-5.2
...
Merge release-5.2 into master
2018-03-08 13:21:26 -08:00
2c92ef8ff8
Merge pull request #47 from apple/release-5.1
...
Merge Release 5.1 into Release 5.2
2018-03-08 13:18:45 -08:00
73cec8abad
Merge branch 'release-5.1' of github.com:apple/foundationdb into release-5.1
2018-03-08 11:47:44 -08:00
4f58bca66a
Simple refactor of code...
2018-03-08 11:34:25 -08:00
1c1a497ea2
Refactor getKeyServers to be more readable.
...
Fix possible memory corruption by returning KeyRange instead of KeyRangeRef in getKeyServers.
Simplify getMasterProxies on DatabaseContext class.
2018-03-08 11:34:18 -08:00
03a40354e3
Having 1000 as the limit for Limit for GetKeyServerLocationsRequest sometimes generate large packet warnings. Reduce it to 100.
...
Fix the bug where some of the key server shards may not be fetched.
2018-03-08 11:34:11 -08:00
fdcaf473ae
Don't pass a copy of the StorageServerInterface to storageServerRollbackRebooter. This prevents a situation where the storage server has terminated but the request streams are left open until the underlying KV-store gets closed.
2018-03-08 11:14:24 -08:00
fa7eaea7cf
fix: shards affected by team failure did not properly handle separate teams for the remote and primary data centers
2018-03-08 10:50:05 -08:00
f838bc077e
Merge pull request #36 from ajbeamon/release-5.2
...
Set the address in consistency check processes…
2018-03-07 15:00:14 -08:00
9d4cdc828b
fix: inactive cursors are still useful if their version is larger than the current version
2018-03-07 12:54:53 -08:00
68606c7984
fix: sim2 logic for when a kill is safe was incorrect
2018-03-06 18:38:05 -08:00
2a2ac56529
Merge pull request #22 from alecgrieser/37844532-expose-append-if-fits
...
Expose APPEND_IF_FITS to clients
2018-03-06 16:31:36 -08:00
8c88041608
fix: we must commit to the number of log routers we are going to use when recruiting the primary, because it determines the number of log router tags that will be attached to mutations
2018-03-06 16:31:21 -08:00
232bd496bf
Set the address in consistency check processes in the same way we set it for clients so that it shows up in trace logs. Disallow specifying a public address for consistency check processes.
2018-03-06 15:40:04 -08:00
7f8f655b9c
Revert "Fix build errors"
...
This reverts commit 51804f0504
2018-03-06 10:28:39 -08:00
f2c804e14f
Reverting changes from merge of master into release-5.2 ( b25810711c). Note that we never intend to release master into release-5.2, but if we did we would need to revert this commit.
2018-03-06 10:15:04 -08:00
1194e3a361
added region-based configuration to support a large variety of fearless setups. Currently only 1 primary 1 remote setups are allowed.
2018-03-05 19:27:46 -08:00
aea1f7ba21
Add tests for Client Transaction Profiling correctness
2018-03-05 18:55:23 -08:00
51804f0504
Fix build errors
2018-03-05 15:18:14 -08:00
b25810711c
Merge branch 'master' into release-5.2
2018-03-05 10:32:57 -08:00
8ae640c062
Addressed review comments.
2018-03-02 17:56:49 -08:00
218b7a41e2
add APPEND_IF_FITS to workload and remove guard ; add command to vexillographer
2018-03-02 17:43:39 -08:00
11df1aeabf
Add new api to get shared tlogs id and address
2018-03-02 16:50:30 -08:00
470f5c01f3
changed remoteDcId to a vector of ids, to support future configurations where there are multiple remote databases
2018-02-26 17:09:09 -08:00
a67296b373
do not test fearless configurations to merge with master
2018-02-26 13:31:06 -08:00
8e966fdf9c
simulated cluster tests all configurations. Still needs to randomize the remote and satellite replication, along with them number of remote tlogs, log routers, and satellite tlogs
2018-02-26 13:15:44 -08:00
e3c6b66240
fix: do not commit more data after being stopped
...
fix: prioritize dc locality above exclusion to prevent being stuck after excluding all machines in a data center
2018-02-26 13:13:37 -08:00
37a6a81634
Merge commit '7f6fc3e039c911cd84b8540f7f799fc38a1c1822' into feature-remote-logs
...
# Conflicts:
# fdbserver/workloads/RestartRecovery.actor.cpp
2018-02-23 12:33:28 -08:00
cfcf98cffc
fix: log router tags were not stored at a best location
2018-02-23 12:26:19 -08:00
a49e43000e
fix: did not peek from log routers correctly
2018-02-22 16:13:56 -08:00
719bb5bd0c
Merge pull request #4 from bnamasivayam/getKeyServers-refactor
...
Having 1000 as the limit for Limit for GetKeyServerLocationsRequest s…
2018-02-22 12:39:48 -08:00
2fe2b522d5
Simple refactor of code...
2018-02-22 12:38:14 -08:00
e1162e9238
Merge remote-tracking branch 'upstream/release-5.1'
2018-02-22 11:16:12 -08:00
e2030db5a8
Refactor getKeyServers to be more readable.
...
Fix possible memory corruption by returning KeyRange instead of KeyRangeRef in getKeyServers.
Simplify getMasterProxies on DatabaseContext class.
2018-02-21 17:11:50 -08:00
2aa273df96
addStorageServer was advancing tags too much because of read errors
2018-02-21 17:05:39 -08:00
310f56d98a
fix: tlogs was resized incorrectly
2018-02-21 15:28:02 -08:00
ddb484143c
fix: do not peek from remote logs if they are not fully recovered
2018-02-21 14:06:44 -08:00
0bae9880f1
remove trailing whitespace from our copyright headers ; fixed formatting of python setup.py
2018-02-21 10:25:11 -08:00
6218934c7b
Having 1000 as the limit for Limit for GetKeyServerLocationsRequest sometimes generate large packet warnings. Reduce it to 100.
...
Fix the bug where some of the key server shards may not be fetched.
2018-02-20 17:41:34 -08:00
1dc6a8d4bd
fix: the tlog can peek from log systems that have been recovered even if it does not match its recoverFrom set
2018-02-20 14:50:13 -08:00
aadc06de99
Merge remote-tracking branch 'upstream/release-5.1'
2018-02-20 14:28:29 -08:00
9ea963ddd6
fix: the master did not detect core state changes if it changed while writing
...
fix: do not attempt to use three_data_hall when in a fearless deployment
fix: log router tags are ephemeral and can be cleared after every recovery
2018-02-19 16:49:57 -08:00
1b5628d2c5
testing a single configured fearless setup in simulated cluster
...
consolidated simulation connection disablers into one call in the tester
automatically reconfigure from a fearless setup in simulation
2018-02-18 12:59:43 -08:00
31b89a638f
added satellite_none and remote_none options to unconfigure from a fearless setup
...
fix: log_router configuration was broken
2018-02-17 13:51:17 -08:00
54fc81b260
Improved backup error reporting in backup status. The most recent error for each error type is reported along with how long ago the error occurred, and errors are divided into two categories based on whether or not they occurred since the most recent backup progress.
2018-02-16 19:38:31 -08:00
dc93759e15
suppressed trace events that are spammy
2018-02-16 16:01:19 -08:00
cb25564d38
simulated cluster supports fearless configurations
...
removed unused simulation variables
run the simulation with only 1 coordinator most of the time, since we protect the coordinator from being killed, and protecting too many things is bad for simulation
2018-02-15 18:32:39 -08:00
ad19d3926b
fix: make sure there are enough machines in each dc to support triple replication for the configure workload
2018-02-14 17:06:22 -08:00
5303962af6
re-enabled configure database and remove servers safely, even though they do not work with fearless
2018-02-14 16:07:23 -08:00
ead3892e77
fix: prevent fast spin for future version
2018-02-14 15:16:18 -08:00
110309272c
fix: do not count a server as read-write unless it has a recent version, because it could have been readable a long time ago
2018-02-14 15:09:19 -08:00
3300c2efed
Enable slow task profiling in the consistency check processes.
2018-02-14 09:50:12 -08:00
d2b0c07558
storage servers continue to attempt to pop old tags after the log system updates
2018-02-13 18:34:13 -08:00
1fedcba890
fix: do not use log router tags when configured without remote logs
...
fix: data distribution tracks undesired storage servers
re-enabled consistency check
2018-02-13 17:01:34 -08:00
a52ea4eb78
restored 5.1 functionality of simulated cluster. Will test assigned primary and remote data centers. Does not test remote replication or satellite logs
2018-02-10 13:27:51 -08:00
42405c78a5
Merge commit '4038bd2fd968d88861f2cebd442ce511724816cb' into feature-remote-logs
...
# Conflicts:
# fdbserver/ClusterController.actor.cpp
# fdbserver/Knobs.cpp
2018-02-10 12:08:52 -08:00
fbadcc6eea
changing a storage server’s tag must be the first mutations applied in a version, because privatized mutations applied earlier in the same version will use the old tag
2018-02-09 18:21:29 -08:00
c7b3be5b19
re-enabled better master exists
...
the cluster controller can choose a better data center for itself and let the workers know where the next cluster controller should be recruited
2018-02-09 16:48:55 -08:00
acb876d520
Merge branch 'release-5.1'
2018-02-07 15:11:52 -08:00
d0caffd339
fix: knob was set to incorrect value
2018-02-06 18:11:45 -08:00
3a49211c44
Merge branch 'release-5.1'
2018-02-06 13:58:35 -08:00
7de40413d5
Merge branch 'release-5.1' of github.com:apple/foundationdb into release-5.1
2018-02-06 13:44:25 -08:00
0792d5e3dd
Fix: last restorable version for a backup tag name (a separate value from the latest restorable version for a configured backup) was not being updated.
...
Fix: backup blob speed was sometimes an error because the JSON $sum merge operator did not support mixed numeric types.
Fix: JSON merge operator handling was squashing errors in some cases, which was generally obscuring the backup speed metric issue.
Cleaned up some of the JSON object merging logic.
Improved error messages in JSON merge operators. Added JSON merge operator tests for mixed numeric math and improved readability of test output.
2018-02-06 13:44:04 -08:00
b7dde88029
fix: the cluster controller did not consider the master sharing the same process as the cluster controller as bad in all needed locations
...
waited too long for good recruitment locations, which would add too much time to recoveries of clusters that do not use machine classes
2018-02-06 11:30:05 -08:00
63a9f2aed6
fix: history tags were being incorrectly popped
...
fix: history tags were not cleared when a storage server was removed
2018-02-03 12:20:18 -08:00
ebd94bb654
removed a separately configurable storage team size for the remote data center, because it did not make sense
...
fix: the master did not monitor for the failure of remote logs
stop merge attempts when a data center is failed
fixed a variety of other problems with data distribution when a data center is failed
2018-02-02 11:46:04 -08:00
766964ff48
fix: dest tags were not repopulated when the tag cache was cleared
2018-01-31 17:35:48 -08:00
0c601d6f85
Purge past version references
2018-01-31 12:05:41 -08:00
6b54d56ca7
gracefully exit if attempting to upgrade from 4.X versions
2018-01-30 17:10:50 -08:00
b48d8ce96d
getTeam will return an unhealthy exact match if all teams are unhealthy. Resubmit relocation requests once healthy teams are available
2018-01-30 17:00:51 -08:00
4160765fa1
added a buggify which reboots a server immediately after it has changed its locality
2018-01-29 18:21:28 -08:00
af97a512f5
to support more complicated policies in the future for determining the best location for a tag within a set of tlogs, use an integer instead of a bool
2018-01-29 17:48:18 -08:00
497bc3fe83
fix: txsTag needs to choose the same best location as 5.X version of the software
2018-01-29 17:09:35 -08:00
29c5d4ad3d
upgrades from 5.X mostly supported, still some remaining correctness problems
2018-01-28 11:52:54 -08:00
79d94214a4
Merge commit 'f4ffc9752b5ec66ac47f5f684a5d8be06a7eae6e' into feature-remote-logs
2018-01-25 10:12:06 -08:00
2744646090
Merge branch 'release-5.0' into release-5.1
2018-01-22 11:57:58 -08:00
188562ccbc
fix: Status should create its DatabaseConfiguration using fromKeyValues(). This makes sure that various state is correctly set if not specified in the configuration.
2018-01-22 11:40:08 -08:00
66b2218989
added tlog support for upgrading from 5.X clusters. Does not support upgrading from 4.X or earlier. Untested, storage servers still need the ability to change their tag.
2018-01-21 12:21:46 -08:00
698ef4117e
Merge branch 'master' into feature-remote-logs
2018-01-20 10:34:30 -08:00
b5eba4f13a
fix: do not check for desired data centers if they have not been set
2018-01-20 10:28:59 -08:00
35b91bfb55
Add back (in different form) some ratekeeper trace events when a storage server or log doesn't respond. Add actualTPS (named TPSBasis) to RkUpdate.
2018-01-18 14:51:38 -08:00
b78e0a362a
fix: do not pause when running multiple backup tests simultaneously
2018-01-18 12:24:33 -08:00
2e46ee3dba
fix: getTeam works when there are no teams
2018-01-17 17:49:13 -08:00
264dc44dfa
fixed many more bugs associated with running without remote logs
2018-01-17 17:03:17 -08:00
93b34a945f
Major usability and performance improvements to backup management. Backup descriptions now calculate and display timestamps using TimeKeeper data (if given a cluster) and restorability of snapshots. Expire now requires a --force option to leave a backup unrestorable or unrestorable after a given point in time, specified by version or timestamp. BackupContainerFilesystem now maintains metadata on key version boundaries in order to avoid large list operations for describe and expire operations. Blob parallel recursive list operations can now take a path (aka prefix) filter function. New describe and expire options are available in fdbbackup.
2018-01-17 04:09:43 -08:00
8f58bdd1cd
fixed a large number of problems related to running without remote logs
2018-01-16 18:12:40 -08:00
316e200a0c
fix: compilation errors after merge
2018-01-16 10:48:50 -08:00
21482a45e1
Merge branch 'master' into feature-remote-logs
...
# Conflicts:
# fdbserver/DBCoreState.h
# fdbserver/LogSystem.h
# fdbserver/LogSystemPeekCursor.actor.cpp
# fdbserver/TLogServer.actor.cpp
2018-01-14 13:40:24 -08:00
645dc5ead6
warmRange needs to get a read version occasionally to prevent it from overwhelming the proxy
...
quietDatabase waits for all data distribution to be completely finished so that databases are cached in a cleaner state
2018-01-14 12:50:52 -08:00
be643d6937
fix: the tlog did not cancel recovery properly when stopped
2018-01-12 17:18:14 -08:00
3915d6825c
we need to check the server list at a higher priority, because if we do not notice a storage server interface change for a long period of time, we will mark it as failed
2018-01-12 12:51:07 -08:00
de119f192d
fixed a priority inversion where the tlog would prefer to copy data from the previous generation rather than make data durable (leading to being ratekeeper controlled)
2018-01-11 16:09:49 -08:00
29ebb19388
Merge branch 'release-5.0' into release-5.1
2018-01-11 15:43:37 -08:00
22e5a0b257
formatting
2018-01-11 14:44:09 -08:00
173a8de3ed
DBCoreState supports upgrades from 3.0 versions
2018-01-11 14:39:51 -08:00
2f5073d00f
Some visual studio project cleanup.
2018-01-10 10:07:18 -08:00
022df3b91b
backup and restore sometimes took too long in simulation
2018-01-09 17:26:42 -08:00
645f68212b
make timekeeper priority system immediate
2018-01-08 18:21:00 -08:00
370e8a9903
fix: split metrics could fail an assert in a very rare scenario
2018-01-08 18:20:22 -08:00
9630deba3a
fixed a number of bugs related to running fearless without remote logs
2018-01-08 12:04:19 -08:00
d3116fb336
masterRecoveryDuration is only a sevWarnAlways outside of simulation
2018-01-07 15:37:45 -08:00
4e8bc273b3
added a version of getKeyRangeLocations that checks for endpoint failures
...
fix: did not add the cluster controller to id_used in all cases
removed obsolete fixmes
2018-01-07 15:32:43 -08:00
30710f7493
syncLogId was not necessary
2018-01-06 14:52:39 -08:00
3ec45d38a0
Merge branch 'master' into feature-remote-logs
...
# Conflicts:
# tests/fast/SidebandWithStatus.txt
# tests/rare/LargeApiCorrectnessStatus.txt
# tests/slow/DDBalanceAndRemoveStatus.txt
2018-01-06 13:54:45 -08:00
10c3fc165e
fix: after recovering from disk, only allow peeking data the was fully recovered
2018-01-06 13:49:13 -08:00
b86f68ceb8
Added new test that combines atomic backup/restore. Added randomization to delays in AtomicRestore workload.
2018-01-05 14:43:21 -08:00
63751fb0e2
fix: remote logs are not in the log system until the recovery is complete so they cannot be used to determine if this is the correct log system to recover from
2018-01-05 14:15:25 -08:00
5ac4f73978
Merge branch 'release-5.1' into feature-remote-logs
...
# Conflicts:
# fdbclient/NativeAPI.actor.cpp
# fdbrpc/Locality.h
# fdbrpc/simulator.h
# fdbserver/ApplyMetadataMutation.h
# fdbserver/ClusterController.actor.cpp
# fdbserver/LogSystemPeekCursor.actor.cpp
# fdbserver/MasterProxyServer.actor.cpp
# fdbserver/SimulatedCluster.actor.cpp
# fdbserver/TLogServer.actor.cpp
# fdbserver/TagPartitionedLogSystem.actor.cpp
# fdbserver/WorkerInterface.h
# fdbserver/masterserver.actor.cpp
# flow/Net2.actor.cpp
# tests/fast/SidebandWithStatus.txt
# tests/rare/LargeApiCorrectnessStatus.txt
# tests/slow/DDBalanceAndRemoveStatus.txt
2018-01-05 11:33:42 -08:00
5015119115
Generalize the message that gets displayed in status if a cluster file's contents are incorrect.
2018-01-05 10:29:47 -08:00
e11f461cbd
fix: better master exists needs to check master fitness before tlogs or proxies because that is the order of recruitment
2018-01-04 15:19:46 -08:00
f8f1c48d83
sometimes test pausing backups
2018-01-04 11:40:08 -08:00
f2c4beed9f
fix: tlogFitness did not consider it better to have one tlog of a better fitness
...
fix: checkStable was not used in all places in better master exists
fix: we need to call checkOutstanding on worker registration in all cases
fix: in case persistentData is keyValueStoreMemory, we need to make sure it is fully recovered before writing to it
2018-01-04 11:33:02 -08:00
6d5dd9bd27
fix: we cannot pipeline disk queue commits until after the first commit is successful
2018-01-02 13:30:27 -08:00
86958cb08d
Merge pull request #226 from cie/fix-taskBucket-unblockFuture
...
Modify TaskBucketCorrectness to support chain and multiple tasks
2017-12-20 18:00:54 -08:00
91e5abeaa6
Modify TaskBucketCorrectness to support chain and multiple tasks
2017-12-20 17:02:49 -08:00
f70e3b9fe8
Add or change a bunch of comments to provide descriptions of function contracts.
...
This cleans up a bit of the VersionStamp DR work I did, and leaves hints and
advice for anyone who will be touching mutation applying code in the future.
2017-12-20 16:57:14 -08:00
982f0dcb1e
Merge pull request #222 from cie/alexmiller/drtimefix2
...
Fix yet another VersionStamp DR issue.
2017-12-20 15:09:23 -08:00
b5a6bc0ab7
Fix VersionStamp problems by instead adding a COMMIT_ON_FIRST_PROXY transaction option.
...
Simulation identified the fact that we can violate the
VersionStamps-are-always-increasing promise via the following series of events:
1. On proxy 0, dumpData adds commit requests to proxy 0's commit promise stream
2. To any proxy, a client submits the first transaction of abortBackup, which stops further dumpData calls on proxy 0.
3. To any proxy that is not proxy 0, submit a transaction that checks if it needs to upgrade the destination version.
4. The transaction from (3) is committed
5. Transactions from (1) are committed
This is possible because the dumpData transactions have no read conflict
ranges, and thus it's impossible to make them abort due to "conflicting"
transactions. There's also no promise that if client C sends a commit to proxy
A, and later a client D sends a commit to proxy B, that B must log its commit
after A. (We only promise that if C is told it was committed before D is told
it was committed, then A committed before B.)
There was a failed attempt to fix this problem. We tried to add read conflict
ranges to dumpData transactions so that they could be aborted by "conflicting"
transactions. However, this failed because this now means that dumpData
transactions require conflict resolution, and the stale read version that they
use can cause them to be aborted with a transaction_too_old error.
(Transactions that don't have read conflict ranges will never return
transaction_too_old, because with no reads, the read snapshot version is
effectively meaningless.) This was never previously possible, so the existing
code doesn't retry commits, and to make things more complicated, the dumpData
commits must be applied in order. This would require either adding
dependencies to transactions (if A is going to commit then B must also be/have
committed), which would be complicated, or submitting transactions with a fixed
read version, and replaying the failed commits with a higher read version once
we get a transaction_too_old error, which would unacceptably slow down the
maximum throughput of dumpData.
Thus, we've instead elected to add a special transaction option that bypasses
proxy load balancing for commits, and always commits against proxy 0. We can
know for certain that after the transaction from (2) is committed, all of the
dumpData transactions that will be committed have been added to the commit
promise stream on proxy 0. Thus, if we enqueue another transaction against
proxy 0, we can know that it will be placed into the promise stream after all
of the dumpData transactions, thus providing the semantics that we require: no
dumpData transaction can commit after the destination version upgrade
transaction.
2017-12-20 15:04:04 -08:00
e0d9cea008
Merge branch 'master' into continuous-backup
...
# Conflicts:
# fdbclient/FileBackupAgent.actor.cpp
# fdbrpc/BlobStore.actor.cpp
2017-12-19 23:02:14 -08:00
c7dbd31a1e
Refactoring: Create a common prefixRange and do UID->Key once in backup.
2017-12-19 17:17:50 -08:00
1488c12c18
Simulation will return and error and print if any non-suppressed SevError events were logged.
...
This means that loops like `seed=1; while ./fdbserver -r simulation -s $seed;
do seed=$(($seed+1)); done` to find an example of an often failing test. This
also means joshua will report ExitCode errors on anything that has a SevError
in the log.
As a part of this, we also implicitly downgrade any injected errors to SevWarnAlways.
2017-12-19 17:17:50 -08:00
e28641886d
TraceEvent improvements. Minor bug fix, restore log writing tasks didn't have the log file endVersion but it's only for logging purposes.
2017-12-19 15:27:04 -08:00
a5601877b3
fix: valgrind issue with destruction ordering
2017-12-18 15:31:59 -08:00
1dc9eceb6d
optimize GetKeyLocationRequests on the proxy so they only require a single map lookup, instead of doing 3 + (3* [number of ranges]) lookups
2017-12-15 20:13:44 -08:00
33f9f1a95c
Added SnapshotDispatch task for writing snapshots in random order over a specified period of time and adapting speed to a growing or shrinking database. TaskBucket now supports scheduling tasks. TaskFuture now correctly recognizes multiple tasks in its callback space. TaskBucket extendTimeout() now supports specifying the new timeout version. Submitting a backup now requires a snapshot duration.
2017-12-14 01:44:38 -08:00
7ce93426ed
fix: connection disabler in removeServerSafely needs to run for the whole test to avoid getting stuck on include all
2017-12-12 18:38:57 -08:00
4495a19299
Merge pull request #220 from cie/alexmiller/flowprofcircus
...
Add class restrictions to CpuProfiler, and fix metric crash.
2017-12-11 14:13:22 -08:00
73a0a07eac
clients ask for key location information directly from the proxy, instead of reading it from the database
2017-12-09 16:10:22 -08:00
48660e9ce5
Add class restrictions to CpuProfiler, and fix metric crash.
...
This change largely refactors away the old meaning of the value given to
flow_profiler, which was the number of machines that we'd be profiling, and
instead replaces it with the classes of processes to profile for the duration
of the test. Most importantly, this means that one can profile in circus with
a configuration that has "ssd" in it, and the circus run will still complete
(as long as the argument isn't "storage").
And also finally add some other fixes I had to the same file to conditionally
change the name of the metric we're looking for to comply with what's actually
written.
2017-12-07 19:28:29 -08:00
abb2dd1ebc
Merge pull request #214 from cie/alexmiller/fallocate
...
Use fallocate to zero ranges instead of writing zeroes
2017-12-06 13:47:40 -08:00
5a947212ed
fix: ensure all prior commits have completed before returning that a commit has committed from the disk queue
2017-12-06 12:31:07 -08:00
f8e89a40ac
Bug fixes, take(1) is incorrect usage of FlowLock.
2017-12-04 10:25:47 -08:00
49dac11a5f
added a SevWarnAlways for when a disk queue file grows larger than 20GB
2017-12-01 15:05:17 -08:00
482ac38ca6
added knobs so that the client failure monitoring update rate and the server failure monitoring update rate are separate knobs
2017-12-01 13:04:32 -08:00
c3918d892a
do not use bandwidth splitting on the keyServer shard, lots of sets and clears to this shard generally means you do not want to create additional data distribution work
2017-11-30 18:28:16 -08:00
196258080b
Refactor zeroing a chunk of a file from DiskQueue into IAsyncFile.
...
If we're going to do the work to provide more optimized ways to zero files,
then I'd feel better with this being in a more common place, so that any other
zero-ers are likely to reuse it. It also makes testing easier/more obvious.
Also, because it's needed for correctness, fix the aligned_alloc for OSX, which
wasn't aligned, and use an actually aligned allocation function.
2017-11-30 17:57:55 -08:00
c7a120c59d
Rename IAsyncFile::incrementalDelete -> IAsyncFileSystem::incrementalDeleteFile.
...
`deleteFile` existed in IAsyncFileSystem, so an incremental delete function
seems to belong more as a virtual method on IAsyncFileSystem than a static
method on IAsyncFile, and the naming should match.
As long as we're here, change IAsyncFile to declare a virtual destructor, so
that it has good and proper C++ behavior. I presume this is what was vaguely
intended by the default constructor definition that previously existed?
2017-11-30 17:19:10 -08:00
7f72aa7de5
fix: a storage server does not ever need to rollback before a version restored from disk
2017-11-30 11:19:43 -08:00
e5a682948c
Merge pull request #212 from cie/check-cluster-controller-desired-class
...
Check cluster controller using desired process class in consistency c…
2017-11-29 15:57:51 -08:00
8ba0eaebff
Check cluster controller using desired process class in consistency check
2017-11-29 15:09:23 -08:00
8c51bc4ac4
fixed low latency tests in a way that gives us better test coverage
2017-11-28 18:20:29 -08:00
dc624a54dc
fix: avoid flushing large queues in simulation when checking latency
2017-11-27 17:23:20 -08:00
1b1c8e985a
Merge branch 'master' into backup-container-refactor
...
# Conflicts:
# fdbclient/FileBackupAgent.actor.cpp
2017-11-25 19:54:51 -08:00
6695c9e6a2
Bug fixes and improvements to error handling and trace events. The most serious bug was that restore would start at the wrong version, possibly skipping early log and range files.
2017-11-25 00:46:16 -08:00
f19cb3bbbd
Merge pull request #208 from cie/alexmiller/grvtfix
...
Fix the GRV performance regression
2017-11-17 15:00:44 -08:00
d9a98aa968
Remove commented code
2017-11-16 17:25:37 -08:00
0d5dc15ac8
Fix double recoveries
2017-11-16 16:58:55 -08:00
e9412bbb11
Fix the GRV performance regression introduced by adding the policy engine to GRV calculations.
...
Construction of LocalityGroup from LocalityData is expensive, and the previous
code greatly ran afoul of that. The policy engine does a large amount of
interning of strings and building compressed maps to make the expected many
future selectReplica calls cheap. Unfortunately we don't call selectReplicas,
so much of this work is undesireable for us, and a large amount of CPU time is
spent doing this initialization work.
The new changes aggressively do the minimal LocalityGroup::add() calls
necessary, and make them as cheap as possibly by removing all elements from
LocalityData that don't need to be considered by the policy.
This optimization was also applied to the PeekCursor used during recovery,
which should speed recoveries up by a small amount.
2017-11-16 16:15:52 -08:00
ad456a939a
Merge pull request #206 from cie/change-excluded-cluster-controller
...
Change excluded cluster controller
2017-11-15 17:28:33 -08:00
f96faf72d9
Add fullyRecoveredConfig for checking exclusions
2017-11-15 17:15:24 -08:00
30464e943c
Merge pull request #205 from cie/cleanup-spammy-traceevents
...
Cleanup spammy traceevents
2017-11-15 12:41:37 -08:00
e113dba0e3
added a new trace event tracking master recovery durations
2017-11-15 12:38:26 -08:00
a77162b53d
Merge branch 'master' into backup-container-refactor
...
# Conflicts:
# fdbclient/BackupAgent.h
# fdbclient/FileBackupAgent.actor.cpp
# fdbclient/KeyBackedTypes.h
2017-11-15 08:14:47 -08:00
3dfaf13b67
IBackupContainer has been rewritten to be a logical interface for storing, reading, deleting, expiring, and querying backup data. The details of how the data is organized or stored is now hidden from users of the interface. Both the local and blobstore containers have been rewritten, the key changes being a multi level directory structure and no more use of temporary files or pseudo-symlinks in the blob store implementation. This refactor has a large impact radius as the previous backup container was just a thin wrapper that presented a single level list of files and offered no methods for managing or interpreting the file structure so all of that logic was spread around other places in the code base. This made moving to the new blob store schema very messy, and without this refactor further changes in the future would only be worse.
...
Several backup tasks have been cleaned up / simplified because they no longer need to manage the ‘raw’ structure of the backup. The addition of IBackupFile and its finish() method simplified the log and range writer tasks. Updated BlobStoreEndpoint to support now-required bucket creation and bucket listing prefix/delimiter options for finding common prefixes. Added KeyBackedSet<T> type. Moved JSONDoc to its own header. Added platform::findFilesRecursively().
Still to do: update command line tool to use new IBackupContainer interface, fix bugs in Restore startup.
2017-11-14 23:33:17 -08:00
df922bc973
Change excluded cluster controller
2017-11-14 13:57:37 -08:00
bb1297c686
Remove RkServerQueueInfo and RkTLogQueueInfo trace events, since this information is more or less already logged on the storage servers and tlogs. Update the quiet database check and magnesium to use the information from the logs and storage servers.
2017-11-14 12:59:42 -08:00
3b952efb4e
Remove events from cluster controller that get logged for roughly every worker upon recovery, master registration, etc.
2017-11-14 10:15:45 -08:00
0fea5e9c2f
Convert client_invalid_operation errors to ASSERTs.
2017-11-13 11:38:34 -08:00
cd085764f1
Do not automatically change a cluster file that does not match what you expect.
2017-11-10 14:12:45 -08:00
311d1ca87d
A variety of fixes that collectively fix using flow profiling in circus.
...
To run, use --co=flow_profiling=-1, because reasons.
2017-11-07 13:55:16 -08:00
706bf1e018
fix: we cannot trigger better master exists before a master is fully recovered because exclusions changed by the provisional master will not be committed until the master is fully recovered
2017-11-04 12:48:04 -07:00
57aba0b3bc
fix: excluded servers were the same fitness as storage servers for the master role
...
fix: better master exists did not considers exclusion for master fitness
2017-11-03 17:09:14 -07:00
42fad5efe5
Introduce cluster controller process class in circus
2017-11-03 14:22:55 -07:00
dcc9aafab7
Merge branch 'master' of github.com:apple/foundationdb
2017-11-02 10:47:59 -07:00
c033d8efd8
Fix typo message and remove extra TraceEvent which overwrites the expected one
2017-11-02 10:47:51 -07:00
3efaaec479
onMasterProxiesChanged was being triggered when any member of ClientDBInfo changed. Change the behavior to be triggered only when proxies field in ClientDBInfo is changed.
2017-11-01 18:29:56 -07:00
7cf17df821
Merge branch 'master' into log-group-for-unsupported-clients
...
# Conflicts:
# flow/Net2.actor.cpp
# tests/fast/SidebandWithStatus.txt
# tests/rare/LargeApiCorrectnessStatus.txt
# tests/slow/DDBalanceAndRemoveStatus.txt
2017-11-01 11:31:02 -07:00
31caac67dc
Rename supported_versions[x].clients to supported_versions[x].connected_clients
2017-11-01 10:41:30 -07:00
988bc0207f
Reset Client Transaction profiling parameters when the config keys are cleared.
2017-10-31 15:40:57 -07:00
5a4a5985fd
Merge branch 'release-5.0'
2017-10-30 08:31:23 -07:00
87321f5017
Merge branch 'release-4.6' into release-5.0
2017-10-30 08:31:01 -07:00
54d82c0d92
Merge pull request #194 from cie/alexmiller/valgrind
...
Fix valgrind errors
2017-10-27 17:25:12 -07:00
e0d33ef8d7
Preemptively fix profiler-related valgrind errors/straight out bugs.
...
I forgot to initialize some fields in requests.
2017-10-27 17:20:19 -07:00
aa0c2ae317
only increase the max shard size if the shard begins in the keyServer keyspace, do not increase the minimum shard size
2017-10-27 14:22:26 -07:00
3a4078bdda
the keyservers shards are always a fixed large size
2017-10-27 11:52:11 -07:00
cfefab18fb
Merge branch 'master' into add-new-atomic-ops
2017-10-25 18:03:34 -07:00
3d5658940a
Addressed Review Comments
2017-10-25 16:42:05 -07:00
9dd588dcce
Addressed review comments.
...
Changed naming for NewMin and NewAnd to MinV2 and AndV2
2017-10-25 14:48:05 -07:00
d852a53ae4
Merge pull request #181 from cie/throttle-spammy-logs
...
Throttle spammy logs
2017-10-25 13:45:55 -07:00
2f6d55a52f
Add correctness tests for all atomic ops
2017-10-25 13:36:49 -07:00
4d54a73f5b
Merge pull request #191 from cie/count-cluster-controller-role
...
Take cluster controller role into consideration when recruiting workers
2017-10-25 12:09:15 -07:00
f39cce9b8d
Use processId instead of address for comparison
2017-10-25 11:35:29 -07:00
5fcef911f0
Take cluster controller role into consideration when recruiting workers
2017-10-25 10:35:46 -07:00
48901a9223
added a list of tlog IDs that are missing to status
2017-10-24 16:28:50 -07:00
c2a117fe07
Merge pull request #189 from cie/enable-check-desired-class
...
Enable checkUsingDesiredClasses() in consistency check
2017-10-24 15:18:21 -07:00
defdc6550d
Exclude excluded processses when getting testers
2017-10-24 15:16:34 -07:00
df74e2a373
re-added support for non-copying tlog recovery
2017-10-24 15:09:31 -07:00
3865c5ae0e
Enable checkUsingDesiredClasses() in consistency check
2017-10-24 12:58:54 -07:00
8c3bdc5b3b
Make atomic ops differentiate between unset and empty values.
2017-10-23 16:48:13 -07:00
7a36fd2134
disabled a variety of simulation tests to get correctness clean
2017-10-19 15:49:54 -07:00
e2c1e87df6
made a large number of fixes to make fearless DR correctness clean.
2017-10-19 15:36:32 -07:00
360b777b78
Fail with correct error code in case of abort or discontinue of
...
non-existing backups.
2017-10-18 23:17:48 -07:00
dd6d8f3b0e
Merge branch 'master' into add-new-atomic-ops
2017-10-18 16:36:44 -07:00
2007f3799f
Don't ignore TimeKeeper failures.
2017-10-18 14:31:31 -07:00
314511f4d7
Fixing spaces in BackupCorrectness TraceEvents.
2017-10-18 14:27:52 -07:00
7b9bc1d715
Merge pull request #170 from cie/alexmiller/flowprofile
...
Add support for profiling a running fdb cluster to fdbcli, fix security issues, and add an improved backtrace.
2017-10-16 16:51:53 -07:00
f997cb9038
Add a string knob to hold the Log directory, and write profiles to it.
...
This is the combination of two small changes.
1. Add support for a string knob type.
2. Change profiles to be written to the log directory instead of the working
directory.
We have three options of where to write files: the working directory, the data
directory, and the log directory.
The working directory may be set to a non-writable location, and likely
contains the fdb binaries. Allowing these files to be overwritten would likely
not be a wise idea.
The data directory hosts our sqlite b-trees. It would also be very unfortunate
if these were ever overwritten by an unfortunate profile name.
The log directory contains logs. Out of the three, these matter the least if
they disappear or become corrupted.
Thus, we write to the log directory.
2017-10-16 16:05:02 -07:00
c5fbe33df6
Disallow arbitrary paths for storing profiles.
...
Previously, one could request profiles to be stored at
"../../../../../../etc/passwd". Now we expand the paths, including symlinks,
and ensure that the target is a child of the targetted subdirectory. This was
the least convoluted way I could figure out to handle paths.
2017-10-16 16:05:02 -07:00
91a26a170c
Add toggleable profiling support to fdbserver+fdbcli.
...
This adds the fdbcli commands:
* profile list -- Lists all workers in a way that doesn't fill `kill`'s list.
* profile flow run -- Allows starting flow profiling on a set of hosts for a specified interval.
And threads through all the support for enabling and disabling profiling as an RPC.
2017-10-16 16:05:02 -07:00
312f614133
Add the new ops and AND to NON_ASSOCIATIVE_MASK.
...
In the storage server, read the entire value if the op is ByteMin or ByteMax.
2017-10-16 11:06:31 -07:00
e0be1ef1e0
Merge branch 'release-5.0'
2017-10-16 10:08:11 -07:00
432726ba2d
Merge branch 'release-4.6' into release-5.0
2017-10-16 09:54:21 -07:00
68eccb681e
Merge pull request #173 from bmuppana/master
...
Backup log messages.
2017-10-13 18:31:53 -07:00
215bcb8d3e
Merge pull request #157 from cie/choose-leader-on-stateless-processes
...
Catch and update processClass change from DBSource
2017-10-13 14:03:29 -07:00
5bcdd37c0d
Move UID generation and add initialClass
2017-10-13 13:46:37 -07:00
12edd27281
Introduce prevChangeID to CandidacyRequest and LeaderHeartbeatRequest
2017-10-12 17:11:58 -07:00
d1e9d28239
Backup log messages.
2017-10-12 16:12:42 -07:00
11517f7bfc
Merge branch 'master' into continuous-backup
...
# Conflicts:
# fdbclient/FileBackupAgent.actor.cpp
2017-10-12 11:03:23 -07:00
c24b941485
Fix erroneous std::move in indexed set, and clean up addMetric users.
...
This is a follow-on to c4eb73d0. Thanks to Bala for pointing out the unchanged
std::move usage, and there appeared to not be many existing users of addMetric
anyway.
2017-10-11 17:36:51 -07:00
8e0bea2795
Update API_VERSION from 500 to 510
2017-10-11 13:49:38 -07:00
c3d8412abb
Merge pull request #166 from cie/alexmiller/deathservice
...
Fix potential division by zero issues via RPC.
2017-10-10 16:47:38 -07:00
ff1b49be2e
Merge branch 'master' into feature-remote-logs
...
# Conflicts:
# fdbserver/DatabaseConfiguration.cpp
2017-10-10 16:07:59 -07:00
8feb3b8fbc
fixed conflict range workload by just disabling timeKeeper instead of the check, because it should be a more robust fix
2017-10-10 16:01:02 -07:00
eeebf10030
Modified existing behavior of MIN and AND atomic ops. The new behavior results in a 'SET' if the atomic op is performed on a non -existing key.
...
Added new atomic ops ByteMin and ByteMax that does lexicographic comparison of byte strings.
2017-10-10 13:02:22 -07:00
c8525dc3e7
timekeeper is constantly changing keys in the system keyspace, so do not report errors on key mismatches on keys in the system keyspace
2017-10-10 12:04:56 -07:00
3d2103075d
data distribution tracks teams for each data center separately
2017-10-10 10:36:33 -07:00
5e6eba365b
fix: always set confChange, because popVersion is not deterministic across proxies, and confChange needs to be set deterministically
2017-10-06 18:37:08 -07:00
93b3d0e4e7
fix: toMap didn’t report logs proxies and resolvers
2017-10-06 15:55:50 -07:00
15962cf079
Merge branch 'master' into feature-remote-logs
...
# Conflicts:
# fdbrpc/Locality.cpp
# fdbrpc/Locality.h
# fdbserver/ClusterController.actor.cpp
# fdbserver/ClusterRecruitmentInterface.h
# fdbserver/TLogServer.actor.cpp
# fdbserver/TagPartitionedLogSystem.actor.cpp
# fdbserver/WorkerInterface.h
# fdbserver/fdbserver.vcxproj.filters
# fdbserver/masterserver.actor.cpp
# fdbserver/worker.actor.cpp
# flow/error_definitions.h
2017-10-05 17:09:44 -07:00
a21c8a820b
Move cpuProfilerRequest from WorkerInterface to ClientWorkerInterface.
...
A way to access this stream is required if we wish to be able to toggle
profiling from fdbcli. There's two ways to do this:
1. Use `monitorLeader()` to get a `ClusterControllerFullInterface`, and use
`getWorkers` from there to get a list of `WorkerInterface`s, from which we can
access cpuProfilerRequest.
2. Move cpuProfilerRequest to ClientWorkerInterface and use the existing code
in the client that can fetch a list of all `ClientWorkerInterface`s.
The split between WorkerInterface and ClientWorkerInterface appears to be
what a client might have a need to call versus what is fdbserver-internal (and
thus no client should even want to call). Thus, it seems to make more sense to
acknowledge that profiling is useful to be able to toggle from a client, and go
with option (2).
2017-10-05 14:08:28 -07:00
3edc2824a9
Add initialClass to RegisterWorkerRequest 2
2017-10-05 11:03:25 -07:00
05f7626e39
Add initialClass to RegisterWorkerRequest
2017-10-04 17:11:12 -07:00
3c70df57b5
Fix cluster controller review comments
2017-10-04 15:48:55 -07:00
e55cc447d2
Address code review comments.
...
* Fixed memory corruption with SystemData key constants
* Removed duplication in ClusterController
* Reworked fdbcli actions to better represent explicit vs default assignments
2017-10-04 13:36:18 -07:00
5063793f36
Revert line ending change
2017-10-04 11:19:19 -07:00
706427ee62
Fix potential division by zero issues via RPC.
...
A carefully crafted SplitMetricRequest could have caused division by zero.
It's not really great to offer Division By Zero As A Service, so let's just
return an error instead.
2017-10-03 22:11:08 -07:00
3a2ddcc84a
Add destinations that are read-write to the source list, so that cancelled data movement can contribute to copying the data for the next movement.
2017-10-03 17:39:08 -07:00
0e153cdd35
Throttle Spammy logs. Three knobs are added.
...
Trace Events are sampled and cached with an expiration set. Every TraceEvent above SevDebug is checked against this cache to see if it exceeded a set threshold. If yes, then throttle the TraceEvent.
If a TraceEvent is throttled, a warning msg is logged.
2017-10-02 18:43:11 -07:00
6ea9903c82
Merge branch 'release-5.0'
...
# Conflicts:
# fdbbackup/backup.actor.cpp
# fdbserver/ClusterController.actor.cpp
# versions.target
2017-10-01 18:46:44 -07:00
0949c4be65
Revert "Fixed problem with master being recruited on excluded servers"
...
This reverts commit 1f7b624734a8ad6e896dd3f01f9cdf334ca62486.
2017-10-01 16:30:19 -07:00
696d432462
Revert "fix: excluded servers are worst fit for master rather than never assign (so that we can recover if every process has been excluded)"
...
This reverts commit 83b2ce68c8e1a29fc1559598cc38d3ef7eb46101.
2017-10-01 16:29:32 -07:00
0dde15f1d2
fix: excluded servers are worst fit for master rather than never assign (so that we can recover if every process has been excluded)
...
fix: better master exists did not use exclusions because the configuration was reset
2017-10-01 16:26:58 -07:00
636ce4a131
Replace leader when find a better one
2017-09-29 16:34:55 -07:00
11668bb359
Fixing code review comments.
2017-09-29 15:58:36 -07:00
b7ce9d996c
Comment out verbose TraceEvents in preparation for pushing.
2017-09-29 15:58:36 -07:00
c40c1bb5fe
Add a new workload: BackupToDBAbort, which does an ACI switchover.
...
This is to allower easier testing of non-durable switchovers without having to
wiggle into BackupToDBCorrectness's view of the world.
2017-09-29 15:58:36 -07:00
9e9a96ae76
Make VersionStamp workload able to run with DR-style workloads.
...
* It is now tolerant of locked database errors, and handles them correctly.
* There is an option to specify which database to verify against.
2017-09-29 15:58:36 -07:00
34630b6130
Make VersionStamp workload can handle commit_unknown_result.
...
Previously, if a transaction failed with commit_unknown_result, and was
actually committed, it would look like data that magically appeared in the
database and verification would fail.
Now, we explicitly re-read and check to see if the commit happened, so that we
may maintain an accurate understanding of what the database state should be.
2017-09-29 15:58:36 -07:00
23945b9fea
VersionStamp can co-exist with other workloads that write data to the database.
...
VersionStamp previously would range-read the entire database during validation.
This has the unfortunate effect of making it fail during validation if run with
any other workload that writes keys to the database.
Now, all keys written and read are done with a configurable prefix, so that it
may co-exist with a variety of other workloads.
2017-09-29 15:58:36 -07:00
370a6afb80
Make VersionStamp have an option to be tolerant of data being lost.
2017-09-29 15:58:36 -07:00
Evan Tschannen