12ccd3b146
typo
2022-07-20 09:35:57 -05:00
e0f6897481
fixing merge conflicts
2022-07-20 09:11:37 -05:00
b521dc2f58
Bind DeterministicRandom to OpenSSL RNG
2022-07-20 16:03:09 +02:00
6e43a50ea1
cleanup
2022-07-20 08:39:32 -05:00
5540f92e2e
Refactoring randomExp to the proper place
2022-07-20 08:36:03 -05:00
e3cbd63b6d
fixing merge conficts
2022-07-20 08:20:48 -05:00
3f8f44dd16
Merge branch 'main' into improved_cf_testing
2022-07-20 08:19:52 -05:00
922a4523a1
disabling popped data checking again
2022-07-20 08:19:27 -05:00
0b674bf0c4
Merge branch 'main' into cf_bw_operational_fixes
2022-07-20 08:03:59 -05:00
fd9201f60b
Merge branch 'main' into cf_metadata_rewrite
2022-07-20 07:55:00 -05:00
44885aa719
cleanup
2022-07-20 07:46:57 -05:00
78b6a96006
Merge branch 'main' into granule_merging_batch
2022-07-20 07:42:26 -05:00
4000682578
moving comment
2022-07-20 07:35:30 -05:00
0874e553cd
Place generateRandomData() under {I|Deterministic}Random
2022-07-20 13:21:11 +02:00
0f094d2aa1
Fix ScopeEventFieldTypeMismatch error for TLogMetrics
...
Backport changes made to TLogServer in #4616 back to old TLog implementations.
Old implementations were using SpecialCounter, which is string. The new type
is int64_t. Without the change, we can have many events like:
<Event Severity="30" Time="1658165532.958152" DateTime="2022-07-18T17:32:12Z" Type="ScopeEventFieldTypeMismatch" ID="0000000000000000" EventType="TraceEvent.TLogMetrics" FieldName="QueueDiskBytesUsed" OldType="Int64" NewType="String" ThreadID="2451559325190099131" Machine="10.242.248.26:4703" LogGroup="xxxx" Roles="TL" />
2022-07-19 22:27:29 -07:00
a7469b925b
Merge pull request #7630 from jzhou77/main
...
Add getMappedRange latency metrics
2022-07-19 22:13:50 -07:00
e8baba8009
Merge pull request #7575 from xis19/lb
...
Notes on Load Balancer
2022-07-19 17:50:25 -07:00
12b6f386cb
Refactoring granule flush to retry properly on granule rollback
2022-07-19 19:49:20 -05:00
c357a90b30
Ensure change coordinators request came from same generation proxy
...
There was a rare but possible issue where a change coordinators request
could be in flight, but reading `\xff/coordinators` would return the old
set of coordinators, even though a previous attempt to write it returned
`commit_unknown_result`. This happened if there was an unrelated
recovery between setting `\xff/coordinators` and the updated
coordinators reaching each machine. The `commit_unknown_result` caused
by this recovery meant the change coordinators retry loop would read
`\xff/coordinators`, but since the request was ongoing it would read the
old set of coordinators. The fix is to have the cluster controller
ignore any change coordinators request from an old generation, meaning
when the retry loop reads the old coordiantors from `\xff/coordinators`,
it is guaranteed that the in progress change coordinators message will
be rejected when arriving at the cluster controller.
2022-07-19 17:44:48 -07:00
8d2cde32d9
Added global-tag-throttling.md
2022-07-19 17:04:04 -07:00
8a18fa23cf
Reenable GlobalTagThrottler_GotClientRate trace events
2022-07-19 17:04:04 -07:00
f197314cb5
Add /GlobalTagThrottler/MultiTagActiveThrottling3 unit test
2022-07-19 17:04:04 -07:00
118eb4d93b
Add /GlobalTagThrottler/MultiTagActiveThrottling2 unit test and fix bug uncovered in GlobalTagThrottlerImpl::getLimitingTps
2022-07-19 17:04:04 -07:00
b4e711f1c3
Make parameter more readable in GlobalTagThrottlerTesting::runClient
2022-07-19 17:04:04 -07:00
20ac60fb11
Set throttling ratio in GlobalTagThrottler::tryUpdateAutoThrottling
2022-07-19 17:04:04 -07:00
f41515e66b
Implement GlobalTagThrottler::busy*TagCount methods
2022-07-19 17:04:01 -07:00
166de4b704
Fixing merge convergence bugs
2022-07-19 18:44:40 -05:00
72e72f6d87
Add getMappedRange latency metrics
2022-07-19 16:31:24 -07:00
afba51b7f8
Add tracing to GlobalTagThrottler
2022-07-19 16:29:11 -07:00
fe05cc5c72
Update busy read tag reporting in status json
2022-07-19 16:29:11 -07:00
145d10e3a4
Compute cluster-wide average transaction cost for each tag only once in getClientRates
2022-07-19 16:29:11 -07:00
080518d014
Use getQuota method in GlobalTagThrottlerImpl::getDesiredTps
2022-07-19 16:29:11 -07:00
d0851a67e2
Update TransactionTagCounter::startNewInterval tracing
2022-07-19 16:29:11 -07:00
2306757e90
Fix GlobalTagThrottler::autoThrottleCount
2022-07-19 16:29:11 -07:00
4977805d8e
Fix failing global tag throttling unit tests
2022-07-19 16:29:11 -07:00
c86ae6cee5
Fix /GlobalTagThrottler/Simple unit test
2022-07-19 16:29:11 -07:00
e128c517d3
New GlobalTagThrottler implementation tracking more per-storage
...
server metrics
2022-07-19 16:29:11 -07:00
6a63db08c8
Added /GlobalTagThrottler/ReservedWriteQuota unit test
2022-07-19 16:29:11 -07:00
5b0eb135e0
Guarantee reserved quota in GlobalTagThrottler
2022-07-19 16:29:11 -07:00
8e08033974
Add /GlobalTagThrottler/MultiTagActiveThrottling unit test
2022-07-19 16:29:11 -07:00
bac583ef0c
Add new active throttling unit test for global tag throttler
2022-07-19 16:29:11 -07:00
34a78a82f1
Add MockStorageServer class for global tag throttler testing
2022-07-19 16:29:11 -07:00
88ca6376ce
Add LimitType and OpType enum classes for global tag throttler
2022-07-19 16:29:11 -07:00
fb6540ab43
Add throttling ratio to GlobalTagThrottler
2022-07-19 16:29:10 -07:00
ab2110142a
Add /GlobalTagThrottler/RemoveQuota unit test
2022-07-19 16:29:10 -07:00
019900be67
Add GlobalTagThrottlerImpl::removeUnseenTags
2022-07-19 16:29:10 -07:00
3161bcfa52
Remove outdated TODO and FIXME comments from GlobalTagThrottlerImpl
2022-07-19 16:29:06 -07:00
b49c36f0b0
Add StorageQueueInfo::getWriteQueueSizeLimitRatio method
2022-07-19 16:28:27 -07:00
bc62b538b1
Merge pull request #7627 from jzhou77/remove-metrics
...
Remove unused "readQueueSizeMetric"
2022-07-19 15:55:52 -07:00
7e296c2367
simple replication ( #7625 )
2022-07-19 18:30:34 -04:00
Josh Slocum