b8da9f83cb
HBASE-16302 age of last shipped op and age of last applied op should be histograms
...
Signed-off-by: Ashish Singhi <ashishsinghi@apache.org>
2016-11-29 13:54:28 +05:30
7b2673db12
HBASE-16561 Add metrics about read/write/scan queue length and active read/write/scan handler count
...
Signed-off-by: zhangduo <zhangduo@apache.org>
2016-11-29 16:09:56 +08:00
be042652aa
Revert "HBASE-16561 Add metrics about read/write/scan queue length and active read/write/scan handler count"
...
Forget to add signoff
This reverts commit 5ec218dbc2
2016-11-29 16:09:22 +08:00
5ec218dbc2
HBASE-16561 Add metrics about read/write/scan queue length and active read/write/scan handler count
2016-11-29 16:00:37 +08:00
cdf539a8e0
HBASE-17189 TestMasterObserver#wasModifyTableActionCalled uses wrong variables (Stephen Yuan Jiang)
2016-11-28 23:18:42 -08:00
987205caf9
HBASE-17072 CPU usage starts to climb up to 90-100% when using G1GC
...
Removes ThreadLocal. Uses AtomicReference instead (based on patch
posted up in HBASE-10676 "Removing ThreadLocal of PrefetchedHeader in
HFileBlock.FSReaderV2 make higher perforamce of scan")
Signed-off-by: Michael Stack <stack@apache.org>
2016-11-28 13:41:17 -08:00
10c070825f
HBASE-17116 [PerformanceEvaluation] Add option to configure block size (Yi Liang)
2016-11-27 19:13:08 -08:00
2f35956eb8
HBASE-17171 Proactively catch the case when no time remains for random reads
...
The framework sets a configuration property to control how long reads
should be executed. When writes take too long, no time remains for reads
and the user sees an error about a property they must set. We should
prevent this case and log an appropriate message.
Also fixes a rogue character in the class-level javadoc.
Signed-off-by: Michael Stack <stack@apache.org>
2016-11-23 11:41:04 -08:00
fb1ace490c
HBASE-17095 The ClientSimpleScanner keeps retrying if the hfile is corrupt or cannot found
2016-11-22 11:26:57 +08:00
2da5ed098e
HBASE-17118 StoreScanner leaked in KeyValueHeap (addendum)
2016-11-21 20:55:52 +08:00
e8f056935b
HBASE-17131 Avoid livelock caused by HRegion#processRowsWithLocks (ChiaPing Tsai)
2016-11-20 18:17:21 -08:00
e30329e372
HBASE-17127 Locate region should fail fast if underlying Connection already closed
2016-11-19 23:51:25 +08:00
3c45ff08d9
HBASE-17088 Refactor RWQueueRpcExecutor/BalancedQueueRpcExecutor/RpcExecutor
...
Signed-off-by: zhangduo <zhangduo@apache.org>
2016-11-19 14:18:06 +08:00
26e3164481
HBASE-16708 Expose endpoint Coprocessor name in responseTooSlow log messages (Yi Liang)
2016-11-18 11:09:55 -08:00
0a171717e7
HBASE-16335 Update to latest Apache parent pom
...
Signed-off-by: Michael Stack <stack@apache.org>
2016-11-17 13:51:11 -08:00
19441937ea
HBASE-17058 Lower epsilon used for jitter verification from HBASE-15324
2016-11-17 12:29:08 -08:00
c6f1b6e624
HBASE-17112 Prevent setting timestamp of delta operations the same as previous value's (Phil Yang)
2016-11-17 09:04:39 -08:00
d722b2aab7
HBASE-17118 StoreScanner leaked in KeyValueHeap (binlijin)
2016-11-17 08:46:11 -08:00
bf0483c37c
HBASE-17091 IntegrationTestZKAndFSPermissions failed with 'KeeperException'
2016-11-15 13:09:32 -08:00
e54826434e
HBASE-17044 Fix merge failed before creating merged region leaves meta inconsistent
2016-11-14 17:14:48 -08:00
e01ee2fd1d
HBASE-17074 PreCommit job always fails because of OOM
2016-11-15 08:29:44 +08:00
b77bfe9d3b
HBASE-17077 Don't copy the replication queue belonging to the peer which has been deleted (Guanghao Zhang)
2016-11-13 07:00:25 -08:00
469462c850
HBASE-17062 RegionSplitter throws ClassCastException (Jeongdae Kim)
2016-11-11 07:18:22 -08:00
44ab659b93
HBASE-16962: Add readPoint to preCompactScannerOpen() and preFlushScannerOpen() API
...
Signed-off-by: anoopsamjohn <anoopsamjohn@gmail.com>
2016-11-11 11:09:55 +05:30
18b31fdd32
HBASE-17020 keylen in midkey() dont computed correctly
...
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-11 08:01:00 +08:00
a6397e3b0c
HBASE-16938 TableCFsUpdater maybe failed due to no write permission on peerNode
...
Signed-off-by: Enis Soztutar <enis@apache.org>
2016-11-10 14:07:20 -08:00
dac73eceb0
HBASE-16570 Compute region locality in parallel at startup (addendum)
...
Addendum mainly for:
1. Avoid interfering with block location cache in RegionLocationFinder
2. Avoid refreshing block lcoations during HMaster startup (or else the startup could be really slow)
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-10 16:53:39 +08:00
e929156f96
HBASE-16985 TestClusterId failed due to wrong hbase rootdir
...
Signed-off-by: Michael Stack <stack@apache.org>
2016-11-09 17:19:31 -08:00
1e322e68a5
HBASE-17054 Compactor#preCreateCoprocScanner should be passed user
2016-11-09 07:00:19 -08:00
d248d6b0b3
HBASE-17039 SimpleLoadBalancer schedules large amount of invalid region moves
...
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-09 17:07:28 +08:00
123d26ed90
HBASE-17017 Remove the current per-region latency histogram metrics
2016-11-08 18:31:12 -08:00
a70f73c1e1
HBASE-16983 TestMultiTableSnapshotInputFormat failing with Unable to create region directory: /tmp/... (Addendum by Guanghao Zhang)
2016-11-08 11:59:49 -08:00
97276da9a7
HBASE-17010 Serial replication should handle daughter regions being assigned to another RS (Phil Yang)
2016-11-08 06:35:12 -08:00
874cf5128f
HBASE-17042 Remove 'public' keyword from MasterObserver interface (Stephen Yuan Jiang)
2016-11-07 17:51:44 -08:00
b99690ac6b
HBASE-17033 LogRoller makes a lot of allocations unnecessarily
2016-11-07 14:31:30 -08:00
2fdba6521d
HBASE-16992 The usage of mutation from CP is weird. (ChiaPing Tsai)
2016-11-07 23:26:27 +05:30
ecd4de938b
HBASE-17026 VerifyReplication log should distinguish whether good row key is result of revalidation
2016-11-07 07:41:55 -08:00
c4132bbf30
HBASE-16840 Reuse cell's timestamp and type in ScanQueryMatcher
...
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-07 22:42:46 +08:00
a67481209f
Revert "HBASE-16840 Reuse cell's timestamp and type in ScanQueryMatcher" to update author
...
This reverts commit 4d8611fa0f
2016-11-07 22:42:38 +08:00
4d8611fa0f
HBASE-16840 Reuse cell's timestamp and type in ScanQueryMatcher
...
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-07 21:38:03 +08:00
3063943c78
HBASE-17032 CallQueueTooBigException and CallDroppedException should not be triggering PFFE
2016-11-06 21:34:11 -08:00
9bc9f9b597
HBASE-17004 IntegrationTestManyRegions verifies that many regions get assigned within given time. To do so, it spawns a new thread and uses CountDownLatch.await() to timeout.
...
Replacing this mechanism with junit @ClassRule to timeout the test.
Also adds missing kdc deps in hbase-it/pom.xml
Change-Id: I00930c2f974b4215e3f82a0ec007d9ef3ebd7cdd
2016-11-04 11:48:01 -07:00
8ade73c0cb
HBASE-16946 Provide Raw scan as an option in VerifyReplication (Sreekar Pallapothu)
2016-11-04 03:36:17 -07:00
5bfec397d1
HBASE-16960 RegionServer hang when aborting
...
Signed-off-by: Yu Li <liyu@apache.org>
2016-11-04 14:08:42 +08:00
51ba7cfde3
HBASE-17006 Give name to existing threads.
...
Having thread names in logs and thread dumps greatly improve debugability. This patch is simply adding the names to the threads we spawn.
Change-Id: I6ff22cc3804bb81147dde3a8e9ab671633c6f6ce
2016-11-03 18:31:03 -07:00
b4676d51ad
HBASE-14329 Report region in transition should check all regions in request
...
Signed-off-by: Gary Helmling <garyh@apache.org>
2016-11-03 11:32:19 -07:00
4fe51ebaa7
HBASE-16964 Always clear successfully archived files from compacted files list
2016-11-03 09:28:22 -07:00
514add0086
HBASE-16972 Log more details for Scan#next request when responseTooSlow
2016-11-02 14:33:44 +08:00
961b952171
HBASE-16980 TestRowProcessorEndpoint failing consistently (Yu Li)
2016-11-01 19:09:17 -07:00
6113f9a34f
HBASE-16765 New SteppingRegionSplitPolicy, avoid too aggressive spread of regions for small tables.
2016-11-01 13:07:12 -07:00
Ashu Pachauri
Guanghao Zhang
zhangduo
Stephen Yuan Jiang
Michael Stack
Jerry He
Josh Elser
Jingcheng Du
binlijin
tedyu
Yu Li
Jan Hentschel
Esteban Gutierrez
Enis Soztutar
Andrew Purtell
thiruvel
Yu Sun
Charlie Qiangeng Xu
anoopsamjohn
Mikhail Antonov
Apekshit Sharma
Eddie Elizondo
Gary Helmling
Lars Hofhansl