Commit Graph

238 Commits

Author SHA1 Message Date
Ethan Feng
5595f2f4b3
[CELEBORN-124]Add buffer stream. (#1069) 2023-01-06 15:54:52 +08:00
Shuang
3b2be25a50
[CELEBORN-173] refactor minicluster and fix ut (#1147) 2023-01-05 20:39:19 +08:00
Angerszhuuuu
5edb21d210
[CELEBORN-168][FOLLOWUP] Device metrics should use long value and add size unit in metric name (#1143)
* [CELEBORN-168][FOLLOWUP] Device metrics should use long value and add size unit in metric name
2023-01-05 11:45:19 +08:00
nafiy
3e80cf2b87
[CELEBORN-168][FEATURE] Add disk usage related metrics for Worker (#1127) 2023-01-05 10:35:51 +08:00
Angerszhuuuu
425e31797c
[CELEBORN-182][BUG] StorageManager should not delete shuffle file when enable graceful shutdown (#1126) 2022-12-30 18:13:36 +08:00
Angerszhuuuu
7d7192af14
[CELEBORN-179][BUG] Repeat remove expired shuffle throw NPE (#1124) 2022-12-29 15:47:05 +08:00
Angerszhuuuu
6411fe71b1
[CELEBORN-178][BUG] Default registered flag should be false, not null (#1123) 2022-12-29 15:24:09 +08:00
nafiy
77cb7a0477
[CELEBORN-169][REFACTOR] Extract ObservedDevice out from LocalDeviceMonitor (#1113)
* [CELEBORN-169][REFACTOR] Extract ObservedDevice out from LocalDeviceMonitor
2022-12-28 14:29:00 +08:00
Ethan Feng
5aa959a335
[CELEBORN-157] Change prefix of configurations to celeborn. (#1104) 2022-12-21 15:17:28 +08:00
nafiy
f13dfb7421
[CELEBORN-113][FEATURE] Add metrics to monitor non-critical error number on local device (#1100) 2022-12-20 22:30:55 +08:00
Keyong Zhou
2f0682265e
[CELEBORN-119] Add timeout for pushdata (#1097) 2022-12-20 20:40:42 +08:00
zky.zhoukeyong
3a4fd04f33 Revert "[CELEBORN-120] MapPartitionFileWriter completes some functions to support mappartition (#1062)"
This reverts commit aa5a4d8c41.
2022-12-17 11:10:54 +08:00
Ethan Feng
39394526a8
[CELEBORN-142]Keep committed partition locations semantic consistent when commit files on HDFS. (#1091) 2022-12-16 19:02:02 +08:00
zhongqiangczq
aa5a4d8c41
[CELEBORN-120] MapPartitionFileWriter completes some functions to support mappartition (#1062) 2022-12-16 18:40:22 +08:00
nafiy
c931663e5f
[CELEBORN-110][REFACTOR] Notify critical error after collecting a certain number of non-critical error (#1055) 2022-12-16 15:47:36 +08:00
Ethan Feng
65cb36c002
[CELEBORN-83][FOLLOWUP] Fix various bugs when using HDFS as storage. (#1065) 2022-12-15 15:20:29 +08:00
Cheng Pan
ec371c0026
[CELEBORN-132] ShuffleClient should not implement Cloneable (#1077) 2022-12-14 10:04:39 +08:00
Keyong Zhou
5a3d397781
[CELEBORN-130] Correct CommitFilesTime metric (#1073) 2022-12-13 20:02:21 +08:00
zhongqiangczq
97991a3404
[CELEBORN-126] Fileinfo adds member bufferSize (#1068) 2022-12-13 16:36:26 +08:00
zhongqiangczq
edf85de8f6
[CELEBORN-123] PushDataHandler handleRpcRequestCore fix bug about val isMaster (#1063) 2022-12-12 15:51:58 +08:00
zhongqiangczq
c7258cfc03
[CELEBORN-103] add handleMapPartitionPushData to support mappartition (#1048) 2022-12-08 11:22:43 +08:00
zhongqiangczq
ea1c630173
[CELEBORN-80] FileWriter supports MapPartition (#1025) 2022-12-08 10:46:26 +08:00
Ethan Feng
acfaf59ab3
[CELEBORN-91] Refactor memory tracker to support read buffer. (#1038)
* [CELEBORN-91] Refactor memory tracker to support read buffer.
2022-12-05 15:38:43 +08:00
zhongqiangczq
b262591da8
[CELEBORN-71] pushdatahandler supports mappartition write: handshake/regionstart/regionfinish (#1013) 2022-12-05 13:05:35 +08:00
Binjie Yang
d6ee3c18bc
[CELEBORN-98][IMPROVEMENT] Remove unreachable code block in master/work arguments (#1042) 2022-12-02 22:53:28 +08:00
Angerszhuuuu
fc5ca42c14
[CELEBORN-96][REFACTOR] PushMergedData return partition not found use same code path (#1039) 2022-12-02 14:09:00 +08:00
Ethan Feng
dd02070e4b
[CELEBORN-83] Fix various bug when using HDFS as storage.
1. fix incompatibility between Hadoop 2 and Hadoop 3.
2. fix hdfs writer will never be called when there are no healthy disks.
3. fix an NPE when HDFS file writer close.
2022-11-30 19:33:18 +08:00
Ethan Feng
02e446284d
[CELEBORN-74] Device monitor should respect storage dir configured usable space (#1023) 2022-11-29 17:10:18 +08:00
Angerszhuuuu
d26e73209b
[CELEBORN-76] Support batch commit hard split partition before stage end 2022-11-29 13:09:01 +08:00
Angerszhuuuu
c8e5315b9c
[CELEBORN-23][FOLLOWUP] Both master and slave data should return HARD_SPLIT during shutdown (#1018) 2022-11-28 22:05:07 +08:00
Keyong Zhou
61e04b77fd
[CELEBORN-70][FOLLOWUP] Add epoch for each commitFiles request. (#1015)
* [CELEBORN-70][FOLLOWUP] Add epoch for each commitFiles request. Address comments.
2022-11-28 14:08:20 +08:00
Ethan Feng
cfa9b7f700
[CELEBORN-18] Refactor stream manager to distinguish map partition and reduce partition. (#997) 2022-11-28 12:02:38 +08:00
Keyong Zhou
d381df71f8
[CELEBORN-70] Add epoch for each commitFiles request (#1012) 2022-11-27 21:05:14 +08:00
Keyong Zhou
f8bb2cd47d
[CELEBORN-12]Retry on CommitFile request (#1011) 2022-11-26 20:56:24 +08:00
Keyong Zhou
9214b82181
[CELEBORN-68] Client might fetch incorrect data chunk (#1010) 2022-11-26 18:06:06 +08:00
Ethan Feng
93dbf3f8b1
[CELEBORN-67] Revert "Fix fetch incorrect data chunk" related commits (#1006)
* Revert "[CELEBORN-50][FOLLOWUP] Channel inactive may cause new client use old stream id to fetch data (#999)"

This reverts commit 1e8f6dc5e8.

* Revert "[CELEBORN-50] Channel inActive may cause new client use old stream id to fetch data cause IllegalStateException. (#1000)"

This reverts commit f1c4d675d6.

* Revert "[CELEBORN-49] Deadlock when kill worker in shuffle read (#998)"

This reverts commit 0be4b3399c.

* Revert "[CELEBORN-47][IMPROVEMENT] Refine logs about tracking fetch chunk (#995)"

This reverts commit 2b05228871.

* Revert "[BUG] Fix fetch incorrect data chunk (#926)"

This reverts commit 6f043f8a

* Revert "[ISSUE-925][FOLLOWUP] Refactor class name of RetryingChunkReceiveCallback (#954)"

This reverts commit 64e8ebf1
2022-11-25 20:57:47 +08:00
Angerszhuuuu
2b05228871
[CELEBORN-47][IMPROVEMENT] Refine logs about tracking fetch chunk (#995) 2022-11-23 11:56:10 +08:00
Ethan Feng
ee243f286d
[CELEBORN-4] Add metrics about top disk used apps. (#985) 2022-11-22 20:06:36 +08:00
Angerszhuuuu
e12000cb67
[CELEBORN-42][BUG] PushMergedData use wrong call back when partition not found (#991) 2022-11-22 18:29:15 +08:00
Angerszhuuuu
5ec278f99a
[ISSUE-987][FEATURE] During worker shutdown, return HARD_SPLIT for all existed partition (#988) 2022-11-22 14:29:55 +08:00
zhongqiangczq
7adcb5b933
[CELEBORN-6] [REFACTOR] PushDataHandler code refactor (#966) 2022-11-16 11:04:24 +08:00
leesf
0b8376e2c7
Cleanup some code (#943) 2022-11-11 13:58:39 +08:00
Ethan Feng
6f043f8ae9
[BUG] Fix fetch incorrect data chunk (#926) 2022-11-09 22:31:39 +08:00
leesf
aac68c3571
Rename RssException to CelebornException (#938) 2022-11-08 10:08:21 +08:00
leesf
496f44eda4
Shutdown worker if initialized failed. (#931) 2022-11-07 19:33:35 +08:00
Angerszhuuuu
99a7b85708
[ISSUE-932][REFACTOR] Device check should not directly reportError (#933)
* [ISSUE-932][REFACTOR] Device check should not directly reportError
2022-11-07 15:15:08 +08:00
nafiy
11081eac6c
[ISSUE-879][BUG] When notifyError, should destroy corresponding file writers (#912)
* [ISSUE-879][BUG] When notifyError, should destroy corresponding file writers
2022-11-07 14:01:51 +08:00
Angerszhuuuu
100e0057e8
[ISSUE-921][BUG] Flush Error should report non critical error (#928) 2022-11-07 11:56:11 +08:00
leesf
3699683a3b
Fix and migrate some configs (#927) 2022-11-07 09:41:38 +08:00
Angerszhuuuu
38e15d89e6
[ISSUE-902][IMPROVEMENT][FOLLOWUP] LifecycleManager should reserve blacklist with irrecoverable status (#914) 2022-11-04 15:54:45 +08:00
Angerszhuuuu
ea4ed10e5c
[ISSUE-901][BUG] During worker graceful shutdown, worker should report itself as unavailable and avoid master allocate slots on it. (#905) 2022-11-02 16:09:58 +08:00
Zhen Wang
643eb84541
[MINOR] Fix typo (#898) 2022-11-01 10:03:15 +08:00
nafiy
ce3dc889fa
[ISSUE-867][BUG] Create writer failed should report non-critical error instead of critical error (#883) 2022-10-31 21:23:16 +08:00
nafiy
9b1c70f219
[ISSUE-880][BUG] onTrim when flushFileWriters() should catch each file writer's exception, avoid block flush all file writers (#894) 2022-10-31 14:31:22 +08:00
Angerszhuuuu
87fcfa767f
[ISSUE-887][REFACTOR] Configuration type convert to Enum (#888)
* [ISSUE-332][FOLLOWUP] Add deps in worker's pom

* [Refactor] Modify package name of utils to keep consistence

* [Refactor] Modify package name of utils to keep consistence

* [REFACTOR] Remove unused isRegistered in controller

* [ISSUE-887][REFACTOR] Configuration type convert to Enum

* update

* update

* Update RssShuffleManager.java
2022-10-29 13:41:06 +08:00
Cheng Pan
d7be6006e7
Migrate network related conf to structured conf system (#875)
* Migrate network related conf to structured conf system

* migrate

* fix

* fix

* worker

* fix

* nit

* review

* nit
2022-10-28 10:45:52 +08:00
Angerszhuuuu
d283cca4e1
[ISSUE-869][REFACTOR] Migrate partition size/sorter related conf to Celeborn ConfigEntity (#870) 2022-10-27 16:49:55 +08:00
Angerszhuuuu
26dcc118c6
[ISSUE-871][REFACTOR] Migrate Worker conf to Celeborn Configuration System (#873)
* [ISSUE-871][REFACTOR] Migrate Worker conf to Celeborn Configuration System
2022-10-27 15:35:29 +08:00
Angerszhuuuu
5333819cb0
[ISSUE-866][BUG] Create File twice should show clear log (#876) 2022-10-27 14:52:45 +08:00
nafiy
e44e8c9610
[ISSUE-828][REFACTOR] Migrate memory tracker related configs to ConfigEntry (#831)
* [ISSUE-828][REFACTOR] Migrate memory tracker related configs to ConfigEntry

* Fix based on review

* update doc

* resolve review feedback

* fix

* Fix based on review

* fix based on review
2022-10-25 21:16:53 +08:00
AngersZhuuuu
0bd0a3e9f4
[ISSUE-847][REFACTOR] Migrate codec conf to Celeborn Configuration System (#848)
* [ISSUE-847][REFACTOR] Migrate codec conf to Celeborn Configuration System

* Update CelebornConf.scala

* follow comments

* update

* update

* update

* Update client.md
2022-10-25 09:16:46 +08:00
Ethan Feng
4df0d4a456
[TEST] Fix unstable LZ4 unit test (#816) 2022-10-24 15:36:06 +08:00
Cheng Pan
8d7d397e71
Fix Configuration page and polish naming (#838)
* Fix Configuration page and polish naming

* nit

* nit

* comment
2022-10-24 12:46:25 +08:00
Ethan Feng
74843f20a9
[BUG] Fix worker lost caused by UnsupportedOperationException (#837) 2022-10-24 11:20:42 +08:00
Keyong Zhou
63752e7a37
[BUG] RegisterShuffle should not increase epoch (#833) 2022-10-23 23:40:32 +08:00
Ethan Feng
392a252baa
[FOLLOWUP][ISSUE-813]Update doc and fix typo. (#825) 2022-10-22 23:02:22 +08:00
AngersZhuuuu
f2610e3b6f
[ISSUE-829][REFACTOR] Unify name of PUSH_DATA_FAIL_MAIN (#830) 2022-10-21 19:06:33 +08:00
nafiy
1a8a36e8fe
[ISSUE-812][Refactor] Migrate metrics system related configs to ConfigEntry (#821) 2022-10-21 13:57:58 +08:00
AngersZhuuuu
a773c8e6db
[ISSUE-820][Refactor] Rename RssConf to CelebornConf (#826) 2022-10-20 20:13:13 +08:00
AngersZhuuuu
8344479df1
[ISSUE-818][REFACTOR] Move existing RssConf.xxx conf method to RssConf class (#822)
* [ISSUE-818][REFACTOR] Move existing RssConf.xxx conf method to RssConf class


Co-authored-by: Ethan Feng <ethan.aquarius.fmx@gmail.com>
2022-10-20 18:10:59 +08:00
Ethan Feng
5c761a8df3
[ISSUE-813][Refactor] Refactor flusher configurations. (#813)
* Refactor flusher configurations.

* Refactor flusher configurations.

* Update.

* remove brackets.

* update docs.

* rename.

* update.

* update docs.

* update.

* update.

* update.

* update.

* update.

* update.

* update.

* format.

* update.

* update.
2022-10-20 15:23:17 +08:00
nafiy
1e5bed2da7
[ISSUE-806][REFACTOR] Remove ResourceConsumption out of ControlMessage (#810)
* [ISSUE-806][REFACTOR] Remove ResourceConsumption out of ControlMessage

* add line before method

* reformat
2022-10-19 17:14:51 +08:00
AngersZhuuuu
23c65a27a9
[ISSUE-798][REFACTOR] Migrate worker-recover related conf to ConfigEntry (#799) 2022-10-19 16:42:00 +08:00
nafiy
a75bce905e
[ISSUE-805][REFACTOR] Remove UserIdentifier out of ControlMessage (#808) 2022-10-19 15:32:53 +08:00
Cheng Pan
efad4abb5d
Migrate a bunch of configurations (#786) 2022-10-18 10:44:01 +08:00
nafiy
0e5beb9562
[ISSUE-774][REFACTOR] Add cache to avoid redundant UserIdentifier object when recover fileinfo (#781) 2022-10-17 21:27:54 +08:00
nafiy
0dcf946c9b
[ISSUE-751][REFACTOR] Move userResourceConsumption to WorkerInfo's parameter and format WorkerInfo's toString() (#767) 2022-10-17 17:58:39 +08:00
Cheng Pan
ea67f4e060
Introduce categories to ConfigEntry and migrate configurations (#775) 2022-10-17 16:56:54 +08:00
Ethan Feng
0959894155
[BUG]Fix rss worker register failure problem. (#777) 2022-10-17 09:50:04 +08:00
Cheng Pan
96e969f46e
[BUILD] Extract project.version to Maven Property (#772) 2022-10-16 19:01:40 +08:00
nafiy
373b4a744a
[ISSUE-750][Refactor] Add UserIdentifier as a field of file info (#759) 2022-10-13 23:15:44 +08:00
Cheng Pan
5829bda21a
Rework and migrate HA configuration system (#763) 2022-10-13 22:35:01 +08:00
Cheng Pan
f01a696313
Migrate and refactor configuration for master endpoints (#752) 2022-10-11 21:33:21 +08:00
nafiy
3ed38f1e72
[ISSUE-642][FEATURE] worker storage manger store user to shuffke key relation and recover from level db (#706) 2022-10-10 18:18:34 +08:00
AngersZhuuuu
13aeb4b644
[ISSUE-736][BUG] Heartbeat worker should update disk info into WorkInfo too to keep consistence with master (#737) 2022-10-09 15:41:01 +08:00
AngersZhuuuu
f2a234f870
[ISSUE-739][REFACTOR] Use object wrap pb message method (#740) 2022-10-09 11:53:48 +08:00
Ethan Feng
6deda248ac
[REFACTOR]move lifecycle manager to correct package. (#730) 2022-10-08 18:14:08 +08:00
Cheng Pan
ab16b4f101
[INFRA] Rename modules w/ celeborn prefix (#723) 2022-10-08 08:05:57 +08:00