Jian He
|
4a8508501b
|
YARN-5009. NMLeveldbStateStoreService database can grow substantially leading to longer recovery times. Contributed by Jason Lowe
|
2016-04-28 21:54:11 -07:00 |
|
Arun Suresh
|
341888a0aa
|
YARN-4412. Create ClusterMonitor to compute ordered list of preferred NMs for OPPORTUNITIC containers. (asuresh)
|
2016-04-26 20:12:12 -07:00 |
|
Karthik Kambatla
|
1a3f1482e2
|
YARN-4795. ContainerMetrics drops records. (Daniel Templeton via kasha)
|
2016-04-26 06:15:36 -07:00 |
|
Arun Suresh
|
c282a08f38
|
YARN-2885. Create AMRMProxy request interceptor and ContainerAllocator to distribute OPPORTUNISTIC containers to appropriate Nodes (asuresh)
(cherry picked from commit 2bf025278a318b0452fdc9ece4427b4c42124e39)
|
2016-04-24 22:38:33 -07:00 |
|
Karthik Kambatla
|
c8172f5f14
|
YARN-2883. Queuing of container requests in the NM. (Konstantinos Karanasos and Arun Suresh via kasha)
|
2016-04-20 09:55:50 -07:00 |
|
Jason Lowe
|
3150ae8108
|
YARN-4924. NM recovery race can lead to container not cleaned up. Contributed by sandflee
|
2016-04-14 19:17:14 +00:00 |
|
Robert Kanter
|
0d9194df00
|
YARN-4541. Change log message in LocalizedResource#handle() to DEBUG (rchiang via rkanter)
|
2016-04-13 17:45:18 -07:00 |
|
Naganarasimha
|
437e9d6475
|
YARN-4810. NM applicationpage cause internal error 500. Contributed by Bibin A Chundatt.
|
2016-04-12 17:59:46 +05:30 |
|
Akira Ajisaka
|
1ff27f9d12
|
YARN-4630. Remove useless boxing/unboxing code. Contributed by Kousuke Saruta.
|
2016-04-11 14:55:03 +09:00 |
|
Karthik Kambatla
|
e82f961a39
|
YARN-4756. Unnecessary wait in Node Status Updater during reboot. (Eric Badger via kasha)
|
2016-04-07 17:05:29 -07:00 |
|
Varun Vasudev
|
b41e65e5bc
|
YARN-4906. Capture container start/finish time in container metrics. Contributed by Jian He.
|
2016-04-06 13:41:33 +05:30 |
|
naganarasimha
|
5092c94195
|
YARN-4746. yarn web services should convert parse failures of appId, appAttemptId and containerId to 400. Contributed by Bibin A Chundatt
|
2016-04-04 16:25:03 +05:30 |
|
Jian He
|
0dd9bcab97
|
YARN-4811. Generate histograms in ContainerMetrics for actual container resource usage
|
2016-03-31 14:28:13 -07:00 |
|
Jason Lowe
|
948b758070
|
YARN-4773. Log aggregation performs extraneous filesystem operations when rolling log aggregation is disabled. Contributed by Jun Gong
|
2016-03-28 23:00:56 +00:00 |
|
Jian He
|
55ae143923
|
YARN-4117. End to end unit test with mini YARN cluster for AMRMProxy Service. Contributed by Giovanni Matteo Fumarola
|
2016-03-27 20:22:12 -07:00 |
|
Eric Payne
|
92b7e0d413
|
YARN-4686. MiniYARNCluster.start() returns before cluster is completely started. Contributed by Eric Badger.
|
2016-03-18 16:12:47 +00:00 |
|
Vinod Kumar Vavilapalli
|
b2661765a5
|
YARN-4762. Fixed CgroupHandler's creation and usage to avoid NodeManagers crashing when LinuxContainerExecutor is enabled. (Sidharta Seethana via vinodkv)
|
2016-03-07 11:08:17 -08:00 |
|
Jason Lowe
|
059caf9989
|
YARN-4744. Too many signal to container failure in case of LCE. Contributed by Sidharta Seethana
|
2016-03-07 15:40:01 +00:00 |
|
Varun Vasudev
|
8ed2e060e8
|
YARN-4245. Generalize config file handling in container-executor. Contributed by Sidharta Seethana.
|
2016-03-07 16:18:35 +05:30 |
|
Varun Vasudev
|
e51a8c1056
|
YARN-4737. Add CSRF filter support in YARN. Contributed by Jonathan Maron.
|
2016-03-07 15:26:44 +05:30 |
|
Jason Lowe
|
c58a6d53c5
|
YARN-4731. container-executor should not follow symlinks in recursive_unlink_children. Contributed by Colin Patrick McCabe
|
2016-02-29 15:24:35 +00:00 |
|
Ming Ma
|
7f3139e54d
|
YARN-4720. Skip unnecessary NN operations in log aggregation. (Jun Gong via mingma)
|
2016-02-26 08:40:05 -08:00 |
|
Robert Kanter
|
d7fdec1e6b
|
YARN-4579. Allow DefaultContainerExecutor container log directory permissions to be configurable (rchiang via rkanter)
|
2016-02-25 16:36:38 -08:00 |
|
Robert Kanter
|
954dd57043
|
YARN-4697. NM aggregation thread pool is not bound by limits (haibochen via rkanter)
|
2016-02-24 15:00:24 -08:00 |
|
Jason Lowe
|
d284e187b8
|
YARN-2046. Out of band heartbeats are sent only on container kill and possibly too early. Contributed by Ming Ma
|
2016-02-23 20:49:09 +00:00 |
|
Varun Vasudev
|
140cb5d745
|
YARN-4709. NMWebServices produces incorrect JSON for containers. Contributed by Varun Saxena.
|
2016-02-23 12:29:25 +05:30 |
|
Varun Vasudev
|
fa00d3e205
|
YARN-4655. Log uncaught exceptions/errors in various thread pools in YARN. Contributed by Sidharta Seethana.
|
2016-02-11 12:06:42 +05:30 |
|
Jason Lowe
|
fa328e2d39
|
YARN-4594. container-executor fails to remove directory tree when chmod required. Contributed by Colin Patrick McCabe
|
2016-02-03 17:21:12 +00:00 |
|
Varun Vasudev
|
1cd55e0c17
|
YARN-4649. Add additional logging to some NM state store operations. Contributed by Sidharta Seethana
|
2016-02-02 09:25:23 +05:30 |
|
Jason Lowe
|
61382ff8fa
|
YARN-4643. Container recovery is broken with delegating container runtime. Contributed by Sidharta Seethana
|
2016-01-28 18:59:35 +00:00 |
|
Vinod Kumar Vavilapalli (I am also known as @tshooter.)
|
2085e60a96
|
YARN-3542. Refactored existing CPU cgroups support to use the newer and integrated ResourceHandler mechanism, and also deprecated the old LCEResourceHandler inteface hierarchy. Contributed by Varun Vasudev.
|
2016-01-25 16:19:36 -08:00 |
|
Jian He
|
992dd2f783
|
YARN-4520. Finished app info is unnecessarily persisted in NM state-store if container is acquired but not lunched on this node. Contributed by sandflee
|
2016-01-25 15:36:14 -08:00 |
|
Jason Lowe
|
46e5ea81e0
|
YARN-4598. Invalid event: RESOURCE_FAILED at CONTAINER_CLEANEDUP_AFTER_KILL. Contributed by tangshangwen
|
2016-01-22 21:55:01 +00:00 |
|
Varun Vasudev
|
b41a7e89d1
|
YARN-4578. Directories that are mounted in docker containers need to be more restrictive/container-specific. Contributed by Sidharta Seethana.
|
2016-01-22 14:43:14 +05:30 |
|
Wangda Tan
|
89d1fd5dac
|
HADOOP-12356. Fix computing CPU usage statistics on Windows. (Inigo Goiri via wangda)
|
2016-01-19 21:27:38 +08:00 |
|
Karthik Kambatla
|
d40859fab1
|
YARN-4526. Make SystemClock singleton so AppSchedulingInfo could use it. (kasha)
|
2016-01-18 10:58:14 +01:00 |
|
Colin Patrick Mccabe
|
b2c155f810
|
HADOOP-12712. Fix some cmake plugin and native build warnings (cmccabe)
|
2016-01-15 12:29:18 -08:00 |
|
Colin Patrick Mccabe
|
b1ed28fa77
|
HADOOP-8887. Use a Maven plugin to build the native code using CMake (cmccabe)
|
2016-01-14 11:02:34 -08:00 |
|
Varun Vasudev
|
3ddb92bd30
|
YARN-4553. Add cgroups support for docker containers. Contributed by Sidharta Seethana.
|
2016-01-14 14:29:29 +05:30 |
|
Akira Ajisaka
|
52b77577c4
|
YARN-4544. All the log messages about rolling monitoring interval are shown with WARN level. Contributed by Takashi Ohnishi.
|
2016-01-08 01:12:46 +09:00 |
|
Rohith Sharma K S
|
f9e36dea96
|
YARN-4530. LocalizedResource trigger a NPE Cause the NodeManager exit. (tangshangwen via rohithsharmaks)
|
2016-01-04 09:58:13 +05:30 |
|
Gera Shegalov
|
2c17b81569
|
YARN-2934. Improve handling of container's stderr. (Naganarasimha G R via gera)
|
2015-12-24 23:48:05 -08:00 |
|
Vinod Kumar Vavilapalli (I am also known as @tshooter.)
|
4e7d32c0db
|
YARN-1856. Added cgroups based memory monitoring for containers as another alternative to custom memory-monitoring. Contributed by Varun Vasudev.
|
2015-12-17 12:13:03 -08:00 |
|
Wangda Tan
|
79c41b1d83
|
YARN-4293. ResourceUtilization should be a part of yarn node CLI. (Sunil G via wangda)
|
2015-12-16 13:18:19 -08:00 |
|
Wangda Tan
|
dfcbbddb09
|
YARN-4309. Add container launch related debug information to container logs when a container fails. (Varun Vasudev via wangda)
|
2015-12-14 11:13:22 -08:00 |
|
rohithsharmaks
|
15c3e7ffe3
|
YARN-4431. Not necessary to do unRegisterNM() if NM get stop due to failed to connect to RM. (Junpin Du via rohithsharmaks)
|
2015-12-09 10:50:43 +05:30 |
|
Steve Loughran
|
65f395226b
|
HADOOP-12321. Make JvmPauseMonitor an AbstractService. (Sunil G via Stevel) [includes HDFS-8947 MAPREDUCE-6462 and YARN-4072]
|
2015-12-06 17:43:35 +00:00 |
|
Jian He
|
9f77ccad73
|
YARN-3840. Resource Manager web ui issue when sorting application by id (with application having id > 9999). Contributed by Mohammad Shahid Khan and Varun Saxena
|
2015-12-03 12:48:50 -08:00 |
|
Junping Du
|
62e9348bc1
|
YARN-4408. Fix issue that NodeManager still reports negative running containers. Contributed by Robert Kanter.
|
2015-12-03 06:36:37 -08:00 |
|
Karthik Kambatla
|
52948bb20b
|
YARN-3980. Plumb resource-utilization info in node heartbeat through to the scheduler. (Inigo Goiri via kasha)
|
2015-11-24 13:47:17 +05:30 |
|