big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
24,572 Commits 2 Branches 2 Tags 264 MiB
e9ba4f4591
Commit Graph

549 Commits

Author SHA1 Message Date
Akira Ajisaka
3f573b6751 HDFS-12920. HDFS default value change (with adding time unit) breaks old version MR tarball work with new version (3.0) of hadoop. (#3227) 
Revert "HDFS-10845. Change defaults in hdfs-site.xml to match timeunit type. Contributed by Yiqun Lin"

This reverts commit b6d839a60c.

 Conflicts:
	hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml

(cherry picked from commit 2f2f822488)
 2021-07-26 01:54:32 +09:00
crossfire
3faae2e06d
HDFS-15650. Make the socket timeout for computing checksum of striped blocks configurable (#2414) 
(cherry picked from commit 4bb25c810b)
 2021-07-16 11:07:27 +08:00
litao
5fc61d2e56 HDFS-16076. Avoid using slow DataNodes for reading by sorting locations (#3117) 
(cherry picked from commit fdef2b4cca)
 2021-06-24 13:27:33 +09:00
Hui Fei
e55d76e26c
HDFS-13671. Namenode deletes large dir slowly caused by FoldedTreeSet#removeAndGet (#3113) 
Conflicts:
	hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/server/blockmanagement/TestBlockManager.java
	hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/server/datanode/fsdataset/impl/TestFsDatasetImpl.java
 2021-06-18 14:41:02 +08:00
litao
46d4b51bff
HDFS-15814. Make some parameters configurable for DataNodeDiskMetrics for branch-3.3 (#3021) 2021-06-08 00:10:37 -07:00
litao
29414871bd
HDFS-15879. Exclude slow nodes when choose targets for blocks (#2928) 2021-04-21 10:41:13 +09:00
Stephen O'Donnell
0e6cd352b5
HDFS-15160. ReplicaMap, Disk Balancer, Directory Scanner and various FsDatasetImpl methods should use datanode readlock. Contributed by Stephen O'Donnell. (#2813) 
Signed-off-by: Wei-Chiu Chuang <weichiu@apache.org>
(cherry picked from commit 2a67e2b1a0)

 Conflicts:
	hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DirectoryScanner.java
	hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/fsdataset/impl/FsDatasetImpl.java
 2021-04-09 10:25:14 +01:00
He Xiaoqiao
df99ac0399 HDFS-15942. Increase Quota initialization threads. Contributed by Stephen O'Donnell. 
(cherry picked from commit 459df41997)
 2021-04-08 13:15:37 +01:00
touchida
dca2bf9dd5 HDFS-15759. EC: Verify EC reconstruction correctness on DataNode (#2585) 
(cherry picked from commit 95e6892675)
 2021-04-08 17:20:08 +08:00
Karthik Palanisamy
769df1e964 HDFS-15253 Default checkpoint transfer speed, 50mb per second (#2366) 
(cherry picked from commit df4006eb81)
 2021-03-30 22:29:49 +08:00
Ayush Saxena
7f20fad419 HDFS-14383. Compute datanode load based on StoragePolicy. Contributed by Ayush Saxena. 
(cherry picked from commit 2e8cafac3b)
 2021-03-30 22:29:48 +08:00
Stephen O'Donnell
56ef16468a
HADOOP-17222. Create socket address leveraging URI cache (#2817) 
Contributed by fanrui.

Signed-off-by: Mingliang Liu <liuml07@apache.org>
Signed-off-by: He Xiaoqiao <hexiaoqiao@apache.org>
 2021-03-30 11:59:44 +01:00
Karthik Palanisamy
c96821ece8 HDFS-15610 Reduced datanode upgrade/hardlink thread from 12 to 6 (#2365) 
(cherry picked from commit 735e85a1d2)
 2021-03-24 17:44:29 +08:00
sunlisheng
a8c0083b1b HDFS-15809. DeadNodeDetector does not remove live nodes from dead node set. Contributed by Jinglun. 
(cherry picked from commit 7025f39944)
 2021-03-24 14:04:47 +08:00
Neil
bc5458bbd4 HDFS-15720 namenode audit async logger should add some log4j config (#2532) 
(cherry picked from commit 9bd3c9bc50)
 2020-12-10 13:50:32 -08:00
Takanobu Asanuma
d78bf82722 HDFS-15538. Fix the documentation for dfs.namenode.replication.max-streams in hdfs-default.xml. Contributed by Xieming Li. 
(cherry picked from commit f56cd88d7d)
 2020-11-13 11:05:20 +09:00
Kihwal Lee
cf932a7e2d HDFS-15618. Improve datanode shutdown latency. Contributed by Ahmed Hussein. 2020-10-22 09:55:28 -05:00
Ayush Saxena
9eaa3520e6 HDFS-15243. Add an option to prevent sub-directories of protected directories from deletion. Contributed by liuyanyu. 
(cherry picked from commit 0fe49036e5)
 2020-08-26 23:07:22 -07:00
Ayush Saxena
3915d1afc7 HDFS-15356. Unify configuration dfs.ha.allow.stale.reads to DFSConfigKeys. Contributed by Xiaoqiao He. 
(cherry picked from commit 178336f8a8)
 2020-05-18 09:58:59 -07:00
Wei-Chiu Chuang
240cba7e6d HDFS-15202 Boost short circuit cache (rebase PR-1884) (#2016) 
(cherry picked from commit 2abcf7762a)
 2020-05-18 09:41:11 -07:00
Wei-Chiu Chuang
289f8acc64 Revert "HDFS-15202 Boost short circuit cache (rebase PR-1884) (#2016)" 
This reverts commit ad9a6a0ee3.
 2020-05-18 09:41:03 -07:00
Wei-Chiu Chuang
032ccba67c HDFS-15207. VolumeScanner skip to scan blocks accessed during recent scan peroid. Contributed by Yang Yun. 
(cherry picked from commit 50caba1a92)
 2020-05-18 08:42:20 -07:00
pustota2009
ad9a6a0ee3 HDFS-15202 Boost short circuit cache (rebase PR-1884) (#2016) 
Added parameter dfs.client.short.circuit.num improving HDFS-client's massive reading performance by create few instances ShortCircuit caches instead of one. It helps avoid locks and lets CPU do job.

(cherry picked from commit 86e6aa8eec)
 2020-05-18 07:05:03 -07:00
S O'Donnell
433aaeefa4 HDFS-15255. Consider StorageType when DatanodeManager#sortLocatedBlock(). Contributed by Lisheng Sun. 2020-05-12 15:25:05 +01:00
Ayush Saxena
4e0d99c4d6 HDFS-14283. DFSInputStream to prefer cached replica. Contributed by Lisheng Sun. 2020-05-06 17:02:40 +05:30
Inigo Goiri
cdcb77a2c5 HDFS-15075. Remove process command timing from BPServiceActor. Contributed by Xiaoqiao He. 2020-03-25 11:30:54 -07:00
Arpit Agarwal
a700803a18
HDFS-15154. Allow only hdfs superusers the ability to assign HDFS storage policies. Contributed by Siddharth Wagle. 
Change-Id: I32d6dd2837945b8fc026a759aa367c55daefe348
 2020-03-25 10:28:30 -07:00
Ayush Saxena
ea87d60493 HDFS-13377. The owner of folder can set quota for his sub folder. Contributed by Yang Yun. 2020-03-24 22:56:09 +05:30
Ayush Saxena
f9bb2a8cc5 HDFS-15200. Delete Corrupt Replica Immediately Irrespective of Replicas On Stale Storage. Contributed by Ayush Saxena. 2020-03-19 22:26:34 +05:30
Wei-Chiu Chuang
7b637a3341 HDFS-14820. The default 8KB buffer of BlockReaderRemote#newBlockReader#BufferedOutputStream is too big. Contributed by Lisheng Sun. 2020-03-13 19:01:23 -07:00
Ayush Saxena
1a636da041 HDFS-15033. Support to save replica cached files to other place and make expired time configurable. Contributed by Yang Yun. 2020-02-29 09:55:29 +05:30
Stephen O'Donnell
900430b990 HDFS-14861. Reset LowRedundancyBlocks Iterator periodically. Contributed by Stephen O'Donnell. 
Signed-off-by: Wei-Chiu Chuang <weichiu@apache.org>
 2020-02-25 13:28:50 -08:00
Ayush Saxena
b5698e0c33 HDFS-15176. Enable GcTimePercentage Metric in NameNode's JvmMetrics. Contributed by Jinglun. 2020-02-24 00:07:18 +05:30
Ayush Saxena
9eb7a8bdf8 HDFS-15041. Make MAX_LOCK_HOLD_MS and full queue size configurable. Contributed by zhuqi. 2020-02-23 14:25:39 +05:30
Kihwal Lee
9b8a78d97b HDFS-14758. Make lease hard limit configurable and reduce the default. 
Contributed by hemanthboyina.
 2020-02-11 12:40:00 -06:00
Stephen O'Donnell
d7c136b9ed HDFS-15150. Introduce read write lock to Datanode. Contributed Stephen O'Donnell. 
Signed-off-by: Wei-Chiu Chuang <weichiu@apache.org>
 2020-02-11 08:00:15 -08:00
Kihwal Lee
d10f77e3c9 HDFS-15119. Allow expiration of cached locations in DFSInputStream. 
Contributed by Ahmed Hussein.
 2020-01-24 09:15:27 -06:00
Kihwal Lee
bd03053ea2 HDFS-14968. Add ability to log stale datanodes. Contributed by Ahmed Hussein. 2020-01-22 09:14:38 -06:00
Chao Sun
d7c4f8ab21 HDFS-13616. Batch listing of multiple directories (#1725) 2020-01-15 17:22:47 -08:00
Ayush Saxena
cebce0a348 HDFS-14578. AvailableSpaceBlockPlacementPolicy always prefers local node. Contributed by Ayush Saxena. 2020-01-11 10:29:11 +05:30
Ayush Saxena
b32757c616 HDFS-15107. dfs.client.server-defaults.validity.period.ms to support time units. Contributed by Ayush Saxena. 2020-01-10 08:14:56 +05:30
Rakesh Radhakrishnan
d79cce20ab HDFS-14740. Recover data blocks from persistent memory read cache during datanode restarts. Contributed by Feilong He. 2020-01-02 11:44:00 +05:30
Stephen O'Donnell
c93cb6790e HDFS-14854. Create improved decommission monitor implementation. Contributed by Stephen O'Donnell. 
Reviewed-by: Inigo Goiri <inigoiri@apache.org>
Signed-off-by: Wei-Chiu Chuang <weichiu@apache.org>
 2019-12-10 17:16:43 -08:00
Masatake Iwasaki
11cd5b6e39 HDFS-15028. Keep the capacity of volume and reduce a system call. Contributed by Yang Yun. 
Signed-off-by: Masatake Iwasaki <iwasakims@apache.org>
 2019-12-07 08:46:45 +09:00
Yiqun Lin
c8bef4d6a6 HDFS-14649. Add suspect probe for DeadNodeDetector. Contributed by Lisheng Sun. 2019-11-27 10:57:20 +08:00
Yiqun Lin
9b6906fe91 HDFS-14651. DeadNodeDetector checks dead node periodically. Contributed by Lisheng Sun. 2019-11-22 10:53:55 +08:00
Yiqun Lin
b3119b9ab6 HDFS-14648. Implement DeadNodeDetector basic model. Contributed by Lisheng Sun. 2019-11-16 11:32:41 +08:00
He Xiaoqiao
c892a879dd HDFS-14882. Consider DataNode load when #getBlockLocation. Contributed by Xiaoqiao He. 
Signed-off-by: Wei-Chiu Chuang <weichiu@apache.org>

Reviewed-by: Inigo Goiri <inigoiri@apache.org>
Reviewed-by: Istvan Fajth <pifta@cloudera.com>
 2019-11-15 12:16:31 -08:00
Erik Krogen
b2cc8b6b4a HDFS-14973. More strictly enforce Balancer/Mover/SPS throttling of getBlocks RPCs to NameNodes. Contributed by Erik Krogen. 2019-11-15 10:10:37 -08:00
Eric Yang
30ed24a421 HDFS-14730. Removed unused configuration dfs.web.authentication.filter. 
Contributed by Chen Zhang
 2019-10-28 19:27:32 -04:00