Domovská stránka Prehľadávať Pomoc
Registrovať Prihlásiť sa
apache
/
hadoop
zrkadlo https://github.com/apache/hadoop.git
2
0
Fork 1
Súbory Issues 0 Wiki
Strom: a9beec0221
Branche Tagy

História revízii

Autor SHA1 Správa Dátum
  Haohui Mai a9beec0221 HDFS-7258. CacheReplicationMonitor rescan schedule log should use DEBUG level instead of INFO level. Contributed by Xiaoyu Yao. 10 rokov pred
  Vinayakumar B a8b1a63b8f Addendum: HDFS-10271. 9 rokov pred
  Zhe Zhang 3fea7f0a38 HDFS-9688. Test the effect of nested encryption zones in HDFS downgrade. 9 rokov pred
  Junping Du 43ac0b09e3 Set the release date for 2.6.4. 9 rokov pred
  Arpit Agarwal d833823daf HDFS-9752. Permanent write failures may happen to slow writers during datanode rolling upgrades. (Contributed by Walter Su) 9 rokov pred
  Zhe Zhang 1b25855b9b HDFS-9347. Invariant assumption in TestQuorumJournalManager.shutdown() is wrong. Contributed by Wei-Chiu Chuang. 9 rokov pred
  Vinayakumar B ea517acfb6 HDFS-9629. Update the footer of Web UI to show year 2016 (Contributed by Xiao Chen and Vinayakumar B) 9 rokov pred
  Junping Du 89bfc884a5 Adding release 2.6.5 to CHANGES.txt. 9 rokov pred
  Kihwal Lee d8416aec3c HDFS-9220. Reading small file (< 512 bytes) that is open for append fails due to incorrect checksum. Contributed by Jing Zhao. 9 rokov pred
  Junping Du cd93382a59 HDFS-8722. Optimize datanode writes for small writes and flushes. Contributed by Kihwal Lee. 9 rokov pred
  Junping Du 30626ad35f HDFS-9178. Slow datanode I/O can cause a wrong node to be marked bad. Contributed by Kihwal Lee. 9 rokov pred
  Junping Du 572b5872fe HDFS-4660. Block corruption can happen during pipeline recovery. Contributed by Kihwal Lee. 9 rokov pred
  Colin Patrick Mccabe 8ef73cd4ce HDFS-7694. FSDataInputStream should support "unbuffer" (cmccabe) 10 rokov pred
  Tsz-Wo Nicholas Sze b05bb4984d HDFS-9294. DFSClient deadlock when close file and failed to renew lease. Contributed by Brahma Reddy Battula 9 rokov pred
  Arpit Agarwal f758dacb70 HDFS-9415. Document dfs.cluster.administrators and dfs.permissions.superusergroup. (Contributed by Xiaobing Zhou) 9 rokov pred
  Junping Du f5c50cd888 Add missing CHANGES.txt entry for HDFS-8767 for branch-2.6 9 rokov pred
  Kihwal Lee 04b8a19f81 HDFS-9574. Reduce client failures during datanode restart. Contributed by Kihwal Lee. 9 rokov pred
  Vinayakumar B 79da1283d6 HDFS-9600. do not check replication if the block is under construction (Contributed by Phil Yang) 9 rokov pred
  Junping Du 236a6ba13e HDFS-9445. Datanode may deadlock while handling a bad volume. Contributed by Walter Su. 9 rokov pred
  Akira Ajisaka 0381556a42 Set release date for 2.6.3 9 rokov pred
  Akira Ajisaka aadc864988 HDFS-6945. BlockManager should remove a block from excessReplicateMap and decrement ExcessBlocks metric when the block is removed. Contributed by Akira AJISAKA. 10 rokov pred
  Vinod Kumar Vavilapalli e7e0c4c0dd HDFS-9273. Moving to 2.6.3 CHANGES section to reflect the backport. 9 rokov pred
  cnauroth 339714baa0 HDFS-9273. ACLs on root directory may be lost after NN restart. Contributed by Xiao Chen. 9 rokov pred
  Zhe Zhang 4c631e8c73 HDFS-9314. Improve BlockPlacementPolicyDefault's picking of excess replicas. Contributed by Xiao Chen. 9 rokov pred
  Zhe Zhang 089169e4e5 HDFS-9313. Possible NullPointerException in BlockManager if no excess replica can be chosen. Contributed by Ming Ma. Branch-2.7 patch contributed by Xiao Chen. 9 rokov pred
  Zhe Zhang 30dc4334bf HDFS-8647. Abstract BlockManager's rack policy into BlockPlacementPolicy. Contributed by Brahma Reddy Battula. Branch-2.6 patch contributed by Xiao Chen. 9 rokov pred
  Junping Du e710a11a7f Creating 2.6.4 entries in CHANGES.txt files. 9 rokov pred
  Andrew Wang b2dd21e82d HDFS-9470. Encryption zone on root not loaded from fsimage after NN restart. Xiao Chen via wang. 9 rokov pred
  Tsz-Wo Nicholas Sze d2518fd562 HDFS-9434. Recommission a datanode with 500k blocks may pause NN for 30 seconds for printing info log messags. 9 rokov pred
  Tsz-Wo Nicholas Sze 83fcbd49a7 Revert "HDFS-9434. Recommission a datanode with 500k blocks may pause NN for 30 seconds for printing info log messags." 9 rokov pred

Novšie Staršie