[
https://issues.apache.org/jira/browse/HDFS-11553?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Andrew Wang updated HDFS-11553:
-------------------------------
Component/s: erasure-coding
> Erasure Coding: Missing parity blocks in the block group are warned as
> corrupt blocks
> -------------------------------------------------------------------------------------
>
> Key: HDFS-11553
> URL: https://issues.apache.org/jira/browse/HDFS-11553
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: erasure-coding
> Reporter: Manoj Govindassamy
> Assignee: Manoj Govindassamy
> Labels: hdfs-ec-3.0-nice-to-have
>
> Currently, {{DFSStripedOutputStream}} verifies if the allocated block
> locations are at least numDataBlocks length. That is, for the EC Policy
> RS-6-3-64K, though the total needed DNs for a full EC Block Group is 9,
> Clients will be able to successfully create a DFSStripedOutputStream with
> just 6 DNs. Moreover, the output stream thus created with less DNs will
> totally ignore writing Parity Blocks. HDFS-11552 is tracking the improvement
> needed to accommodate Parity Blocks along with Data Blocks from the same
> Block Group.
> {code}
> [Thread-5] WARN hdfs.DFSOutputStream
> (DFSStripedOutputStream.java:allocateNewBlock(497)) - Failed to get block
> location for parity block, index=6
> [Thread-5] WARN hdfs.DFSOutputStream
> (DFSStripedOutputStream.java:allocateNewBlock(497)) - Failed to get block
> location for parity block, index=7
> [Thread-5] WARN hdfs.DFSOutputStream
> (DFSStripedOutputStream.java:allocateNewBlock(497)) - Failed to get block
> location for parity block, index=8
> {code}
> In the above case, upon file stream close we get the following warning
> message when the parity blocks are not yet written out. The warning message
> claims that there are 3 corrupt blocks, which is in-correct. Its just the EC
> redundancy is not sufficient and not corrupt or lost yet. This warning
> message in the context of above usecase need to be fixed.
> {code}
> INFO namenode.FSNamesystem (FSNamesystem.java:checkBlocksComplete(2726)) -
> BLOCK* blk_-9223372036854775792_1002 is COMMITTED but not COMPLETE(numNodes=
> 0 < minimum = 6) in file /ec/test1
> INFO hdfs.StateChange (FSNamesystem.java:completeFile(2679)) - DIR*
> completeFile: /ec/test1 is closed by DFSClient_NONMAPREDUCE_-1900076771_17
> WARN hdfs.DFSOutputStream
> (DFSStripedOutputStream.java:logCorruptBlocks(1117)) - Block group <1> has 3
> corrupt blocks. It's at high risk of losing data.
> {code}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
