You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-issues@hadoop.apache.org by "Xiao Chen (JIRA)" <ji...@apache.org> on 2018/01/24 04:54:00 UTC
[jira] [Commented] (HDFS-12528) Short-circuit reads unnecessarily
disabled for a long time
[ https://issues.apache.org/jira/browse/HDFS-12528?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16336895#comment-16336895 ]
Xiao Chen commented on HDFS-12528:
----------------------------------
Attaching a patch to do just #1, with enhanced unit tests from John to test behavior for the default (disable for 10 minutes) and the never disable (0). Reason didn't do #2 is I think the threshold is really a subjective thing, and it feels to me having #1 would be sufficient for the requests so far from this jira.
> Short-circuit reads unnecessarily disabled for a long time
> ----------------------------------------------------------
>
> Key: HDFS-12528
> URL: https://issues.apache.org/jira/browse/HDFS-12528
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: hdfs-client, performance
> Affects Versions: 2.6.0
> Reporter: Andre Araujo
> Assignee: Xiao Chen
> Priority: Major
> Attachments: HDFS-12528.000.patch
>
>
> We have scenarios where data ingestion makes use of the -appendToFile operation to add new data to existing HDFS files. In these situations, we're frequently running into the problem described below.
> We're using Impala to query the HDFS data with short-circuit reads (SCR) enabled. After each file read, Impala "unbuffer"'s the HDFS file to reduce the memory footprint. In some cases, though, Impala still keeps the HDFS file handle open for reuse.
> The "unbuffer" call, however, causes the file's current block reader to be closed, which makes the associated ShortCircuitReplica evictable from the ShortCircuitCache. When the cluster is under load, this means that the ShortCircuitReplica can be purged off the cache pretty fast, which closes the file descriptor to the underlying storage file.
> That means that when Impala re-reads the file it has to re-open the storage files associated with the ShortCircuitReplica's that were evicted from the cache. If there were no appends to those blocks, the re-open will succeed without problems. If one block was appended since the ShortCircuitReplica was created, the re-open will fail with the following error:
> {code}
> Meta file for BP-810388474-172.31.113.69-1499543341726:blk_1074012183_273087 not found
> {code}
> This error is handled as an "unknown response" by the BlockReaderFactory [1], which disables short-circuit reads for 10 minutes [2] for the client.
> These 10 minutes without SCR can have a big performance impact for the client operations. In this particular case ("Meta file not found") it would suffice to return null without disabling SCR. This particular block read would fall back to the normal, non-short-circuited, path and other SCR requests would continue to work as expected.
> It might also be interesting to be able to control how long SCR is disabled for in the "unknown response" case. 10 minutes seems a bit to long and not being able to change that is a problem.
> [1] https://github.com/apache/hadoop/blob/f67237cbe7bc48a1b9088e990800b37529f1db2a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/impl/BlockReaderFactory.java#L646
> [2] https://github.com/apache/hadoop/blob/f67237cbe7bc48a1b9088e990800b37529f1db2a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/shortcircuit/DomainSocketFactory.java#L97
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-help@hadoop.apache.org