[
https://issues.apache.org/jira/browse/HDFS-12914?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16845376#comment-16845376
]
Santosh Marella commented on HDFS-12914:
----------------------------------------
Another interesting thing we found is that calls to {{getNumLiveDatanodes}} is
probably the main cause for the slowness in FBR processing. In a way,
HDFS-14171 might help us to avoid running into this issue in the first place.
However, I feel it is still good to have a fix for this JIRA, as FBR processing
can be slow due to some other reasons. A cleaner way to deal with lease expiry
can save us from partial processing of FBRs.
> Block report leases cause missing blocks until next report
> ----------------------------------------------------------
>
> Key: HDFS-12914
> URL: https://issues.apache.org/jira/browse/HDFS-12914
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: namenode
> Affects Versions: 2.8.0, 2.9.2
> Reporter: Daryn Sharp
> Assignee: Santosh Marella
> Priority: Critical
> Attachments: HDFS-12914-branch-2.001.patch, HDFS-12914-trunk.00.patch
>
>
> {{BlockReportLeaseManager#checkLease}} will reject FBRs from DNs for
> conditions such as "unknown datanode", "not in pending set", "lease has
> expired", wrong lease id, etc. Lease rejection does not throw an exception.
> It returns false which bubbles up to {{NameNodeRpcServer#blockReport}} and
> interpreted as {{noStaleStorages}}.
> A re-registering node whose FBR is rejected from an invalid lease becomes
> active with _no blocks_. A replication storm ensues possibly causing DNs to
> temporarily go dead (HDFS-12645), leading to more FBR lease rejections on
> re-registration. The cluster will have many "missing blocks" until the DNs
> next FBR is sent and/or forced.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
