[
https://issues.apache.org/jira/browse/HDFS-3077?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13472363#comment-13472363
]
Suresh Srinivas commented on HDFS-3077:
---------------------------------------
I wanted to avoid two threads of discussions going on at the same time...
bq. But, I'm not sure it's simpler or more robust. My reasoning is that
starting a new epoch (thus fencing the prior writer) is semantically different
than beginning recovery for a particular segment. So I think it's clearer to
put them in different pieces of code, even if they could be piggy-backed one on
top of the other for future round trips.
I think it is more robust because of less number of messages. Lets say it is
not more robust - at least now the protocol is starts looking more relatable to
ZAB/Paxos. {{NEWEPOCH + ACK}} in ZAB or {{Prepare + Promise}} in paxos indeed
fences/prevents the writer with older epoch. So I am not sure separation of
fencing makes the design clearer. In my case it was the opposite.
bq. Another reason is that the current separation allows correct behavior in
the face of IPC retries on PrepareRecovery, since PrepareRecovery is
idempotent. NewEpoch is necessarily not idempotent, because it is the one IPC
that requires a strictly greater epoch id (in order to preserve uniqueness of
epochs). This means that, if there's some timeout prepare phase, we can safely
add retries a few times to get past it, while such a policy doesn't work on
NewEpoch.
I did not understand this well. Why are we retrying any request to
JournalNodes? Given most of the requests are not idempotent and cannot be
retried why is this an advantage?
> Quorum-based protocol for reading and writing edit logs
> -------------------------------------------------------
>
> Key: HDFS-3077
> URL: https://issues.apache.org/jira/browse/HDFS-3077
> Project: Hadoop HDFS
> Issue Type: New Feature
> Components: ha, name-node
> Reporter: Todd Lipcon
> Assignee: Todd Lipcon
> Fix For: QuorumJournalManager (HDFS-3077)
>
> Attachments: hdfs-3077-partial.txt, hdfs-3077-test-merge.txt,
> hdfs-3077.txt, hdfs-3077.txt, hdfs-3077.txt, hdfs-3077.txt, hdfs-3077.txt,
> hdfs-3077.txt, hdfs-3077.txt, qjournal-design.pdf, qjournal-design.pdf,
> qjournal-design.pdf, qjournal-design.pdf, qjournal-design.pdf,
> qjournal-design.pdf, qjournal-design.tex, qjournal-design.tex
>
>
> Currently, one of the weak points of the HA design is that it relies on
> shared storage such as an NFS filer for the shared edit log. One alternative
> that has been proposed is to depend on BookKeeper, a ZooKeeper subproject
> which provides a highly available replicated edit log on commodity hardware.
> This JIRA is to implement another alternative, based on a quorum commit
> protocol, integrated more tightly in HDFS and with the requirements driven
> only by HDFS's needs rather than more generic use cases. More details to
> follow.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
