[
https://issues.apache.org/jira/browse/MESOS-3572?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Neil Conway updated MESOS-3572:
-------------------------------
Description:
Right now, the catchup protocol does a full Paxos round for every log entry
missing from a recovering replica. This should be unnecessary for "learned" log
entries, because there is no uncertainty about the status of such log entries.
We'll probably only need to do a full Paxos round for entries near the tail of
the log.
To motivate changing this, it would be good to first measure the performance of
the catchup protocol to understand if/when performance improvements would be
useful. There's also [MESOS-770], which mentions the idea of doing catchup in
parallel.
was:
Right now, the catchup protocol does a full Paxos round for every log entry
missing from a recovering replica. This should be unnecessary for "learned" log
entries, because there is no uncertainty about the status of such log entries.
We'll probably only need to do a full Paxos round for entries near the tail of
the log.
To motivate changing this, it would be good to first measure the performance of
the catchup protocol to understand if/when performance improvements would be
useful. There's also [MESOS-736], which is about how to do catchup in parallel.
Issue Type: Improvement (was: Bug)
> Faster catchup protocol for "learned" replicated log entries
> ------------------------------------------------------------
>
> Key: MESOS-3572
> URL: https://issues.apache.org/jira/browse/MESOS-3572
> Project: Mesos
> Issue Type: Improvement
> Reporter: Neil Conway
>
> Right now, the catchup protocol does a full Paxos round for every log entry
> missing from a recovering replica. This should be unnecessary for "learned"
> log entries, because there is no uncertainty about the status of such log
> entries. We'll probably only need to do a full Paxos round for entries near
> the tail of the log.
> To motivate changing this, it would be good to first measure the performance
> of the catchup protocol to understand if/when performance improvements would
> be useful. There's also [MESOS-770], which mentions the idea of doing catchup
> in parallel.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
