[
https://issues.apache.org/jira/browse/IGNITE-22835?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18056639#comment-18056639
]
Alexey Scherbakov commented on IGNITE-22835:
--------------------------------------------
I believe there are 2 reasons:
1. Rocksdb log has more overhead - a call to write a log takes more time
2. Shared event loop prevents log disruptor batching, so the number of log
write calls grows. logit writes are much lighter and don't prevent pipeline
stalls too much in this case.
> Latency penalty for using disruptor threads
> -------------------------------------------
>
> Key: IGNITE-22835
> URL: https://issues.apache.org/jira/browse/IGNITE-22835
> Project: Ignite
> Issue Type: Improvement
> Reporter: Vladislav Pyatkov
> Assignee: Alexey Scherbakov
> Priority: Major
> Labels: ignite-3
> Time Spent: 10m
> Remaining Estimate: 0h
>
> h3. Motivation
> All three disruptors are part of the RAFT implementation. Each time a command
> has to be replicated, all the disruptors are used. This leads to a bad impact
> on the entire operation's latency.
> {noformat}
> onBeforeApplyCmd:%node_3344%JRaft-Request-Processor-3 0.2 5415400 5415600
> Here is hidden 6.1 us
> RaftNodeOnEvent:%node_3344%JRaft-NodeImpl-Disruptor_stripe_2-0 0.0 5421700
> 5421700
> --
> RaftNodeOnEvent:%node_3344%JRaft-NodeImpl-Disruptor_stripe_2-0 0.0 5421700
> 5421700
> Here is hidden 2.8 us
> LogManagerOnEvent:%node_3344%JRaft-LogManager-Disruptor_stripe_2-0 0.1
> 5424500 5424600
> --
> flushLog:%node_3344%JRaft-LogManager-Disruptor_stripe_2-0 18.7 5426400 5445100
> Here is hidden 2.9 us
> FSMCallerOnEvent:%node_3344%JRaft-FSMCaller-Disruptor_stripe_1-0 0.1 5448000
> 5448100
> {noformat}
> h3. Definition of done
> * We can try to use the disruptor wait policy, depending on the case.
> * Maybe we can reduce a number of the dusruptor queues.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
