cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Peter Schuller (JIRA)" <>
Subject [jira] Commented: (CASSANDRA-1991) CFS.maybeSwitchMemtable() calls CommitLog.instance.getContext(), which may block, under flusher lock write lock
Date Mon, 24 Jan 2011 22:01:44 GMT


Peter Schuller commented on CASSANDRA-1991:

I'll revisit and try to figure out how to decrease fragility/complexity. CASSANDRA-1955 had
the potential to increase complexity even more to this part of the code (I was close to suggesting
a less complete solution there just to avoid tackling it properly as the "proper" fix required
moving certain things out from under the flusher lock).

I'm thinking a bigger change may be worth it if the result is clearer and less complex.

Disregarding for a moment the additional complexity implied by the last patch, would you agree
though that it is at least plausibly a good idea, given that it can be done cleanly, to separate
checkpointing from flushing, and that it is a good idea to make checkpoint explicit rather
than an implicit side-effect of all flushes?

It "feels" like there exists a clean solution that would address both this and CASSANDRA-1955
implicitly without an increase in complexity. Just need to find it.

> CFS.maybeSwitchMemtable() calls CommitLog.instance.getContext(), which may block, under
flusher lock write lock
> ---------------------------------------------------------------------------------------------------------------
>                 Key: CASSANDRA-1991
>                 URL:
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Peter Schuller
>            Assignee: Peter Schuller
>         Attachments: 1991-checkpointing-flush.txt, 1991-logchanges.txt, 1991-trunk-v2.txt,
1991-trunk.txt, 1991-v3.txt, 1991-v4.txt, 1991-v5.txt, 1991-v6.txt, 1991-v7.txt, 1991-v8.txt,
> While investigate CASSANDRA-1955 I realized I was seeing very poor latencies for reasons
that had nothing to do with flush_writers, even when using periodic commit log mode (and flush
writers set ridiculously high, 500).
> It turns out writes blocked were slow because Table.apply() was spending lots of time
(I can easily trigger seconds on moderate work-load) trying to acquire a flusher lock read
lock ("flush lock millis" log printout in the logging patch I'll attach).
> That in turns is caused by CFS.maybeSwitchMemtable() which acquires the flusher lock
write lock.
> Bisecting further revealed that the offending line of code that blocked was:
>                     final CommitLogSegment.CommitLogContext ctx = writeCommitLog ? CommitLog.instance.getContext()
: null;
> Indeed, CommitLog.getContext() simply returns currentSegment().getContext(), but does
so by submitting a callable on the service executor. So independently of flush writers, this
can block all (global, for all cf:s) writes very easily, and does.
> I'll attach a file that is an independent Python script that triggers it on my macos
laptop (with an intel SSD, which is why I was particularly surprised) (it assumes CPython,
out-of-the-box-or-almost Cassandra on localhost that isn't in a cluster, and it will drop/recreate
a keyspace called '1955').
> I'm also attaching, just FYI, the patch with log entries that I used while tracking it
> Finally, I'll attach a patch with a suggested solution of keeping track of the latest
commit log with an AtomicReference (as an alternative to synchronizing all access to segments).
With that patch applied, latencies are not affected by my trigger case like they were before.
There are some sub-optimal > 100 ms cases on my test machine, but for other reasons. I'm
no longer able to trigger the extremes.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message