Re: XLogInsert scaling, revisited

On Sat, Jun 22, 2013 at 4:32 AM, Heikki Linnakangas <hlinnakangas@vmware.com
> wrote:

> On 21.06.2013 21:55, Jeff Janes wrote:
>
>>
>> Hmm, it looks like the xlog-switch is trying to wait for itself to
> finish. The concurrent TRUNCATE is just being blocked behind the
> xlog-switch, which is stuck on itself.
>
> I wasn't able to reproduce exactly that, but I got a PANIC by running
> pgbench and concurrently doing "select pg_switch_xlog()" many times in psql.
>
> Attached is a new version that fixes at least the problem I saw. Not sure
> if it fixes what you saw, but it's worth a try. How easily can you
> reproduce that?


With v23, it got stuck both times I tried it, once after 4 hours and once
after 6 hours.

With v24, it has been running for 30 hours so far with no problems.  So
there is a pretty good chance that it is fixed.


>
>  This is using the same testing harness as in the last round of this patch.
>>
>
> This one? http://www.postgresql.org/**message-id/CAMkU=1xoA6Fdyoj_**
> 4fMLqpicZR1V9GP7cLnXJdHU+**iGgqb6WUw@mail.gmail.com<http://www.postgresql.org/message-id/CAMkU=1xoA6Fdyoj_4fMLqpicZR1V9GP7cLnXJdHU+iGgqb6WUw@mail.gmail.com>



Yes.  I have cleaned it up some and added use of checksum, I don't know if
any of those things are needed to invoke the problem.


Cheers,

Jeff