On 01/11/2016 06:11 PM, Stas Kelvich wrote:
>> On 11 Jan 2016, at 21:40, Jesper Pedersen <jesper.pedersen@redhat.com> wrote:
>> I have done a run with the patch and it looks really great.
>>
>> Attached is the TPS graph - with a 1pc run too - and the perf profile as a flame graph (28C/56T w/ 256Gb mem, 2 x
RAID10SSD).
>>
>
> Thanks for testing and especially for the flame graph. That is somewhat in between the cases that I have tested. On
commodityserver with dual Xeon (6C each) 2pc speed is about 80% of 1pc speed, but on 60C/120T system that patch didn’t
makesignificant difference because main bottleneck changes from file access to locks on array of running global
transactions.
>
> How did you generated names for your PREPARE’s? One funny thing that I’ve spotted that tx rate increased when i was
usingincrementing counter as GID instead of random string.
>
I'm using https://github.com/jesperpedersen/postgres/tree/pgbench_xa -
so just the client_id.
The strcmp() in MarkAsPreparing() is under the exclusive lock, so maybe
that is what you are seeing, as shorter gid's are faster.
> And can you also share flame graph for 1pc workload?
>
Attached with a new 2pc, as the server runs Linux 4.4.0 now, both using
-F 497 over a 6 min run.
Best regards,
Jesper
