Re: Improving connection scalability: GetSnapshotData()

Hi,

On 2020-09-06 14:05:35 +0300, Konstantin Knizhnik wrote:
> On 04.09.2020 21:53, Andres Freund wrote:
> >
> > > May be it is because of more complex architecture of my server?
> > Think we'll need profiles to know...
>
> This is "perf top" of pgebch -c 100 -j 100 -M prepared -S
>
>   12.16%  postgres                           [.] PinBuffer
>   11.92%  postgres                           [.] LWLockAttemptLock
>    6.46%  postgres                           [.] UnpinBuffer.constprop.11
>    6.03%  postgres                           [.] LWLockRelease
>    3.14%  postgres                           [.] BufferGetBlockNumber
>    3.04%  postgres                           [.] ReadBuffer_common
>    2.13%  [kernel]                           [k] _raw_spin_lock_irqsave
>    2.11%  [kernel]                           [k] switch_mm_irqs_off
>    1.95%  postgres                           [.] _bt_compare
>
>
> Looks like most of the time is pent in buffers locks.

Hm, that is interesting / odd. If you record a profile with call graphs
(e.g. --call-graph dwarf), where are all the LWLockAttemptLock calls
comming from?

I assume the machine you're talking about is an 8 socket machine?

What if you:
a) start postgres and pgbench with numactl --interleave=all
b) start postgres with numactl --interleave=0,1 --cpunodebind=0,1 --membind=0,1
in case you have 4 sockets, or 0,1,2,3 in case you have 8 sockets?

> And which pgbench database scale factor you have used?

200

Another thing you could try is to run 2-4 pgench instances in different
databases.

Greetings,

Andres Freund