|From:||Konstantin Knizhnik <k(dot)knizhnik(at)postgrespro(dot)ru>|
|To:||Andres Freund <andres(at)anarazel(dot)de>|
|Subject:||Re: Improving connection scalability: GetSnapshotData()|
|Views:||Raw Message | Whole Thread | Download mbox | Resend email|
On 06.09.2020 21:52, Andres Freund wrote:
> On 2020-09-05 16:58:31 +0300, Konstantin Knizhnik wrote:
>> On 04.09.2020 21:53, Andres Freund wrote:
>>> I also used huge_pages=on / configured them on the OS level. Otherwise
>>> TLB misses will be a significant factor.
>> As far as I understand there should not be no any TLB misses because size of
>> the shared buffers (8Mb) as several order of magnitude smaler that available
>> physical memory.
> I assume you didn't mean 8MB but 8GB? If so, that's way large enough to
> be bigger than the TLB, particularly across processes (IIRC there's no
> optimization to keep shared mappings de-duplicated between processes
> from the view of the TLB).
Sorry, certainly 8Gb.
I tried huge pages, but it has almost no effect/
|Next Message||Simon.Schneider||2020-09-07 16:48:22||Meaning of pg_stats_subscription.latest_end_time|
|Previous Message||Tom Lane||2020-09-07 16:07:15||Re: Auto-vectorization speeds up multiplication of large-precision numerics|