|From:||Aleksander Alekseev <a(dot)alekseev(at)postgrespro(dot)ru>|
|To:||Andres Freund <andres(at)anarazel(dot)de>|
|Cc:||Robert Haas <robertmhaas(at)gmail(dot)com>, "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org>|
|Subject:||Re: Patch: fix lock contention for HASHHDR.mutex|
|Views:||Raw Message | Whole Thread | Download mbox | Resend email|
> It'd really like to see it being replaced by a queuing lock
> (i.e. lwlock) before we go there. And then maybe partition the
> freelist, and make nentries an atomic.
I believe I just implemented something like this (see attachment). The
idea is to partition PROCLOCK hash table manually into NUM_LOCK_
PARTITIONS smaller and non-partitioned hash tables. Since these tables
are non-partitioned spinlock is not used and there is no lock
On 60-core server we gain 3.5-4 more TPS according to benchmark
described above. As I understand there is no performance degradation in
other cases (different CPU, traditional pgbench, etc).
If this patch seems to be OK I believe we could consider applying the
same change not only to PROCLOCK hash table.
|Next Message||Tom Lane||2015-12-17 16:19:28||Re: Using a single standalone-backend run in initdb (was Re: Bootstrap DATA is a pita)|
|Previous Message||Tomas Vondra||2015-12-17 16:00:47||Re: WIP: bloom filter in Hash Joins with batches|