From: | Ravi Krishna <srkrishna(at)outlook(dot)com> |
---|---|
To: | "pgsql-admin(at)postgresql(dot)org" <pgsql-admin(at)postgresql(dot)org> |
Subject: | Re: Best setting for wal_sync_method |
Date: | 2015-05-07 16:19:14 |
Message-ID: | BAY172-W204C9DEAB4D936F45468A5B9DF0@phx.gbl |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-admin |
Speaking to the sys admins we found that the file system where the WAL was written to did not have direct_io and hence all writes were getting buffered. So we enabled direct_io on that FS and now writes are order of magnitude slower (5x times).
It seems PG already uses O_DIRECT for WAL. So is the enabling of direct_io in the mount options of the FS totally redundant. It definitely has a serious performance impact.
Thanks
From: srkrishna(at)outlook(dot)com
To: pgsql-admin(at)postgresql(dot)org
Subject: [ADMIN] Best setting for wal_sync_method
Date: Thu, 7 May 2015 09:36:36 -0400
On RHEL 6.4 which is the best setting for wal_sync_method for write intensive operations. Is the default fdatasync good for all conditions, including reliability.
Thanks
From | Date | Subject | |
---|---|---|---|
Next Message | Zoltan Szecsei | 2015-05-07 16:27:13 | connect postgresql to a different cluster |
Previous Message | Matheus de Oliveira | 2015-05-07 15:53:21 | Re: where table privileges are stored |