| From: | Scott Ribe <scott_ribe(at)elevated-dev(dot)com> |
|---|---|
| To: | "Gogala, Mladen (Short Hills)" <mladen(dot)gogala(at)Fiserv(dot)com> |
| Cc: | pgsql-admin <pgsql-admin(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: regarding PG on ZFS performance |
| Date: | 2022-04-12 19:48:30 |
| Message-ID: | CD93C6F7-ABB9-4D8E-BB1B-A517B6B00EF9@elevated-dev.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-admin |
> On Apr 12, 2022, at 10:54 AM, Gogala, Mladen (Short Hills) <mladen(dot)gogala(at)Fiserv(dot)com> wrote:
>
> I wouldn’t call turning off data safety “a proper tuning”. It may be faster but can never be deployed to production.
As I explained, that which it protects against cannot happen on a ZFS volume. Therefore turning it off is just fine.
(ZFS fsync operations are themselves atomic, using its own write-ahead log. So full_page_writes does a double write to avoid corruption, but so does ZFS, thus 4X writes, and a major source of slowness. There is NO danger in letting only one of the two do a double-write in order to avoid a partial write ever being read back.)
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Scott Ribe | 2022-04-12 19:50:28 | Re: regarding PG on ZFS performance |
| Previous Message | Scott Ribe | 2022-04-12 16:18:09 | regarding PG on ZFS performance |