| From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
|---|---|
| To: | scott ribe <scott_ribe(at)killerbytes(dot)com> |
| Cc: | Postgresql General <pgsql-general(at)postgresql(dot)org> |
| Subject: | Re: PG on SSD |
| Date: | 2017-03-02 23:31:47 |
| Message-ID: | CAOR=d=1swoz_FZosK+xv-k9JfQZmZjp8FTmN8Mc804tk9WWCTw@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
On Thu, Mar 2, 2017 at 12:42 PM, scott ribe <scott_ribe(at)killerbytes(dot)com> wrote:
> Is it reasonable to run PG on a mirrored pair of something like the Intel SSD DC 3610 series? (For example:
> http://ark.intel.com/products/82935/Intel-SSD-DC-S3610-Series-480GB-2_5in-SATA-6Gbs-20nm-MLC) I'd *hope* that anything Intel classifies as a "Data Center SSD" would be reasonably reliable, have actually-working power loss protection etc, but is that the case?
From the spec sheet they certainly seem to be safe against power loss.
I'd still test by pulling the power cables while running benchmarks to
be sure.
I've used the other Intel enterprise class ssds with good results on
the power plug pull tests.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Michael Paquier | 2017-03-03 00:31:36 | Re: Postgres 9.x table/index stats reset timestamp |
| Previous Message | Zach Walton | 2017-03-02 23:04:26 | Re: Understanding pg_last_xlog_receive_location |