| From: | "Graeme B(dot) Bell" <graeme(dot)bell(at)nibio(dot)no> |
|---|---|
| To: | Bram Van Steenlandt <bram(at)diomedia(dot)be> |
| Cc: | "pgsql-performance(at)postgresql(dot)org" <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: large object write performance |
| Date: | 2015-10-08 10:25:02 |
| Message-ID: | 8809EA0A-C7DE-4CC3-B2E4-9F0062A91B93@skogoglandskap.no |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
> On 08 Oct 2015, at 11:17, Bram Van Steenlandt <bram(at)diomedia(dot)be> wrote:
>
> The database (9.2.9) on the server (freebsd10) runs on a zfs mirror.
> If I copy a file to the mirror using scp I get 37MB/sec
> My script achieves something like 7 or 8MB/sec on large (+100MB) files.
This may help - great blog article about ZFS with postgres and how use you can zfs compression to boost i/o performance substantially.
If your machine is making a lot of smaller writes in postgres (as opposed to presumably large writes by scp) then this may alleviate things a bit.
https://www.citusdata.com/blog/64-zfs-compression
Graeme Bell
p.s. Apologies for top-posting on my previous message.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Graeme B. Bell | 2015-10-08 11:21:50 | Re: large object write performance |
| Previous Message | Graeme B. Bell | 2015-10-08 09:45:16 | Re: large object write performance |