| From: | Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us> |
|---|---|
| To: | Vadim Mikheev <vmikheev(at)sectorbase(dot)com> |
| Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Stuck spins in current |
| Date: | 2001-03-21 13:25:00 |
| Message-ID: | 200103211325.IAA14765@candle.pha.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
> > > BTW, I've got ~320tps with 50 clients inserting (int4, text[1-256])
> > > records into 50 tables (-B 16384, wal_buffers = 256) on Ultra10
> > > with 512Mb RAM, IDE (clients run on the same host as server).
> >
> > Not bad. What were you getting before these recent changes?
>
> As I already reported - with O_DSYNC this test shows 30% better
> performance than with fsync.
>
> (BTW, seems in all my tests I was using -O0 flag...)
Good data point. I could never understand why we would ever use the
normal sync if we had a data-only sync option available. I can imagine
the data-only being the same, but never slower.
--
Bruce Momjian | http://candle.pha.pa.us
pgman(at)candle(dot)pha(dot)pa(dot)us | (610) 853-3000
+ If your life is a hard drive, | 830 Blythe Avenue
+ Christ can be your backup. | Drexel Hill, Pennsylvania 19026
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Jim Buttafuoco | 2001-03-21 13:38:41 | Re: Re: Final Call: RC1 about to go out the door ... |
| Previous Message | Adriaan Joubert | 2001-03-21 13:10:55 | Re: int8 bug on Alpha |