| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Hannu Krosing <hannu(at)tm(dot)ee> |
| Cc: | Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>, pgman(at)candle(dot)pha(dot)pa(dot)us, pgsql-hackers(at)postgresql(dot)org, jwbaker(at)acm(dot)org |
| Subject: | Re: LWLock contention: I think I understand the problem |
| Date: | 2002-01-05 21:44:53 |
| Message-ID: | 13255.1010267093@sss.pgh.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers pgsql-odbc |
Hannu Krosing <hannu(at)tm(dot)ee> writes:
> Could you rerun some of the tests on the same hardware but with
> uniprocesor kernel
I don't have root on that machine, but will see what I can arrange next
week.
> There were some reports about very poor insert performance on 4way vs 1way
> processors.
IIRC, that was fixed for 7.2. (As far as I can tell from profiling,
contention for the shared free-space-map is a complete nonissue, at
least in this test. That was something I was a tad worried about
when I wrote the FSM code, but the tactic of locally caching a current
insertion page seems to have sidestepped the problem nicely.)
>> psql -c 'vacuum' $DB
>>
> Should this not be 'vacuum full' ?
Don't see why I should expend the extra time to do a vacuum full.
The point here is just to ensure a comparable starting state for all
the runs.
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Bear Giles | 2002-01-05 21:49:52 | preannouncement: libpkixpq 0.3 will have crypto |
| Previous Message | Brent Verner | 2002-01-05 21:41:01 | Re: Some interesting results from tweaking spinlocks |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Ashley Cambrell | 2002-01-06 12:01:44 | Re: LWLock contention: I think I understand the problem |
| Previous Message | Hannu Krosing | 2002-01-05 17:54:29 | Re: LWLock contention: I think I understand the problem |