| From: | Teodor Sigaev <teodor(at)sigaev(dot)ru> |
|---|---|
| To: | David Rowley <dgrowleyml(at)gmail(dot)com> |
| Cc: | Pgsql Hackers <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: speedup tidbitmap patch: cache page |
| Date: | 2014-12-17 15:56:48 |
| Message-ID: | 5491A7C0.20708@sigaev.ru |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
> You could well be right, but it would be good to compare the numbers just so we
> know this for sure.
I wasn't right :(
# set work_mem='64kB';
# set enable_seqscan = off;
Patched: 1194.094 ms
Master: 1765.338 ms
> Are you seeing the same?
Fixed too, the mistake was in supposition that current page becomes lossy in
tbm_lossify. It's not always true because tbm_lossify() could lossify only part
of pages and we don't know which. Thank you very much.
--
Teodor Sigaev E-mail: teodor(at)sigaev(dot)ru
WWW: http://www.sigaev.ru/
| Attachment | Content-Type | Size |
|---|---|---|
| tbm_cachepage-2.2.patch.gz | application/x-gzip | 865 bytes |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Heikki Linnakangas | 2014-12-17 16:20:49 | Re: Proposal: Log inability to lock pages during vacuum |
| Previous Message | didier | 2014-12-17 15:56:25 | Re: WALWriter active during recovery |