| From: | KONDO Mitsumasa <kondo(dot)mitsumasa(at)lab(dot)ntt(dot)co(dot)jp> |
|---|---|
| To: | Andres Freund <andres(at)2ndquadrant(dot)com> |
| Cc: | Jeff Davis <pgsql(at)j-davis(dot)com>, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Greg Smith <greg(at)2ndQuadrant(dot)com>, Jon Nelson <jnelson+pgsql(at)jamponi(dot)net>, Hannu Krosing <hannu(at)2ndquadrant(dot)com>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>, Thom Brown <thom(at)linux(dot)com> |
| Subject: | Re: 9.4 regression |
| Date: | 2013-09-05 07:41:28 |
| Message-ID: | 522835A8.1040701@lab.ntt.co.jp |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
(2013/09/05 0:04), Andres Freund wrote:
> I'd vote for adding zeroing *after* the fallocate() first.
+1, with FALLOC_FL_KEEP_SIZE flag.
At least, fallocate with FALLOC_FL_KEEP_SIZE flag is faster than nothing in my
developing sorted checkpoint. I adopted it to relation file, so I don't know
about WAL file.
With FALLOC_FL_KEEP_SIZE flag does not change file size and not do zero fill. It
seems to only get continuous physical disk space in file system.
Here is draft patch.
Regards,
--
Mitsumasa KONDO
NTT Open Source Software Center
| Attachment | Content-Type | Size |
|---|---|---|
| wal-fallocate_keep_size_v0.patch | text/x-diff | 628 bytes |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Pavel Stehule | 2013-09-05 08:42:29 | Re: Improving avg performance for numeric |
| Previous Message | Atri Sharma | 2013-09-05 07:36:35 | Re: [rfc] overhauling pgstat.stat |