| From: | Marti Raudsepp <marti(at)juffo(dot)org> |
|---|---|
| To: | Aidan Van Dyk <aidan(at)highrise(dot)ca> |
| Cc: | Havasvölgyi Ottó <havasvolgyi(dot)otto(at)gmail(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Response time increases over time |
| Date: | 2011-12-08 13:44:42 |
| Message-ID: | CABRT9RC+iRXhvA4KCeR3+hoh179WKyc1QNicpPBD1NbzM4RYdA@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
On Thu, Dec 8, 2011 at 06:37, Aidan Van Dyk <aidan(at)highrise(dot)ca> wrote:
> Let me guess, debian squeeze, with data and xlog on both on a single
> ext3 filesystem, and the fsync done by your commit (xlog) is flushing
> all the dirty data of the entire filesystem (including PG data writes)
> out before it can return...
This is fixed with the data=writeback mount option, right?
(If it's the root file system, you need to add
rootfsflags=data=writeback to your kernel boot flags)
While this setting is safe and recommended for PostgreSQL and other
transactional databases, it can cause garbage to appear in recently
written files after a crash/power loss -- for applications that don't
correctly fsync data to disk.
Regards,
Marti
| From | Date | Subject | |
|---|---|---|---|
| Next Message | voodooless | 2011-12-08 13:57:38 | Re: Partitions and joins lead to index lookups on all partitions |
| Previous Message | Havasvölgyi Ottó | 2011-12-08 08:50:14 | Re: Response time increases over time |