| From: | Alvaro Herrera <alvherre(at)2ndquadrant(dot)com> |
|---|---|
| To: | Andres Freund <andres(at)2ndquadrant(dot)com> |
| Cc: | Jesper Krogh <jesper(at)krogh(dot)cc>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: issue with gininsert under very high load |
| Date: | 2014-02-14 13:02:14 |
| Message-ID: | 20140214130214.GB6342@eldon.alvh.no-ip.org |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Andres Freund wrote:
> On 2014-02-14 08:06:40 +0100, Jesper Krogh wrote:
> > The build in mechanism, that cleanup is i cost paid by the process who
> > happened to fill the pendinglist, is really hard to deal with in
> > production. More control is appreciated, perhaps even an explicit
> > flush-mechanism.. I'd like to batch up inserts during one transaction
> > only and flush on commit.
>
> That doesn't seem likely to work with a reasonable amount of effort. The
> fastupdate list is shared across all processes, so one backend will
> always pay the price for several others.
Unless some other process does it, such as autovacuum.
--
Álvaro Herrera http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andres Freund | 2014-02-14 13:07:55 | Re: Memory ordering issue in LWLockRelease, WakeupWaiters, WALInsertSlotRelease |
| Previous Message | Andres Freund | 2014-02-14 12:58:59 | Re: walsender doesn't send keepalives when writes are pending |