pg.ddx.io  pgsql-performance@postgresql.org mailing list archive  
help / color / mirror / Atom feed
From: Bruce Momjian <pgman@candle.pha.pa.us>
To: Kurt Roeckx <Q@ping.be>
Cc: Tom Lane <tgl@sss.pgh.pa.us>
Cc: Mark Kirkwood <markir@paradise.net.nz>
Cc: pgsql-performance@postgresql.org, PostgreSQL-development <pgsql-hackers@postgresql.org>
Subject: Re: [HACKERS] fsync method checking
Date: Thu, 18 Mar 2004 15:09:25 -0500 (EST)
Message-ID: <200403182009.i2IK9PJ24080@candle.pha.pa.us> (raw)
In-Reply-To: <20040318200359.GA8330@ping.be>

Kurt Roeckx wrote:
> On Thu, Mar 18, 2004 at 02:22:10PM -0500, Bruce Momjian wrote:
> > 
> > OK, what better test do you suggest?  Right now, there has been no
> > testing of these.
> 
> I suggest you start by doing atleast preallocating a 16 MB file
> and do the tests on that, to atleast be somewhat simular to what
> WAL does.
> 
> I have no idea what the access pattern is for normal WAL
> operations or how many times it gets synched.  Does it only do
> f(data)sync() at commit time, or for every block it writes?
> 
> I think if you write more data you'll see more differences
> between O_(D)SYNC and f(data)sync().
> 
> I guess it can depend on if you have lots of small transactions,
> or more big ones.
> 
> Atleast try to make something that covers different access
> patterns.

OK, I preallocated 16mb.  New results:

Simple write timing:
        write                    0.037900

Compare fsync times on write() and non-write() descriptor:
(If the times are similar, fsync() can sync data written
 on a different descriptor.)
        write, fsync, close      0.692942
        write, close, fsync      0.762524

Compare one o_sync write to two:
        one 16k o_sync write     8.494621
        two 8k o_sync writes     4.177680

Compare file sync methods with one 8k write:
        (o_dsync unavailable)
        open o_sync, write       1.836835
        (fdatasync unavailable)
        write, fsync,            1.780872

Compare file sync methods with 2 8k writes:
(The fastest should be used for wal_sync_method)
        (o_dsync unavailable)
        open o_sync, write       4.255614
        (fdatasync unavailable)
        write, fsync,            2.120843

-- 
  Bruce Momjian                        |  http://candle.pha.pa.us
  pgman@candle.pha.pa.us               |  (610) 359-1001
  +  If your life is a hard drive,     |  13 Roberts Road
  +  Christ can be your backup.        |  Newtown Square, Pennsylvania 19073



view thread (42+ messages)  latest in thread

Message-ID: <200403182009.i2IK9PJ24080@candle.pha.pa.us>
Permalink:  ../200403182009.i2IK9PJ24080@candle.pha.pa.us/
Also on:    postgresql.org/message-id/200403182009.i2IK9PJ24080@candle.pha.pa.us

 · 

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients using the --to and --cc options:
  reply via email

  To: pgsql-performance@postgresql.org
  Cc: pgman@candle.pha.pa.us, Q@ping.be, tgl@sss.pgh.pa.us, markir@paradise.net.nz, pgsql-hackers@postgresql.org
  Subject: Re: [HACKERS] fsync method checking
  In-Reply-To: <200403182009.i2IK9PJ24080@candle.pha.pa.us>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox