Received: from maia.hub.org (unknown [200.46.208.211])
	by mail.postgresql.org (Postfix) with ESMTP id C9926637ABA
	for <pgsql-performance-postgresql.org@mail.postgresql.org>;
	Tue,  2 Feb 2010 14:49:28 -0400 (AST)
Received: from mail.postgresql.org ([200.46.204.86])
	by maia.hub.org (mx1.hub.org [200.46.208.211]) (amavisd-maia,
	port 10024) with ESMTP id 59954-01-9
	for <pgsql-performance-postgresql.org@mail.postgresql.org>;
	Tue,  2 Feb 2010 18:49:06 +0000 (UTC)
X-Greylist: domain auto-whitelisted by SQLgrey-1.7.6
Received: from mail-bw0-f218.google.com (mail-bw0-f218.google.com
	[209.85.218.218])
	by mail.postgresql.org (Postfix) with ESMTP id 6F96865A1EC
	for <pgsql-performance@postgresql.org>;
	Tue,  2 Feb 2010 14:06:28 -0400 (AST)
Received: by bwz10 with SMTP id 10so352238bwz.35
	for <multiple recipients>; Tue, 02 Feb 2010 10:06:26 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma;
	h=domainkey-signature:mime-version:received:in-reply-to:references
	:date:message-id:subject:from:to:cc:content-type
	:content-transfer-encoding;
	bh=SvyTXALw+i9vILXn4yvxLN4rAUibKo1A4HeN0/d1yhY=;
	b=i4MMpBfdR0QOK/k9Ck72nMDaCb60KFYoVhGnz6DrnBiBr+Smr2T0aI700TuHnPCEcm
	tz6SJvdtVjiT2ijzAniswDoYNKvGljIrBefVpnxp4mS6bPe2R8evI8WATK8XCOsuziNh
	q2afqyNsaJNd1vTgcZK2p7iYRmv5OvfRhdiSo=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma;
	h=mime-version:in-reply-to:references:date:message-id:subject:from:to
	:cc:content-type:content-transfer-encoding;
	b=xi7+oAk4YWquDEgEmJ4luS/1tghTFI+Af4TBY14CQGuH8JZjUJkfAq/PSgHKtcTkOg
	5/3qCGjvIqLjiOjdPOnY/FfpLV1vNinmxn/JxkCOjKH43G5cVaEwCCsviCl1H1ZNYw+d
	oW4OBWuKoysfHLj7VgLuj7oLFWhI1G4WXSIck=
MIME-Version: 1.0
Received: by 10.239.189.137 with SMTP id t9mr338005hbh.176.1265132172464;
 Tue,
	02 Feb 2010 09:36:12 -0800 (PST)
In-Reply-To: <407d949e1001291056q22915b1cqbce5fbc918a15d69@mail.gmail.com>
References: <4427a97a0912101235x3ade510blcc00d5ce9883c6b6@mail.gmail.com>
	<200912282354.51892.andres@anarazel.de>
	<200912282359.43979.andres@anarazel.de>
	<200912291930.50812.andres@anarazel.de>
	<407d949e1001180835m79ffe3e4w53e20ce2e1a58f2d@mail.gmail.com>
	<407d949e1001190652i43f4f276x6a485f375647219a@mail.gmail.com>
	<9319.1263914746@sss.pgh.pa.us>
	<407d949e1001291056q22915b1cqbce5fbc918a15d69@mail.gmail.com>
Date: Tue, 2 Feb 2010 12:36:12 -0500
Message-ID: <603c8f071002020936k5723e30kd4eac594092aba3b@mail.gmail.com>
Subject: Re: [HACKERS] Re: Faster CREATE DATABASE by delaying fsync (was 8.4.1
	ubuntu karmic slow createdb)
From: Robert Haas <robertmhaas@gmail.com>
To: Greg Stark <gsstark@mit.edu>
Cc: Tom Lane <tgl@sss.pgh.pa.us>, Andres Freund <andres@anarazel.de>,
	pgsql-hackers@postgresql.org, pgsql-performance@postgresql.org,
	Michael Clemmons <glassresistor@gmail.com>,
	Hannu Krosing <hannu@2ndquadrant.com>,
	Scott Marlowe <scott.marlowe@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Virus-Scanned: Maia Mailguard 1.0.1
X-Spam-Status: No, hits=-2.472 tagged_above=-10 required=5 tests=AWL=0.127,
	BAYES_00=-2.599
X-Spam-Level: 
X-Archive-Number: 201002/16
X-Sequence-Number: 37437

On Fri, Jan 29, 2010 at 1:56 PM, Greg Stark <gsstark@mit.edu> wrote:
> On Tue, Jan 19, 2010 at 3:25 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
>> That function *seriously* needs documentation, in particular the fact
>> that it's a no-op on machines without the right kernel call. =A0The name
>> you've chosen is very bad for those semantics. =A0I'd pick something
>> else myself. =A0Maybe "pg_start_data_flush" or something like that?
>>
>
> I would like to make one token argument in favour of the name I
> picked. If it doesn't convince I'll change it since we can always
> revisit the API down the road.
>
> I envision having two function calls, pg_fsync_start() and
> pg_fsync_finish(). The latter will wait until the data synced in the
> first call is actually synced. The fall-back if there's no
> implementation of this would be for fsync_start() to be a noop (or
> something unreliable like posix_fadvise) and fsync_finish() to just be
> a regular fsync.
>
> I think we can accomplish this with sync_file_range() but I need to
> read up on how it actually works a bit more. In this case it doesn't
> make a difference since when we call fsync_finish() it's going to be
> for the entire file and nothing else will have been writing to these
> files. But for wal writing and checkpointing it might have very
> different performance characteristics.
>
> The big objection to this is that then we don't really have an api for
> FADV_DONT_NEED which is more about cache policy than about syncing to
> disk. So for example a sequential scan might want to indicate that it
> isn't planning on reading the buffers it's churning through but
> doesn't want to force them to be written sooner than otherwise and is
> never going to call fsync_finish().

I took a look at this patch today and I agree with Tom that
pg_fsync_start() is a very confusing name.  I don't know what the
right name is, but this doesn't fsync so I don't think it shuld have
fsync in the name.  Maybe something like pg_advise_abandon() or
pg_abandon_cache().  The current name is really wishful thinking:
you're hoping that it will make the kernel start the fsync, but it
might not.  I think pg_start_data_flush() is similarly optimistic.

...Robert