X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id CCEA8D9142 for ; Tue, 20 Sep 2005 12:36:11 -0300 (ADT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 77218-09 for ; Tue, 20 Sep 2005 15:36:02 +0000 (GMT) Received: from zproxy.gmail.com (zproxy.gmail.com [64.233.162.198]) by svr1.postgresql.org (Postfix) with ESMTP id D1FAED8FD4 for ; Tue, 20 Sep 2005 12:35:59 -0300 (ADT) Received: by zproxy.gmail.com with SMTP id 40so283195nzk for ; Tue, 20 Sep 2005 08:35:58 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:references; b=SDze8RgzW1MLCshJg/NyOt2XtktWJM8+5diaqiZGs4cIpKtNG4Q+dWiCkbqrILytnX0/BThTHTqLVP41Qt1iFk9ssag9voek5yHzRg31jq/yQyhoAxX0dGtQc7r+7nhcMDNJA5CBkHSBea9Qdd7xz4y19NCBaZs84KBJn2+viL8= Received: by 10.54.71.20 with SMTP id t20mr1836815wra; Tue, 20 Sep 2005 08:35:58 -0700 (PDT) Received: by 10.54.83.10 with HTTP; Tue, 20 Sep 2005 08:35:58 -0700 (PDT) Message-ID: <33c6269f05092008357973a651@mail.gmail.com> Date: Tue, 20 Sep 2005 11:35:58 -0400 From: Alex Turner Reply-To: armtuk@gmail.com To: Kelly Burkhart Subject: Re: Need for speed 2 Cc: Ron , pgsql-performance@postgresql.org In-Reply-To: <1124996422.6969.47.camel@krb06.tradebot.com> Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_Part_3447_32575630.1127230558130" References: <6.2.3.4.0.20050817140116.05d317b0@pop.earthlink.net> <430D6EED.10603@relevanttraffic.se> <6.2.3.4.0.20050825094630.05e6b160@pop.earthlink.net> <1124996422.6969.47.camel@krb06.tradebot.com> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.146 required=5 tests=[AWL=0.035, HTML_40_50=0.086, HTML_MESSAGE=0.001, RCVD_BY_IP=0.024] X-Spam-Level: X-Archive-Number: 200509/220 X-Sequence-Number: 14528 ------=_Part_3447_32575630.1127230558130 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I have found that while the OS may flush to the controller fast with=20 fsync=3Dtrue, the controller does as it pleases (it has BBU, so I'm not too= =20 worried), so you get great performance because your controller is determine= =20 read/write sequence outside of what is being demanded by an fsync. Alex Turner NetEconomist On 8/25/05, Kelly Burkhart wrote: >=20 > On Thu, 2005-08-25 at 11:16 -0400, Ron wrote: > > ># - Settings - > > > > > >fsync =3D false # turns forced synchronization on or off > > >#wal_sync_method =3D fsync # the default varies across platforms: > > > # fsync, fdatasync, open_sync, or > > > > I hope you have a battery backed write buffer! >=20 > Battery backed write buffer will do nothing here, because the OS is > taking it's sweet time flushing to the controller's battery backed write > buffer! >=20 > Isn't the reason for batter backed controller cache to make fsync()s > fast? >=20 > -K >=20 > ---------------------------(end of broadcast)--------------------------- > TIP 9: In versions below 8.0, the planner will ignore your desire to > choose an index scan if your joining column's datatypes do not > match > ------=_Part_3447_32575630.1127230558130 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I have found that while the OS may flush to the controller fast with fsync=3Dtrue, the controller does as it pleases (it has BBU, so I'm not too worried), so you get great performance because your controller is determine read/write sequence outside of what is being demanded by an fsync.

Alex Turner
NetEconomist

On 8/25/05, Kelly Burkhart <kelly@tradebotsystems.com> wrote:
On Thu, 2005-08-25 at 11:16 -0400, Ron wrote:
> ># - Settings -> >
> >fsync =3D false           &nbs= p;       # turns forced synchronization on or off
> >#wal_sync_method =3D f= sync        # the default varies ac= ross platforms:
> >            = ;            &n= bsp;        # fsync, fdatasync, open_sync, or
>
> I hope you have a battery= backed write buffer!

Battery backed write buffer will do nothing he= re, because the OS is
taking it's sweet time flushing to the controller'= s battery backed write
buffer!

Isn't the reason for batter backed controller cache to m= ake fsync()s
fast?

-K

---------------------------(end of b= roadcast)---------------------------
TIP 9: In versions below 8.0, the p= lanner will ignore your desire to
       choose an index scan if your joini= ng column's datatypes do not
       match<= br>

------=_Part_3447_32575630.1127230558130--