Received: from malur.postgresql.org ([217.196.149.56]) by arkaria.postgresql.org with esmtp (Exim 4.84_2) (envelope-from ) id 1dWfme-0006Es-Si for pgsql-performance@arkaria.postgresql.org; Sun, 16 Jul 2017 09:24:13 +0000 Received: from localhost ([127.0.0.1] helo=postgresql.org) by malur.postgresql.org with smtp (Exim 4.84_2) (envelope-from ) id 1dWfme-0005jS-FM for pgsql-performance@arkaria.postgresql.org; Sun, 16 Jul 2017 09:24:12 +0000 Received: from makus.postgresql.org ([2001:4800:1501:1::229]) by malur.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.84_2) (envelope-from ) id 1dWfku-0001BY-D3 for pgsql-performance@postgresql.org; Sun, 16 Jul 2017 09:22:24 +0000 Received: from mail-qk0-x235.google.com ([2607:f8b0:400d:c09::235]) by makus.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.84_2) (envelope-from ) id 1dWfkr-0003pu-NA for pgsql-performance@postgresql.org; Sun, 16 Jul 2017 09:22:23 +0000 Received: by mail-qk0-x235.google.com with SMTP id p73so39177075qka.2 for ; Sun, 16 Jul 2017 02:22:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc; bh=qXXDuICWgOL0WNO0NOL8IDtkaKWLtiLBMU7KfI+odA0=; b=XieL5TBDWoCpckr3Te+BFjFMJ+OXvd8OzLe+fmTm30OcPk7xbEHGpOXdaYSQaSMGPB 4lRK06oCW8kc5cOYePMTGvymXgSnu05CENgTifSU/1h07duBlzYmMQwbo59cVMcHjBqR PsjCTJaJBOCU/V9AQMwKt7BMbfV5uSFTw63eRdO465+DveOFztBvoMZVRN4mFRod9IhP mLmt/XSJGG37wbprwhatPznvImnOX7DlPqzK3xNUE+xP5mXnEq+7EYKkst2uzLM2I4tz Jrf+t3sKVhBP0qusv1No+cEeGcMuyZQPKmy/lJh+6JevxvvJj6NNtSi3KABKoZ0edlGJ btaw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:cc; bh=qXXDuICWgOL0WNO0NOL8IDtkaKWLtiLBMU7KfI+odA0=; b=m6HjdK435tfPb/r/ko19wjcA8BV4zySpzcl2yZ2yZmFYwSPCvFyECCix1tY/nij32e N/YGHs42nzRSe5h5PU2/xM5J6zKTU33uaUVxCa7idQ9jkIgmdQNXyBrcBRK7+XQIDbgW C4MD0LZIjdI9keN/W5/BKNCNkPwrgFcD9WVod7K/+FNZeSRLjpmPVfNPHyXE1KM6LKU3 CZM/MFWEcY6Qvb1RTe7FNGcIB9lbKI18lrFVIxIEiEsCl/HjJ9PaY6O0HfudjYUnbY1m YpY+mC4AGm/EOhHKz28kM8BV+0Rw6xm09opAJWxgNtomTp6ZGVMEe37HRgahyKptlcM3 cXwA== X-Gm-Message-State: AIVw110oXXiKU5XnD/ggnZuCGErsDtKNF98cmXw5qHOGD9ygzow7xRwg OAsNpb3fJjhjp/n9uBoOn/pNJpe1BA== X-Received: by 10.55.108.68 with SMTP id h65mr20391380qkc.141.1500196940940; Sun, 16 Jul 2017 02:22:20 -0700 (PDT) MIME-Version: 1.0 Received: by 10.12.157.11 with HTTP; Sun, 16 Jul 2017 02:22:00 -0700 (PDT) In-Reply-To: References: From: Charles Nadeau Date: Sun, 16 Jul 2017 11:22:00 +0200 Message-ID: Subject: Re: Very poor read performance, query independent To: Scott Marlowe Cc: Mark Kirkwood , "pgsql-performa." Content-Type: multipart/alternative; boundary="001a114feeb6c20a2605546bd152" List-Archive: List-Help: List-ID: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: X-Mailing-List: pgsql-performance Precedence: bulk Sender: pgsql-performance-owner@postgresql.org --001a114feeb6c20a2605546bd152 Content-Type: text/plain; charset="UTF-8" Scott, The temp tablespace is on a disk of his own. Thanks! Charles On Sat, Jul 15, 2017 at 7:58 PM, Scott Marlowe wrote: > On Sat, Jul 15, 2017 at 11:53 AM, Charles Nadeau > wrote: > > Mark, > > > > I increased the read ahead to 16384 and it doesn't improve performance. > My > > RAID 0 use a stripe size of 256k, the maximum size supported by the > > controller. > > Are your queries still spilling to disk for sorts? If this is the > case, and they're just too big to fit in memory, then you need to move > your temp space, where sorts happen, onto another disk array that > isn't your poor overworked raid-10 array. Contention between sorts and > reads can kill performance quick, esp on spinning rust. > -- Charles Nadeau Ph.D. http://charlesnadeau.blogspot.com/ --001a114feeb6c20a2605546bd152 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Scott,

The temp tablespace is on a disk= of his own.
Thanks!

Charles
=

On Sat, Jul 15, 2= 017 at 7:58 PM, Scott Marlowe <scott.marlowe@gmail.com> wrote:
On Sat, Jul 15,= 2017 at 11:53 AM, Charles Nadeau
<charles.nadeau@gmail.com> wrote:
> Mark,
>
> I increased the read ahead to 16384 and it doesn't improve perform= ance. My
> RAID 0 use a stripe size of 256k, the maximum size supported by the > controller.

Are your queries still spilling to disk for sorts? If this is the case, and they're just too big to fit in memory, then you need to move<= br> your temp space, where sorts happen, onto another disk array that
isn't your poor overworked raid-10 array. Contention between sorts and<= br> reads can kill performance quick, esp on spinning rust.



--
Charles Nadeau Ph.D= .
http:= //charlesnadeau.blogspot.com/
--001a114feeb6c20a2605546bd152--