From mboxrd@z Thu Jan 1 00:00:00 1970 From: Richard Keech Subject: Re: [Consult-list] Re: dm-multipath has great throughput but we'd like more! Date: Thu, 18 May 2006 20:28:17 +1000 Message-ID: <446C4C41.2030705@redhat.com> References: <1147935929.27006.57.camel@baggage> <1147938254.27006.65.camel@baggage> <1147939464.3183.15.camel@nstrug.surrey.redhat.com> <1147945356.3183.39.camel@nstrug.surrey.redhat.com> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0382342279==" Return-path: In-Reply-To: <1147945356.3183.39.camel@nstrug.surrey.redhat.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: "Nicholas C. Strugnell" Cc: device-mapper development , consult-list@redhat.com List-Id: dm-devel.ids This is a multi-part message in MIME format. --===============0382342279== Content-Type: multipart/alternative; boundary="------------070802000101030301050001" This is a multi-part message in MIME format. --------------070802000101030301050001 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Nicholas C. Strugnell wrote: >On Thu, 2006-05-18 at 10:04 +0200, Nicholas C. Strugnell wrote: > > >>On Thu, 2006-05-18 at 08:44 +0100, Bob Gautier wrote: >> >> >>>On Thu, 2006-05-18 at 02:25 -0500, Jonathan E Brassow wrote: >>> >>> >>>>The system bus isn't a limiting factor is it? 64-bit PCI-X will get >>>>8.5 GB/s (plenty), but 32-bit PCI 33MHz got 133MB/s. >>>> >>>>Can your disks sustain that much bandwidth? 10 striped drives might get >>>>better than 200MB/s if done right, I suppose. >>>> >>>> >>>> > > > >>It might make sense to test raw writes to a device with dd and see if >>that gets comparable performance figures - I'll just try that myself >>actually. >> >> > >write throughput to EVA 8000 (8GB write cache), host DL380 with 2x2Gb/s >HBAs, 2GB RAM > >testing 4GB files: > >on filesystems: bonnie++ -d /mnt/tmp -s 4g -f -n 0 -u root > >ext3: 129MB/s sd=0.43 > > I presume this is with journal=ordered. Try with journel=writeback. I've seen benchmarks which suggest it can be close to the speed of ext2. -- Red Hat Home www.redhat.com.au *Richard Keech* Chief Technology Architect Red Hat Asia-Pacific email: rkeech@redhat.com mobile: +61 419 036 463 Level 50, 120 Collins Street Melbourne VIC 3000 phone: +61 3 9225 5258 fax: +61 3 9225 5050 support: 1800 733 428 --------------070802000101030301050001 Content-Type: multipart/related; boundary="------------000605030000080000010301" --------------000605030000080000010301 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Nicholas C. Strugnell wrote:

On Thu, 2006-05-18 at 10:04 +0200, Nicholas C. Strugnell wrote:

On Thu, 2006-05-18 at 08:44 +0100, Bob Gautier wrote:

On Thu, 2006-05-18 at 02:25 -0500, Jonathan E Brassow wrote:

The system bus isn't a limiting factor is it?  64-bit PCI-X will get 
8.5 GB/s (plenty), but 32-bit PCI 33MHz got 133MB/s.

Can your disks sustain that much bandwidth? 10 striped drives might get 
better than 200MB/s if done right, I suppose.

It might make sense to test raw writes to a device with dd and see if
that gets comparable performance figures - I'll just try that myself
actually.


write throughput to EVA 8000 (8GB write cache), host DL380 with 2x2Gb/s
HBAs, 2GB RAM

testing 4GB files:

on filesystems: bonnie++ -d /mnt/tmp -s 4g -f -n 0 -u root

ext3: 129MB/s sd=0.43

I presume this is with journal=ordered. Try with journel=writeback. I've seen benchmarks which suggest it can be close to the speed of ext2.

www.redhat.com.au
Richard Keech Chief Technology Architect Red Hat Asia-Pacific email: rkeech@redhat.com mobile: +61 419 036 463		Level 50, 120 Collins Street Melbourne VIC 3000 phone: +61 3 9225 5258 fax: +61 3 9225 5050 support: 1800 733 428

--------------000605030000080000010301 Content-Type: image/png; name="logo_rh_home.png" Content-Transfer-Encoding: base64 Content-ID: Content-Disposition: inline; filename="logo_rh_home.png" iVBORw0KGgoAAAANSUhEUgAAAGAAAAAfCAMAAAAvMjgeAAAAA3NCSVQICAjb4U/gAAAAz1BM VEUAAADc3NxqamqSAAAzMzOtra1EAACUn58YGBj///9JSUnjAADVAADFxcUUAADMAACDg4OF AADv7+/FAAByAQFUXV0PDw9CQkK8AABneHjV1dUABQW9vb1rAACtAAAnAAD4+PghISGVlZWm pqZVAADn5+czPT1mZma2trZQUFDMzMx3FRU7S0sFAAB1dXWeAAAqKipLYmKNjY1cAADdAAB5 eXlDUlK0AACLAAAbAABMAQEzAAB+AAAJCQlmAAArISGZmZk5OTlwZ2daWlqnAQGIirNOAAAA CXBIWXMAAArwAAAK8AFCrDSYAAAAJXRFWHRTb2Z0d2FyZQBNYWNyb21lZGlhIEZpcmV3b3Jr cyBNWCAyMDA0h3aszwAAA4lJREFUeJzVlWt/ojgUhw8CLnFQKXWBFeokRobLVpdBHS+VLi79 /p9pTwKorTPTzm99s+eFxATOk/zPJUBao0HEQBirYkpuZtA87dyBsxV5eFsAjXHz89oGgwEi nNK+IcC2xLb3h+1yuTxM1NGT+Nu5zSEEwI6Ew5m5MlerlbmZHYafxUR1E4IArKXuqndvmuZw OFQPpjoXM9EtVEJALP3vJqPZ6LBFAGK8rpwrbwKwM+ms602eus+joTTzTh6Bjd938F5GA8nr zJzdr7xaIgGYyChA9H5BrCP+01gBNWD3sN1uuwcM8vBkMwlw3o9zBoZO4vjHgABgizs3u/P9 3WTVMswRfDAKR3A46VTfWVEUCYhgsBFehSifn/YvDUB9fhZh6H0QkFwv2L1cCAxYwg+fhM/N s6jgXSPRxBtusN6K5m2qKJSksrpTzpVmNuABcVtA2M6GSi0sy+UJ0AZbSRh6d935/HARiB1A UwoBM/jacBSSZkZRGLJCeOY4TpbVEqXM950pbpkbBSt6IbEc8B1HlwAYnLx6L+rZ/2o/nwc1 IHaAYTdUFPxhBvioOW+7IwIWxTEPw47fx2kc9FmPUoUtwpCS5qWud7Hx1j6hRvEJgL2jg4pD TMMKWBDisFJElxGAOhuyqklrnQXEZhZtJBL295/eW//mXxiU8wmAEzJ2ICKUYublgQOZUJ1J iTIp+yKrFaUBK98A8Mj/PGzuXwE2otjsE+CI7soCDE3TmA/5FEA6uMwiruHrYV5pmXMG1LdY hGn72+Ne3XgtxFMxxODTE8CtAX5RFBjcKTaA/C2gRIDuZxa3jDOgKhzmVpqU4ncfnpYH9eVF HS13EuxeARKdo5UKXiFrsai9BoRiryS9kGi8LlNCppXUYqF9+fbH49evj9/815XcAFIHtEY0 HfMKkwbT6hJAc3mD9S9O0HhI6zJpmxtv7mb7NYD0AI56EE+nJHRxyLkGbwHiEwsEYE0uACfj Uz0ltFMDOrwFAGgCMNbqBaYQ3ZCjo0ivqG4pZWYrThLEloFBJonG9TC/AlhakhJMcrdaRFUY tQesEktm4njhZlnmWkjTE01zrX5S9UkpuwIJMCo8S5KktHTUqedq6fEKIHtKDhH2HmKT06Vp 2616Spo2etpjMbDxHVovyofS7+N3YhSmfWpfA8R+3Z9fIr9i3wOEnR/fHzcB0A9cxf8JcFP7 /wP+BbU7qQpvLpa/AAAAAElFTkSuQmCC --------------000605030000080000010301-- --------------070802000101030301050001-- --===============0382342279== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline --===============0382342279==--