Re: How to best use 32 15k.7 300GB drives?

<br /> On 1/28/2011 11:44 AM, Scott Carey wrote: <blockquote cite="mid:C9683F12.1E3D5%25scott@richrelevance.com"
type="cite"><div><br/></div><div><br /></div><span id="OLK_SRC_BODY_SECTION"><div><div>On 1/27/11 4:11 PM, "Alan
Hodgson"<<a href="mailto:ahodgson@simkin.ca" moz-do-not-send="true">ahodgson@simkin.ca</a>>
wrote:</div></div><div><br/></div><blockquote id="MAC_OUTLOOK_ATTRIBUTION_BLOCKQUOTE" style="padding: 0pt 0pt 0pt 5px;
margin:0pt 0pt 0pt 5px;"><div><style type="text/css">
 
p, li { white-space: pre-wrap; }
</style><div style="font-family: 'Ubuntu'; font-size: 11pt;             font-weight: 400; font-style: normal;"><p
style="margin:0px; text-indent: 0px;">On January 27, 2011, Robert Schnabel <<a href="mailto:schnabelr@missouri.edu"
moz-do-not-send="true">schnabelr@missouri.edu</a>>wrote:<p style="margin: 0px; text-indent: 0px;">> So my
questionsare 1) am I'm crazy for doing this, 2) would you change<p style="margin: 0px; text-indent: 0px;">> anything
and3) is it acceptable to put the xlog & wal (and perhaps tmp<p style="margin: 0px; text-indent: 0px;">>
filespace)on a different controller than everything else? Please keep<p style="margin: 0px; text-indent: 0px;">> in
mindI'm a geneticist who happens to know a little bit about<p style="margin: 0px; text-indent: 0px;">>
bioinformaticsand not the reverse. :-)<p style="margin: 0px; text-indent: 0px;">> <p style="margin: 0px;
text-indent:0px;">Putting the WAL on a second controller does help, if you're write-heavy.<p style="margin: 0px;
text-indent:0px;">I tried separating indexes and data once on one server and didn't really notice that it helped much.
Managingthe space was problematic. I would suggest putting those together on a single RAID-10 of all the 300GB drives
(minusa spare). It will probably outperform separate arrays most of the time, and be much easier to
manage.</div></div></blockquote></span><div><br/></div><div>If you go this route, I suggest two equally sized RAID 10's
ondifferent controllers fir index + data, with software raid-0 on top of that.  RAID 10 will max out a controller after
6to 10 drives, usually.  Using the OS RAID 0 to aggregate the throughput of two controllers works great.</div><div><br
/></div><div>WALonly has to be a little bit faster than your network in most cases.  I've never seen it be a bottleneck
onlarge bulk loads if it is on its own controller with 120MB/sec write throughput.  I suppose a bulk load from COPY
mightstress it a bit more, but CPU ends up the bottleneck in postgres once you have I/O hardware this
capable.</div><div><br/></div></blockquote> Do you mean 14 drives in one box as RAID10's on one controller, then 14
drivesin the other box on a second controller, then software RAID0 each of the two RAID10's together essentially as a
single4 TB array?  Would you still recommend doing this with Windows?<br /> Bob<br /><br /><br /><br />