<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 TRANSITIONAL//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; CHARSET=UTF-8">
<META NAME="GENERATOR" CONTENT="GtkHTML/3.12.0">
</HEAD>
<BODY>
Thanks Gordan,<BR>
I re-read my email after your response, and realized high availability is another big priority (hence our using heartbeat). My thought was that an initial drive failure in the RAID array should be handled within the current primary system, with DRBD/heartbeat fail-over as the next tier of failure recovery. Which brings up another question; how does DRBD handle RAID set failures? Obviously, a mirrored drive's failure would be transparent, but what about in the case of a striped set? Is there a way to determine that a striped set has failed and is in rebuild, and trigger DRBD to fail over to the secondary system where no rebuild is taking place? Maybe a Linux-HA question?<BR>
<BR>
Doug<BR>
On Tue, 2008-03-04 at 13:44 +0000, drbd@bobich.net wrote:
<BLOCKQUOTE TYPE=CITE>
<PRE>
<FONT COLOR="#000000">On Tue, 4 Mar 2008, Doug Knight wrote:</FONT>
<FONT COLOR="#000000">> Performance is a first priority, followed by</FONT>
<FONT COLOR="#000000">> disk space, so I've been looking at RAID 10 and RAID 50 as possible</FONT>
<FONT COLOR="#000000">> setups. We're planning on using 15K drives, which limits each physical</FONT>
<FONT COLOR="#000000">> drive to 146GB, which is why I need the striping. The controllers will</FONT>
<FONT COLOR="#000000">> have battery backed up cache, which from the postgres groups I've been</FONT>
<FONT COLOR="#000000">> told will give us a significant performance boost.</FONT>
<FONT COLOR="#000000">[...]</FONT>
<FONT COLOR="#000000">> The system we're looking at is the Dell PowerEdge 6800, most</FONT>
<FONT COLOR="#000000">> likely with a non-DRBD mirrored system drive, plus a DRBD replicated</FONT>
<FONT COLOR="#000000">> RAID 10 or 50 array supporting around 500GB.</FONT>
<FONT COLOR="#000000">If performance is your 1st priority, then do you really need more than </FONT>
<FONT COLOR="#000000">RAID 01? Have each machine with a RAID0 stripe (apart from possibly the </FONT>
<FONT COLOR="#000000">system/root partition), and then mirror it using DRBD (RAID1). RAID 51 </FONT>
<FONT COLOR="#000000">seems a bit OTT if you want performance first, and you'll still get </FONT>
<FONT COLOR="#000000">mirroring from DRBD.</FONT>
<FONT COLOR="#000000">Just make sure that your bus and controller can keep up with </FONT>
<FONT COLOR="#000000">the throughput of so many drives. The PCI(X/e/...) bus will only handle so </FONT>
<FONT COLOR="#000000">much bandwidth, and you are unlikely to see more than 80% of it even under </FONT>
<FONT COLOR="#000000">optimal conditions. If your drives between them can sustainedly (or </FONT>
<FONT COLOR="#000000">even just with buffer->controller bursts - new drives have big </FONT>
<FONT COLOR="#000000">caches!) churn out more than that, then you might as well get </FONT>
<FONT COLOR="#000000">slower/bigger/cheaper (pick any two ;-) drives.</FONT>
<FONT COLOR="#000000">Gordan</FONT>
<FONT COLOR="#000000">_______________________________________________</FONT>
<FONT COLOR="#000000">drbd-user mailing list</FONT>
<FONT COLOR="#000000"><A HREF="mailto:drbd-user@lists.linbit.com">drbd-user@lists.linbit.com</A></FONT>
<FONT COLOR="#000000"><A HREF="http://lists.linbit.com/mailman/listinfo/drbd-user">http://lists.linbit.com/mailman/listinfo/drbd-user</A></FONT>
</PRE>
</BLOCKQUOTE>
</BODY>
</HTML>