<div>I was musing about the (to me, novel) idea of multi RAID on one box (probably the head node of a cluster or subcluster), by analogy with CPU cache levels; RAID0 with a few 10K rpm drives for speed, RAID6 with many 7200 drives for size and reliability; then I'd be able to go fast until a failure, then rollback to a checkpoint served by the RAID6. This is just a gedankenexperiment.
<div>I don't have any particular configuration in mind, I don't have a cluster and it will probably be a small number of superannuated Alpha boxes if I do it at all this summer.</div>
<div><span class="gmail_quote">On 8/27/07, <b class="gmail_sendername">Jeffrey B. Layton</b> <<a href="mailto:email@example.com">firstname.lastname@example.org</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Peter St. John wrote:<br>> How about using RAID 5 for a working filesystem and RAID 6 for<br>> checkpointing? Or is that effectively what 6+1 does?
<br>> I'm imagining RAID 0 for scratch and virtual memory, so you want three<br>> disk systems:-)<br>> Peter<br><br>Choosing good RAID solutions depends upon what you want to<br>do with the particular file system. For example, what do you
<br>mean by "working file system", "check pointing" and so on?<br>You also have to take into account the RAID level, the size of<br>the disks, and the probability of a read error. This will help<br>you determine what RAID level to chose.
<br><br>I know this is vague, but we could continue this off-line if you<br>like (I don't know if anyone is interested in the details).<br><br>Jeff<br><br></blockquote></div><br>