<br><div class="gmail_quote">On Thu, Dec 3, 2009 at 6:08 AM, Christopher G. Stach II <span dir="ltr"><<a href="mailto:cgs@ldsys.net">cgs@ldsys.net</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="im">----- "Grant McWilliams" <<a href="mailto:grantmasterflash@gmail.com">grantmasterflash@gmail.com</a>> wrote:<br>
<br>
> On Wed, Dec 2, 2009 at 9:48 PM, Christopher G. Stach II <<br>
> <a href="mailto:cgs@ldsys.net">cgs@ldsys.net</a> > wrote:<br>
><br>
> ----- "Grant McWilliams" < <a href="mailto:grantmasterflash@gmail.com">grantmasterflash@gmail.com</a> > wrote:<br>
><br>
</div><div class="im">> > a RAID 10 (or 0+1) will never reach the write... performance of<br>
> > a RAID-5.<br>
><br>
> (*cough* If you keep the number of disks constant or the amount of<br>
> usable space? "Things working" tends to trump CapEx, despite the<br>
> associated pain, so I will go with "amount of usable space.")<br>
><br>
> No.<br>
><br>
> --<br>
> Christopher G. Stach II<br>
><br>
> Nice quality reading. I like theories as much as the next person but<br>
> I'm wondering if the Toms Hardware guys are on crack or you disapprove<br>
> of their testing methods.<br>
><br>
> <a href="http://www.tomshardware.com/reviews/external-raid-storage,1922-9.html" target="_blank">http://www.tomshardware.com/reviews/external-raid-storage,1922-9.html</a><br>
<br>
</div>They used a constant number of disks to compare two different hardware implementations, not to compare RAID 5 vs. RAID 10. They got the expected ~50% improvement from the extra stripe segment in RAID 5 with a serial access pattern. Unfortunately, that's neither real world use nor the typical way you would fulfill requirements. If you read ahead to the following pages, you have a nice comparison of random access patterns and RAID 10 coming out ahead (with one less stripe segment and a lot less risk):<br>
<br>
<a href="http://www.tomshardware.com/reviews/external-raid-storage,1922-11.html" target="_blank">http://www.tomshardware.com/reviews/external-raid-storage,1922-11.html</a><br>
<a href="http://www.tomshardware.com/reviews/external-raid-storage,1922-12.html" target="_blank">http://www.tomshardware.com/reviews/external-raid-storage,1922-12.html</a><br>
<div><div></div><div class="h5"><br>
--<br>
Christopher G. Stach II<br>
<br></div></div></blockquote></div><br>So if I have 6 drives on my RAID controller which do I choose? If I have to add two more drives to the RAID 10 to equal the performance of a RAID 5 I could just make it a RAID 5 and be faster still. RAID 5 is faster than RAID 10 for reads and writes.<br>
<br>However, you are right on the IOs. The RAID 10 pretty much trounced RAID 5 on IOs in all tests.<br>What wasn't in the test (but is in others that they've done) is RAID 6. I'm not sure I'm sold on it because it gives us about the same level of redundancy as RAID 10 but with less performance than RAID 5. Theoretically it would get soundly trounced by RAID 10 on IOs and maybe be slower on r/w transfer as well. <br>
<br clear="all">Grant McWilliams<br><br>Some people, when confronted with a problem, think "I know, I'll use Windows." <br>Now they have two problems.<br><br><br>