<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Hi John,<br>
<br>
<div class="moz-cite-prefix">On 1/19/2016 5:28 PM, John van Ommen
wrote:<br>
</div>
<blockquote
cite="mid:CAL0qdMMd9pSMi6zFnUst3MHSizns0yJ9Ws0tFnU8tLYk2cND_A@mail.gmail.com"
type="cite">
<div dir="ltr">I have a client who isn't happy with the
performance of their storage.
<div>The client is currently running a mix of SAS HDDs and SATA
SSDs.</div>
<div><br>
</div>
<div>They wanted to remove the SAS HDDs and replace them with
SSDs, so the entire array would be SSDs.</div>
<div><br>
</div>
<div>I was running benchmarks on the current hardware and I
found that the performance of the HDD array was close to the
performance of the SSD array.</div>
<div><br>
</div>
<div>To me, this indicates that we're reaching the limits of the
controller that it's attached to. (An LSI RAID controller
that's built into the system board.)</div>
<div><br>
</div>
<div>I was about to recommend that they add a controller, when I
realized that we may be reaching the limits of the PCI-E bus
itself.</div>
<div><br>
</div>
<div>Before I go and make a bad recommendation, I have a few
questions:<br>
<br>
1) Am I correct in assuming that the RAID controller, though
physically on the system board, is still running through the
PCI-E bus, just as if it was plugged into a slot?<br>
</div>
</div>
</blockquote>
Yes. In pre Intel SandyBridge architecture like Westmere processors,
there used to be a bridge chipset that extends the PCIe lanes to
addone cards, while in Sandybridge and onwards PCIe lanes comes
straight from the processor.<br>
<br>
<blockquote
cite="mid:CAL0qdMMd9pSMi6zFnUst3MHSizns0yJ9Ws0tFnU8tLYk2cND_A@mail.gmail.com"
type="cite">
<div dir="ltr">
<div>2) Am I correct in assuming that the limit for the PCI-E
bus (version 2) is 500Mb/s? (<a moz-do-not-send="true"
href="https://en.wikipedia.org/wiki/PCI_Express">https://en.wikipedia.org/wiki/PCI_Express</a>)<br>
</div>
</div>
</blockquote>
I think you meant to say 500MB/sec per lane. Now what does the
motherboard say about the RAID controller, is it x4 or x8 ? So you
can multiply lane speed to x4 or x8. If x8 then using a PCIe Gen 2.0
bus, it should provide 8 x 500 = 4000MB or 32Gbps. Whether the RAID
card can provide this much traffic or not that's another thing.<br>
<br>
<blockquote
cite="mid:CAL0qdMMd9pSMi6zFnUst3MHSizns0yJ9Ws0tFnU8tLYk2cND_A@mail.gmail.com"
type="cite">
<div dir="ltr">
<div>And if points one and two are correct, is my hypothesis
that adding more SSDs won't improve things true?<br>
<br>
Right now my benchmarks are showing that sequential reads are
hitting about 600Mb/s. (I haven't confirmed if their server is
PCI-E 2.0 or 3.0)<br>
</div>
</div>
</blockquote>
A single Samsung SSD 850PRO claims reads to be close to 550MB/sec.
There could be multiple factors affecting performance involving RAID
card, PCIe bus, RAID settings, cpu affinity etc.<br>
<br>
-Azher<br>
<br>
<blockquote
cite="mid:CAL0qdMMd9pSMi6zFnUst3MHSizns0yJ9Ws0tFnU8tLYk2cND_A@mail.gmail.com"
type="cite">
<div dir="ltr">
<div><br>
John</div>
</div>
<br>
-- <br>
This message has been scanned for viruses and
<br>
dangerous content by
<a moz-do-not-send="true" href="http://www.mailscanner.info/"><b>MailScanner</b></a>,
and is
<br>
believed to be clean.
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
Mailing list: <a class="moz-txt-link-freetext" href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack</a>
Post to : <a class="moz-txt-link-abbreviated" href="mailto:openstack@lists.openstack.org">openstack@lists.openstack.org</a>
Unsubscribe : <a class="moz-txt-link-freetext" href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack</a>
</pre>
</blockquote>
<br>
</body>
</html>