<div dir="ltr"><br><br><div class="gmail_quote">On Sun, May 8, 2011 at 1:21 PM, guy keren <span dir="ltr"><<a href="mailto:choo@actcom.co.il">choo@actcom.co.il</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div><div></div><div class="h5">On Sun, 2011-05-08 at 12:26 +0300, shimi wrote:<br>
> On Sun, May 8, 2011 at 12:01 PM, guy keren <<a href="mailto:choo@actcom.co.il">choo@actcom.co.il</a>> wrote:<br>
><br>
> do you have the ability to extract wear leveling information<br>
> from your<br>
> SSD? it would be interesting to know whether the drive is<br>
> being used in<br>
> a manner that will indeed comply with the life-time expentency<br>
> it is<br>
> sold with (5 years?), or better, or worse.<br>
><br>
><br>
> I don't know, how do you extract such information?<br>
><br>
> The rated MTBF of my specific drive is 2 million hours. If I still<br>
> know my math, that's some 228 years....<br>
><br>
> -- Shimi<br>
<br>
</div></div>wear leveling has nothing to do with MTBF. once you write ~100,000 times<br>
to a single cell in the SSD - it's dead. due to the wear leveling<br>
methods of the SSD - this will happen once you write ~100,000 times to<br>
all cell groups on the SSD - assuming the wear-leveling algorithm of the<br>
SSD is implemented without glitches.<br>
<br></blockquote><div><br>I know... I was referring more to the "life time expectancy it is sold with" when I quoted that number. Unless block write fails do not consist of "a failure", and if not, I don't know what is, in an SSD :).<br>
<br>Obviously on a DB data disk it is going to happen much faster than on my desktop. <br><br>b.t.w. IIRC when a cell dies, it does so "gracefully"; I.e. no data is lost, and there are spare blocks for that case... and even when they're all full, you just get to the point that you still have your data read-only. I vaguely remember I read that somewhere... and if it's indeed like that, this is still way better than a regular hard drive - those tend to usually take all your data with them, and are much more sensitive to many things (shock - physical/electric, heat, etc...)<br>
<br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
note that these writes don't come only from the host - many of them are<br>
generated internally by the SSD, due to its wear-leveling algorithms. an<br>
SSD could perform several writes for each host-initiated write operation<br>
on average. intel claims their X25-E has very impressive algorithms in<br>
this regard. it'll be interesting to check these claims with the actual<br>
state of your SSD.<br>
<br></blockquote><div>I know that too :) <br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<br>
fetching wear-leveling info is SSD-dependent. you'll need to check if<br>
intel provides a tool to do that on linux, for your SSD.<br>
<font color="#888888"><br></font></blockquote><div>Google didn't help me a lot in that regard (I understand there's a Win$ SW maybe to do that; "Unfortunately", I don't have code from Redmond anywhere inside my chassis.)<br>
<br>So if you find something yourself, I'm willing to test...<br><br>-- Shimi <br></div></div><br></div>