Re: kernel work week of 3-Feb-2010 HEADS UP (interleaved swap te
--00032555b1b25fba13047f1452a1
Content-Type: text/plain; charset=ISO-8859-1
2010/2/8 Matthew Dillon <dillon@apollo.backplane.com>
> The latest commit adds write clustering and some additional features
> to the swapcache, plus a manual page: swapcache(8).
>
> The write clustering significantly reduces the IOPS rate for writes to
> the swapcache and appears to improve the SSDs performance (presumably
> it has an earlier time write-combining and erasing).
>
> --
>
> Just for the hell of it I set up two 40G Intel SSDs as 2x interleaved
>
Are you using a RAID-0 (striping) here? Or is there a way to tell dumpon to
use
more than one device for swap caching?
I'd expect random reads from files to profit much more than linear reads
when
compared against hard disks. Do you share this assumption? Do you have any
numbers on this kind of benchmark? Can you think of any other real-world
benchmarks that would make sense to execute on such a machine?
I could do some testing on a big machine, equipped with 2x120 GB SSD, once
I
get the network controller to work (82576 Intel PRO/1000 not working on
DragonFly).
Regards,
Michael
--00032555b1b25fba13047f1452a1
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
<br><br><div class=3D"gmail_quote">2010/2/8 Matthew Dillon <span dir=3D"ltr=
"><<a href=3D"mailto:dillon@apollo.backplane.com">dillon@apollo.backplan=
e.com</a>></span><br><blockquote class=3D"gmail_quote" style=3D"margin:0=
0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
=A0 =A0The latest commit adds write clustering and some additional feature=
s<br>
=A0 =A0to the swapcache, plus a manual page: swapcache(8).<br>
<br>
=A0 =A0The write clustering significantly reduces the IOPS rate for writes=
to<br>
=A0 =A0the swapcache and appears to improve the SSDs performance (presumab=
ly<br>
=A0 =A0it has an earlier time write-combining and erasing).<br>
<br>
=A0 =A0--<br>
<br>
=A0 =A0Just for the hell of it I set up two 40G Intel SSDs as 2x interleav=
ed<br></blockquote><div><br></div><div>Are you using a RAID-0 (striping) he=
re? Or is there a way to tell dumpon to use</div><div>more than one device =
for swap caching?</div>
<div><br></div><div>I'd expect random reads from files to profit much m=
ore than linear reads when</div><div>compared against hard disks. Do you sh=
are this assumption?=A0Do you have any</div><div>numbers on this kind of be=
nchmark? Can you think of any other real-world benchmarks that would make s=
ense to=A0execute on such a machine?=A0</div>
<div>I could do some testing on a big machine, equipped=A0with 2x120 GB SSD=
, once I=A0</div><div>get the network controller to work (82576 Intel PRO/1=
000 not working=A0on DragonFly).</div><div><br></div><div>Regards,</div><di=
v>
<br></div><div>=A0=A0Michael</div></div>
--00032555b1b25fba13047f1452a1--
討論串 (同標題文章)
完整討論串 (本文為第 1 之 4 篇)：