I believe it was already mentioned this includes any caching done by the
client. Its not exactly the same as raw IO, so a lot of the "doesn't make
sense" parts are cache effects on the client-side. My point wasn't so much
that "look we get better then we can do in theory" but "we are doing on-par
with expensive dedicated boxes." (I believe that Equallogic was about 10k
USD, when it was purchased without drives, although I'm not up-to-date on
current pricing).
Andrew Hettinger
http://Prominic.NET || [EMAIL PROTECTED]
Tel: 866.339.3169 (toll free) -or- +1.217.356.2888 x.110 (int'l)
Fax: 866.372.3356 (toll free) -or- +1.217.356.3356 (int'l)
Mobile direct: 1.217.621.2540
CompTIA A+, CompTIA Network+, MCP
[EMAIL PROTECTED] wrote on 10/19/2007 02:14:33 PM:
> Thanks for posting the results.
>
> The thruput (MBps) shown on the graphs doesn't make sense
> considering you are using 4x1G ports for iSCSI traffic. In most of
> the graphs, I see thruput which far exceeds the max bandwidth you
> can achieve collectively on all the links (~400 MBps single
> direction, ~800 MBps bi-directional). Am I missing something?
>
> Again, thanks for taking time to post the graphs.
>
>
> This message posted from opensolaris.org
> _______________________________________________
> storage-discuss mailing list
> [email protected]
> http://mail.opensolaris.org/mailman/listinfo/storage-discuss
_______________________________________________
storage-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/storage-discuss
