Chris Csanady wrote:
On 3/29/07, Lida Horn <[EMAIL PROTECTED]> wrote:
Please give us feedback with respect to how the si3124 driver works
for you.
I have a pair of si3132 based cards on a Tyan K8E motherboard, and
unfortunately, I am seeing what look like command timeouts with the
b59 si3124 driver. With an iostat running in the background, I get
something like this for about a minute each time:
extended device statistics
r/s w/s kr/s kw/s wait actv wsvc_t asvc_t %w %b device
0.0 0.0 0.0 0.0 3.0 1.0 0.0 0.0 100 100 c9t1d0
It happens almost immediately when copying a sizable file between SMB
shares of the same pool, though also more rarely when doing local I/O.
I have never encountered it with read only I/O patterns.
Also, the performance seems to vary widely. In general though, it
feels a bit more sluggish than the nForce4 SATA, and a scrub of the
pool took significantly longer.
You know this sounds awfully like what I have encountered with my si3124
card. I have had long periods of inactivity while doing rcp from a Linux
based host to the Solaris box. Sometimes it appears early, sometimes it
appears late in the copy. Maybe this is also the cause of the problems I
had trying to get a Windows 2000 server to use an iSCSI shared ZFS
volume I had made.
_______________________________________________
driver-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/driver-discuss
