Andrew Harvey wrote:
> Hi, thanks for highlighting that.
> 
> I made the changes to /kernel/drv/e1000g.conf and did an 'update_drv e1000g' 
> + reboot. Unfortunately it hasn't really solved the performance problem - the 
> figures I am getting now are mixed: 29.4MB/s down (2MB/s better) and 74.9MB/s 
> up (13MB/s worse).

In that case, I suggest reverting the change.  The problem I was
describing has far starker consequences -- 100-to-1 or more in terms of
performance.  If you're only seeing a few percent difference, then the
problem I described (and that affects me) almost certainly cannot be
your problem.

> r...@seraph:~# kstat -m e1000g -i 0
> ...
>         XOFFs_Recvd                     106
>         XOFFs_Xmitd                     0
>         XONs_Recvd                      2
>         XONs_Xmitd                      0
>         Xmit_TCP_Seg_Contexts           0
>         Xmit_TCP_Seg_Contexts_Fail      0
>         Xmit_with_No_CRS                0

It's still interesting that you're getting XOFF (flow control) messages
from your local switch.  It suggests that your switch is
bandwidth-limited in some way.  Are both peers in this test at 1Gbps?
Is it possible to try a different switch?

-- 
James Carlson         42.703N 71.076W         <[email protected]>
_______________________________________________
networking-discuss mailing list
[email protected]

Reply via email to