<br><font size=2 face="sans-serif">Michael,</font>
<br>
<br><font size=2 face="sans-serif">Different workloads could use different
send/recv queue sizes, also different HCAs could pick up different send/recv
queue sizes to utilize the HCA performance. These parameters should be
tunable instead of setting default values in IPoIB. Also Kevin pointed
out, we don't want to waste the kernel memory when not necessary.</font>
<br>
<br><font size=2 face="sans-serif">Without each HCA vendor support resizing
send/recv/completion queue pairs, the tuning method is limited to only
as loadable modules. Patch is under testing, and will be available for
review soon.</font>
<br><font size=2 face="sans-serif"><br>
Thanks<br>
Shirley Ma<br>
IBM Linux Technology Center<br>
15300 SW Koll Parkway<br>
Beaverton, OR 97006-6063<br>
Phone(Fax): (503) 578-7638</font>