<br><font size=2><tt>Roland,</tt></font>
<br>
<br><font size=2><tt>We really want a big sendq/recvq size in cluster nodes,
much higher than 256. Setting a big default QP sendq and recvq sizes would
not be applied to any HCA driver. Each HCA has its own max QP queue size.
Making these parameters tunable makes more sense.</tt></font>
<br><font size=2><tt> </tt></font>
<br><font size=2><tt>In the meanwhile I am working on a patch to remove
TX_RING in IPoIB and replace RX_RING with dynamic queue. TX_RING/RX_RING
in IPoIB confuses users. These two parameters are not as same concept as
Ethernet device here. It would take me quite a while to finish it (including
patch validation, performance testing.)</tt></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>