Hey Vlad, Please pull these two critical bug fixes for iw_cxgb3 from:
ssh://[email protected]/~swise/scm/ofed_kernel.git ofed_1_5 The are needed in ofed-1.5.2 for large cluster stability. Thanks Steve. -------- commit d3a225ba07fdd7bf4eccaab383818dde41231166 Author: Steve Wise <[email protected]> Date: Sat Aug 28 08:07:38 2010 -0500 RDMA/cxgb3: Remove BUG_ON() on CQ rearm failure Failure to rearm a CQ means the cxgb3 device is wedged, but we shouldn't kill the whole system with a BUG_ON() if this happens. Signed-off-by: Steve Wise <[email protected]> Signed-off-by: Roland Dreier <[email protected]> commit f3495ab83c7906ada0fea19867c16c634014e160 Author: Steve Wise <[email protected]> Date: Sat Aug 28 08:02:42 2010 -0500 RDMA/cxgb3: Don't exceed the max HW CQ depth. From: Steve Wise <[email protected]> The max depth supported by T3 is 64K entries. This bug will cause stalls and possibly crashes in large MPI clusters. Signed-off-by: Steve Wise <[email protected]> _______________________________________________ ewg mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
