On 5/27/07, Michael S. Tsirkin <[EMAIL PROTECTED]> wrote:
> Quoting Or Gerlitz <[EMAIL PROTECTED]>: > Subject: Re: Re: [PATCH for-2.6.22] IB/ipoib: fix SRQ WR leak > > Roland Dreier wrote: > >OK, I crossed my fingers and merged this for 2.6.22 > > Somehow it seems when applying this patch to OFED something goes wrong, > please see https://bugs.openfabrics.org/show_bug.cgi?id=636 Yes, it seems that we shouldn't keep a QP in error state for extended periods of time, since that moves hardware to the slow path.
what actually is the "hardware slow path" ? Or.
_______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
