Quoting r. Roland Dreier <[EMAIL PROTECTED]>: > Subject: Re: PATCH] mthca - command interface - revised > > Michael> AFAIK, which of the two options gives better performance > Michael> might depend on the application and the specific system. > Michael> For now, Eli made the simpler option the default. > > Have you seen cases where using the HCR is faster? It seems that in > both cases we are doing posted writes to PCI memory, except that the > HCR case has to do at least one (slow) read to check the go bit. The > doorbell case does use more write barriers since all the writes have > to be ordered, but I have a hard time believing that the write > barriers are anywhere near as expensive as the read of the go bit.
We did not yet figure it out why. Possibly some systems slow down if you do a lot of PIO writes in a burst. -- Michael S. Tsirkin Staff Engineer, Mellanox Technologies _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
