Roland Dreier wrote:
So I'm finally looking at applying this patch. And I wonder why you
only do this for QP buffers -- it seems every other object allocated
with mthca_alloc_buf(), namely CQs, SRQs and mem-free doorbell records,
are all also page aligned, and similarly waste memory.
So should we not just replace the posix_memalign() in alloc_buf with
anonymous mmap, and end up with a simpler patch that saves even more
memory?
BTW - we tested these patches here and they are working and indeed save
memory
I think this idea is good.
Tziporet
_______________________________________________
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
