Re: [PATCH 39 of 39] IB/ipath - use streaming copy in RDMA interrupt handler to reduce packet loss
From: Bryan O'Sullivan <hidden>
Date: 2006-06-29 23:34:26
Also in:
lkml
From: Bryan O'Sullivan <hidden>
Date: 2006-06-29 23:34:26
Also in:
lkml
On Thu, 2006-06-29 at 15:03 -0700, David Miller wrote:
I'm not good with names :-)
Heh. I'll call it memcpy_nc for now, then, and people can retch all over the name as they please when I submit a more suitably generic patch.
Note that there also might be cases where using such a memcpy variant might be the wrong thing to do. For example, for a very tightly coupled CMT cpu implementation which has the memory controller, L2 cache, PCI controller, etc. all on the same die and the PCI controller makes use of the L2 cache just like the cpu threads do, using this kind of memcpy would always be the wrong thing to do.
I'm not quite following you, though I assume you're referring to Niagara or Rock :-) Are you saying a memcpy_nc would do worse than plain memcpy, or worse than some other memcpy-like routine? <b