Andrew Morton wrote:
Patrick McHardy <kaber@trash.net> wrote:No in fact it implies the hash _is_ good. The more hash buckets are in use, the more
Does this not imply that the hash isn't very good?David S. Miller wrote:Sorry, i didn't meant to waste your time.Posting a patch without describing why the change is being made is always a bad idea. I delete such emails. I'm stupid and I need to be told what a patch does and why.
The current ip_fragment evictor kills the oldest entry of each hash bucket
starting with 0 instead of killing the oldest entry of all buckets. This leads
to unfair behaviour if one of the higher hash slots carries alot of fragments.
This patch holds the frag heads in a lru queue so we can kills the least
recently used first. Each arriving fragment counts as usage.
"innocent" frag heads are killed if a high bucket uses alot of memory.
Patrick
-
: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
