Re: kmalloc optimization

From: Albert D. Cahalan (acahalan@cs.uml.edu)
Date: Sun Aug 27 2000 - 14:49:19 EST


Andi Kleen writes:
>>> 1500bytes slab unfortunately is not too useful, because it
>>> does not fit well in 4K pages (you would need 8K or 16K page
>>> allocations, which the mm system does not like much due to
>>> fragmentation)
>>
>> Doesn't matter (too much).
>
> On 32MB machines it was a big problem in my experiments.

You tried using 1632-byte chunks split from 8 kB allocations?
The 8 kB blocks can be allocated well in advance of need, so
that the fragmentation problem doesn't hurt too much.

What about huge network servers, like those used for benchmarks?
We already have a TCP window size option... might as well change
that to be a general large-memory networking option if needed.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Thu Aug 31 2000 - 21:00:19 EST