[PATCH] per-cpu slab

From: Manfred Spraul (manfreds@colorfullife.com)
Date: Thu Jun 08 2000 - 13:22:18 EST

I've virtually finished my per-cpu slab patch.

http://colorfullife.com/~manfreds/slab/patch-slab-cpu-E

changes since patch -A:

* UP fixed
* docu updated
* minor statistics change: c_error from atomic_t to unsigned int
* fix for the DMA caches, kmalloc(GFP_DMA) works again.
* smp drain cpu cache moved, kmem_cache_destroy works again.
* proc_getdata now static

The patch is well tested, please give it a try.

I'm still interested in

* which statistics should I collect about the per-cpu arrays?
* which realistic benchmarks can I run with a 10 Mbit NE2000 network
card :-/
* ideas for further improvements.

If you want to benchmark the code: disable SLAB_DEBUG_SUPPORT &
SLAB_STATS, otherwise you'll see a huge slowdown: double free detection
is now always on, and red zoning is also enabled (SLAB_FORCED_DEBUG). 

--
	Manfred

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

This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:15 EST