http://people.redhat.com/mingo/swap-speedup/swap-speedup-2.4.3-B3
(the patch is against 2.4.4-pre6 or 2.4.3-ac13.)
-B3 includes Marcelo's patch for another area that blocks unnecesserily on
locked swapcache pages: async swapcache readahead. Marcello did some tests
which shows that this fix brought some nice improvements too.
"make -j32 bzImage" using 128MB mem, 128MB swap, 4 CPUs:
stock 2.4.3-ac13
----------------
real 4m0.678s
user 4m2.870s
sys 0m38.920s
swap-speedup-A2
---------------
real 3m24.190s
user 4m1.070s
sys 0m31.950s
swap-speedup-B3 (A2 + Marcelo's swapin-readahead non-blocking patch)
---------------
real 3m7.410s
user 4m0.940s
sys 0m28.680s
ie. for this kernel compile test:
swap-speedup-A2 is a 18% speedup relative to stock 2.4.3-ac13
swap-speedup-B3 is a 28% speedup relative to stock 2.4.3-ac13
and the amount of CPU time spent in the kernel has been reduced
significantly as well.
I believe all the correctness and SMP-locking issues have been taken care
of in -B3 as well.
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/