aboutsummaryrefslogtreecommitdiffstats
path: root/samples
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2008-03-04 14:28:35 -0800
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-03-04 16:35:11 -0800
commitbe852795e1c8d3829ddf3cb1ce806113611fa555 (patch)
tree3671dbd5ba64f11650f93fdd9178666bcbb84f7e /samples
parente3892296de632e3f9299d9fabe0c746740004891 (diff)
downloadmrst-s0i3-test-be852795e1c8d3829ddf3cb1ce806113611fa555.tar.gz
mrst-s0i3-test-be852795e1c8d3829ddf3cb1ce806113611fa555.tar.xz
mrst-s0i3-test-be852795e1c8d3829ddf3cb1ce806113611fa555.zip
alloc_percpu() fails to allocate percpu data
Some oprofile results obtained while using tbench on a 2x2 cpu machine were very surprising. For example, loopback_xmit() function was using high number of cpu cycles to perform the statistic updates, supposed to be real cheap since they use percpu data pcpu_lstats = netdev_priv(dev); lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id()); lb_stats->packets++; /* HERE : serious contention */ lb_stats->bytes += skb->len; struct pcpu_lstats is a small structure containing two longs. It appears that on my 32bits platform, alloc_percpu(8) allocates a single cache line, instead of giving to each cpu a separate cache line. Using the following patch gave me impressive boost in various benchmarks ( 6 % in tbench) (all percpu_counters hit this bug too) Long term fix (ie >= 2.6.26) would be to let each CPU allocate their own block of memory, so that we dont need to roudup sizes to L1_CACHE_BYTES, or merging the SGI stuff of course... Note : SLUB vs SLAB is important here to *show* the improvement, since they dont have the same minimum allocation sizes (8 bytes vs 32 bytes). This could very well explain regressions some guys reported when they switched to SLUB. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'samples')
0 files changed, 0 insertions, 0 deletions