summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorNick Piggin <npiggin@kernel.dk>2011-01-07 17:50:09 +1100
committerNick Piggin <npiggin@kernel.dk>2011-01-07 17:50:32 +1100
commit9d55c369bb5e695e629bc35cba2ef607755b3bee (patch)
treed97cd498a67f1f7987d4403ef90e399516a3b8c9 /fs
parente1bb57826381199cc79fbf44e9dfeee58fc7b339 (diff)
downloadlinux-9d55c369bb5e695e629bc35cba2ef607755b3bee.tar.bz2
fs: implement faster dentry memcmp
The standard memcmp function on a Westmere system shows up hot in profiles in the `git diff` workload (both parallel and single threaded), and it is likely due to the costs associated with trapping into microcode, and little opportunity to improve memory access (dentry name is not likely to take up more than a cacheline). So replace it with an open-coded byte comparison. This increases code size by 8 bytes in the critical __d_lookup_rcu function, but the speedup is huge, averaging 10 runs of each: git diff st user sys elapsed CPU before 1.15 2.57 3.82 97.1 after 1.14 2.35 3.61 96.8 git diff mt user sys elapsed CPU before 1.27 3.85 1.46 349 after 1.26 3.54 1.43 333 Elapsed time for single threaded git diff at 95.0% confidence: -0.21 +/- 0.01 -5.45% +/- 0.24% It's -0.66% +/- 0.06% elapsed time on my Opteron, so rep cmp costs on the fam10h seem to be relatively smaller, but there is still a win. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Diffstat (limited to 'fs')
-rw-r--r--fs/dcache.c12
1 files changed, 3 insertions, 9 deletions
diff --git a/fs/dcache.c b/fs/dcache.c
index 2a4ce7dc2306..5699d4c027cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1454,9 +1454,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (qstr->len != len)
- continue;
- if (memcmp(qstr->name, name, len))
+ if (dentry_cmp(qstr->name, qstr->len, name, len))
continue;
__dget(alias);
return alias;
@@ -1810,9 +1808,7 @@ seqretry:
tlen, tname, name))
continue;
} else {
- if (tlen != len)
- continue;
- if (memcmp(tname, str, tlen))
+ if (dentry_cmp(tname, tlen, str, len))
continue;
}
/*
@@ -1925,9 +1921,7 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
tlen, tname, name))
goto next;
} else {
- if (tlen != len)
- goto next;
- if (memcmp(tname, str, tlen))
+ if (dentry_cmp(tname, tlen, str, len))
goto next;
}