JFS: performance patch
Basically, we saw a large amount of time spent in the
jfs_strfromUCS_le() function, mispredicting the branch inside the
loop, so I just added some unlikely modifiers to the if statements to
re-ordered the code. Again, these simple changes provided > 2 % on
spec-sfs, so please consider it for inclusion.
Signed-off-by: Dave Kleikamp <shaggy@austin.ibm.com>
diff --git a/fs/jfs/jfs_unicode.c b/fs/jfs/jfs_unicode.c
index b32208aa..f327dec 100644
--- a/fs/jfs/jfs_unicode.c
+++ b/fs/jfs/jfs_unicode.c
@@ -51,8 +51,9 @@
}
} else {
for (i = 0; (i < len) && from[i]; i++) {
- if (le16_to_cpu(from[i]) & 0xff00) {
- if (warn) {
+ if (unlikely(le16_to_cpu(from[i]) & 0xff00)) {
+ to[i] = '?';
+ if (unlikely(warn)) {
warn--;
warn_again--;
printk(KERN_ERR
@@ -61,7 +62,7 @@
printk(KERN_ERR
"mount with iocharset=utf8 to access\n");
}
- to[i] = '?';
+
}
else
to[i] = (char) (le16_to_cpu(from[i]));