kernbench-16 on 2.5.59 vs 2.5.59-mm6
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 11 lines · Martin J. Bligh
Going from 59 to 59-mm6, I get:
Kernbench-16:
Elapsed User System CPU 2.5.59 47.45 568.02 143.17 1498.17 2.5.59-mm6 47.18 567.15 138.62 1495.50Summary: Scheduler stuff seems like a wash (schedule ->
do_schedule). Seems to be some sort of rearrangement of the dcache stuff which appears to be mildly beneficial (what's going in there?).
Quoted 5 lines
diffprofile (+ gets worse, - gets better).
2023
do_schedule
485dentry_open
289 .text.lock.file_table
Looks like you are getting hit by contention on files_lock. I have been messing around with some code to split up the files_lock, but I can't seem to get the locking in the tty layer right.
Hmm.. .text.lock.namei is probably dcache_lock. -mms no longer has dcache_rcu, so not quite sure what helped you here.
Thanks
Dipankar