[lkml]   [2000]   [Nov]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Subjectlocks.c: removal of semaphores
I got 5250 Req/s with your locks-sem.patch on normal Apache.
It is good performance on normal Apache.

Andrew Morton writes:
> Kouichi, could you please test the performance of this on
> your 8-way with Apache+fcntl serialisation? (the normal
> Apache). Please use 2.4.0-test10-pre5, not 2.4.0-test10.
> Something has gone funny with test10 and I'm getting much
> lower rates.

Followings are the recent data with/without serialization.

w/ serialize w/o serialize
240t10pre5 2237 5358
240t10pre5+P2 5253 5355**
240t10pre5+P3 --- NG
240t10pre5+locksem 5250 ---
**: once we found deadlock
NG: cannot complete measurement
--: we've not measured.

Normal apache on various kernel setting as follows:

> test8 5287 <-- best performance
> test10-pre5+P2 5258
> 240t10pre5+locksem 5250
> test9+P2 5243
> test9+mypatch 5192 <-- a little bit worse
> test10-pre5+P1 5187
> test1 3702 <-- no good scalability
> test10-pre5 2255 <-- negative scalability
> test9 2193

We also did durability test of 2.4.0-test10-pre5. Unfortunately
enough, we didn't successfully complete the test of Apache w/o
serialization (-DSINGLE_LISTEN_UNSERIALIZED_ACCEPT), it couldn't
continue to run for a night. The kernel got complete deadlock.

The message is:
"Unable to handle kernel NULL pointer dereference NMI watchdog detected LOCKUP on CPU1."

Yes, obviously it's not Andrew's problem, that is genuine test10-pre5.

Hidden bugs are awakened by removing serialization.

If the bug is same as what I observed, It is NULL pointer dereference
on run-queue list.
Computer Systems Laboratory, Fujitsu Labs.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
Please read the FAQ at

 \ /
  Last update: 2005-03-22 12:45    [W:0.031 / U:0.360 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site