Messages in this thread | | | Date | Mon, 8 Apr 2013 02:17:50 +0000 | From | Eric Wong <> | Subject | Re: [RFC PATCH] wfcqueue: implement __wfcq_enqueue_head() (v3) |
| |
Mathieu Desnoyers <mathieu.desnoyers@efficios.com> wrote: > Changes since v2: > * Only issue cmpxchg() if queue was empty. > * Add missing memory barrier.
Thanks!
There's a slight drop in performance either from the barrier or larger code, but I'm not worried (it was around 9-10s before wfcqueue).
$ time ./eponeshotmt -c 1000000 -w 4 -t 4 -f 10 real 0m 5.83s user 0m 1.35s sys 0m 21.95s
I also ran v2 on Davide Libenzi's totalmess epoll stresser for a few hours yesterday without failures. Running totalmess right now on v3, so far so good :)
Tested-by: Eric Wong <normalperson@yhbt.net>
| |