Re: dev_lock() contention for fdesc syscalls -- possible fix

2014-11-10 Thread Konstantin Belousov
On Mon, Nov 10, 2014 at 10:44:12AM +0100, Luigi Rizzo wrote: > On Mon, Nov 10, 2014 at 10:34:57AM +0200, Konstantin Belousov wrote: > > On Mon, Nov 10, 2014 at 02:49:39AM +0100, Luigi Rizzo wrote: > > > It was noticed that there is huge dev_lock() contention when multiple > > > processes do a poll(

Re: dev_lock() contention for fdesc syscalls -- possible fix

2014-11-10 Thread Luigi Rizzo
On Mon, Nov 10, 2014 at 10:34:57AM +0200, Konstantin Belousov wrote: > On Mon, Nov 10, 2014 at 02:49:39AM +0100, Luigi Rizzo wrote: > > It was noticed that there is huge dev_lock() contention when multiple > > processes do a poll() even on independent file descriptors. > > > > Turns out that not j

Re: dev_lock() contention for fdesc syscalls -- possible fix

2014-11-10 Thread Konstantin Belousov
On Mon, Nov 10, 2014 at 02:49:39AM +0100, Luigi Rizzo wrote: > It was noticed that there is huge dev_lock() contention when multiple > processes do a poll() even on independent file descriptors. > > Turns out that not just poll but most syscalls on file descriptors > (as opposed to sockets) in sys

dev_lock() contention for fdesc syscalls -- possible fix

2014-11-09 Thread Luigi Rizzo
It was noticed that there is huge dev_lock() contention when multiple processes do a poll() even on independent file descriptors. Turns out that not just poll but most syscalls on file descriptors (as opposed to sockets) in sys/fs/devfs/devfs_vnops.c including devfs_poll_f(), devfs_ioctl_f() and r