![]() | |||||||||||||
Messages in this thread |
On Thu, Jan 16, 2003 at 04:47:30AM +0000, William Lee Irwin III wrote: > On Wed, Jan 15, 2003 at 08:18:13PM -0800, Dave Hansen wrote: > > file_table:_raw_read_lock() 3300000 > > Call Trace: > > [<c0152469>] fget+0x9d/0xa0 > > [<c0152b27>] sys_fsync+0x21/0xbe > > [<c0151b53>] sys_writev+0x47/0x56 > > [<c010931f>] syscall_call+0x7/0xb > read_lock(&file->files_lock); You mean read_lock(&files->file_lock); :) Dave, does your webserver benchmark clone() tasks with CLONE_FILES ? Unless the fd table is shared, can't see why there would be contention on this. If it is indeed necessary to share fd table, then there is a somewhat unmaintained lockfree fget() patch (files_struct_rcu) that you might want to try. > > On Wed, Jan 15, 2003 at 08:18:13PM -0800, Dave Hansen wrote: > > time:_raw_write_lock() 1350000 > > Call Trace: > > [<c010f321>] timer_interrupt+0x99/0x9c > > [<c010b150>] handle_IRQ_event+0x38/0x5c > > read_lock_irqsave(&xtime_lock, flags) > or > write_lock_irq(&xtime_lock); ISTR a patch from Stephen Hemminger at OSDL that used Andrea's sequence number trick based rwlock (frlock) to implement do_gettimeofday. It might be relevant here. Thanks Dipankar - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | ||||||||||||
| Last update: 2005-03-22 12:32 [from the cache] ©2003-2008 | |||||||||||||