Messages in this thread | | | Date | Sun, 23 Sep 2007 23:17:13 -0700 | From | Andrew Morton <> | Subject | Re: [PATCH 24/25] r/o bind mounts: track number of mount writers |
| |
On Thu, 20 Sep 2007 12:53:20 -0700 Dave Hansen <haveblue@us.ibm.com> wrote:
> This is the real meat of the entire series. It actually > implements the tracking of the number of writers to a mount. > However, it causes scalability problems because there can > be hundreds of cpus doing open()/close() on files on the > same mnt at the same time. Even an atomic_t in the mnt > has massive scalaing problems because the cacheline gets > so terribly contended. > > This uses a statically-allocated percpu variable. All > operations are local to a cpu as long that cpu operates on > the same mount, and there are no writer count imbalances. > Writer count imbalances happen when a write is taken on one > cpu, and released on another, like when an open/close pair > is performed on two different cpus because the task moved.
Did you test with lockdep enabled?
============================================= [ INFO: possible recursive locking detected ] 2.6.23-rc7-mm1 #1 --------------------------------------------- swapper/1 is trying to acquire lock: (&writer->lock){--..}, at: [<c0197a32>] lock_and_coalesce_cpu_mnt_writer_counts+0x32/0x70
but task is already holding lock: (&writer->lock){--..}, at: [<c0197a32>] lock_and_coalesce_cpu_mnt_writer_counts+0x32/0x70
other info that might help us debug this: 1 lock held by swapper/1: #0: (&writer->lock){--..}, at: [<c0197a32>] lock_and_coalesce_cpu_mnt_writer_counts+0x32/0x70
stack backtrace: [<c0103ffa>] show_trace_log_lvl+0x1a/0x30 [<c0104b82>] show_trace+0x12/0x20 [<c0104c96>] dump_stack+0x16/0x20 [<c0144dc5>] __lock_acquire+0xde5/0x10a0 [<c01450fa>] lock_acquire+0x7a/0xa0 [<c03e734c>] _spin_lock+0x2c/0x40 [<c0197a32>] lock_and_coalesce_cpu_mnt_writer_counts+0x32/0x70 [<c01982c6>] mntput_no_expire+0x36/0xc0 [<c0188f15>] path_release_on_umount+0x15/0x20 [<c0198930>] sys_umount+0x40/0x230 [<c010070b>] name_to_dev_t+0x9b/0x270 [<c05230c2>] prepare_namespace+0x62/0x1b0 [<c05226ca>] kernel_init+0x21a/0x320 [<c0103b47>] kernel_thread_helper+0x7/0x10 =======================
It look like a false positive to me, but really, for a patchset of this complexity and maturity I cannot fathom how it could have escaped any lockdep testing.
- 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/
| |