On Tue, Sep 3, 2013 at 8:01 AM, Ingo Molnar <mingo@xxxxxxxxxx> wrote:
>
> * Waiman Long <waiman.long@xxxxxx> wrote:
>
>> On 08/30/2013 10:42 PM, Al Viro wrote:
>> >On Sat, Aug 31, 2013 at 03:35:16AM +0100, Al Viro wrote:
>> >
>> >>Aha... OK, I see what's going on. We end up with shm_mnt *not* marked
>> >>as long-living vfsmount, even though it lives forever. See if the
>> >>following helps; if it does (and I very much expect it to), we want to
>> >>put it in -stable. As it is, you get slow path in mntput() each time
>> >>a file created by shmem_file_setup() gets closed. For no reason whatsoever...
>> >We still want MS_NOUSER on shm_mnt, so we'd better make sure that
>> >shmem_fill_super() sets it on the internal instance... Fixed variant
>> >follows:
>> >
>> >Signed-off-by: Al Viro<viro@xxxxxxxxxxxxxxxxxx>
>> >diff --git a/mm/shmem.c b/mm/shmem.c
>> >index e43dc55..5261498 100644
>> >--- a/mm/shmem.c
>> >+++ b/mm/shmem.c
>> >@@ -2615,13 +2615,15 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
>> > * tmpfs instance, limiting inodes to one per page of lowmem;
>> > * but the internal instance is left unlimited.
>> > */
>> >- if (!(sb->s_flags& MS_NOUSER)) {
>> >+ if (!(sb->s_flags& MS_KERNMOUNT)) {
>> > sbinfo->max_blocks = shmem_default_max_blocks();
>> > sbinfo->max_inodes = shmem_default_max_inodes();
>> > if (shmem_parse_options(data, sbinfo, false)) {
>> > err = -EINVAL;
>> > goto failed;
>> > }
>> >+ } else {
>> >+ sb->s_flags |= MS_NOUSER;
>> > }
>> > sb->s_export_op =&shmem_export_ops;
>> > sb->s_flags |= MS_NOSEC;
>> >@@ -2831,8 +2833,7 @@ int __init shmem_init(void)
>> > goto out2;
>> > }
>> >
>> >- shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER,
>> >- shmem_fs_type.name, NULL);
>> >+ shm_mnt = kern_mount(&shmem_fs_type);
>> > if (IS_ERR(shm_mnt)) {
>> > error = PTR_ERR(shm_mnt);
>> > printk(KERN_ERR "Could not kern_mount tmpfs\n");
>>
>> Yes, that patch worked. It eliminated the lglock as a bottleneck in
>> the AIM7 workload. The lg_global_lock did not show up in the perf
>> profile, whereas the lg_local_lock was only 0.07%.
>
> Just curious: what's the worst bottleneck now in the optimized kernel? :-)
>
> Thanks,
>
> Ingo
Can someone summarize this thread (70+ postings)?
Which patches are needed? And fixing what?
( Can people provide separate patches with a proper changelog? )
Improvements?
Thanks.
- Sedat (still struggling with perf) -
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
