On 6/16/20 12:47 AM, Jan Kara wrote:
> On Mon 15-06-20 19:26:38, Amir Goldstein wrote:
>>> This patch changes alloc_file_pseudo() to always opt out of fsnotify by
>>> setting FMODE_NONOTIFY flag so that no check is made for fsnotify watchers
>>> on pseudo files. This should be safe as the underlying helper for the
>>> dentry is d_alloc_pseudo which explicitly states that no lookups are ever
>>> performed meaning that fanotify should have nothing useful to attach to.
>>>
>>> The test motivating this was "perf bench sched messaging --pipe". On
>>> a single-socket machine using threads the difference of the patch was
>>> as follows.
>>>
>>> 5.7.0 5.7.0
>>> vanilla nofsnotify-v1r1
>>> Amean 1 1.3837 ( 0.00%) 1.3547 ( 2.10%)
>>> Amean 3 3.7360 ( 0.00%) 3.6543 ( 2.19%)
>>> Amean 5 5.8130 ( 0.00%) 5.7233 * 1.54%*
>>> Amean 7 8.1490 ( 0.00%) 7.9730 * 2.16%*
>>> Amean 12 14.6843 ( 0.00%) 14.1820 ( 3.42%)
>>> Amean 18 21.8840 ( 0.00%) 21.7460 ( 0.63%)
>>> Amean 24 28.8697 ( 0.00%) 29.1680 ( -1.03%)
>>> Amean 30 36.0787 ( 0.00%) 35.2640 * 2.26%*
>>> Amean 32 38.0527 ( 0.00%) 38.1223 ( -0.18%)
>>>
>>> The difference is small but in some cases it's outside the noise so
>>> while marginal, there is still some small benefit to ignoring fsnotify
>>> for files allocated via alloc_file_pseudo in some cases.
>>>
>>> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
>>
>> Reviewed-by: Amir Goldstein <amir73il@xxxxxxxxx>
>
> Thanks for the patch Mel and for review Amir! I've added the patch to my
> tree with small amendments to the changelog.
>
> Honza
>
Note this patch broke some user programs (one instance being packetdrill)
Typical legacy packetdrill script has :
// Create a socket and set it to non-blocking.
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
But after this change, fcntl(3, F_GETFL) returns 0x4000002
FMODE_NONOTIFY was not meant to be visible to user space. (otherwise
there would be a O_NONOTIFY) ?
