Re: fsnotify: minimise overhead when there are no marks related to sb

[Amir Goldstein <amir73il@gmail.com>]

On Mon, Jul 27, 2020 at 10:44 AM Jan Kara <jack@suse.cz> wrote:
>
> On Sun 26-07-20 18:20:26, Amir Goldstein wrote:
> > On Thu, Jul 9, 2020 at 8:56 PM Amir Goldstein <amir73il@gmail.com> wrote:
> > >
> > > > > > Otherwise the patch looks good. One observation though: The (mask &
> > > > > > FS_MODIFY) check means that all vfs_write() calls end up going through the
> > > > > > "slower" path iterating all mark types and checking whether there are marks
> > > > > > anyway. That could be relatively simply optimized using a hidden mask flag
> > > > > > like FS_ALWAYS_RECEIVE_MODIFY which would be set when there's some mark
> > > > > > needing special handling of FS_MODIFY... Not sure if we care enough at this
> > > > > > point...
> > > > >
> > > > > Yeh that sounds low hanging.
> > > > > Actually, I Don't think we need to define a flag for that.
> > > > > __fsnotify_recalc_mask() can add FS_MODIFY to the object's mask if needed.
> > > >
> > > > Yes, that would be even more elegant.
> > > >
> > > > > I will take a look at that as part of FS_PRE_MODIFY work.
> > > > > But in general, we should fight the urge to optimize theoretic
> > > > > performance issues...
> > > >
> > > > Agreed. I just suspect this may bring measurable benefit for hackbench pipe
> > > > or tiny tmpfs writes after seeing Mel's results. But as I wrote this is a
> > > > separate idea and without some numbers confirming my suspicion I don't
> > > > think the complication is worth it so I don't want you to burn time on this
> > > > unless you're really interested :).
> > > >
> > >
> > > You know me ;-)
> > > FS_MODIFY optimization pushed to fsnotify_pre_modify branch.
> > > Only tested that LTP tests pass.
> > >
> > > Note that this is only expected to improve performance in case there *are*
> > > marks, but not marks with ignore mask, because there is an earlier
> > > optimization in fsnotify() for the no marks case.
> > >
> >
> > Hi Mel,
> >
> > After following up on Jan's suggestion above, I realized there is another
> > low hanging optimization we can make.
> >
> > As you may remember, one of the solutions we considered was to exclude
> > special or internal sb's from notifications based on some SB flag, but making
> > assumptions about which sb are expected to provide notifications turned out
> > to be a risky game.
> >
> > We can however, keep a counter on sb to *know* there are no watches
> > on any object in this sb, so the test:
> >
> >         if (!sb->s_fsnotify_marks &&
> >             (!mnt || !mnt->mnt_fsnotify_marks) &&
> >             (!inode || !inode->i_fsnotify_marks))
> >                 return 0;
> >
> > Which is not so nice for inlining, can be summarized as:
> >
> >         if (atomic_long_read(&inode->i_sb->s_fsnotify_obj_refs) == 0)
> >                 return 0;
> >
> > Which is nicer for inlining.
>
> That's a nice idea. I was just wondering why do you account only inode
> references in the superblock. Because if there's only say mount watch,
> s_fsnotify_obj_refs will be 0 and you will wrongly skip reporting. Or am I
> misunderstanding something? I'd rather have counter like
> sb->s_fsnotify_connectors, that will account all connectors related to the
> superblock - i.e., connectors attached to the superblock, mounts referring
> to the superblock, or inodes referring to the superblock...
>

Yeh, that is what I did.
Those two commits change the former s_fsnotify_inode_refs
to s_fsnotify_obj_refs which counts objects (inodes/mounts/sb) pointed to
be connectors.
I agree that s_fsnotify_connectors may be a better choice of name ;-)

de1255f8a64c fsnotify: count all objects with attached connectors
5e6c3af6e2df fsnotify: count s_fsnotify_inode_refs for attached connectors

Thanks,
Amir.