On Wed, Feb 03, 2016 at 04:49:43PM +0300, Andrey Ryabinin wrote:
>
>
> On 02/03/2016 03:12 PM, Vladimir Davydov wrote:
>
> >> ub = get_exec_ub();
> >> @@ -246,15 +252,18 @@ SYSCALL_DEFINE0(sync)
> >> fsb = __ve_fsync_behavior(ve);
> >> if (fsb == FSYNC_NEVER)
> >> goto skip;
> >> +
> >> + if (fsb == FSYNC_FILTERED)
> >> + sync_ub = get_io_ub();
> >> }
> >>
> >> - wakeup_flusher_threads(0, WB_REASON_SYNC);
> >> - iterate_supers(sync_inodes_one_sb, NULL);
> >> - iterate_supers(sync_fs_one_sb, &nowait);
> >> - iterate_supers(sync_fs_one_sb, &wait);
> >> + wakeup_flusher_threads_ub(0, ub, WB_REASON_SYNC);
> >
> > s/ub,/sync_ub,
> >
> > ?
> >
>
> Yup,
>
> >> + iterate_supers(sync_inodes_one_sb, sync_ub);
> >> + sync_filesystems(sync_ub, nowait);
> >> + sync_filesystems(sync_ub, wait);
> >> iterate_bdevs(fdatawrite_one_bdev, NULL);
> >> iterate_bdevs(fdatawait_one_bdev, NULL);
> >
> > If sync_ub != NULL, you sync inodes and bdevs twice, here and in
> > sync_filesystems_ve. Better move all the iterate_supers/bdevs from here
> > to sync_filesystems under !ub branch?
> >
>
> I'm thinking about something like this:
>
> @@ -255,15 +253,22 @@ SYSCALL_DEFINE0(sync)
>
> if (fsb == FSYNC_FILTERED)
> sync_ub = get_io_ub();
> +
> + if (sync_ub && (sync_ub != get_ub0())) {
> + wakeup_flusher_threads_ub(0, sync_ub, WB_REASON_SYNC);
> + sync_filesystems_ve(get_exec_env(), ub, nowait);
> + sync_filesystems_ve(get_exec_env(), ub, wait);
> + goto skip;
> + }
> }
>
>
> !sync_ub path left untouched.
>
Looks good to me.
_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
