[v1] f2fs: fix max open zone constraints

  We can get the number of remaining available zone
resources by subtracting the number of active logs from
the number of max active zones of zoned devices. We can
use these available zone resources to reduce the number
of pending bio when switching zones.
If max active zones is 0, there is no limit.

Signed-off-by: Wenjie Qi <qwjhust@gmail.com>
---
 fs/f2fs/data.c  | 32 +++++++++++++++++++++++++-------
 fs/f2fs/f2fs.h  |  2 ++
 fs/f2fs/super.c | 11 +++++++++++
 3 files changed, 38 insertions(+), 7 deletions(-)
  

On Tue, Jan 16, 2024 at 6:36 AM Wenjie Qi <qwjhust@gmail.com> wrote:
>
> We can get the number of remaining available zone
> resources by subtracting the number of active logs from
> the number of max active zones of zoned devices. We can
> use these available zone resources to reduce the number
> of pending bio when switching zones.
> If max active zones is 0, there is no limit.
>
> Signed-off-by: Wenjie Qi <qwjhust@gmail.com>
> ---
>  fs/f2fs/data.c  | 32 +++++++++++++++++++++++++-------
>  fs/f2fs/f2fs.h  |  2 ++
>  fs/f2fs/super.c | 11 +++++++++++
>  3 files changed, 38 insertions(+), 7 deletions(-)
>
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index dce8defdf4c7..0b62ca296074 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -392,6 +392,19 @@ static void f2fs_zone_write_end_io(struct bio *bio)
>         complete(&io->zone_wait);
>         f2fs_write_end_io(bio);
>  }
> +
> +static void f2fs_zone_write_end_io_nowait(struct bio *bio)
> +{
> +#ifdef CONFIG_F2FS_IOSTAT
> +       struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
> +       struct f2fs_sb_info *sbi = iostat_ctx->sbi;
> +#else
> +       struct f2fs_sb_info *sbi = (struct f2fs_sb_info *)bio->bi_private;
> +#endif
> +
> +       atomic_inc(&sbi->available_active_zones);
> +       f2fs_write_end_io(bio);
> +}
>  #endif

I don't think this works. Let's assume we start with 2
available_active_zones and 4 active logs.
How about 4 active logs reach at the end of the zones at the same time?

>
>  struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
> @@ -1085,14 +1098,19 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
>                 goto next;
>  out:
>  #ifdef CONFIG_BLK_DEV_ZONED
> -       if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
> +       if (f2fs_sb_has_blkzoned(sbi) && sbi->max_active_zones && btype < META &&
>                         is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
> -               bio_get(io->bio);
> -               reinit_completion(&io->zone_wait);
> -               io->bi_private = io->bio->bi_private;
> -               io->bio->bi_private = io;
> -               io->bio->bi_end_io = f2fs_zone_write_end_io;
> -               io->zone_pending_bio = io->bio;
> +               if (!atomic_add_negative(-1, &sbi->available_active_zones)) {
> +                       io->bio->bi_end_io = f2fs_zone_write_end_io_nowait;
> +               } else {
> +                       atomic_inc(&sbi->available_active_zones);
> +                       bio_get(io->bio);
> +                       reinit_completion(&io->zone_wait);
> +                       io->bi_private = io->bio->bi_private;
> +                       io->bio->bi_private = io;
> +                       io->bio->bi_end_io = f2fs_zone_write_end_io;
> +                       io->zone_pending_bio = io->bio;
> +               }
>                 __submit_merged_bio(io);
>         }
>  #endif
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 65294e3b0bef..2aade367ac66 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -1551,6 +1551,8 @@ struct f2fs_sb_info {
>
>  #ifdef CONFIG_BLK_DEV_ZONED
>         unsigned int blocks_per_blkz;           /* F2FS blocks per zone */
> +       unsigned int max_active_zones;          /* max zone resources of the zoned device */
> +       atomic_t available_active_zones;        /* remaining zone resources for zone switch */
>  #endif
>
>         /* for node-related operations */
> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> index 206d03c82d96..6711283ff187 100644
> --- a/fs/f2fs/super.c
> +++ b/fs/f2fs/super.c
> @@ -2385,6 +2385,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
>         if (err)
>                 goto restore_opts;
>
> +#ifdef CONFIG_BLK_DEV_ZONED
> +       if (sbi->max_active_zones)
> +               atomic_set(&sbi->available_active_zones,
> +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> +#endif
> +
>         /* flush outstanding errors before changing fs state */
>         flush_work(&sbi->s_error_work);
>
> @@ -3932,6 +3938,11 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
>         if (!f2fs_sb_has_blkzoned(sbi))
>                 return 0;
>
> +       sbi->max_active_zones = bdev_max_active_zones(bdev);
> +       if (sbi->max_active_zones)
> +               atomic_set(&sbi->available_active_zones,
> +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> +

Need to make available_active_zones not be negative, right?
Hmm, need to make sure active_logs should be equal or less than
max_active_zones.

>         zone_sectors = bdev_zone_sectors(bdev);
>         if (!is_power_of_2(zone_sectors)) {
>                 f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
> --
> 2.34.1
>
>
>
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
  

On Tue, Jan 16, 2024 at 2:58 PM Daeho Jeong <daeho43@gmail.com> wrote:
>
> On Tue, Jan 16, 2024 at 6:36 AM Wenjie Qi <qwjhust@gmail.com> wrote:
> >
> > We can get the number of remaining available zone
> > resources by subtracting the number of active logs from
> > the number of max active zones of zoned devices. We can
> > use these available zone resources to reduce the number
> > of pending bio when switching zones.
> > If max active zones is 0, there is no limit.
> >
> > Signed-off-by: Wenjie Qi <qwjhust@gmail.com>
> > ---
> >  fs/f2fs/data.c  | 32 +++++++++++++++++++++++++-------
> >  fs/f2fs/f2fs.h  |  2 ++
> >  fs/f2fs/super.c | 11 +++++++++++
> >  3 files changed, 38 insertions(+), 7 deletions(-)
> >
> > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> > index dce8defdf4c7..0b62ca296074 100644
> > --- a/fs/f2fs/data.c
> > +++ b/fs/f2fs/data.c
> > @@ -392,6 +392,19 @@ static void f2fs_zone_write_end_io(struct bio *bio)
> >         complete(&io->zone_wait);
> >         f2fs_write_end_io(bio);
> >  }
> > +
> > +static void f2fs_zone_write_end_io_nowait(struct bio *bio)
> > +{
> > +#ifdef CONFIG_F2FS_IOSTAT
> > +       struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
> > +       struct f2fs_sb_info *sbi = iostat_ctx->sbi;
> > +#else
> > +       struct f2fs_sb_info *sbi = (struct f2fs_sb_info *)bio->bi_private;
> > +#endif
> > +
> > +       atomic_inc(&sbi->available_active_zones);
> > +       f2fs_write_end_io(bio);
> > +}
> >  #endif
>
> I don't think this works. Let's assume we start with 2
> available_active_zones and 4 active logs.
> How about 4 active logs reach at the end of the zones at the same time?

Sorry, I was confused. It would work. However, it might be a little clumsy.
How about using a data structure like a counting semaphore?
We can decrease it as we open a zone and increase it as we close a zone.

>
> >
> >  struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
> > @@ -1085,14 +1098,19 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
> >                 goto next;
> >  out:
> >  #ifdef CONFIG_BLK_DEV_ZONED
> > -       if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
> > +       if (f2fs_sb_has_blkzoned(sbi) && sbi->max_active_zones && btype < META &&
> >                         is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
> > -               bio_get(io->bio);
> > -               reinit_completion(&io->zone_wait);
> > -               io->bi_private = io->bio->bi_private;
> > -               io->bio->bi_private = io;
> > -               io->bio->bi_end_io = f2fs_zone_write_end_io;
> > -               io->zone_pending_bio = io->bio;
> > +               if (!atomic_add_negative(-1, &sbi->available_active_zones)) {
> > +                       io->bio->bi_end_io = f2fs_zone_write_end_io_nowait;
> > +               } else {
> > +                       atomic_inc(&sbi->available_active_zones);
> > +                       bio_get(io->bio);
> > +                       reinit_completion(&io->zone_wait);
> > +                       io->bi_private = io->bio->bi_private;
> > +                       io->bio->bi_private = io;
> > +                       io->bio->bi_end_io = f2fs_zone_write_end_io;
> > +                       io->zone_pending_bio = io->bio;
> > +               }
> >                 __submit_merged_bio(io);
> >         }
> >  #endif
> > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > index 65294e3b0bef..2aade367ac66 100644
> > --- a/fs/f2fs/f2fs.h
> > +++ b/fs/f2fs/f2fs.h
> > @@ -1551,6 +1551,8 @@ struct f2fs_sb_info {
> >
> >  #ifdef CONFIG_BLK_DEV_ZONED
> >         unsigned int blocks_per_blkz;           /* F2FS blocks per zone */
> > +       unsigned int max_active_zones;          /* max zone resources of the zoned device */
> > +       atomic_t available_active_zones;        /* remaining zone resources for zone switch */
> >  #endif
> >
> >         /* for node-related operations */
> > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> > index 206d03c82d96..6711283ff187 100644
> > --- a/fs/f2fs/super.c
> > +++ b/fs/f2fs/super.c
> > @@ -2385,6 +2385,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
> >         if (err)
> >                 goto restore_opts;
> >
> > +#ifdef CONFIG_BLK_DEV_ZONED
> > +       if (sbi->max_active_zones)
> > +               atomic_set(&sbi->available_active_zones,
> > +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> > +#endif
> > +
> >         /* flush outstanding errors before changing fs state */
> >         flush_work(&sbi->s_error_work);
> >
> > @@ -3932,6 +3938,11 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
> >         if (!f2fs_sb_has_blkzoned(sbi))
> >                 return 0;
> >
> > +       sbi->max_active_zones = bdev_max_active_zones(bdev);
> > +       if (sbi->max_active_zones)
> > +               atomic_set(&sbi->available_active_zones,
> > +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> > +
>
> Need to make available_active_zones not be negative, right?
> Hmm, need to make sure active_logs should be equal or less than
> max_active_zones.
>
> >         zone_sectors = bdev_zone_sectors(bdev);
> >         if (!is_power_of_2(zone_sectors)) {
> >                 f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
> > --
> > 2.34.1
> >
> >
> >
> > _______________________________________________
> > Linux-f2fs-devel mailing list
> > Linux-f2fs-devel@lists.sourceforge.net
> > https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
  

Do you mean we down the semaphore when we write the first block of the zone
and up it when the last bio of the zone finishes? That seems a bit more concise.

On Wed, Jan 17, 2024 at 7:12 AM Daeho Jeong <daeho43@gmail.com> wrote:
>
> On Tue, Jan 16, 2024 at 2:58 PM Daeho Jeong <daeho43@gmail.com> wrote:
> >
> > On Tue, Jan 16, 2024 at 6:36 AM Wenjie Qi <qwjhust@gmail.com> wrote:
> > >
> > > We can get the number of remaining available zone
> > > resources by subtracting the number of active logs from
> > > the number of max active zones of zoned devices. We can
> > > use these available zone resources to reduce the number
> > > of pending bio when switching zones.
> > > If max active zones is 0, there is no limit.
> > >
> > > Signed-off-by: Wenjie Qi <qwjhust@gmail.com>
> > > ---
> > >  fs/f2fs/data.c  | 32 +++++++++++++++++++++++++-------
> > >  fs/f2fs/f2fs.h  |  2 ++
> > >  fs/f2fs/super.c | 11 +++++++++++
> > >  3 files changed, 38 insertions(+), 7 deletions(-)
> > >
> > > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> > > index dce8defdf4c7..0b62ca296074 100644
> > > --- a/fs/f2fs/data.c
> > > +++ b/fs/f2fs/data.c
> > > @@ -392,6 +392,19 @@ static void f2fs_zone_write_end_io(struct bio *bio)
> > >         complete(&io->zone_wait);
> > >         f2fs_write_end_io(bio);
> > >  }
> > > +
> > > +static void f2fs_zone_write_end_io_nowait(struct bio *bio)
> > > +{
> > > +#ifdef CONFIG_F2FS_IOSTAT
> > > +       struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
> > > +       struct f2fs_sb_info *sbi = iostat_ctx->sbi;
> > > +#else
> > > +       struct f2fs_sb_info *sbi = (struct f2fs_sb_info *)bio->bi_private;
> > > +#endif
> > > +
> > > +       atomic_inc(&sbi->available_active_zones);
> > > +       f2fs_write_end_io(bio);
> > > +}
> > >  #endif
> >
> > I don't think this works. Let's assume we start with 2
> > available_active_zones and 4 active logs.
> > How about 4 active logs reach at the end of the zones at the same time?
>
> Sorry, I was confused. It would work. However, it might be a little clumsy.
> How about using a data structure like a counting semaphore?
> We can decrease it as we open a zone and increase it as we close a zone.
>
> >
> > >
> > >  struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
> > > @@ -1085,14 +1098,19 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
> > >                 goto next;
> > >  out:
> > >  #ifdef CONFIG_BLK_DEV_ZONED
> > > -       if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
> > > +       if (f2fs_sb_has_blkzoned(sbi) && sbi->max_active_zones && btype < META &&
> > >                         is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
> > > -               bio_get(io->bio);
> > > -               reinit_completion(&io->zone_wait);
> > > -               io->bi_private = io->bio->bi_private;
> > > -               io->bio->bi_private = io;
> > > -               io->bio->bi_end_io = f2fs_zone_write_end_io;
> > > -               io->zone_pending_bio = io->bio;
> > > +               if (!atomic_add_negative(-1, &sbi->available_active_zones)) {
> > > +                       io->bio->bi_end_io = f2fs_zone_write_end_io_nowait;
> > > +               } else {
> > > +                       atomic_inc(&sbi->available_active_zones);
> > > +                       bio_get(io->bio);
> > > +                       reinit_completion(&io->zone_wait);
> > > +                       io->bi_private = io->bio->bi_private;
> > > +                       io->bio->bi_private = io;
> > > +                       io->bio->bi_end_io = f2fs_zone_write_end_io;
> > > +                       io->zone_pending_bio = io->bio;
> > > +               }
> > >                 __submit_merged_bio(io);
> > >         }
> > >  #endif
> > > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > > index 65294e3b0bef..2aade367ac66 100644
> > > --- a/fs/f2fs/f2fs.h
> > > +++ b/fs/f2fs/f2fs.h
> > > @@ -1551,6 +1551,8 @@ struct f2fs_sb_info {
> > >
> > >  #ifdef CONFIG_BLK_DEV_ZONED
> > >         unsigned int blocks_per_blkz;           /* F2FS blocks per zone */
> > > +       unsigned int max_active_zones;          /* max zone resources of the zoned device */
> > > +       atomic_t available_active_zones;        /* remaining zone resources for zone switch */
> > >  #endif
> > >
> > >         /* for node-related operations */
> > > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> > > index 206d03c82d96..6711283ff187 100644
> > > --- a/fs/f2fs/super.c
> > > +++ b/fs/f2fs/super.c
> > > @@ -2385,6 +2385,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
> > >         if (err)
> > >                 goto restore_opts;
> > >
> > > +#ifdef CONFIG_BLK_DEV_ZONED
> > > +       if (sbi->max_active_zones)
> > > +               atomic_set(&sbi->available_active_zones,
> > > +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> > > +#endif
> > > +
> > >         /* flush outstanding errors before changing fs state */
> > >         flush_work(&sbi->s_error_work);
> > >
> > > @@ -3932,6 +3938,11 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
> > >         if (!f2fs_sb_has_blkzoned(sbi))
> > >                 return 0;
> > >
> > > +       sbi->max_active_zones = bdev_max_active_zones(bdev);
> > > +       if (sbi->max_active_zones)
> > > +               atomic_set(&sbi->available_active_zones,
> > > +                               sbi->max_active_zones - F2FS_OPTION(sbi).active_logs);
> > > +
> >
> > Need to make available_active_zones not be negative, right?
> > Hmm, need to make sure active_logs should be equal or less than
> > max_active_zones.
> >
> > >         zone_sectors = bdev_zone_sectors(bdev);
> > >         if (!is_power_of_2(zone_sectors)) {
> > >                 f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
> > > --
> > > 2.34.1
> > >
> > >
> > >
> > > _______________________________________________
> > > Linux-f2fs-devel mailing list
> > > Linux-f2fs-devel@lists.sourceforge.net
> > > https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel