btrfs: zoned: revive max_zone_append_bytes

This patch is basically a revert of commit 5a80d1c6a270 ("btrfs: zoned:
remove max_zone_append_size logic"), but without unnecessary ASSERT and
check. The max_zone_append_size will be used as a hint to estimate the
number of extents to cover delalloc/writeback region in the later commits.

The size of a ZONE APPEND bio is also limited by queue_max_segments(), so
this commit considers it to calculate max_zone_append_size. Technically, a
bio can be larger than queue_max_segments() * PAGE_SIZE if the pages are
contiguous. But, it is safe to consider "queue_max_segments() * PAGE_SIZE"
as an upper limit of an extent size to calculate the number of extents
needed to write data.

Reviewed-by: Johannes Thumshirn <[email protected]>
Signed-off-by: Naohiro Aota <[email protected]>
Signed-off-by: David Sterba <[email protected]>

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 64c65d0f7d06760280559c457882a3be2d72af62..b2a161227ac518ec098bb33d25f0911cd9651c0f 100644 (file)
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1070,6 +1070,8 @@ struct btrfs_fs_info {
         */
        u64 zone_size;
 
         */
        u64 zone_size;
 

+       /* Max size to emit ZONE_APPEND write command */
+       u64 max_zone_append_size;

        struct mutex zoned_meta_io_lock;
        spinlock_t treelog_bg_lock;
        u64 treelog_bg;
        struct mutex zoned_meta_io_lock;
        spinlock_t treelog_bg_lock;
        u64 treelog_bg;

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 79a2d48a5251656b05b8dd9db40e8d0f237a6155..bdc533fa80ae68b8d28358faa3fbef2074e0607c 100644 (file)
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -415,6 +415,16 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
        nr_sectors = bdev_nr_sectors(bdev);
        zone_info->zone_size_shift = ilog2(zone_info->zone_size);
        zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
        nr_sectors = bdev_nr_sectors(bdev);
        zone_info->zone_size_shift = ilog2(zone_info->zone_size);
        zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);

+       /*
+        * We limit max_zone_append_size also by max_segments *
+        * PAGE_SIZE. Technically, we can have multiple pages per segment. But,
+        * since btrfs adds the pages one by one to a bio, and btrfs cannot
+        * increase the metadata reservation even if it increases the number of
+        * extents, it is safe to stick with the limit.
+        */
+       zone_info->max_zone_append_size =
+               min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+                     (u64)bdev_max_segments(bdev) << PAGE_SHIFT);

        if (!IS_ALIGNED(nr_sectors, zone_sectors))
                zone_info->nr_zones++;
 
        if (!IS_ALIGNED(nr_sectors, zone_sectors))
                zone_info->nr_zones++;
 


@@ -640,6 +650,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
        u64 zoned_devices = 0;
        u64 nr_devices = 0;
        u64 zone_size = 0;
        u64 zoned_devices = 0;
        u64 nr_devices = 0;
        u64 zone_size = 0;

+       u64 max_zone_append_size = 0;

        const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED);
        int ret = 0;
 
        const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED);
        int ret = 0;
 


@@ -674,6 +685,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
                                ret = -EINVAL;
                                goto out;
                        }
                                ret = -EINVAL;
                                goto out;
                        }

+                       if (!max_zone_append_size ||
+                           (zone_info->max_zone_append_size &&
+                            zone_info->max_zone_append_size < max_zone_append_size))
+                               max_zone_append_size =
+                                       zone_info->max_zone_append_size;

                }
                nr_devices++;
        }
                }
                nr_devices++;
        }


@@ -723,6 +739,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
        }
 
        fs_info->zone_size = zone_size;
        }
 
        fs_info->zone_size = zone_size;

+       fs_info->max_zone_append_size = max_zone_append_size;

        fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
 
        /*
        fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
 
        /*

diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 6b2eec99162bfcb124c947f79b83ca17fa7d846e..9caeab07fd3808ad203c95ee2e62d9009573df04 100644 (file)
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -19,6 +19,7 @@ struct btrfs_zoned_device_info {
         */
        u64 zone_size;
        u8  zone_size_shift;
         */
        u64 zone_size;
        u8  zone_size_shift;

+       u64 max_zone_append_size;

        u32 nr_zones;
        unsigned int max_active_zones;
        atomic_t active_zones_left;
        u32 nr_zones;
        unsigned int max_active_zones;
        atomic_t active_zones_left;