This is a note to let you know that I've just added the patch titled btrfs: make the bg_reclaim_threshold per-space info to the 5.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: btrfs-make-the-bg_reclaim_threshold-per-space-info.patch and it can be found in the queue-5.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit e4ae7bab98014a3d07e59efe09a829cb15cb518f Author: Josef Bacik <josef@xxxxxxxxxxxxxx> Date: Tue Mar 29 01:56:06 2022 -0700 btrfs: make the bg_reclaim_threshold per-space info [ Upstream commit bb5a098d9791f184899499531ff4411089e2a5e0 ] For non-zoned file systems it's useful to have the auto reclaim feature, however there are different use cases for non-zoned, for example we may not want to reclaim metadata chunks ever, only data chunks. Move this sysfs flag to per-space_info. This won't affect current users because this tunable only ever did anything for zoned, and that is currently hidden behind BTRFS_CONFIG_DEBUG. Tested-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx> Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx> [ jth restore global bg_reclaim_threshold ] Signed-off-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx> Reviewed-by: David Sterba <dsterba@xxxxxxxx> Signed-off-by: David Sterba <dsterba@xxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 01a408db5683..ef84bc5030cd 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2630,16 +2630,19 @@ int __btrfs_add_free_space(struct btrfs_block_group *block_group, static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, u64 bytenr, u64 size, bool used) { - struct btrfs_fs_info *fs_info = block_group->fs_info; + struct btrfs_space_info *sinfo = block_group->space_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; - const int bg_reclaim_threshold = READ_ONCE(fs_info->bg_reclaim_threshold); + int bg_reclaim_threshold = 0; bool initial = (size == block_group->length); u64 reclaimable_unusable; WARN_ON(!initial && offset + size > block_group->zone_capacity); + if (!initial) + bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); + spin_lock(&ctl->tree_lock); if (!used) to_free = size; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 56a7c99fc03e..85608acb9557 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -181,6 +181,12 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info) found->full = 0; } +/* + * Block groups with more than this value (percents) of unusable space will be + * scheduled for background reclaim. + */ +#define BTRFS_DEFAULT_ZONED_RECLAIM_THRESH (75) + static int create_space_info(struct btrfs_fs_info *info, u64 flags) { @@ -203,6 +209,9 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) INIT_LIST_HEAD(&space_info->priority_tickets); space_info->clamp = 1; + if (btrfs_is_zoned(info)) + space_info->bg_reclaim_threshold = BTRFS_DEFAULT_ZONED_RECLAIM_THRESH; + ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) return ret; diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index d841fed73492..a803e29bd781 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -24,6 +24,12 @@ struct btrfs_space_info { the space info if we had an ENOSPC in the allocator. */ + /* + * Once a block group drops below this threshold (percents) we'll + * schedule it for reclaim. + */ + int bg_reclaim_threshold; + int clamp; /* Used to scale our threshold for preemptive flushing. The value is >> clamp, so turns out to be a 2^clamp divisor. */ diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index ba78ca5aabbb..43845cae0c74 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -722,6 +722,42 @@ SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); +static ssize_t btrfs_sinfo_bg_reclaim_threshold_show(struct kobject *kobj, + struct kobj_attribute *a, + char *buf) +{ + struct btrfs_space_info *space_info = to_space_info(kobj); + ssize_t ret; + + ret = sysfs_emit(buf, "%d\n", READ_ONCE(space_info->bg_reclaim_threshold)); + + return ret; +} + +static ssize_t btrfs_sinfo_bg_reclaim_threshold_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_space_info *space_info = to_space_info(kobj); + int thresh; + int ret; + + ret = kstrtoint(buf, 10, &thresh); + if (ret) + return ret; + + if (thresh != 0 && (thresh <= 50 || thresh > 100)) + return -EINVAL; + + WRITE_ONCE(space_info->bg_reclaim_threshold, thresh); + + return len; +} + +BTRFS_ATTR_RW(space_info, bg_reclaim_threshold, + btrfs_sinfo_bg_reclaim_threshold_show, + btrfs_sinfo_bg_reclaim_threshold_store); + /* * Allocation information about block group types. * @@ -738,6 +774,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), + BTRFS_ATTR_PTR(space_info, bg_reclaim_threshold), NULL, }; ATTRIBUTE_GROUPS(space_info); diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index c424417e19bb..199b69670fa2 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -10,11 +10,7 @@ #include "block-group.h" #include "btrfs_inode.h" -/* - * Block groups with more than this value (percents) of unusable space will be - * scheduled for background reclaim. - */ -#define BTRFS_DEFAULT_RECLAIM_THRESH 75 +#define BTRFS_DEFAULT_RECLAIM_THRESH (75) struct btrfs_zoned_device_info { /*