btrfs: calculate discard delay based on number of extents

An earlier patch keeps track of discardable_extents. These are
undiscarded extents managed by the free space cache. Here, we will use
this to dynamically calculate the discard delay interval.

There are 3 rate to consider. The first is the target convergence rate,
the rate to discard all discardable_extents over the
BTRFS_DISCARD_TARGET_MSEC time frame. This is clamped by the lower
limit, the iops limit or BTRFS_DISCARD_MIN_DELAY (1ms), and the upper
limit, BTRFS_DISCARD_MAX_DELAY (1s). We reevaluate this delay every
transaction commit.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Dennis Zhou
2020-01-02 16:26:35 -05:00
committed by David Sterba
parent 5dc7c10b87
commit a230930084
5 changed files with 88 additions and 5 deletions

View File

@@ -15,6 +15,12 @@
#define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC)
#define BTRFS_DISCARD_UNUSED_DELAY (10ULL * NSEC_PER_SEC)
/* Target completion latency of discarding all discardable extents */
#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60UL * MSEC_PER_SEC)
#define BTRFS_DISCARD_MIN_DELAY_MSEC (1UL)
#define BTRFS_DISCARD_MAX_DELAY_MSEC (1000UL)
#define BTRFS_DISCARD_MAX_IOPS (10U)
static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl,
struct btrfs_block_group *block_group)
{
@@ -235,11 +241,17 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
block_group = find_next_block_group(discard_ctl, now);
if (block_group) {
u64 delay = 0;
unsigned long delay = discard_ctl->delay;
if (now < block_group->discard_eligible_time)
delay = nsecs_to_jiffies(
block_group->discard_eligible_time - now);
/*
* This timeout is to hopefully prevent immediate discarding
* in a recently allocated block group.
*/
if (now < block_group->discard_eligible_time) {
u64 bg_timeout = block_group->discard_eligible_time - now;
delay = max(delay, nsecs_to_jiffies(bg_timeout));
}
mod_delayed_work(discard_ctl->discard_workers,
&discard_ctl->work, delay);
@@ -342,6 +354,39 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl)
test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags));
}
/**
* btrfs_discard_calc_delay - recalculate the base delay
* @discard_ctl: discard control
*
* Recalculate the base delay which is based off the total number of
* discardable_extents. Clamp this between the lower_limit (iops_limit or 1ms)
* and the upper_limit (BTRFS_DISCARD_MAX_DELAY_MSEC).
*/
void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
{
s32 discardable_extents;
u32 iops_limit;
unsigned long delay;
unsigned long lower_limit = BTRFS_DISCARD_MIN_DELAY_MSEC;
discardable_extents = atomic_read(&discard_ctl->discardable_extents);
if (!discardable_extents)
return;
spin_lock(&discard_ctl->lock);
iops_limit = READ_ONCE(discard_ctl->iops_limit);
if (iops_limit)
lower_limit = max_t(unsigned long, lower_limit,
MSEC_PER_SEC / iops_limit);
delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
delay = clamp(delay, lower_limit, BTRFS_DISCARD_MAX_DELAY_MSEC);
discard_ctl->delay = msecs_to_jiffies(delay);
spin_unlock(&discard_ctl->lock);
}
/**
* btrfs_discard_update_discardable - propagate discard counters
* @block_group: block_group of interest
@@ -464,6 +509,8 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
atomic_set(&discard_ctl->discardable_extents, 0);
atomic64_set(&discard_ctl->discardable_bytes, 0);
discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
}
void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)