@@ -467,6 +467,8 @@ struct btrfs_discard_ctl {
struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
atomic_t discardable_extents;
atomic64_t discardable_bytes;
+ u32 delay;
+ u32 iops_limit;
};
/* delayed seq elem */
@@ -16,6 +16,11 @@
/* This is an initial delay to give some chance for lba reuse. */
#define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC)
+/* Target completion latency of discarding all discardable extents. */
+#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60ULL * MSEC_PER_SEC)
+#define BTRFS_DISCARD_MAX_DELAY (10000UL)
+#define BTRFS_DISCARD_MAX_IOPS (10UL)
+
static struct list_head *btrfs_get_discard_list(
struct btrfs_discard_ctl *discard_ctl,
struct btrfs_block_group_cache *cache)
@@ -232,11 +237,17 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
cache = find_next_cache(discard_ctl, now);
if (cache) {
- u64 delay = 0;
+ u32 delay = discard_ctl->delay;
+
+ /*
+ * This timeout is to hopefully prevent immediate discarding
+ * in a recently allocated block group.
+ */
+ if (now < cache->discard_eligible_time) {
+ u64 bg_timeout = cache->discard_eligible_time - now;
- if (now < cache->discard_eligible_time)
- delay = nsecs_to_jiffies(cache->discard_eligible_time -
- now);
+ delay = max_t(u64, delay, nsecs_to_jiffies(bg_timeout));
+ }
mod_delayed_work(discard_ctl->discard_workers,
&discard_ctl->work,
@@ -337,6 +348,37 @@ 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 with the iops_limit and
+ * BTRFS_DISCARD_MAX_DELAY.
+ */
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
+{
+ s32 discardable_extents =
+ atomic_read(&discard_ctl->discardable_extents);
+ s32 iops_limit;
+ unsigned long delay;
+
+ if (!discardable_extents)
+ return;
+
+ spin_lock(&discard_ctl->lock);
+
+ iops_limit = READ_ONCE(discard_ctl->iops_limit);
+ if (iops_limit)
+ iops_limit = MSEC_PER_SEC / iops_limit;
+
+ delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
+ delay = clamp_t(s32, delay, iops_limit, BTRFS_DISCARD_MAX_DELAY);
+ discard_ctl->delay = msecs_to_jiffies(delay);
+
+ spin_unlock(&discard_ctl->lock);
+}
+
/**
* btrfs_discard_update_discardable - propagate discard counters
* @cache: block_group of interest
@@ -463,6 +505,8 @@ 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;
+ discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
}
void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
@@ -25,6 +25,7 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
/* Update operations. */
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);
void btrfs_discard_update_discardable(struct btrfs_block_group_cache *cache,
struct btrfs_free_space_ctl *ctl);
@@ -2921,8 +2921,10 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
cond_resched();
}
- if (btrfs_test_opt(fs_info, DISCARD_ASYNC))
+ if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) {
+ btrfs_discard_calc_delay(&fs_info->discard_ctl);
btrfs_discard_schedule_work(&fs_info->discard_ctl, true);
+ }
/*
* Transaction is finished. We don't need the lock anymore. We
@@ -341,9 +341,40 @@ static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj,
}
BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show);
+static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj,
+ struct kobj_attribute *a,
+ char *buf)
+{
+ struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ READ_ONCE(fs_info->discard_ctl.iops_limit));
+}
+
+static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj,
+ struct kobj_attribute *a,
+ const char *buf, size_t len)
+{
+ struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+ struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
+ u32 iops_limit;
+ int ret;
+
+ ret = kstrtou32(buf, 10, &iops_limit);
+ if (ret)
+ return -EINVAL;
+
+ WRITE_ONCE(discard_ctl->iops_limit, iops_limit);
+
+ return len;
+}
+BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show,
+ btrfs_discard_iops_limit_store);
+
static const struct attribute *discard_attrs[] = {
BTRFS_ATTR_PTR(discard, discardable_extents),
BTRFS_ATTR_PTR(discard, discardable_bytes),
+ BTRFS_ATTR_PTR(discard, iops_limit),
NULL,
};