aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorDennis Zhou <dennis@kernel.org>2020-01-02 16:26:39 -0500
committerDavid Sterba <dsterba@suse.com>2020-01-20 16:41:00 +0100
commit7fe6d45e4009d9502fef32ac6222862ac17f8674 (patch)
tree870db67c211f8be19b54e97ae253f6600c846af5 /fs
parentbtrfs: make max async discard size tunable (diff)
downloadlinux-dev-7fe6d45e4009d9502fef32ac6222862ac17f8674.tar.xz
linux-dev-7fe6d45e4009d9502fef32ac6222862ac17f8674.zip
btrfs: have multiple discard lists
Non-block group destruction discarding currently only had a single list with no minimum discard length. This can lead to caravaning more meaningful discards behind a heavily fragmented block group. This adds support for multiple lists with minimum discard lengths to prevent the caravan effect. We promote block groups back up when we exceed the BTRFS_ASYNC_DISCARD_MAX_FILTER size, currently we support only 2 lists with filters of 1MB and 32KB respectively. 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>
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/discard.c105
-rw-r--r--fs/btrfs/discard.h5
-rw-r--r--fs/btrfs/free-space-cache.c55
-rw-r--r--fs/btrfs/free-space-cache.h2
5 files changed, 145 insertions, 24 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index fa6c95fdf5c6..486b9d1532eb 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -456,7 +456,7 @@ struct btrfs_full_stripe_locks_tree {
* afterwards represent monotonically decreasing discard filter sizes to
* prioritize what should be discarded next.
*/
-#define BTRFS_NR_DISCARD_LISTS 2
+#define BTRFS_NR_DISCARD_LISTS 3
#define BTRFS_DISCARD_INDEX_UNUSED 0
#define BTRFS_DISCARD_INDEX_START 1
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 5fdd82c356a4..0299981d0c62 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -22,6 +22,13 @@
#define BTRFS_DISCARD_MAX_DELAY_MSEC (1000UL)
#define BTRFS_DISCARD_MAX_IOPS (10U)
+/* Montonically decreasing minimum length filters after index 0 */
+static int discard_minlen[BTRFS_NR_DISCARD_LISTS] = {
+ 0,
+ BTRFS_ASYNC_DISCARD_MAX_FILTER,
+ BTRFS_ASYNC_DISCARD_MIN_FILTER
+};
+
static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl,
struct btrfs_block_group *block_group)
{
@@ -139,16 +146,18 @@ static struct btrfs_block_group *find_next_block_group(
* peek_discard_list - wrap find_next_block_group()
* @discard_ctl: discard control
* @discard_state: the discard_state of the block_group after state management
+ * @discard_index: the discard_index of the block_group after state management
*
* This wraps find_next_block_group() and sets the block_group to be in use.
* discard_state's control flow is managed here. Variables related to
- * discard_state are reset here as needed (eg. discard_cursor). @discard_state
- * is remembered as it may change while we're discarding, but we want the
- * discard to execute in the context determined here.
+ * discard_state are reset here as needed (eg discard_cursor). @discard_state
+ * and @discard_index are remembered as it may change while we're discarding,
+ * but we want the discard to execute in the context determined here.
*/
static struct btrfs_block_group *peek_discard_list(
struct btrfs_discard_ctl *discard_ctl,
- enum btrfs_discard_state *discard_state)
+ enum btrfs_discard_state *discard_state,
+ int *discard_index)
{
struct btrfs_block_group *block_group;
const u64 now = ktime_get_ns();
@@ -169,6 +178,7 @@ again:
}
discard_ctl->block_group = block_group;
*discard_state = block_group->discard_state;
+ *discard_index = block_group->discard_index;
} else {
block_group = NULL;
}
@@ -179,6 +189,64 @@ again:
}
/**
+ * btrfs_discard_check_filter - updates a block groups filters
+ * @block_group: block group of interest
+ * @bytes: recently freed region size after coalescing
+ *
+ * Async discard maintains multiple lists with progressively smaller filters
+ * to prioritize discarding based on size. Should a free space that matches
+ * a larger filter be returned to the free_space_cache, prioritize that discard
+ * by moving @block_group to the proper filter.
+ */
+void btrfs_discard_check_filter(struct btrfs_block_group *block_group,
+ u64 bytes)
+{
+ struct btrfs_discard_ctl *discard_ctl;
+
+ if (!block_group ||
+ !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
+ return;
+
+ discard_ctl = &block_group->fs_info->discard_ctl;
+
+ if (block_group->discard_index > BTRFS_DISCARD_INDEX_START &&
+ bytes >= discard_minlen[block_group->discard_index - 1]) {
+ int i;
+
+ remove_from_discard_list(discard_ctl, block_group);
+
+ for (i = BTRFS_DISCARD_INDEX_START; i < BTRFS_NR_DISCARD_LISTS;
+ i++) {
+ if (bytes >= discard_minlen[i]) {
+ block_group->discard_index = i;
+ add_to_discard_list(discard_ctl, block_group);
+ break;
+ }
+ }
+ }
+}
+
+/**
+ * btrfs_update_discard_index - moves a block group along the discard lists
+ * @discard_ctl: discard control
+ * @block_group: block_group of interest
+ *
+ * Increment @block_group's discard_index. If it falls of the list, let it be.
+ * Otherwise add it back to the appropriate list.
+ */
+static void btrfs_update_discard_index(struct btrfs_discard_ctl *discard_ctl,
+ struct btrfs_block_group *block_group)
+{
+ block_group->discard_index++;
+ if (block_group->discard_index == BTRFS_NR_DISCARD_LISTS) {
+ block_group->discard_index = 1;
+ return;
+ }
+
+ add_to_discard_list(discard_ctl, block_group);
+}
+
+/**
* btrfs_discard_cancel_work - remove a block_group from the discard lists
* @discard_ctl: discard control
* @block_group: block_group of interest
@@ -295,6 +363,8 @@ static void btrfs_finish_discard_pass(struct btrfs_discard_ctl *discard_ctl,
btrfs_mark_bg_unused(block_group);
else
add_to_discard_unused_list(discard_ctl, block_group);
+ } else {
+ btrfs_update_discard_index(discard_ctl, block_group);
}
}
@@ -311,25 +381,42 @@ static void btrfs_discard_workfn(struct work_struct *work)
struct btrfs_discard_ctl *discard_ctl;
struct btrfs_block_group *block_group;
enum btrfs_discard_state discard_state;
+ int discard_index = 0;
u64 trimmed = 0;
+ u64 minlen = 0;
discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
- block_group = peek_discard_list(discard_ctl, &discard_state);
+ block_group = peek_discard_list(discard_ctl, &discard_state,
+ &discard_index);
if (!block_group || !btrfs_run_discard_work(discard_ctl))
return;
/* Perform discarding */
- if (discard_state == BTRFS_DISCARD_BITMAPS)
+ minlen = discard_minlen[discard_index];
+
+ if (discard_state == BTRFS_DISCARD_BITMAPS) {
+ u64 maxlen = 0;
+
+ /*
+ * Use the previous levels minimum discard length as the max
+ * length filter. In the case something is added to make a
+ * region go beyond the max filter, the entire bitmap is set
+ * back to BTRFS_TRIM_STATE_UNTRIMMED.
+ */
+ if (discard_index != BTRFS_DISCARD_INDEX_UNUSED)
+ maxlen = discard_minlen[discard_index - 1];
+
btrfs_trim_block_group_bitmaps(block_group, &trimmed,
block_group->discard_cursor,
btrfs_block_group_end(block_group),
- 0, true);
- else
+ minlen, maxlen, true);
+ } else {
btrfs_trim_block_group_extents(block_group, &trimmed,
block_group->discard_cursor,
btrfs_block_group_end(block_group),
- 0, true);
+ minlen, true);
+ }
discard_ctl->prev_discard = trimmed;
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index f9445ee5dcc3..21a15776dac4 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -11,6 +11,11 @@ struct btrfs_block_group;
/* Discard size limits */
#define BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE (SZ_64M)
+#define BTRFS_ASYNC_DISCARD_MAX_FILTER (SZ_1M)
+#define BTRFS_ASYNC_DISCARD_MIN_FILTER (SZ_32K)
+
+/* List operations */
+void btrfs_discard_check_filter(struct btrfs_block_group *block_group, u64 bytes);
/* Work operations */
void btrfs_discard_cancel_work(struct btrfs_discard_ctl *discard_ctl,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index db90bea30a8d..a4340657b7f1 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2465,6 +2465,7 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_block_group *block_group = ctl->private;
struct btrfs_free_space *info;
int ret = 0;
+ u64 filter_bytes = bytes;
info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
if (!info)
@@ -2501,6 +2502,8 @@ link:
*/
steal_from_bitmap(ctl, info, true);
+ filter_bytes = max(filter_bytes, info->bytes);
+
ret = link_free_space(ctl, info);
if (ret)
kmem_cache_free(btrfs_free_space_cachep, info);
@@ -2513,8 +2516,10 @@ out:
ASSERT(ret != -EEXIST);
}
- if (trim_state != BTRFS_TRIM_STATE_TRIMMED)
+ if (trim_state != BTRFS_TRIM_STATE_TRIMMED) {
+ btrfs_discard_check_filter(block_group, filter_bytes);
btrfs_discard_queue_work(&fs_info->discard_ctl, block_group);
+ }
return ret;
}
@@ -3478,7 +3483,14 @@ static int trim_no_bitmap(struct btrfs_block_group *block_group,
goto next;
}
unlink_free_space(ctl, entry);
- if (max_discard_size && bytes > max_discard_size) {
+ /*
+ * Let bytes = BTRFS_MAX_DISCARD_SIZE + X.
+ * If X < BTRFS_ASYNC_DISCARD_MIN_FILTER, we won't trim
+ * X when we come back around. So trim it now.
+ */
+ if (max_discard_size &&
+ bytes >= (max_discard_size +
+ BTRFS_ASYNC_DISCARD_MIN_FILTER)) {
bytes = max_discard_size;
extent_bytes = max_discard_size;
entry->offset += max_discard_size;
@@ -3585,7 +3597,7 @@ static void end_trimming_bitmap(struct btrfs_free_space_ctl *ctl,
*/
static int trim_bitmaps(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 end, u64 minlen,
- bool async)
+ u64 maxlen, bool async)
{
struct btrfs_discard_ctl *discard_ctl =
&block_group->fs_info->discard_ctl;
@@ -3613,7 +3625,15 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
}
entry = tree_search_offset(ctl, offset, 1, 0);
- if (!entry || (async && start == offset &&
+ /*
+ * Bitmaps are marked trimmed lossily now to prevent constant
+ * discarding of the same bitmap (the reason why we are bound
+ * by the filters). So, retrim the block group bitmaps when we
+ * are preparing to punt to the unused_bgs list. This uses
+ * @minlen to determine if we are in BTRFS_DISCARD_INDEX_UNUSED
+ * which is the only discard index which sets minlen to 0.
+ */
+ if (!entry || (async && minlen && start == offset &&
btrfs_free_space_trimmed(entry))) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
@@ -3634,10 +3654,10 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
ret2 = search_bitmap(ctl, entry, &start, &bytes, false);
if (ret2 || start >= end) {
/*
- * This keeps the invariant that all bytes are trimmed
- * if BTRFS_TRIM_STATE_TRIMMED is set on a bitmap.
+ * We lossily consider a bitmap trimmed if we only skip
+ * over regions <= BTRFS_ASYNC_DISCARD_MIN_FILTER.
*/
- if (ret2 && !minlen)
+ if (ret2 && minlen <= BTRFS_ASYNC_DISCARD_MIN_FILTER)
end_trimming_bitmap(ctl, entry);
else
entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
@@ -3658,14 +3678,21 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
}
bytes = min(bytes, end - start);
- if (bytes < minlen) {
- entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
+ if (bytes < minlen || (async && maxlen && bytes > maxlen)) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
- if (async && max_discard_size && bytes > max_discard_size)
+ /*
+ * Let bytes = BTRFS_MAX_DISCARD_SIZE + X.
+ * If X < @minlen, we won't trim X when we come back around.
+ * So trim it now. We differ here from trimming extents as we
+ * don't keep individual state per bit.
+ */
+ if (async &&
+ max_discard_size &&
+ bytes > (max_discard_size + minlen))
bytes = max_discard_size;
bitmap_clear_bits(ctl, entry, start, bytes);
@@ -3773,7 +3800,7 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group,
if (ret)
goto out;
- ret = trim_bitmaps(block_group, trimmed, start, end, minlen, false);
+ ret = trim_bitmaps(block_group, trimmed, start, end, minlen, 0, false);
div64_u64_rem(end, BITS_PER_BITMAP * ctl->unit, &rem);
/* If we ended in the middle of a bitmap, reset the trimming flag */
if (rem)
@@ -3807,7 +3834,7 @@ int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
- bool async)
+ u64 maxlen, bool async)
{
int ret;
@@ -3821,7 +3848,9 @@ int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
btrfs_get_block_group_trimming(block_group);
spin_unlock(&block_group->lock);
- ret = trim_bitmaps(block_group, trimmed, start, end, minlen, async);
+ ret = trim_bitmaps(block_group, trimmed, start, end, minlen, maxlen,
+ async);
+
btrfs_put_block_group_trimming(block_group);
return ret;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 5018190a49a3..2e0a8077aa74 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -146,7 +146,7 @@ int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
bool async);
int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
- bool async);
+ u64 maxlen, bool async);
/* Support functions for running our sanity tests */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS