From: Josef Bacik <josef@toxicpanda.com>
Date: Fri, 9 Oct 2020 09:28:20 -0400
Subject: btrfs: track ordered bytes instead of just dio ordered bytes
Git-commit: 5deb17e18e27a3502f21581ba4d086e762b86b31
Patch-mainline: v5.12-rc1
References: bsc#1135481
We track dio_bytes because the shrink delalloc code needs to know if we
have more DIO in flight than we have normal buffered IO. The reason for
this is because we can't "flush" DIO, we have to just wait on the
ordered extents to finish.
However this is true of all ordered extents. If we have more ordered
space outstanding than dirty pages we should be waiting on ordered
extents. We already are ok on this front technically, because we always
do a FLUSH_DELALLOC_WAIT loop, but I want to use the ordered counter in
the preemptive flushing code as well, so change this to count all
ordered bytes instead of just DIO ordered bytes.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Acked-by: Nikolay Borisov <nborisov@suse.com>
---
fs/btrfs/ctree.h | 2 +-
fs/btrfs/disk-io.c | 14 +++++++-------
fs/btrfs/ordered-data.c | 13 ++++++-------
fs/btrfs/space-info.c | 18 +++++++-----------
4 files changed, 21 insertions(+), 26 deletions(-)
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -775,7 +775,7 @@ struct btrfs_fs_info {
/* used to keep from writing metadata until there is a nice batch */
struct percpu_counter dirty_metadata_bytes;
struct percpu_counter delalloc_bytes;
- struct percpu_counter dio_bytes;
+ struct percpu_counter ordered_bytes;
s32 dirty_metadata_batch;
s32 delalloc_batch;
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2485,7 +2485,7 @@ int open_ctree(struct super_block *sb,
goto fail;
}
- ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL);
+ ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_srcu;
@@ -2494,7 +2494,7 @@ int open_ctree(struct super_block *sb,
ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
- goto fail_dio_bytes;
+ goto fail_ordered_bytes;
}
fs_info->dirty_metadata_batch = PAGE_SIZE *
(1 + ilog2(nr_cpu_ids));
@@ -3186,8 +3186,8 @@ fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
-fail_dio_bytes:
- percpu_counter_destroy(&fs_info->dio_bytes);
+fail_ordered_bytes:
+ percpu_counter_destroy(&fs_info->ordered_bytes);
fail_srcu:
cleanup_srcu_struct(&fs_info->subvol_srcu);
fail:
@@ -3885,9 +3885,9 @@ void close_ctree(struct btrfs_fs_info *f
percpu_counter_sum(&fs_info->delalloc_bytes));
}
- if (percpu_counter_sum(&fs_info->dio_bytes))
+ if (percpu_counter_sum(&fs_info->ordered_bytes))
btrfs_info(fs_info, "at unmount dio bytes count %lld",
- percpu_counter_sum(&fs_info->dio_bytes));
+ percpu_counter_sum(&fs_info->ordered_bytes));
btrfs_sysfs_remove_mounted(fs_info);
btrfs_sysfs_remove_fsid(fs_info->fs_devices);
@@ -3920,7 +3920,7 @@ void close_ctree(struct btrfs_fs_info *f
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
- percpu_counter_destroy(&fs_info->dio_bytes);
+ percpu_counter_destroy(&fs_info->ordered_bytes);
percpu_counter_destroy(&fs_info->bio_counter);
cleanup_srcu_struct(&fs_info->subvol_srcu);
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -224,11 +224,11 @@ static int __btrfs_add_ordered_extent(st
if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
set_bit(type, &entry->flags);
- if (dio) {
- percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes,
- fs_info->delalloc_batch);
+ percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes,
+ fs_info->delalloc_batch);
+
+ if (dio)
set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
- }
/* one ref for the tree */
refcount_set(&entry->refs, 1);
@@ -512,9 +512,8 @@ void btrfs_remove_ordered_extent(struct
btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,
false);
- if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
- percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes,
- fs_info->delalloc_batch);
+ percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
+ fs_info->delalloc_batch);
tree = &btrfs_inode->ordered_tree;
spin_lock_irq(&tree->lock);
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -377,7 +377,7 @@ static void shrink_delalloc(struct btrfs
{
struct btrfs_trans_handle *trans;
u64 delalloc_bytes;
- u64 dio_bytes;
+ u64 ordered_bytes;
u64 items;
long time_left;
int loops;
@@ -401,25 +401,20 @@ static void shrink_delalloc(struct btrfs
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
- dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
- if (delalloc_bytes == 0 && dio_bytes == 0) {
- if (trans)
- return;
- if (wait_ordered)
- btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
+ ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
+ if (delalloc_bytes == 0 && ordered_bytes == 0)
return;
- }
/*
* If we are doing more ordered than delalloc we need to just wait on
* ordered extents, otherwise we'll waste time trying to flush delalloc
* that likely won't give us the space back we need.
*/
- if (dio_bytes > delalloc_bytes)
+ if (ordered_bytes > delalloc_bytes)
wait_ordered = true;
loops = 0;
- while ((delalloc_bytes || dio_bytes) && loops < 3) {
+ while ((delalloc_bytes || ordered_bytes) && loops < 3) {
u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
btrfs_start_delalloc_roots(fs_info, nr_pages);
@@ -443,7 +438,8 @@ static void shrink_delalloc(struct btrfs
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
- dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
+ ordered_bytes = percpu_counter_sum_positive(
+ &fs_info->ordered_bytes);
}
}