From cb6cbab79055ca207ad88bc54226b48ececdcef0 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 27 Sep 2023 13:47:01 -0400
Subject: [PATCH] btrfs: adjust overcommit logic when very close to full
A user reported some unpleasant behavior with very small file systems.
The reproducer is this
$ mkfs.btrfs -f -m single -b 8g /dev/vdb
$ mount /dev/vdb /mnt/test
$ dd if=/dev/zero of=/mnt/test/testfile bs=512M count=20
This will result in usage that looks like this
Overall:
Device size: 8.00GiB
Device allocated: 8.00GiB
Device unallocated: 1.00MiB
Device missing: 0.00B
Device slack: 2.00GiB
Used: 5.47GiB
Free (estimated): 2.52GiB (min: 2.52GiB)
Free (statfs, df): 0.00B
Data ratio: 1.00
Metadata ratio: 1.00
Global reserve: 5.50MiB (used: 0.00B)
Multiple profiles: no
Data,single: Size:7.99GiB, Used:5.46GiB (68.41%)
/dev/vdb 7.99GiB
Metadata,single: Size:8.00MiB, Used:5.77MiB (72.07%)
/dev/vdb 8.00MiB
System,single: Size:4.00MiB, Used:16.00KiB (0.39%)
/dev/vdb 4.00MiB
Unallocated:
/dev/vdb 1.00MiB
As you can see we've gotten ourselves quite full with metadata, with all
of the disk being allocated for data.
On smaller file systems there's not a lot of time before we get full, so
our overcommit behavior bites us here. Generally speaking data
reservations result in chunk allocations as we assume reservation ==
actual use for data. This means at any point we could end up with a
chunk allocation for data, and if we're very close to full we could do
this before we have a chance to figure out that we need another metadata
chunk.
Address this by adjusting the overcommit logic. Simply put we need to
take away 1 chunk from the available chunk space in case of a data
reservation. This will allow us to stop overcommitting before we
potentially lose this space to a data allocation. With this fix in
place we properly allocate a metadata chunk before we're completely
full, allowing for enough slack space in metadata.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/space-info.c | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 45114df89de13..571bb13587d5e 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -345,8 +345,10 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
enum btrfs_reserve_flush_enum flush)
{
+ struct btrfs_space_info *data_sinfo;
u64 profile;
u64 avail;
+ u64 data_chunk_size;
int factor;
if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM)
@@ -364,6 +366,36 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
*/
factor = btrfs_bg_type_to_factor(profile);
avail = div_u64(avail, factor);
+ if (avail == 0)
+ return 0;
+
+ /*
+ * Calculate the data_chunk_size, space_info->chunk_size is the
+ * "optimal" chunk size based on the fs size. However when we actually
+ * allocate the chunk we will strip this down further, making it no more
+ * than 10% of the disk or 1G, whichever is smaller.
+ */
+ data_sinfo = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
+ data_chunk_size = min(data_sinfo->chunk_size,
+ mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
+ data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+
+ /*
+ * Since data allocations immediately use block groups as part of the
+ * reservation, because we assume that data reservations will == actual
+ * usage, we could potentially overcommit and then immediately have that
+ * available space used by a data allocation, which could put us in a
+ * bind when we get close to filling the file system.
+ *
+ * To handle this simply remove the data_chunk_size from the available
+ * space. If we are relatively empty this won't affect our ability to
+ * overcommit much, and if we're very close to full it'll keep us from
+ * getting into a position where we've given ourselves very little
+ * metadata wiggle room.
+ */
+ if (avail <= data_chunk_size)
+ return 0;
+ avail -= data_chunk_size;
/*
* If we aren't flushing all things, let us overcommit up to
--
GitLab