Hi list,
After upgrading my Fedora 23 system from 4.4.12 to 4.7.2, I'm seeing one
btrfs-cleaner process stuck at 100% CPU. The problem disappears when
going back to 4.4 kernel (4.4.17), but is also present with Fedora
kernel 4.6.6-200.fc23.
4.4.12 and 4.4.17 are built from source, with 2 patches (see attached).
4.7.2 is built from source without any patch.
Main Btrfs is RAID1 on 2 disks behind bcache, with 13 sub-volumes, and
less than 300 snapshots (more details below). There are 2 other Btrfs
used for backup, so not mounted when the problem appears.
The btrfs-cleaner jumps at 100% after about ~15 min uptime. I let it run
about ~18 hours, btrfs-cleaner stayed at 100%. Unmounting all the
sub-volumes clears the problem. There is no error in the logs, all the
sub-volumes are mounted ok, I can use the system. I did a scrub and
balance, which finished without any error.
I'm back on 4.4.17 now, but what can I do to debug this problem ?
[jdg@tiare ~]$ sudo btrfs fi sh
Label: none uuid: c5b8386b-b81d-4473-9340-7b8a74fc3a3c
Total devices 2 FS bytes used 1.04TiB
devid 1 size 1.82TiB used 1.08TiB path /dev/bcache0
devid 2 size 1.82TiB used 1.08TiB path /dev/bcache1
Label: none uuid: e86cf0f5-ae16-408c-a4f8-19727aa2a3d4
Total devices 1 FS bytes used 191.20GiB
devid 1 size 279.46GiB used 240.06GiB path /dev/sdd
Label: none uuid: d0d09c79-42d7-4958-bccb-480eb27aec38
Total devices 1 FS bytes used 611.38GiB
devid 1 size 931.51GiB used 620.07GiB path /dev/sde
[jdg@tiare ~]$ sudo btrfs fi usage /home/jdg/
Overall:
Device size: 3.64TiB
Device allocated: 2.16TiB
Device unallocated: 1.48TiB
Device missing: 0.00B
Used: 2.08TiB
Free (estimated): 798.35GiB (min: 798.35GiB)
Data ratio: 2.00
Metadata ratio: 2.00
Global reserve: 512.00MiB (used: 0.00B)
Data,RAID1: Size:1.08TiB, Used:1.04TiB
/dev/bcache0 1.08TiB
/dev/bcache1 1.08TiB
Metadata,RAID1: Size:4.00GiB, Used:2.74GiB
/dev/bcache0 4.00GiB
/dev/bcache1 4.00GiB
System,RAID1: Size:32.00MiB, Used:256.00KiB
/dev/bcache0 32.00MiB
/dev/bcache1 32.00MiB
Unallocated:
/dev/bcache0 757.99GiB
/dev/bcache1 757.99GiB
[jdg@tiare ~]$ mount -t btrfs
/dev/bcache0 on /var/lib/pgsql type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1131,subvol=/pgsql)
/dev/bcache0 on /home/SysNux type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1062,subvol=/SysNux)
/dev/bcache0 on /home/Vidéos type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1281,subvol=/Vidéos)
/dev/bcache0 on /var/lib/libvirt/images type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1136,subvol=/images-vm)
/dev/bcache0 on /mnt/snapshots type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1292,subvol=/Snapshots)
/dev/bcache0 on /home/Photos type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=676,subvol=/Photos)
/dev/bcache0 on /home/vaiana type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1076,subvol=/vaiana)
/dev/bcache0 on /home/Films type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=258,subvol=/Films)
/dev/bcache0 on /home/Partage type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1059,subvol=/Partage)
/dev/bcache0 on /home/jdg type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1073,subvol=/jdg)
/dev/bcache0 on /home/michael type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1075,subvol=/michael)
/dev/bcache0 on /home/cathy type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=1074,subvol=/cathy)
/dev/bcache0 on /home/Musique type btrfs
(rw,noatime,nodiratime,seclabel,compress=zlib,ssd,space_cache,autodefrag,skip_balance,subvolid=961,subvol=/Musique)
Thanks,
--
Jean-Denis Girard
SysNux Systèmes Linux en Polynésie française
https://www.sysnux.pf/ Tél: +689 40.50.10.40 / GSM: +689 87.797.527
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 977e715..11fd981 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1516,27 +1516,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
- BTRFS_INODE_PREALLOC)) {
- ret = check_can_nocow(inode, pos, &write_bytes);
- if (ret < 0)
- break;
- if (ret > 0) {
- /*
- * For nodata cow case, no need to reserve
- * data space.
- */
- only_release_metadata = true;
- /*
- * our prealloc extent may be smaller than
- * write_bytes, so scale down.
- */
- num_pages = DIV_ROUND_UP(write_bytes + offset,
- PAGE_CACHE_SIZE);
- reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- goto reserve_metadata;
- }
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ check_can_nocow(inode, pos, &write_bytes) > 0) {
+ /*
+ * For nodata cow case, no need to reserve
+ * data space.
+ */
+ only_release_metadata = true;
+ /*
+ * our prealloc extent may be smaller than
+ * write_bytes, so scale down.
+ */
+ num_pages = DIV_ROUND_UP(write_bytes + offset,
+ PAGE_CACHE_SIZE);
+ reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+ goto reserve_metadata;
}
+
ret = btrfs_check_data_free_space(inode, pos, write_bytes);
if (ret < 0)
break;
diff -Naur linux-4.4.6.ORIG/fs/btrfs/ctree.c linux-4.4.6/fs/btrfs/ctree.c
--- linux-4.4.6.ORIG/fs/btrfs/ctree.c 2016-01-10 13:01:32.000000000 -1000
+++ linux-4.4.6/fs/btrfs/ctree.c 2016-03-30 06:19:16.397973820 -1000
@@ -20,6 +20,7 @@
#include <linux/slab.h>
#include <linux/rbtree.h>
#include "ctree.h"
+#include <linux/vmalloc.h>
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
@@ -5362,10 +5363,13 @@
goto out;
}
- tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
+ tmp_buf = kmalloc(left_root->nodesize, GFP_KERNEL | __GFP_NOWARN);
if (!tmp_buf) {
- ret = -ENOMEM;
- goto out;
+ tmp_buf = vmalloc(left_root->nodesize);
+ if (!tmp_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
}
left_path->search_commit_root = 1;
@@ -5566,7 +5570,7 @@
out:
btrfs_free_path(left_path);
btrfs_free_path(right_path);
- kfree(tmp_buf);
+ kvfree(tmp_buf);
return ret;
}
