running wheezy Debian 3.16.3-2~bpo70+1 system has locked up 2 nights in a row running rsync copying from remote to a ~100TB btrfs. Only job running on the server, no interactive users or anything. soft locks showed up in kern.log across many CPUs shortly before system became non-responsive. First lines of the call traces via: grep '8 17:12' /var/log/kern.log | cut -d" " --complement -f 1,2,3,4,5,6 | grep -A1 'Call Trace:' | egrep -v '\-\-|Call Trace:'
I've gone back to 3.14, which I've never had issues with. sar report from 5 minutes prior looked pretty normal, no swap depletion. Let me know if you want more info [30328.735511] [<ffffffffa0227df8>] ? btrfs_lookup_file_extent+0x38/0x40 [btrfs] [30328.747283] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.759289] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.775303] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.787311] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.799324] [<ffffffffa026cfaf>] ? btrfs_tree_read_lock+0x3f/0x110 [btrfs] [30328.839351] [<ffffffffa026cfaf>] ? btrfs_tree_read_lock+0x3f/0x110 [btrfs] [30328.855363] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.867373] [<ffffffffa026cecc>] ? btrfs_clear_lock_blocking_rw+0x4c/0xf0 [btrfs] [30328.879384] [<ffffffffa026cfaf>] ? btrfs_tree_read_lock+0x3f/0x110 [btrfs] [30328.891394] [<ffffffffa026cecc>] ? btrfs_clear_lock_blocking_rw+0x4c/0xf0 [btrfs] [30328.907407] [<ffffffffa026d353>] ? btrfs_tree_lock+0xd3/0x1e0 [btrfs] [30328.919396] [<ffffffffa026cfaf>] ? btrfs_tree_read_lock+0x3f/0x110 [btrfs] -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
