search for: bdi_writeback_thread

I suspect this might be related to previous btrfs errors I''ve had on the same filesystem. See: http://python.ca/nas/linux/btrfs_bug.txt The most recent kernel message is: WARNING: at fs/btrfs/extent-tree.c:8239 btrfs_free_block_groups+0x218/0x275() Hardware name: MS-7388 Modules linked in: udf crc_itu_t isofs loop nls_iso8859_1 vboxnetflt vboxdrv nls_utf8 nls_cp437

...l_irq_save+0x15/0x1b Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff8113f8e2>] wb_do_writeback+0x86/0x19d Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff81060bb4>] ? process_timeout+0x0/0x10 Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff8113fa81>] bdi_writeback_thread+0x88/0x1e5 Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff8113f9f9>] ? bdi_writeback_thread+0x0/0x1e5 Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff8106ebaf>] kthread+0x84/0x8c Jul 8 11:49:40 xback2 kernel: [74920.681032] [<ffffffff8100a9e4>] kernel_threa...

Hi, Recently, I made a btrfs to use. And I met slowness problem. Trying to diag it. I found this: 1. dd if=/dev/zero of=test count=1024 bs=1MB This is fast, at about 25MB/s, and reasonable iowait. 2. dd if=/dev/zero of=test count=1 bs=1GB This is pretty slow, at about 1.5MB/s, and 90%+ iowait, constantly. May I know why it works like this? Thanks. -- To unsubscribe from this list: send the

...ffffff811af850>] writeback_sb_inodes+0x1a0/0x350 [ 386.319685] [<ffffffff811afbbf>] wb_writeback+0xef/0x340 [ 386.319693] [<ffffffff811b1468>] wb_do_writeback+0xb8/0x1d0 [ 386.319701] [<ffffffff81067c20>] ? usleep_range+0x50/0x50 [ 386.319709] [<ffffffff811b160b>] bdi_writeback_thread+0x8b/0x290 [ 386.319717] [<ffffffff811b1580>] ? wb_do_writeback+0x1d0/0x1d0 [ 386.319723] [<ffffffff8107c3f3>] kthread+0x93/0xa0 [ 386.319730] [<ffffffff816a7a84>] kernel_thread_helper+0x4/0x10 [ 386.319738] [<ffffffff8107c360>] ? flush_kthread_worker+0xb0/0xb0 [ 38...

I''ve been working on running down intermittent ENOSPC issues. I can only seem to replicate ENOSPC errors when running zlib compression. However, I have been seeing similar ENOSPC errors to a lesser extent when playing with the LZ4HC patches. I apologize for not following up on this sooner, but I had drifted away from using zlib, and didn''t notice there was still an issue. My

...161 Jun 11 10:59:38 mithrandir kernel: [ 620.646824] [<ffffffff8139e665>] ? _raw_spin_unlock_irqrestore+0x20/0x2b Jun 11 10:59:38 mithrandir kernel: [ 620.646827] [<ffffffff8103c036>] ? del_timer+0x6b/0x79 Jun 11 10:59:38 mithrandir kernel: [ 620.646830] [<ffffffff810ce83d>] bdi_writeback_thread+0x6d/0x151 Jun 11 10:59:38 mithrandir kernel: [ 620.646833] [<ffffffff810ce7d0>] ? wb_do_writeback+0x161/0x161 Jun 11 10:59:38 mithrandir kernel: [ 620.646836] [<ffffffff81047bb0>] kthread+0x7f/0x87 Jun 11 10:59:38 mithrandir kernel: [ 620.646839] [<ffffffff8139fd54>] kernel...

We need an smb_mb() before waitqueue_active to avoid missing wakeups. Before Mitch was hitting a deadlock between the ordered flushers and the transaction commit because the ordered flushers were waiting for more refs and were never woken up, so those smp_mb()''s are the most important. Everything else I added for correctness sake and to avoid getting bitten by this again somewhere else.