You are really putting this stuff through the wringer -- nobody else hits these issues so frequently!
Can you remind us of your test setup? I'd like to figure out how you're killing these FSes so badly. And just randomly, I'd try ext4 before xfs. :) -Greg On Fri, May 27, 2011 at 4:59 AM, Fyodor Ustinov <[email protected]> wrote: > Hi! > > ceph is a very powerful thing. > > it kills ext3: > > [49531.320004] [<ffffffff811d3c4c>] ext3_new_blocks+0x40c/0x6b0 > [49531.320004] [<ffffffff811d3f11>] ext3_new_block+0x21/0x30 > [49531.320004] [<ffffffff811e798e>] ext3_xattr_block_set+0x2ae/0x790 > [49531.320004] [<ffffffff811e86ba>] ext3_xattr_set_handle+0x30a/0x4c0 > [49531.320004] [<ffffffff811e88f5>] ext3_xattr_set+0x85/0xe0 > [49531.320004] [<ffffffff81277053>] ? > security_inode_exec_permission+0x23/0x30 > [49531.320004] [<ffffffff811e8ae9>] ext3_xattr_user_set+0x49/0x50 > [49531.320004] [<ffffffff811818e4>] generic_setxattr+0x74/0x90 > [49531.320004] [<ffffffff811820c0>] __vfs_setxattr_noperm+0x50/0x1a0 > [49531.320004] [<ffffffff8116adb8>] ? inode_permission+0xa8/0xd0 > [49531.320004] [<ffffffff811822cc>] vfs_setxattr+0xbc/0xc0 > [49531.320004] [<ffffffff81182392>] setxattr+0xc2/0x150 > [49531.320004] [<ffffffff8114fec0>] ? kmem_cache_free+0x20/0x110 > [49531.320004] [<ffffffff8116ae33>] ? putname+0x33/0x50 > [49531.320004] [<ffffffff8116ef84>] ? user_path_at+0x64/0xa0 > [49531.320004] [<ffffffff815d3493>] ? schedule+0x3d3/0xa00 > [49531.320004] [<ffffffff81099c7b>] ? sys_futex+0x7b/0x180 > [49531.320004] [<ffffffff811824b5>] sys_setxattr+0x95/0xb0 > [49531.320004] [<ffffffff815ddec2>] system_call_fastpath+0x16/0x1b > > it kills btrfs: > > [91970.322381] [<ffffffff81062bbf>] warn_slowpath_common+0x7f/0xc0 > [91970.322385] [<ffffffff81062c1a>] warn_slowpath_null+0x1a/0x20 > [91970.322394] [<ffffffffa01a1b58>] btrfs_alloc_free_block+0x1f8/0x330 > [btrfs] > [91970.322403] [<ffffffffa018f6cf>] __btrfs_cow_block+0x14f/0x600 [btrfs] > [91970.322414] [<ffffffffa01ab5c0>] ? btrfs_buffer_uptodate+0x50/0x70 > [btrfs] > [91970.322422] [<ffffffffa018fc93>] btrfs_cow_block+0x113/0x240 [btrfs] > [91970.322431] [<ffffffffa0194c15>] btrfs_search_slot+0x555/0x850 [btrfs] > [91970.322441] [<ffffffffa01a82af>] btrfs_lookup_inode+0x2f/0xa0 [btrfs] > [91970.322453] [<ffffffffa01b597e>] btrfs_update_inode+0x5e/0x100 [btrfs] > [91970.322464] [<ffffffffa01b9957>] btrfs_truncate+0x587/0x600 [btrfs] > [91970.322476] [<ffffffffa01b9cef>] btrfs_setsize+0x4f/0xd0 [btrfs] > [91970.322488] [<ffffffffa01b9e2c>] btrfs_setattr+0xbc/0xd0 [btrfs] > [91970.322492] [<ffffffff8117aa89>] notify_change+0x189/0x370 > [91970.322496] [<ffffffff8115eb11>] do_truncate+0x61/0x90 > [91970.322500] [<ffffffff8116a323>] ? generic_permission+0x23/0xd0 > [91970.322504] [<ffffffff8116bec2>] ? get_write_access+0x42/0x70 > [91970.322507] [<ffffffff8115ecca>] sys_truncate+0x18a/0x1a0 > [91970.322512] [<ffffffff815ddec2>] system_call_fastpath+0x16/0x1b > > [91973.333974] [<ffffffff81062bbf>] warn_slowpath_common+0x7f/0xc0 > [91973.333978] [<ffffffff81062c1a>] warn_slowpath_null+0x1a/0x20 > [91973.333990] [<ffffffffa01b568b>] btrfs_orphan_commit_root+0xbb/0xd0 > [btrfs] > [91973.334001] [<ffffffffa01aee84>] commit_fs_roots.clone.20+0x94/0x120 > [btrfs] > [91973.334013] [<ffffffffa01afc62>] btrfs_commit_transaction+0x342/0x7c0 > [btrfs] > [91973.334017] [<ffffffff810846d0>] ? wake_up_bit+0x40/0x40 > [91973.334021] [<ffffffff81051dd1>] ? finish_task_switch+0x41/0xe0 > [91973.334033] [<ffffffffa01b00e0>] ? btrfs_commit_transaction+0x7c0/0x7c0 > [btrfs] > [91973.334044] [<ffffffffa01b00ff>] do_async_commit+0x1f/0x30 [btrfs] > [91973.334048] [<ffffffff8107ecdd>] process_one_work+0x11d/0x420 > [91973.334052] [<ffffffff8107f799>] worker_thread+0x169/0x360 > [91973.334055] [<ffffffff8107f630>] ? manage_workers.clone.21+0x240/0x240 > [91973.334059] [<ffffffff81083f36>] kthread+0x96/0xa0 > [91973.334063] [<ffffffff815defe4>] kernel_thread_helper+0x4/0x10 > [91973.334067] [<ffffffff81083ea0>] ? flush_kthread_worker+0xb0/0xb0 > [91973.334070] [<ffffffff815defe0>] ? gs_change+0x13/0x13 > > I choose what to kill next? XFS may be? (bloodthirsty grins). > > WBR, > Fyodor. > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to [email protected] > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
