Project

General

Profile

Actions

Bug #5036

closed

`ls` hangs on random folder

Added by Quan Tong Anh almost 11 years ago. Updated over 10 years ago.

Status:
Resolved
Priority:
High
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

Source:
other
Tags:
Backport:
Regression:
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

strace hangs at "getdents(3,": https://clbin.com/LktUw

The informations when dumping via SysRq:

kernel: ls              D ffff88062b3bdac8     0 10297   9519 0x00000080
kernel: ffff88062c2a1988 0000000000000086 ffff88062c2a1908 ffff880600000001
kernel: 0000000000012b00 ffff88062c2a1fd8 ffff88062c2a0010 0000000000012b00
kernel: ffff88062c2a1fd8 0000000000012b00 ffff88062aa434e0 ffff88062b3bd520
kernel: Call Trace:
kernel: [<ffffffff8151110f>] schedule+0x3f/0x60
kernel: [<ffffffff815115ad>] schedule_timeout+0x1fd/0x2e0
kernel: [<ffffffff8107f8e5>] ? queue_work_on+0x25/0x30
kernel: [<ffffffff8107faaf>] ? queue_work+0x1f/0x30
kernel: [<ffffffff8107fb6d>] ? queue_delayed_work+0x2d/0x40
kernel: [<ffffffff81510f43>] wait_for_common+0xd3/0x180
kernel: [<ffffffff810575d0>] ? try_to_wake_up+0x2a0/0x2a0
kernel: [<ffffffff8151102d>] wait_for_completion_killable+0x1d/0x30
kernel: [<ffffffffa02a68c5>] ceph_mdsc_do_request+0x135/0x2b0 [ceph]
kernel: [<ffffffffa028ea97>] ceph_lookup+0x117/0x300 [ceph]
kernel: [<ffffffff81170865>] d_alloc_and_lookup+0x45/0x90
kernel: [<ffffffff8117bb95>] ? d_lookup+0x35/0x60
kernel: [<ffffffff811725d0>] do_lookup+0x2e0/0x330
kernel: [<ffffffff81173b2f>] link_path_walk+0x18f/0x920
kernel: [<ffffffff8117275e>] ? path_init+0x13e/0x3d0
kernel: [<ffffffff8107f8e5>] ? queue_work_on+0x25/0x30
kernel: [<ffffffff81174925>] path_lookupat+0x55/0x680
kernel: [<ffffffff81174f81>] do_path_lookup+0x31/0xc0
kernel: [<ffffffff81175cc9>] user_path_at_empty+0x59/0xa0
kernel: [<ffffffffa0288c59>] ? ceph_do_getattr+0xf9/0x190 [ceph]
kernel: [<ffffffffa0288d36>] ? ceph_getattr+0x46/0x100 [ceph]
kernel: [<ffffffff8116a778>] ? cp_new_stat+0xf8/0x110
kernel: [<ffffffff81175d21>] user_path_at+0x11/0x20
kernel: [<ffffffff8116a85c>] vfs_fstatat+0x4c/0x90
kernel: [<ffffffff8116a90e>] vfs_lstat+0x1e/0x20
kernel: [<ffffffff8116a934>] sys_newlstat+0x24/0x50
kernel: [<ffffffff810c3fbf>] ? audit_syscall_entry+0x1bf/0x1f0
kernel: [<ffffffff8151b182>] system_call_fastpath+0x16/0x1b

This problem happened with both of mount types: kernel module and FUSE.
# uname -r
3.0.71-1.el6.elrepo.x86_64

Please let me know if you need any further information.

Actions

Also available in: Atom PDF