[LU-11646] Getting LBUG kernel panic's

• Status: Open
• Project: Lustre
• Affects Version/s: Lustre 2.10.4
• Type: Bug
• Priority: Major
• Reporter: David Racily (Inactive)
• Assignee: Zhenyu Xu
• Resolution: Unresolved

Environment

CentOS Linux release 7.3.1611 (Core)
Linux scdm1804.jlab.org 3.10.0-514.el7.x86_64 #1 SMP Tue Nov 22 16:42:41 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux
kmod-lustre-client-2.10.4-1.el7.centos.x86_64
lustre-client-2.10.4-1.el7.centos.x86_64

• Epic/Theme: kernel-panic
• Severity: 3

Description

Experiencing LRU kernel panics and reboot of systems. 

On terminal at kernel panic the following is displayed:

kernel:[1333527.166678] LustreError: 68:0:(cl_page.c:410:cl_vmpage_page()) ASSERTION( page->cp_type == CPT_CACHEABLE ) failed:

This has happened several different systems:

KERNEL: /usr/lib/debug/lib/modules/3.10.0-514.el7.x86_64/vmlinux
DUMPFILE: /var/crash/127.0.0.1-2018-11-07-19:19:44/vmcore [PARTIAL DUMP]
CPUS: 8
DATE: Wed Nov 7 19:18:32 2018
UPTIME: 15 days, 10:25:29
LOAD AVERAGE: 4.80, 4.70, 3.88
TASKS: 635
NODENAME: scdm1804.jlab.org
RELEASE: 3.10.0-514.el7.x86_64
VERSION: #1 SMP Tue Nov 22 16:42:41 UTC 2016
MACHINE: x86_64 (3600 Mhz)
MEMORY: 95.4 GB
PANIC: "Kernel panic - not syncing: LBUG"
PID: 68
COMMAND: "khugepaged"
TASK: ffff880c402aedd0 [THREAD_INFO: ffff880c3c294000]
CPU: 7
STATE: TASK_RUNNING (PANIC)

[1333527.166678] LustreError: 68:0:(cl_page.c:410:cl_vmpage_page()) ASSERTION( page->cp_type == CPT_CACHEABLE ) failed:
[1333527.167005] LustreError: 68:0:(cl_page.c:410:cl_vmpage_page()) LBUG
[1333527.167173] Pid: 68, comm: khugepaged
[1333527.167174]
Call Trace:
[1333527.167193] [<ffffffffa0ac27ee>] libcfs_call_trace+0x4e/0x60 [libcfs]
[1333527.167200] [<ffffffffa0ac287c>] lbug_with_loc+0x4c/0xb0 [libcfs]
[1333527.167234] [<ffffffffa0c8f870>] cl_page_slice_add+0x0/0x140 [obdclass]
[1333527.167261] [<ffffffffa109dba3>] ll_releasepage+0x73/0x1a0 [lustre]
[1333527.167266] [<ffffffff81180462>] try_to_release_page+0x32/0x50
[1333527.167269] [<ffffffff811953a0>] shrink_page_list+0x950/0xb00
[1333527.167273] [<ffffffff81195bda>] shrink_inactive_list+0x1fa/0x630
[1333527.167276] [<ffffffff81196775>] shrink_lruvec+0x385/0x770
[1333527.167279] [<ffffffff810c4e83>] ? wake_up_process+0x23/0x40
[1333527.167282] [<ffffffff81196bd6>] shrink_zone+0x76/0x1a0
[1333527.167285] [<ffffffff81196f6d>] zone_reclaim+0x26d/0x2f0
[1333527.167288] [<ffffffff8118a424>] get_page_from_freelist+0x2c4/0x9f0
[1333527.167292] [<ffffffff81029569>] ? __switch_to+0xd9/0x4c0
[1333527.167295] [<ffffffff8168b070>] ? __schedule+0x3b0/0x990
[1333527.167298] [<ffffffff8118acc6>] __alloc_pages_nodemask+0x176/0x420
[1333527.167300] [<ffffffff8118e920>] ? __pagevec_lru_add_fn+0x0/0x220
[1333527.167303] [<ffffffff811e8983>] khugepaged_scan_mm_slot+0x433/0xc70
[1333527.167306] [<ffffffff811e9417>] khugepaged+0x257/0x480
[1333527.167310] [<ffffffff810b1600>] ? autoremove_wake_function+0x0/0x40
[1333527.167312] [<ffffffff811e91c0>] ? khugepaged+0x0/0x480
[1333527.167315] [<ffffffff810b052f>] kthread+0xcf/0xe0
[1333527.167317] [<ffffffff810b0460>] ? kthread+0x0/0xe0
[1333527.167321] [<ffffffff81696518>] ret_from_fork+0x58/0x90
[1333527.167324] [<ffffffff810b0460>] ? kthread+0x0/0xe0
[1333527.167326]
[1333527.167327] Kernel panic - not syncing: LBUG
[1333527.167490] CPU: 7 PID: 68 Comm: khugepaged Tainted: G W OE ------------ 3.10.0-514.el7.x86_64 #1
[1333527.167812] Hardware name: Supermicro SYS-2029BT-HNR/X11DPT-B, BIOS 2.0b 02/24/2018
[1333527.168125] ffffffffa0ae0e8b 00000000a7bd8849 ffff880c3c2976c8 ffffffff81685fac
[1333527.168453] ffff880c3c297748 ffffffff8167f3b3 ffffffff00000008 ffff880c3c297758
[1333527.168774] ffff880c3c2976f8 00000000a7bd8849 00000000a7bd8849 0000000000000246
[1333527.169096] Call Trace:
[1333527.169252] [<ffffffff81685fac>] dump_stack+0x19/0x1b
[1333527.169417] [<ffffffff8167f3b3>] panic+0xe3/0x1f2
[1333527.169586] [<ffffffffa0ac2894>] lbug_with_loc+0x64/0xb0 [libcfs]
[1333527.169787] [<ffffffffa0c8f870>] cl_vmpage_page+0x140/0x140 [obdclass]
[1333527.169969] [<ffffffffa109dba3>] ll_releasepage+0x73/0x1a0 [lustre]
[1333527.170138] [<ffffffff81180462>] try_to_release_page+0x32/0x50
[1333527.170305] [<ffffffff811953a0>] shrink_page_list+0x950/0xb00
[1333527.170471] [<ffffffff81195bda>] shrink_inactive_list+0x1fa/0x630
[1333527.170639] [<ffffffff81196775>] shrink_lruvec+0x385/0x770
[1333527.170804] [<ffffffff810c4e83>] ? wake_up_process+0x23/0x40
[1333527.170971] [<ffffffff81196bd6>] shrink_zone+0x76/0x1a0
[1333527.171135] [<ffffffff81196f6d>] zone_reclaim+0x26d/0x2f0
[1333527.171300] [<ffffffff8118a424>] get_page_from_freelist+0x2c4/0x9f0
[1333527.171469] [<ffffffff81029569>] ? __switch_to+0xd9/0x4c0
[1333527.171634] [<ffffffff8168b070>] ? __schedule+0x3b0/0x990
[1333527.171799] [<ffffffff8118acc6>] __alloc_pages_nodemask+0x176/0x420
[1333527.171967] [<ffffffff8118e920>] ? lru_deactivate_fn+0x1d0/0x1d0
[1333527.172134] [<ffffffff811e8983>] khugepaged_scan_mm_slot+0x433/0xc70
[1333527.172303] [<ffffffff811e9417>] khugepaged+0x257/0x480
[1333527.172468] [<ffffffff810b1600>] ? wake_up_atomic_t+0x30/0x30
[1333527.172633] [<ffffffff811e91c0>] ? khugepaged_scan_mm_slot+0xc70/0xc70
[1333527.172813] [<ffffffff810b052f>] kthread+0xcf/0xe0
[1333527.172975] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140
[1333527.173142] [<ffffffff81696518>] ret_from_fork+0x58/0x90
[1333527.173306] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140

 

 

Comments

[Peter Jones]

Bobijam

Can you please advise?

Thanks

Peter

[Andreas Dilger]

It is interesting that the problematic command is khugepaged. Do you have huge pages configured and in use on the client? It may be that this is interacting badly with the IO handling?

[David Racily (Inactive)]

root@scdm1804:~] cat /sys/kernel/mm/transparent_hugepage/enabled
[always] madvise never

root@scdm1804:~] cat /proc/meminfo |grep Huge
AnonHugePages: 4759552 kB
HugePages_Total: 0
HugePages_Free: 0
HugePages_Rsvd: 0
HugePages_Surp: 0
Hugepagesize: 2048 kB