************************ crashinfo ************************* /exports/testreports/42551/testresults/sanity-pfl-ldiskfs-DNE-centos7_x86_64-centos7_x86_64/oleg250-client-timeout-core (3.10.0-7.9-debug) +==========================+ | *** Crashinfo v1.3.7 *** | +==========================+ +++WARNING+++ PARTIAL DUMP with size(vmcore) < 25% size(RAM) KERNEL: /tmp/crash-anaysis.1Ej2f/vmlinux [TAINTED] DUMPFILE: /exports/testreports/42551/testresults/sanity-pfl-ldiskfs-DNE-centos7_x86_64-centos7_x86_64/oleg250-client-timeout-core [PARTIAL DUMP] CPUS: 4 DATE: Wed May 8 19:04:06 EDT 2024 UPTIME: 01:03:18 LOAD AVERAGE: 5.00, 4.99, 4.89 TASKS: 161 NODENAME: oleg250-client.virtnet RELEASE: 3.10.0-7.9-debug VERSION: #1 SMP Sat Mar 26 23:28:42 EDT 2022 MACHINE: x86_64 (2399 Mhz) MEMORY: 4 GB PANIC: "" +--------------------------+ >------------------------| Per-cpu Stacks ('bt -a') |------------------------< +--------------------------+ -- CPU#0 -- PID=0 CPU=0 CMD=swapper/0 #-1 native_safe_halt+0xb, 449 bytes of data #0 default_idle+0x1e #1 default_enter_idle+0x45 #2 cpuidle_enter_state+0x40 #3 cpuidle_idle_call+0xd8 #4 arch_cpu_idle+0xe #5 cpu_startup_entry+0x14a #6 rest_init+0x8e #7 start_kernel+0x456 #8 x86_64_start_reservations+0x2a #9 x86_64_start_kernel+0x152 #10 start_cpu+0x5 -- CPU#1 -- PID=0 CPU=1 CMD=swapper/1 #-1 native_safe_halt+0xb, 449 bytes of data #0 default_idle+0x1e #1 default_enter_idle+0x45 #2 cpuidle_enter_state+0x40 #3 cpuidle_idle_call+0xd8 #4 arch_cpu_idle+0xe #5 cpu_startup_entry+0x14a #6 start_secondary+0x1eb #7 start_cpu+0x5 -- CPU#2 -- PID=0 CPU=2 CMD=swapper/2 #-1 native_safe_halt+0xb, 449 bytes of data #0 default_idle+0x1e #1 default_enter_idle+0x45 #2 cpuidle_enter_state+0x40 #3 cpuidle_idle_call+0xd8 #4 arch_cpu_idle+0xe #5 cpu_startup_entry+0x14a #6 start_secondary+0x1eb #7 start_cpu+0x5 -- CPU#3 -- PID=0 CPU=3 CMD=swapper/3 #-1 native_safe_halt+0xb, 449 bytes of data #0 default_idle+0x1e #1 default_enter_idle+0x45 #2 cpuidle_enter_state+0x40 #3 cpuidle_idle_call+0xd8 #4 arch_cpu_idle+0xe #5 cpu_startup_entry+0x14a #6 start_secondary+0x1eb #7 start_cpu+0x5 +--------------------------------+ >---------------------| How This Dump Has Been Created |---------------------< +--------------------------------+ Cannot identify the specific condition that triggered vmcore +---------------+ >------------------------------| Tasks Summary |------------------------------< +---------------+ Number of Threads That Ran Recently ----------------------------------- last second 14 last 5s 29 last 60s 31 ----- Total Numbers of Threads per State ------ TASK_INTERRUPTIBLE 152 TASK_RUNNING 1 TASK_UNINTERRUPTIBLE 5 +++WARNING+++ There are 3 threads running in their own namespaces Use 'taskinfo --ns' to get more details +-----------------------+ >--------------------------| 5 Most Recent Threads |--------------------------< +-----------------------+ PID CMD Age ARGS ----- -------------- ------ ---------------------------- 9 rcu_sched 0 ms (no user stack) 1995 lnet_discovery 0 ms (no user stack) 904 in:imjournal 0 ms /usr/sbin/rsyslogd -n 11 rcuos/0 100 ms (no user stack) 21409 ldlm_bl_08 132 ms (no user stack) +------------------------+ >-------------------------| Memory Usage (kmem -i) |-------------------------< +------------------------+ PAGES TOTAL PERCENTAGE TOTAL MEM 955079 3.6 GB ---- FREE 852253 3.3 GB 89% of TOTAL MEM USED 102826 401.7 MB 10% of TOTAL MEM SHARED 13220 51.6 MB 1% of TOTAL MEM BUFFERS 5195 20.3 MB 0% of TOTAL MEM CACHED 49394 192.9 MB 5% of TOTAL MEM SLAB 12759 49.8 MB 1% of TOTAL MEM TOTAL HUGE 0 0 ---- HUGE FREE 0 0 0% of TOTAL HUGE TOTAL SWAP 262143 1024 MB ---- SWAP USED 0 0 0% of TOTAL SWAP SWAP FREE 262143 1024 MB 100% of TOTAL SWAP COMMIT LIMIT 739682 2.8 GB ---- COMMITTED 61629 240.7 MB 8% of TOTAL LIMIT +++three oldest UNINTERRUPTIBLE threads ... ran 3612s ago PID=11724 CPU=2 CMD=ldlm_bl_05 #0 __schedule+0x2e2 #1 schedule+0x29 #2 schedule_timeout+0x209 #3 io_schedule_timeout+0xad #4 io_schedule+0x18 #5 bit_wait_io+0x11 #6 __wait_on_bit_lock+0x5f #7 __lock_page+0x74 #8 __find_lock_page+0x66 #9 find_lock_page+0xe #10 truncate_inode_pages_range+0x4d9 #11 osc_discard_cb+0x20a #12 osc_page_gang_lookup+0x20f #13 osc_lock_discard_pages+0x16a #14 osc_ldlm_blocking_ast+0x35d #15 ldlm_cancel_callback+0x84 #16 ldlm_cli_cancel_local+0xb2 #17 ldlm_cli_cancel+0xd1 #18 osc_ldlm_blocking_ast+0x18a #19 ldlm_handle_bl_callback+0xc5 #20 ldlm_bl_thread_main+0x5fc #21 kthread+0xe4 #22 ret_from_fork_nospec_begin+0x7 ... ran 3613s ago PID=5358 CPU=3 CMD=ldlm_bl_02 #0 __schedule+0x2e2 #1 schedule+0x29 #2 schedule_timeout+0x209 #3 io_schedule_timeout+0xad #4 io_schedule+0x18 #5 bit_wait_io+0x11 #6 __wait_on_bit_lock+0x5f #7 __lock_page+0x74 #8 __find_lock_page+0x66 #9 find_lock_page+0xe #10 truncate_inode_pages_range+0x4d9 #11 osc_discard_cb+0x20a #12 osc_page_gang_lookup+0x20f #13 osc_lock_discard_pages+0x16a #14 osc_ldlm_blocking_ast+0x35d #15 ldlm_cancel_callback+0x84 #16 ldlm_cli_cancel_local+0xb2 #17 ldlm_cli_cancel+0xd1 #18 osc_ldlm_blocking_ast+0x18a #19 ldlm_handle_bl_callback+0xc5 #20 ldlm_bl_thread_main+0x5fc #21 kthread+0xe4 #22 ret_from_fork_nospec_begin+0x7 ... ran 3617s ago PID=5865 CPU=3 CMD=ldlm_bl_03 #0 __schedule+0x2e2 #1 schedule+0x29 #2 schedule_timeout+0x209 #3 io_schedule_timeout+0xad #4 io_schedule+0x18 #5 bit_wait_io+0x11 #6 __wait_on_bit_lock+0x5f #7 __lock_page+0x74 #8 __find_lock_page+0x66 #9 find_lock_page+0xe #10 truncate_inode_pages_range+0x4d9 #11 osc_discard_cb+0x20a #12 osc_page_gang_lookup+0x20f #13 mdc_lock_flush+0x19f #14 mdc_dlm_canceling+0x101 #15 mdc_object_flush+0x37 #16 cl_object_flush+0x68 #17 lov_flush_composite+0xc3 #18 lov_object_flush+0x68 #19 cl_object_flush+0x68 #20 ll_lock_cancel_bits+0x417 #21 ll_md_blocking_ast+0x30f #22 ldlm_cancel_callback+0x84 #23 ldlm_cli_cancel_local+0xb2 #24 ldlm_cli_cancel+0xd1 #25 ll_md_blocking_ast+0x22a #26 ldlm_handle_bl_callback+0xc5 #27 ldlm_bl_thread_main+0x5fc #28 kthread+0xe4 #29 ret_from_fork_nospec_begin+0x7 +-------------------------------+ >----------------------| Scheduler Runqueues (per CPU) |----------------------< +-------------------------------+ ---+ CPU=0 ---- | CURRENT TASK , CMD=swapper/0 ---+ CPU=1 ---- | CURRENT TASK , CMD=swapper/1 ---+ CPU=2 ---- | CURRENT TASK , CMD=swapper/2 ---+ CPU=3 ---- | CURRENT TASK , CMD=swapper/3 +------------------------+ >-------------------------| Network Status Summary |-------------------------< +------------------------+ TCP Connection Info ------------------- ESTABLISHED 6 LISTEN 3 NAGLE disabled (TCP_NODELAY): 5 user_data set (NFS etc.): 4 UDP Connection Info ------------------- 2 UDP sockets, 0 in ESTABLISHED Unix Connection Info ------------------------ ESTABLISHED 26 CLOSE 18 LISTEN 8 Raw sockets info -------------------- CLOSE 1 Interfaces Info --------------- How long ago (in seconds) interfaces transmitted/received? Name RX TX ---- ---------- --------- lo n/a 3795.9 eth0 n/a 0.9 RSS_TOTAL=77216 pages, %mem= 1.3 +++WARNING+++ Possible hang +++WARNING+++ Run 'hanginfo' to get more details +------------+ >-------------------------------| Mounted FS |-------------------------------< +------------+ MOUNT SUPERBLK TYPE DEVNAME DIRNAME ffff880138cca000 ffff880139940800 rootfs rootfs / ffff88012aa9c000 ffff880137325800 sysfs sysfs /sys ffff88012aa9c1c0 ffff880139944000 proc proc /proc ffff88012aa9c380 ffff880137678000 devtmpfs devtmpfs /dev ffff88012aa9c540 ffff8800b6c59800 securityfs securityfs /sys/kernel/security ffff88012aa9c700 ffff880137326000 tmpfs tmpfs /dev/shm ffff88012aa9c8c0 ffff8801370c6800 devpts devpts /dev/pts ffff88012aa9ca80 ffff880137326800 tmpfs tmpfs /run ffff88012aa9cc40 ffff880137327000 tmpfs tmpfs /sys/fs/cgroup ffff88012aa9ce00 ffff880137327800 cgroup cgroup /sys/fs/cgroup/systemd ffff88012aa9cfc0 ffff88012aad8000 pstore pstore /sys/fs/pstore ffff88012aa9d180 ffff88012aada000 cgroup cgroup /sys/fs/cgroup/devices ffff88012aa9d340 ffff88012aad9800 cgroup cgroup /sys/fs/cgroup/net_cls,net_prio ffff88012aa9d500 ffff88012aad9000 cgroup cgroup /sys/fs/cgroup/cpuset ffff88012aa9d6c0 ffff88012aad8800 cgroup cgroup /sys/fs/cgroup/memory ffff88012aa9d880 ffff88012aada800 cgroup cgroup /sys/fs/cgroup/freezer ffff88012aa9da40 ffff88012aadb000 cgroup cgroup /sys/fs/cgroup/hugetlb ffff88012aa9dc00 ffff88012aadb800 cgroup cgroup /sys/fs/cgroup/pids ffff88012aa9ddc0 ffff88012aadc000 cgroup cgroup /sys/fs/cgroup/perf_event ffff88012aad0000 ffff88012aadc800 cgroup cgroup /sys/fs/cgroup/blkio ffff88012aad01c0 ffff88012aadd000 cgroup cgroup /sys/fs/cgroup/cpu,cpuacct ffff880137668540 ffff880137015800 configfs configfs /sys/kernel/config ffff8801370b8e00 ffff8800b60ff000 ext4 /dev/nbd0 / ffff88012aad08c0 ffff8800b6c5e000 rpc_pipefs rpc_pipefs /var/lib/nfs/rpc_pipefs ffff880137668c40 ffff8800b58b9800 autofs systemd-1 /proc/sys/fs/binfmt_misc ffff8801370b8fc0 ffff880139947800 debugfs debugfs /sys/kernel/debug ffff880137668e00 ffff88012b288000 mqueue mqueue /dev/mqueue ffff88012aad0a80 ffff88012a5da000 hugetlbfs hugetlbfs /dev/hugepages ffff88012aad0c40 ffff88012a5de000 binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc/ ffff8801370b9180 ffff88012a588000 ramfs none /mnt ffff8801370b9340 ffff88012a58d800 tmpfs none /var/lib/stateless/writable ffff88012aad0fc0 ffff88012a4fc800 squashfs /dev/vda /home/green/git/lustre-release ffff8801370b9500 ffff88012a58d800 tmpfs none /var/cache/man ffff880138ccac40 ffff88012a58d800 tmpfs none /var/log ffff880137668fc0 ffff88012a58d800 tmpfs none /var/lib/dbus ffff880137669180 ffff88012a58d800 tmpfs none /tmp ffff880137669340 ffff88012a58d800 tmpfs none /var/lib/dhclient ffff880137669500 ffff88012a58d800 tmpfs none /var/tmp ffff8801376696c0 ffff88012a58d800 tmpfs none /var/lib/NetworkManager ffff88012aad1180 ffff88012a58d800 tmpfs none /var/lib/systemd/random-seed ffff88012aad1340 ffff88012a58d800 tmpfs none /var/spool ffff88012aad1500 ffff88012a58d800 tmpfs none /var/lib/nfs ffff88012aad16c0 ffff88012a58d800 tmpfs none /var/lib/gssproxy ffff88012d7e6000 ffff88012a58d800 tmpfs none /var/lib/logrotate ffff880137669880 ffff88012a58d800 tmpfs none /etc ffff880137669a40 ffff88012a58d800 tmpfs none /var/lib/rsyslog ffff88012aad1880 ffff88012a58d800 tmpfs none /var/lib/dhclient/var/lib/dhclient ffff8801370b96c0 ffff8800b60fc000 nfs4 192.168.200.253:/exports/state/oleg250-client.virtnet /var/lib/stateless/state ffff88012aad1c00 ffff8800b60fc000 nfs4 192.168.200.253:/exports/state/oleg250-client.virtnet /boot ffff88012aad1a40 ffff8800b60fc000 nfs4 192.168.200.253:/exports/state/oleg250-client.virtnet /etc/etc/kdump.conf ffff88012d7e61c0 ffff8800b6c5e000 rpc_pipefs sunrpc /var/lib/nfs/var/lib/nfs/rpc_pipefs ffff8800b6f16540 ffff8800b064b800 nfs4 192.168.200.253://exports/testreports/42551/testresults/sanity-pfl-ldiskfs-DNE-centos7_x86_64-centos7_x86_64 /tmp/tmp/testlogs ffff8800b5b92fc0 ffff8800b07f5800 tmpfs tmpfs /run/user/0 ffff88012d7e6700 ffff88012a4fc800 squashfs /dev/vda /usr/sbin/mount.lustre ffff88012d7e68c0 ffff88012bd88000 lustre 192.168.202.150@tcp:/lustre /mnt/lustre +-------------------------------+ >----------------------| Last 40 lines of dmesg buffer |----------------------< +-------------------------------+ [ 481.181143] [] ret_from_fork_nospec_begin+0x7/0x21 [ 481.182347] [] ? kthread_create_on_node+0x140/0x140 [ 481.183575] INFO: task ldlm_bl_07:19443 blocked for more than 120 seconds. [ 481.184885] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 481.186332] ldlm_bl_07 D ffff88013776db48 13440 19443 2 0x00000000 [ 481.187663] Call Trace: [ 481.188142] [] ? bit_wait+0x50/0x50 [ 481.189144] [] schedule+0x29/0x70 [ 481.190303] [] schedule_timeout+0x209/0x290 [ 481.191676] [] ? kvm_clock_read+0x33/0x40 [ 481.192855] [] ? kvm_clock_get_cycles+0x9/0x10 [ 481.194003] [] ? bit_wait+0x50/0x50 [ 481.194995] [] io_schedule_timeout+0xad/0x130 [ 481.196146] [] io_schedule+0x18/0x20 [ 481.197236] [] bit_wait_io+0x11/0x50 [ 481.198990] [] __wait_on_bit_lock+0x5f/0xc0 [ 481.201460] [] __lock_page+0x74/0x90 [ 481.202739] [] ? wake_bit_function+0x40/0x40 [ 481.204033] [] __find_lock_page+0x66/0x80 [ 481.205250] [] find_lock_page+0xe/0x20 [ 481.206393] [] truncate_inode_pages_range+0x4d9/0x7d0 [ 481.207991] [] osc_discard_cb+0x20a/0x2a0 [osc] [ 481.209528] [] osc_page_gang_lookup+0x20f/0x4e0 [osc] [ 481.211290] [] ? osc_consume_write_grant+0xe0/0xe0 [osc] [ 481.213117] [] osc_lock_discard_pages+0x16a/0x30f [osc] [ 481.215222] [] osc_ldlm_blocking_ast+0x35d/0x670 [osc] [ 481.216888] [] ldlm_cancel_callback+0x84/0x320 [ptlrpc] [ 481.218646] [] ldlm_cli_cancel_local+0xb2/0x460 [ptlrpc] [ 481.220397] [] ldlm_cli_cancel+0xd1/0x6f0 [ptlrpc] [ 481.221839] [] osc_ldlm_blocking_ast+0x18a/0x670 [osc] [ 481.223928] [] ? osc_ldlm_glimpse_ast+0x510/0x510 [osc] [ 481.226564] [] ldlm_handle_bl_callback+0xc5/0x3e0 [ptlrpc] [ 481.229733] [] ldlm_bl_thread_main+0x5fc/0xb40 [ptlrpc] [ 481.232355] [] ? _raw_spin_unlock_irq+0xe/0x30 [ 481.234072] [] ? wake_up_atomic_t+0x30/0x30 [ 481.235607] [] ? ldlm_handle_bl_callback+0x3e0/0x3e0 [ptlrpc] [ 481.237506] [] kthread+0xe4/0xf0 [ 481.238745] [] ? kthread_create_on_node+0x140/0x140 [ 481.241399] [] ret_from_fork_nospec_begin+0x7/0x21 [ 481.242719] [] ? kthread_create_on_node+0x140/0x140 ****************************************************************************** ************************ A Summary Of Problems Found ************************* ****************************************************************************** -------------------- A list of all +++WARNING+++ messages -------------------- PARTIAL DUMP with size(vmcore) < 25% size(RAM) There are 3 threads running in their own namespaces Use 'taskinfo --ns' to get more details Possible hang Run 'hanginfo' to get more details ------------------------------------------------------------------------------ ** Execution took 11.12s (real) 5.83s (CPU), Child processes: 5.26s