************************ crashinfo ************************* /exports/testreports/47154/testresults/replay-ost-single-zfs-centos7_x86_64-centos7_x86_64/oleg354-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.Pg99U/vmlinux [TAINTED] DUMPFILE: /exports/testreports/47154/testresults/replay-ost-single-zfs-centos7_x86_64-centos7_x86_64/oleg354-client-timeout-core [PARTIAL DUMP] CPUS: 4 DATE: Wed Nov 13 12:30:48 EST 2024 UPTIME: 00:23:38 LOAD AVERAGE: 3.00, 2.87, 2.01 TASKS: 151 NODENAME: oleg354-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 15 last 5s 24 last 60s 31 ----- Total Numbers of Threads per State ------ TASK_INTERRUPTIBLE 144 TASK_RUNNING 1 TASK_UNINTERRUPTIBLE 3 +++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 ----- -------------- ------ ---------------------------- 34 rcuos/3 0 ms (no user stack) 9 rcu_sched 0 ms (no user stack) 1 systemd 0 ms /usr/lib/systemd/systemd --switched-root --system --deserialize 21 1964 ptlrpcd_01_01 264 ms (no user stack) 1956 socknal_sd01_01 265 ms (no user stack) +------------------------+ >-------------------------| Memory Usage (kmem -i) |-------------------------< +------------------------+ PAGES TOTAL PERCENTAGE TOTAL MEM 955079 3.6 GB ---- FREE 861306 3.3 GB 90% of TOTAL MEM USED 93773 366.3 MB 9% of TOTAL MEM SHARED 9864 38.5 MB 1% of TOTAL MEM BUFFERS 5151 20.1 MB 0% of TOTAL MEM CACHED 46222 180.6 MB 4% of TOTAL MEM SLAB 10958 42.8 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 61638 240.8 MB 8% of TOTAL LIMIT +++three oldest UNINTERRUPTIBLE threads ... ran 663s ago PID=9330 CPU=1 CMD=ldlm_bl_01 #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 __cl_page_own+0x373 #9 cl_page_own+0x10 #10 check_and_discard_cb+0x68 #11 osc_page_gang_lookup+0x20f #12 osc_lock_discard_pages+0x16a #13 osc_ldlm_blocking_ast+0x35d #14 ldlm_cancel_callback+0x84 #15 ldlm_cli_cancel_local+0xb2 #16 ldlm_cli_cancel_list_local+0xea #17 ldlm_bl_thread_main+0x988 #18 kthread+0xe4 #19 ret_from_fork_nospec_begin+0x7 ... ran 1260s ago PID=9331 CPU=1 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 __cl_page_own+0x373 #9 cl_page_own+0x10 #10 osc_discard_cb+0xaf #11 osc_page_gang_lookup+0x20f #12 osc_lock_discard_pages+0x16a #13 osc_ldlm_blocking_ast+0x35d #14 ldlm_cancel_callback+0x84 #15 ldlm_cli_cancel_local+0xb2 #16 ldlm_cli_cancel+0xd1 #17 osc_ldlm_blocking_ast+0x18a #18 ldlm_handle_bl_callback+0xc5 #19 ldlm_bl_thread_main+0x5fc #20 kthread+0xe4 #21 ret_from_fork_nospec_begin+0x7 ... ran 1264s ago PID=13655 CPU=0 CMD=rm #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 truncate_inode_pages_range+0x79a #9 truncate_inode_pages_final+0x4c #10 ll_truncate_inode_pages_final+0x30 #11 ll_delete_inode+0x38 #12 evict+0xaf #13 iput+0xf5 #14 do_unlinkat+0x1ae #15 sys_unlinkat+0x1b #16 system_call_fastpath+0x1f, 477 bytes of data +-------------------------------+ >----------------------| 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 1416.7 eth0 n/a 0.3 RSS_TOTAL=75372 pages, %mem= 1.2 +++WARNING+++ Possible hang +++WARNING+++ Run 'hanginfo' to get more details +------------+ >-------------------------------| Mounted FS |-------------------------------< +------------+ MOUNT SUPERBLK TYPE DEVNAME DIRNAME ffff880138cca000 ffff880139940800 rootfs rootfs / ffff880137668380 ffff88013767b800 sysfs sysfs /sys ffff880137668540 ffff880139944000 proc proc /proc ffff880137668700 ffff880137678000 devtmpfs devtmpfs /dev ffff8801376688c0 ffff8800b6d12000 securityfs securityfs /sys/kernel/security ffff880137668a80 ffff88013767c000 tmpfs tmpfs /dev/shm ffff880137668c40 ffff8801372f6000 devpts devpts /dev/pts ffff880137668e00 ffff88013767c800 tmpfs tmpfs /run ffff880137668fc0 ffff88013767d000 tmpfs tmpfs /sys/fs/cgroup ffff880137669180 ffff88013767d800 cgroup cgroup /sys/fs/cgroup/systemd ffff880137669340 ffff88013767e000 pstore pstore /sys/fs/pstore ffff880137669500 ffff88012aa18000 cgroup cgroup /sys/fs/cgroup/devices ffff8801376696c0 ffff88012aa18800 cgroup cgroup /sys/fs/cgroup/perf_event ffff880137669880 ffff88012aa19000 cgroup cgroup /sys/fs/cgroup/freezer ffff880137669a40 ffff88012aa19800 cgroup cgroup /sys/fs/cgroup/net_cls,net_prio ffff880137669c00 ffff88012aa1a000 cgroup cgroup /sys/fs/cgroup/blkio ffff880137669dc0 ffff88012aa1a800 cgroup cgroup /sys/fs/cgroup/cpu,cpuacct ffff88012aa7e000 ffff88012aa1b000 cgroup cgroup /sys/fs/cgroup/cpuset ffff88012aa7e1c0 ffff88012aa1b800 cgroup cgroup /sys/fs/cgroup/hugetlb ffff88012aa7e380 ffff88012aa1c000 cgroup cgroup /sys/fs/cgroup/memory ffff88012aa7e540 ffff88012aa1c800 cgroup cgroup /sys/fs/cgroup/pids ffff88012aa7e8c0 ffff88012aa1f000 configfs configfs /sys/kernel/config ffff88012a524000 ffff8800b599d800 ext4 /dev/nbd0 / ffff88012b262c40 ffff88012aa1d000 rpc_pipefs rpc_pipefs /var/lib/nfs/rpc_pipefs ffff88012a524700 ffff88012a606000 autofs systemd-1 /proc/sys/fs/binfmt_misc ffff8800b63d0540 ffff880139947800 debugfs debugfs /sys/kernel/debug ffff88012a5248c0 ffff8801372f7800 mqueue mqueue /dev/mqueue ffff8800b63d0700 ffff8800b61ac000 hugetlbfs hugetlbfs /dev/hugepages ffff88012b262e00 ffff8800b605c000 binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc/ ffff88012b262fc0 ffff8800b5958800 ramfs none /mnt ffff88012a524a80 ffff88012a603800 tmpfs none /var/lib/stateless/writable ffff88012aa7ea80 ffff88013735d000 squashfs /dev/vda /home/green/git/lustre-release ffff88012a524c40 ffff88012a603800 tmpfs none /var/cache/man ffff88012a524e00 ffff88012a603800 tmpfs none /var/log ffff88012aa7ec40 ffff88012a603800 tmpfs none /var/lib/dbus ffff88012aa7ee00 ffff88012a603800 tmpfs none /tmp ffff88012a524fc0 ffff88012a603800 tmpfs none /var/lib/dhclient ffff88012a525180 ffff88012a603800 tmpfs none /var/tmp ffff88012a525340 ffff88012a603800 tmpfs none /var/lib/NetworkManager ffff88012a525500 ffff88012a603800 tmpfs none /var/lib/systemd/random-seed ffff88012b263180 ffff88012a603800 tmpfs none /var/spool ffff88012a5256c0 ffff88012a603800 tmpfs none /var/lib/nfs ffff88012aa7efc0 ffff88012a603800 tmpfs none /var/lib/gssproxy ffff8800b63d0a80 ffff88012a603800 tmpfs none /var/lib/logrotate ffff88012aa7f180 ffff88012a603800 tmpfs none /etc ffff8800b63d0c40 ffff88012a603800 tmpfs none /var/lib/rsyslog ffff88012aa7f340 ffff88012a603800 tmpfs none /var/lib/dhclient/var/lib/dhclient ffff8800b63d0e00 ffff8800b6c9a800 nfs4 192.168.200.253:/exports/state/oleg354-client.virtnet /var/lib/stateless/state ffff88012a525c00 ffff8800b6c9a800 nfs4 192.168.200.253:/exports/state/oleg354-client.virtnet /boot ffff88012a525dc0 ffff8800b6c9a800 nfs4 192.168.200.253:/exports/state/oleg354-client.virtnet /etc/etc/kdump.conf ffff88012aa7f500 ffff88012aa1d000 rpc_pipefs sunrpc /var/lib/nfs/var/lib/nfs/rpc_pipefs ffff8800b3fefc00 ffff88012b743000 nfs4 192.168.200.253://exports/testreports/47154/testresults/replay-ost-single-zfs-centos7_x86_64-centos7_x86_64 /tmp/tmp/testlogs ffff8800b38fc540 ffff8800b5896800 tmpfs tmpfs /run/user/0 ffff88012aa7f880 ffff88013735d000 squashfs /dev/vda /usr/sbin/mount.lustre ffff8800b63fe1c0 ffff8800a9c96000 lustre 192.168.203.154@tcp:/lustre /mnt/lustre +-------------------------------+ >----------------------| Last 40 lines of dmesg buffer |----------------------< +-------------------------------+ [ 841.332389] [] ? wake_up_atomic_t+0x30/0x30 [ 841.334156] [] ? ldlm_handle_bl_callback+0x3e0/0x3e0 [ptlrpc] [ 841.336370] [] kthread+0xe4/0xf0 [ 841.337817] [] ? kthread_create_on_node+0x140/0x140 [ 841.339728] [] ret_from_fork_nospec_begin+0x7/0x21 [ 841.341622] [] ? kthread_create_on_node+0x140/0x140 [ 841.343449] INFO: task rm:13655 blocked for more than 120 seconds. [ 841.345240] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 841.347467] rm D ffff8800abbaec58 12592 13655 12683 0x00000000 [ 841.349516] Call Trace: [ 841.350236] [] ? bit_wait+0x50/0x50 [ 841.351811] [] schedule+0x29/0x70 [ 841.353263] [] schedule_timeout+0x209/0x290 [ 841.354968] [] ? string.isra.7+0x3b/0xf0 [ 841.356566] [] ? kvm_clock_read+0x33/0x40 [ 841.358259] [] ? kvm_clock_get_cycles+0x9/0x10 [ 841.360027] [] ? ktime_get_ts64+0x4c/0xf0 [ 841.361640] [] ? bit_wait+0x50/0x50 [ 841.363174] [] io_schedule_timeout+0xad/0x130 [ 841.364956] [] io_schedule+0x18/0x20 [ 841.366493] [] bit_wait_io+0x11/0x50 [ 841.368052] [] __wait_on_bit_lock+0x5f/0xc0 [ 841.369748] [] ? __find_get_pages+0x132/0x1f0 [ 841.371532] [] __lock_page+0x74/0x90 [ 841.373123] [] ? wake_bit_function+0x40/0x40 [ 841.374844] [] truncate_inode_pages_range+0x79a/0x7d0 [ 841.376810] [] ? do_raw_spin_unlock+0x49/0x90 [ 841.378542] [] ? __wake_up_common_lock+0x91/0xc0 [ 841.380026] [] ? sched_feat_set+0xf0/0xf0 [ 841.381102] [] ? __wake_up+0x13/0x20 [ 841.382244] [] ? lu_object_put+0x146/0x4c0 [obdclass] [ 841.383638] [] truncate_inode_pages_final+0x4c/0x60 [ 841.384939] [] ll_truncate_inode_pages_final+0x30/0x1f0 [lustre] [ 841.386466] [] ll_delete_inode+0x38/0x150 [lustre] [ 841.387858] [] evict+0xaf/0x180 [ 841.388927] [] iput+0xf5/0x180 [ 841.389917] [] do_unlinkat+0x1ae/0x2b0 [ 841.391087] [] ? trace_do_page_fault+0x56/0x170 [ 841.392302] [] SyS_unlinkat+0x1b/0x40 [ 841.393303] [] system_call_fastpath+0x1f/0x24 ****************************************************************************** ************************ 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 11.13s (real) 5.74s (CPU), Child processes: 5.37s