************************ crashinfo ************************* /exports/testreports/42551/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64/oleg358-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.mzaXm/vmlinux [TAINTED] DUMPFILE: /exports/testreports/42551/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64/oleg358-client-timeout-core [PARTIAL DUMP] CPUS: 4 DATE: Wed May 8 19:22:40 EDT 2024 UPTIME: 01:21:55 LOAD AVERAGE: 4.00, 3.99, 3.91 TASKS: 155 NODENAME: oleg358-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 16 last 5s 26 last 60s 31 ----- Total Numbers of Threads per State ------ TASK_INTERRUPTIBLE 147 TASK_RUNNING 1 TASK_UNINTERRUPTIBLE 4 +++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 ----- -------------- ------ ---------------------------- 13403 ldlm_bl_02 0 ms (no user stack) 11 rcuos/0 0 ms (no user stack) 9 rcu_sched 0 ms (no user stack) 46 kworker/0:1 2 ms (no user stack) 821 gmain 6 ms /usr/sbin/NetworkManager --no-daemon +------------------------+ >-------------------------| Memory Usage (kmem -i) |-------------------------< +------------------------+ PAGES TOTAL PERCENTAGE TOTAL MEM 955079 3.6 GB ---- FREE 854663 3.3 GB 89% of TOTAL MEM USED 100416 392.2 MB 10% of TOTAL MEM SHARED 9843 38.4 MB 1% of TOTAL MEM BUFFERS 5207 20.3 MB 0% of TOTAL MEM CACHED 48473 189.3 MB 5% of TOTAL MEM SLAB 12033 47 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 67948 265.4 MB 9% of TOTAL LIMIT +++three oldest UNINTERRUPTIBLE threads ... ran 3600s ago PID=25555 CPU=1 CMD=lctl #0 __schedule+0x2e2 #1 schedule+0x29 #2 schedule_timeout+0x209 #3 wait_for_completion+0xfc #4 __ldlm_bl_to_thread+0xfd #5 ldlm_bl_to_thread+0x22b #6 ldlm_bl_to_thread_list+0x19 #7 ldlm_cancel_lru+0x7e #8 lru_size_store+0x67 #9 lustre_attr_store+0x18 #10 sysfs_kf_write+0x3d #11 kernfs_fop_write+0x100 #12 vfs_write+0xd6 #13 sys_write+0x7f #14 system_call_fastpath+0x1f, 477 bytes of data ... ran 3601s ago PID=13402 CPU=2 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 __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_list_local+0xea #18 ldlm_bl_thread_main+0x988 #19 kthread+0xe4 #20 ret_from_fork_nospec_begin+0x7 ... ran 3601s ago PID=25556 CPU=0 CMD=lctl #0 __schedule+0x2e2 #1 schedule+0x29 #2 schedule_timeout+0x209 #3 wait_for_completion+0xfc #4 __ldlm_bl_to_thread+0xfd #5 ldlm_bl_to_thread+0x22b #6 ldlm_bl_to_thread_list+0x19 #7 ldlm_cancel_lru+0x7e #8 lru_size_store+0x67 #9 lustre_attr_store+0x18 #10 sysfs_kf_write+0x3d #11 kernfs_fop_write+0x100 #12 vfs_write+0xd6 #13 sys_write+0x7f #14 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 4912.8 eth0 n/a 0.7 RSS_TOTAL=74348 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 / ffff88012aaee000 ffff88012aaf0000 sysfs sysfs /sys ffff88012aaee1c0 ffff880139944000 proc proc /proc ffff88012aaee380 ffff880137678000 devtmpfs devtmpfs /dev ffff88012aaee540 ffff8800b6cb2000 securityfs securityfs /sys/kernel/security ffff88012aaee700 ffff88012aaf0800 tmpfs tmpfs /dev/shm ffff88012aaee8c0 ffff8801372f6000 devpts devpts /dev/pts ffff88012aaeea80 ffff88012aaf1000 tmpfs tmpfs /run ffff88012aaeec40 ffff88012aaf1800 tmpfs tmpfs /sys/fs/cgroup ffff88012aaeee00 ffff88012aaf2000 cgroup cgroup /sys/fs/cgroup/systemd ffff88012aaeefc0 ffff88012aaf2800 pstore pstore /sys/fs/pstore ffff88012aaef180 ffff88012aaf4800 cgroup cgroup /sys/fs/cgroup/net_cls,net_prio ffff88012aaef340 ffff88012aaf4000 cgroup cgroup /sys/fs/cgroup/hugetlb ffff88012aaef500 ffff88012aaf3800 cgroup cgroup /sys/fs/cgroup/cpu,cpuacct ffff88012aaef6c0 ffff88012aaf3000 cgroup cgroup /sys/fs/cgroup/perf_event ffff88012aaef880 ffff88012aaf5000 cgroup cgroup /sys/fs/cgroup/freezer ffff88012aaefa40 ffff88012aaf5800 cgroup cgroup /sys/fs/cgroup/pids ffff88012aaefc00 ffff88012aaf6000 cgroup cgroup /sys/fs/cgroup/devices ffff88012aaefdc0 ffff88012aaf6800 cgroup cgroup /sys/fs/cgroup/memory ffff88012ab02000 ffff88012aaf7000 cgroup cgroup /sys/fs/cgroup/cpuset ffff88012ab021c0 ffff88012aaf7800 cgroup cgroup /sys/fs/cgroup/blkio ffff880138ccb500 ffff88012aa0d800 configfs configfs /sys/kernel/config ffff88012ab02540 ffff8800b6cf6000 ext4 /dev/nbd0 / ffff880137668700 ffff88012aa0d000 rpc_pipefs rpc_pipefs /var/lib/nfs/rpc_pipefs ffff88012ab02c40 ffff8800b6cb3000 autofs systemd-1 /proc/sys/fs/binfmt_misc ffff8801376688c0 ffff880137160800 mqueue mqueue /dev/mqueue ffff88012b246700 ffff880139947800 debugfs debugfs /sys/kernel/debug ffff88012b2468c0 ffff88012a606000 hugetlbfs hugetlbfs /dev/hugepages ffff88012ab02e00 ffff8800b6cb7800 binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc/ ffff88012ab02fc0 ffff8800b6cb7000 ramfs none /mnt ffff88012ab03180 ffff8800b6f07000 tmpfs none /var/lib/stateless/writable ffff880137668c40 ffff8801372f7800 squashfs /dev/vda /home/green/git/lustre-release ffff880137668e00 ffff8800b6f07000 tmpfs none /var/cache/man ffff8800b62c2a80 ffff8800b6f07000 tmpfs none /var/log ffff880137668fc0 ffff8800b6f07000 tmpfs none /var/lib/dbus ffff8800b62c2c40 ffff8800b6f07000 tmpfs none /tmp ffff88012b246a80 ffff8800b6f07000 tmpfs none /var/lib/dhclient ffff88012b246c40 ffff8800b6f07000 tmpfs none /var/tmp ffff88012ab03340 ffff8800b6f07000 tmpfs none /var/lib/NetworkManager ffff88012b246e00 ffff8800b6f07000 tmpfs none /var/lib/systemd/random-seed ffff88012b246fc0 ffff8800b6f07000 tmpfs none /var/spool ffff880137669180 ffff8800b6f07000 tmpfs none /var/lib/nfs ffff88012ab03500 ffff8800b6f07000 tmpfs none /var/lib/gssproxy ffff8800b62c2e00 ffff8800b6f07000 tmpfs none /var/lib/logrotate ffff88012ab036c0 ffff8800b6f07000 tmpfs none /etc ffff88012b247180 ffff8800b6f07000 tmpfs none /var/lib/rsyslog ffff880137669340 ffff8800b6f07000 tmpfs none /var/lib/dhclient/var/lib/dhclient ffff880137669500 ffff8800b3d36000 nfs4 192.168.200.253:/exports/state/oleg358-client.virtnet /var/lib/stateless/state ffff88012ab03880 ffff8800b3d36000 nfs4 192.168.200.253:/exports/state/oleg358-client.virtnet /boot ffff880137669880 ffff8800b3d36000 nfs4 192.168.200.253:/exports/state/oleg358-client.virtnet /etc/etc/kdump.conf ffff880137669a40 ffff88012aa0d000 rpc_pipefs sunrpc /var/lib/nfs/var/lib/nfs/rpc_pipefs ffff8800b5982540 ffff8800b58bf800 nfs4 192.168.200.253://exports/testreports/42551/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64 /tmp/tmp/testlogs ffff8800b59828c0 ffff88012b205000 tmpfs tmpfs /run/user/0 ffff8800b5982fc0 ffff8801372f7800 squashfs /dev/vda /usr/sbin/mount.lustre ffff8800b62c2380 ffff8800afaf8800 lustre 192.168.203.158@tcp:/lustre /mnt/lustre +-------------------------------+ >----------------------| Last 40 lines of dmesg buffer |----------------------< +-------------------------------+ [ 1681.042472] Call Trace: [ 1681.043080] [] ? bit_wait+0x50/0x50 [ 1681.044448] [] schedule+0x29/0x70 [ 1681.045778] [] schedule_timeout+0x209/0x290 [ 1681.047272] [] ? free_object+0x81/0xb0 [ 1681.048612] [] ? kvm_clock_read+0x33/0x40 [ 1681.050032] [] ? kvm_clock_get_cycles+0x9/0x10 [ 1681.051604] [] ? bit_wait+0x50/0x50 [ 1681.052938] [] io_schedule_timeout+0xad/0x130 [ 1681.054396] [] io_schedule+0x18/0x20 [ 1681.055639] [] bit_wait_io+0x11/0x50 [ 1681.056915] [] __wait_on_bit_lock+0x5f/0xc0 [ 1681.058404] [] __lock_page+0x74/0x90 [ 1681.059694] [] ? wake_bit_function+0x40/0x40 [ 1681.061136] [] __find_lock_page+0x66/0x80 [ 1681.062655] [] find_lock_page+0xe/0x20 [ 1681.064017] [] truncate_inode_pages_range+0x4d9/0x7d0 [ 1681.065866] [] ? do_raw_spin_unlock+0x49/0x90 [ 1681.067443] [] ? _raw_spin_unlock+0xe/0x20 [ 1681.068991] [] ? cfs_trace_unlock_tcd+0x27/0x70 [libcfs] [ 1681.070813] [] ? libcfs_debug_msg+0x6d4/0xc20 [libcfs] [ 1681.072638] [] ? osc_cache_wait_range+0x389/0x940 [osc] [ 1681.074562] [] ? cl_page_state_set+0x19/0x50 [obdclass] [ 1681.076284] [] ? __cl_page_own+0xe9/0x390 [obdclass] [ 1681.077899] [] osc_discard_cb+0x20a/0x2a0 [osc] [ 1681.079416] [] osc_page_gang_lookup+0x20f/0x4e0 [osc] [ 1681.080833] [] ? osc_consume_write_grant+0xe0/0xe0 [osc] [ 1681.082272] [] osc_lock_discard_pages+0x16a/0x30f [osc] [ 1681.083695] [] osc_ldlm_blocking_ast+0x35d/0x670 [osc] [ 1681.085075] [] ldlm_cancel_callback+0x84/0x320 [ptlrpc] [ 1681.086547] [] ldlm_cli_cancel_local+0xb2/0x460 [ptlrpc] [ 1681.088033] [] ldlm_cli_cancel_list_local+0xea/0x270 [ptlrpc] [ 1681.089455] [] ldlm_bl_thread_main+0x988/0xb40 [ptlrpc] [ 1681.090827] [] ? _raw_spin_unlock_irq+0xe/0x30 [ 1681.092203] [] ? wake_up_atomic_t+0x30/0x30 [ 1681.093366] [] ? ldlm_handle_bl_callback+0x3e0/0x3e0 [ptlrpc] [ 1681.094841] [] kthread+0xe4/0xf0 [ 1681.095793] [] ? kthread_create_on_node+0x140/0x140 [ 1681.097157] [] ret_from_fork_nospec_begin+0x7/0x21 [ 1681.098479] [] ? 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 11.28s (real) 5.83s (CPU), Child processes: 5.42s