************************ crashinfo ************************* /exports/testreports/47154/testresults/sanity-slow-ldiskfs-DNE-centos7_x86_64-centos7_x86_64/oleg349-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.ocJhq/vmlinux [TAINTED] DUMPFILE: /exports/testreports/47154/testresults/sanity-slow-ldiskfs-DNE-centos7_x86_64-centos7_x86_64/oleg349-client-timeout-core [PARTIAL DUMP] CPUS: 4 DATE: Wed Nov 13 13:14:18 EST 2024 UPTIME: 01:07:09 LOAD AVERAGE: 4.00, 3.99, 3.81 TASKS: 164 NODENAME: oleg349-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 13 last 5s 25 last 60s 33 ----- Total Numbers of Threads per State ------ TASK_INTERRUPTIBLE 156 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 ----- -------------- ------ ---------------------------- 13848 ldlm_bl_05 0 ms (no user stack) 1999 lnet_discovery 0 ms (no user stack) 34 rcuos/3 0 ms (no user stack) 9 rcu_sched 43 ms (no user stack) 1 systemd 49 ms /usr/lib/systemd/systemd --switched-root --system --deserialize 22 +------------------------+ >-------------------------| Memory Usage (kmem -i) |-------------------------< +------------------------+ PAGES TOTAL PERCENTAGE TOTAL MEM 955079 3.6 GB ---- FREE 828254 3.2 GB 86% of TOTAL MEM USED 126825 495.4 MB 13% of TOTAL MEM SHARED 29283 114.4 MB 3% of TOTAL MEM BUFFERS 5230 20.4 MB 0% of TOTAL MEM CACHED 71746 280.3 MB 7% of TOTAL MEM SLAB 12829 50.1 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 64716 252.8 MB 8% of TOTAL LIMIT +++three oldest UNINTERRUPTIBLE threads ... ran 2904s ago PID=13908 CPU=2 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 ... ran 2905s ago PID=13903 CPU=2 CMD=ll_imp_inval #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+0x32f #17 cleanup_resource+0x139 #18 ldlm_resource_clean+0x2f #19 cfs_hash_for_each_relax+0x23b #20 cfs_hash_for_each_nolock+0x76 #21 ldlm_namespace_cleanup+0x30 #22 osc_import_event+0x4b9 #23 ptlrpc_invalidate_import+0x293 #24 ptlrpc_invalidate_import_thread+0x7c #25 kthread+0xe4 #26 ret_from_fork_nospec_begin+0x7 ... ran 3005s ago PID=13358 CPU=2 CMD=ldlm_bl_04 #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+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 +-------------------------------+ >----------------------| 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 -------------------- ESTABLISHED 1 Interfaces Info --------------- How long ago (in seconds) interfaces transmitted/received? Name RX TX ---- ---------- --------- lo n/a 4026.9 eth0 n/a 1.3 RSS_TOTAL=84672 pages, %mem= 1.5 +++WARNING+++ Possible hang +++WARNING+++ Run 'hanginfo' to get more details +------------+ >-------------------------------| Mounted FS |-------------------------------< +------------+ MOUNT SUPERBLK TYPE DEVNAME DIRNAME ffff880138cca000 ffff880139940800 rootfs rootfs / ffff88012ab0a000 ffff88012ab10000 sysfs sysfs /sys ffff88012ab0a1c0 ffff880139944000 proc proc /proc ffff88012ab0a380 ffff880137678000 devtmpfs devtmpfs /dev ffff88012ab0a540 ffff8800b6d0a000 securityfs securityfs /sys/kernel/security ffff88012ab0a700 ffff88012ab10800 tmpfs tmpfs /dev/shm ffff88012ab0a8c0 ffff8801372f6000 devpts devpts /dev/pts ffff88012ab0aa80 ffff88012ab11000 tmpfs tmpfs /run ffff88012ab0ac40 ffff88012ab11800 tmpfs tmpfs /sys/fs/cgroup ffff88012ab0ae00 ffff88012ab12000 cgroup cgroup /sys/fs/cgroup/systemd ffff88012ab0afc0 ffff88012ab12800 pstore pstore /sys/fs/pstore ffff88012ab0b180 ffff88012ab14800 cgroup cgroup /sys/fs/cgroup/perf_event ffff88012ab0b340 ffff88012ab14000 cgroup cgroup /sys/fs/cgroup/net_cls,net_prio ffff88012ab0b500 ffff88012ab13800 cgroup cgroup /sys/fs/cgroup/cpu,cpuacct ffff88012ab0b6c0 ffff88012ab13000 cgroup cgroup /sys/fs/cgroup/pids ffff88012ab0b880 ffff88012ab15000 cgroup cgroup /sys/fs/cgroup/hugetlb ffff88012ab0ba40 ffff88012ab15800 cgroup cgroup /sys/fs/cgroup/freezer ffff88012ab0bc00 ffff88012ab16000 cgroup cgroup /sys/fs/cgroup/cpuset ffff88012ab0bdc0 ffff88012ab16800 cgroup cgroup /sys/fs/cgroup/devices ffff88012ab1e000 ffff88012ab17000 cgroup cgroup /sys/fs/cgroup/memory ffff88012ab1e1c0 ffff88012ab17800 cgroup cgroup /sys/fs/cgroup/blkio ffff880137668700 ffff8800b6d0d000 configfs configfs /sys/kernel/config ffff88012ab1e700 ffff88012abb1000 ext4 /dev/nbd0 / ffff88012ab1e8c0 ffff8800b7c1d000 rpc_pipefs rpc_pipefs /var/lib/nfs/rpc_pipefs ffff88012b2668c0 ffff8800b64f3000 autofs systemd-1 /proc/sys/fs/binfmt_misc ffff880137668e00 ffff8801372f7800 mqueue mqueue /dev/mqueue ffff8800b65981c0 ffff880139947800 debugfs debugfs /sys/kernel/debug ffff88012b266c40 ffff8800b64f4000 hugetlbfs hugetlbfs /dev/hugepages ffff88012b266e00 ffff8800b64f2800 binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc/ ffff880137669180 ffff8800b66b7000 ramfs none /mnt ffff88012ab1ea80 ffff8800b6738000 tmpfs none /var/lib/stateless/writable ffff88012b266fc0 ffff88012abb7800 squashfs /dev/vda /home/green/git/lustre-release ffff88012ab1ec40 ffff8800b6738000 tmpfs none /var/cache/man ffff88012b267180 ffff8800b6738000 tmpfs none /var/log ffff88012ab1ee00 ffff8800b6738000 tmpfs none /var/lib/dbus ffff88012b267340 ffff8800b6738000 tmpfs none /tmp ffff88012ab1efc0 ffff8800b6738000 tmpfs none /var/lib/dhclient ffff88012ab1f180 ffff8800b6738000 tmpfs none /var/tmp ffff88012ab1f340 ffff8800b6738000 tmpfs none /var/lib/NetworkManager ffff880137669340 ffff8800b6738000 tmpfs none /var/lib/systemd/random-seed ffff88012ab1f500 ffff8800b6738000 tmpfs none /var/spool ffff880137669500 ffff8800b6738000 tmpfs none /var/lib/nfs ffff88012b267500 ffff8800b6738000 tmpfs none /var/lib/gssproxy ffff88012ab1f6c0 ffff8800b6738000 tmpfs none /var/lib/logrotate ffff88012b2676c0 ffff8800b6738000 tmpfs none /etc ffff88012ab1f880 ffff8800b6738000 tmpfs none /var/lib/rsyslog ffff88012ab1fa40 ffff8800b6738000 tmpfs none /var/lib/dhclient/var/lib/dhclient ffff8801376696c0 ffff88012abb0800 nfs4 192.168.200.253:/exports/state/oleg349-client.virtnet /var/lib/stateless/state ffff88012ab1fc00 ffff88012abb0800 nfs4 192.168.200.253:/exports/state/oleg349-client.virtnet /boot ffff88012ab1fdc0 ffff88012abb0800 nfs4 192.168.200.253:/exports/state/oleg349-client.virtnet /etc/etc/kdump.conf ffff8800b3c38000 ffff8800b7c1d000 rpc_pipefs sunrpc /var/lib/nfs/var/lib/nfs/rpc_pipefs ffff8800b3fe2000 ffff8800b398a800 nfs4 192.168.200.253://exports/testreports/47154/testresults/sanity-slow-ldiskfs-DNE-centos7_x86_64-centos7_x86_64 /tmp/tmp/testlogs ffff8800b5a63c00 ffff8800b6432800 tmpfs tmpfs /run/user/0 ffff880137669c00 ffff88012abb7800 squashfs /dev/vda /usr/sbin/mount.lustre ffff8800b5bc6540 ffff8800b65bf000 lustre 192.168.203.149@tcp:/lustre /mnt/lustre +-------------------------------+ >----------------------| Last 40 lines of dmesg buffer |----------------------< +-------------------------------+ [ 1561.254008] [] ? wake_up_atomic_t+0x30/0x30 [ 1561.255119] [] ? ptlrpc_import_recovery_state_machine+0xa90/0xa90 [ptlrpc] [ 1561.256715] [] ptlrpc_invalidate_import_thread+0x7c/0x280 [ptlrpc] [ 1561.258150] [] kthread+0xe4/0xf0 [ 1561.259120] [] ? kthread_create_on_node+0x140/0x140 [ 1561.260301] [] ret_from_fork_nospec_begin+0x7/0x21 [ 1561.261493] [] ? kthread_create_on_node+0x140/0x140 [ 1561.262705] INFO: task rm:13908 blocked for more than 120 seconds. [ 1561.263845] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1561.265263] rm D ffff8800b38e05f8 11456 13908 13307 0x00000000 [ 1561.266552] Call Trace: [ 1561.267025] [] ? bit_wait+0x50/0x50 [ 1561.268047] [] schedule+0x29/0x70 [ 1561.269024] [] schedule_timeout+0x209/0x290 [ 1561.270138] [] ? string.isra.7+0x3b/0xf0 [ 1561.271225] [] ? kvm_clock_read+0x33/0x40 [ 1561.272298] [] ? kvm_clock_get_cycles+0x9/0x10 [ 1561.273464] [] ? ktime_get_ts64+0x4c/0xf0 [ 1561.274521] [] ? bit_wait+0x50/0x50 [ 1561.275534] [] io_schedule_timeout+0xad/0x130 [ 1561.276702] [] io_schedule+0x18/0x20 [ 1561.277672] [] bit_wait_io+0x11/0x50 [ 1561.278564] [] __wait_on_bit_lock+0x5f/0xc0 [ 1561.279721] [] ? __find_get_pages+0x132/0x1f0 [ 1561.280888] [] __lock_page+0x74/0x90 [ 1561.281870] [] ? wake_bit_function+0x40/0x40 [ 1561.282967] [] truncate_inode_pages_range+0x79a/0x7d0 [ 1561.284194] [] truncate_inode_pages_final+0x4c/0x60 [ 1561.285556] [] ll_truncate_inode_pages_final+0x30/0x1f0 [lustre] [ 1561.287016] [] ll_delete_inode+0x38/0x150 [lustre] [ 1561.288265] [] evict+0xaf/0x180 [ 1561.289263] [] iput+0xf5/0x180 [ 1561.290208] [] do_unlinkat+0x1ae/0x2b0 [ 1561.291262] [] ? mutex_unlock+0xe/0x10 [ 1561.292386] [] ? dnotify_flush+0x46/0x110 [ 1561.293508] [] ? filp_close+0x5b/0x80 [ 1561.294570] [] SyS_unlinkat+0x1b/0x40 [ 1561.295690] [] system_call_fastpath+0x1f/0x24 [ 1789.684097] Lustre: lustre-OST0000-osc-ffff8800b65bf000: disconnect after 24s idle [ 1789.688624] Lustre: Skipped 1 previous similar message ****************************************************************************** ************************ 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 10.53s (real) 5.56s (CPU), Child processes: 4.95s