************************ crashinfo ************************* /exports/testreports/47154/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64/oleg451-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.EB4qA/vmlinux [TAINTED] DUMPFILE: /exports/testreports/47154/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64/oleg451-client-timeout-core [PARTIAL DUMP] CPUS: 4 DATE: Wed Nov 13 13:55:24 EST 2024 UPTIME: 01:48:11 LOAD AVERAGE: 5.00, 4.99, 4.79 TASKS: 167 NODENAME: oleg451-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 26 last 60s 34 ----- Total Numbers of Threads per State ------ TASK_INTERRUPTIBLE 158 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 ----- -------------- ------ ---------------------------- 18535 ldlm_bl_05 0 ms (no user stack) 1949 monitor_thread 0 ms (no user stack) 5475 dbench 16 ms dbench -c client.txt 1 -t 300 5374 kworker/2:0 172 ms (no user stack) 49 kworker/0:1 200 ms (no user stack) +------------------------+ >-------------------------| Memory Usage (kmem -i) |-------------------------< +------------------------+ PAGES TOTAL PERCENTAGE TOTAL MEM 955079 3.6 GB ---- FREE 831271 3.2 GB 87% of TOTAL MEM USED 123808 483.6 MB 12% of TOTAL MEM SHARED 21953 85.8 MB 2% of TOTAL MEM BUFFERS 5225 20.4 MB 0% of TOTAL MEM CACHED 67857 265.1 MB 7% of TOTAL MEM SLAB 13452 52.5 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 69916 273.1 MB 9% of TOTAL LIMIT +++three oldest UNINTERRUPTIBLE threads ... ran 3137s ago PID=18063 CPU=1 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 3237s ago PID=29319 CPU=1 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 __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 3242s ago PID=5476 CPU=0 CMD=dbench #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_unlink+0x16 #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 -------------------- ESTABLISHED 1 Interfaces Info --------------- How long ago (in seconds) interfaces transmitted/received? Name RX TX ---- ---------- --------- lo n/a 6488.7 eth0 n/a 0.4 RSS_TOTAL=100504 pages, %mem= 1.7 +++WARNING+++ Possible hang +++WARNING+++ Run 'hanginfo' to get more details +------------+ >-------------------------------| Mounted FS |-------------------------------< +------------+ MOUNT SUPERBLK TYPE DEVNAME DIRNAME ffff880138cca000 ffff880139940800 rootfs rootfs / ffff880137668380 ffff880137679000 sysfs sysfs /sys ffff880137668540 ffff880139944000 proc proc /proc ffff880137668700 ffff880137678000 devtmpfs devtmpfs /dev ffff8801376688c0 ffff880137320800 securityfs securityfs /sys/kernel/security ffff880137668a80 ffff880137679800 tmpfs tmpfs /dev/shm ffff880137668c40 ffff88013771f000 devpts devpts /dev/pts ffff880137668e00 ffff88013767a000 tmpfs tmpfs /run ffff880137668fc0 ffff88013767a800 tmpfs tmpfs /sys/fs/cgroup ffff880137669180 ffff88013767b000 cgroup cgroup /sys/fs/cgroup/systemd ffff880137669340 ffff88013767b800 pstore pstore /sys/fs/pstore ffff880137669500 ffff88013767d800 cgroup cgroup /sys/fs/cgroup/freezer ffff8801376696c0 ffff88013767d000 cgroup cgroup /sys/fs/cgroup/net_cls,net_prio ffff880137669880 ffff88013767c800 cgroup cgroup /sys/fs/cgroup/devices ffff880137669a40 ffff88013767c000 cgroup cgroup /sys/fs/cgroup/cpuset ffff880137669c00 ffff88013767e000 cgroup cgroup /sys/fs/cgroup/cpu,cpuacct ffff880137669dc0 ffff88013767e800 cgroup cgroup /sys/fs/cgroup/pids ffff88012aafe000 ffff88013767f000 cgroup cgroup /sys/fs/cgroup/perf_event ffff88012aafe1c0 ffff88013767f800 cgroup cgroup /sys/fs/cgroup/hugetlb ffff88012aafe380 ffff88012ab20000 cgroup cgroup /sys/fs/cgroup/memory ffff88012aafe540 ffff88012ab20800 cgroup cgroup /sys/fs/cgroup/blkio ffff88012aafe700 ffff88012ab22800 configfs configfs /sys/kernel/config ffff880137014700 ffff8800b6cde000 ext4 /dev/nbd0 / ffff88012aad8540 ffff880137324800 rpc_pipefs rpc_pipefs /var/lib/nfs/rpc_pipefs ffff88012aad8700 ffff8800b6010000 autofs systemd-1 /proc/sys/fs/binfmt_misc ffff880137014e00 ffff880139947800 debugfs debugfs /sys/kernel/debug ffff88012aaff880 ffff88012b288800 mqueue mqueue /dev/mqueue ffff880138ccb340 ffff88012ab22000 hugetlbfs hugetlbfs /dev/hugepages ffff88012aad88c0 ffff8800b63bf000 binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc/ ffff880137015180 ffff8800b6016800 ramfs none /mnt ffff88012aaffa40 ffff8800b6f9f800 tmpfs none /var/lib/stateless/writable ffff88012aaffc00 ffff88012aa27000 squashfs /dev/vda /home/green/git/lustre-release ffff880130a3a000 ffff8800b6f9f800 tmpfs none /var/cache/man ffff88012aad8a80 ffff8800b6f9f800 tmpfs none /var/log ffff880130a3a1c0 ffff8800b6f9f800 tmpfs none /var/lib/dbus ffff880137015340 ffff8800b6f9f800 tmpfs none /tmp ffff88012aad8c40 ffff8800b6f9f800 tmpfs none /var/lib/dhclient ffff88012aad8e00 ffff8800b6f9f800 tmpfs none /var/tmp ffff88012aad8fc0 ffff8800b6f9f800 tmpfs none /var/lib/NetworkManager ffff88012aad9180 ffff8800b6f9f800 tmpfs none /var/lib/systemd/random-seed ffff880138ccb6c0 ffff8800b6f9f800 tmpfs none /var/spool ffff88012aad9340 ffff8800b6f9f800 tmpfs none /var/lib/nfs ffff880130a3a380 ffff8800b6f9f800 tmpfs none /var/lib/gssproxy ffff880137015500 ffff8800b6f9f800 tmpfs none /var/lib/logrotate ffff88012aad9500 ffff8800b6f9f800 tmpfs none /etc ffff8801370156c0 ffff8800b6f9f800 tmpfs none /var/lib/rsyslog ffff880138ccb880 ffff8800b6f9f800 tmpfs none /var/lib/dhclient/var/lib/dhclient ffff880130a3a540 ffff8800b6f9d800 nfs4 192.168.200.253:/exports/state/oleg451-client.virtnet /var/lib/stateless/state ffff88012aad96c0 ffff8800b6f9d800 nfs4 192.168.200.253:/exports/state/oleg451-client.virtnet /boot ffff880130a3a700 ffff8800b6f9d800 nfs4 192.168.200.253:/exports/state/oleg451-client.virtnet /etc/etc/kdump.conf ffff880130a3a8c0 ffff880137324800 rpc_pipefs sunrpc /var/lib/nfs/var/lib/nfs/rpc_pipefs ffff88012e5b4000 ffff88012ab24800 nfs4 192.168.200.253://exports/testreports/47154/testresults/replay-single-zfs-centos7_x86_64-centos7_x86_64 /tmp/tmp/testlogs ffff8800b39788c0 ffff88012ab24000 tmpfs tmpfs /run/user/0 ffff88012e5b41c0 ffff88012aa27000 squashfs /dev/vda /usr/sbin/mount.lustre ffff8800b3ff48c0 ffff880136889800 lustre 192.168.204.151@tcp:/lustre /mnt/lustre +-------------------------------+ >----------------------| Last 40 lines of dmesg buffer |----------------------< +-------------------------------+ [ 3721.193860] [] ret_from_fork_nospec_begin+0x7/0x21 [ 3721.195248] [] ? kthread_create_on_node+0x140/0x140 [ 3841.196212] INFO: task ldlm_bl_03:29319 blocked for more than 120 seconds. [ 3841.197698] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 3841.199261] ldlm_bl_03 D ffff8800b6189708 12832 29319 2 0x00000000 [ 3841.200880] Call Trace: [ 3841.201384] [] ? bit_wait+0x50/0x50 [ 3841.202585] [] schedule+0x29/0x70 [ 3841.203689] [] schedule_timeout+0x209/0x290 [ 3841.205134] [] ? string.isra.7+0x3b/0xf0 [ 3841.206548] [] ? kvm_clock_read+0x33/0x40 [ 3841.207819] [] ? kvm_clock_get_cycles+0x9/0x10 [ 3841.209326] [] ? bit_wait+0x50/0x50 [ 3841.210534] [] io_schedule_timeout+0xad/0x130 [ 3841.212004] [] io_schedule+0x18/0x20 [ 3841.213288] [] bit_wait_io+0x11/0x50 [ 3841.214465] [] __wait_on_bit_lock+0x5f/0xc0 [ 3841.215708] [] __lock_page+0x74/0x90 [ 3841.216821] [] ? wake_bit_function+0x40/0x40 [ 3841.218171] [] __cl_page_own+0x373/0x390 [obdclass] [ 3841.219651] [] cl_page_own+0x10/0x20 [obdclass] [ 3841.221101] [] osc_discard_cb+0xaf/0x2a0 [osc] [ 3841.222363] [] osc_page_gang_lookup+0x20f/0x4e0 [osc] [ 3841.223805] [] ? osc_consume_write_grant+0xe0/0xe0 [osc] [ 3841.225336] [] osc_lock_discard_pages+0x16a/0x30f [osc] [ 3841.226853] [] osc_ldlm_blocking_ast+0x35d/0x670 [osc] [ 3841.228391] [] ldlm_cancel_callback+0x84/0x320 [ptlrpc] [ 3841.230001] [] ldlm_cli_cancel_local+0xb2/0x480 [ptlrpc] [ 3841.231729] [] ldlm_cli_cancel+0xd1/0x6f0 [ptlrpc] [ 3841.233147] [] osc_ldlm_blocking_ast+0x18a/0x670 [osc] [ 3841.234663] [] ? osc_ldlm_glimpse_ast+0x510/0x510 [osc] [ 3841.236315] [] ldlm_handle_bl_callback+0xc5/0x3e0 [ptlrpc] [ 3841.238006] [] ldlm_bl_thread_main+0x5fc/0xb40 [ptlrpc] [ 3841.239511] [] ? _raw_spin_unlock_irq+0xe/0x30 [ 3841.240902] [] ? wake_up_atomic_t+0x30/0x30 [ 3841.242267] [] ? ldlm_handle_bl_callback+0x3e0/0x3e0 [ptlrpc] [ 3841.243845] [] kthread+0xe4/0xf0 [ 3841.244871] [] ? kthread_create_on_node+0x140/0x140 [ 3841.246355] [] ret_from_fork_nospec_begin+0x7/0x21 [ 3841.247701] [] ? 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 11.01s (real) 5.83s (CPU), Child processes: 5.15s