[LU-10138] recovery-mds-scale test_failover_ost: test_failover_ost returned 1

• Type: Bug
• Resolution: Unresolved
• Priority: Minor
• Affects Version/s: Lustre 2.11.0
• Environment: trevis, failover; servers: CentOS7.4, zfs, branch master, v2.10.54, b3652; clients: CentOS7.4, branch master, v2.10.54, b3652
• Severity: 3
• Assignee: WC Triage
• Reporter: James Casper

Description

https://testing.hpdd.intel.com/test_sessions/46566d21-2975-4c62-8527-438ab3c1663f

A client hit a kernel panic during the second subtest of the failover session. This was followed by all remaining tests not running.

From client console:

Kernel panic - not syncing: softlockup: hung tasks

dump_stack+0x19/0x1b
panic+0xe8/0x20d
? show_regs+0x5f/0x220
watchdog_timer_fn+0x221/0x230
? watchdog+0x40/0x40
__hrtimer_run_queues+0xd4/0x260
hrtimer_interrupt+0xaf/0x1d0
local_apic_timer_interrupt+0x35/0x60
smp_apic_timer_interrupt+0x3d/0x50
apic_timer_interrupt+0x6d/0x80
? sync_inodes_sb+0x11c/0x1f0