[Bug 235856] FreeBSD freezes on AWS EC2 t3 machines

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=235856

--- Comment #32 from mail at rubenvos.com ---
(In reply to Colin Percival from comment #31)

Hi,

I've managed to reboot all servers with the verbose setting active. If the
issue occurs again ill be sure to upload the information you requested (unless
you want to have a look at it "now"?).

One of the machines seemed weirdly impacted by a similar issue whilst receiving
a stream of 5 MB/s (zfs snapshot):

Feb 25 11:04:01 volume3 kernel: ena0: Keep alive watchdog timeout.
Feb 25 11:04:01 volume3 kernel: ena0: Trigger reset is on
Feb 25 11:04:01 volume3 kernel: ena0: device is going DOWN
Feb 25 11:04:19 volume3 kernel: ena0: ena0: device is going UP
Feb 25 11:04:19 volume3 kernel: link is UP
Feb 25 11:05:10 volume3 dhclient[33054]: send_packet6: Network is down
Feb 25 11:05:10 volume3 dhclient[33054]: dhc6: send_packet6() sent -1 of 52
bytes
Feb 25 11:26:32 volume3 kernel: ena0: The number of lost tx completion is above
the threshold (129 > 128). Reset the device
Feb 25 11:26:32 volume3 kernel: ena0: Trigger reset is on
Feb 25 11:26:32 volume3 kernel: ena0: device is going DOWN
Feb 25 11:26:33 volume3 kernel: ena0: free uncompleted tx mbuf qid 1 idx 0x182
Feb 25 11:26:33 volume3 kernel: 
Feb 25 11:26:33 volume3 kernel: stray irq260
Feb 25 11:26:33 volume3 kernel: ena0: ena0: device is going UP
Feb 25 11:26:33 volume3 kernel: link is UP
Feb 25 11:34:06 volume3 shutdown[76043]: reboot by ruben: 

Symptoms : very high load, unresponsive system (freezes/hangs on console). 
No nvme messages though. Unfortunately, I did not yet have the verbose boot
information you requested at that point. Did not have time to further debug
either, since we need this machine up and running (initiated the reboot at
11:34) :(

Regards,

Ruben

-- 
You are receiving this mail because:
You are the assignee for the bug.