On Mon, 2017-01-02 at 07:00 -0500, DAVID S wrote:
> Also, Bart, you mentioned FCoE in your reply to Scott, but I believe
> he is probably using straight FC. This issue appears to only be a
> problem with hypervisors utilizing FC targets, so this seems to
> further cement the original hypothesis that the issue is the way that
> targetcli handles VAAI/ODX. This also seems to confirm that the issue
> isn't with a specific hypervisor, since the original problems reported
> by me and a few others were with ESXi, and Scott's hosts are Hyper-V.
>
> Again, please let me know if I can assist in testing new patches, etc.
Hello David,
Does this mean that both Scott and you are using the tcm_qla2xxx driver at
the target side? Since you are suspecting VAAI/ODX, have you already tried
to configure the ESXi initiator such that it does not use VAAI? I'm not
proposing this as a permanent solution but as an approach to narrow down
what code at the target side is causing the misbehavior.
Next time you run into a lockup at the target side, can you run echo w >
/proc/sysrq-trigger and provide the data that has been added to the system
log by running that command?
Bart.��.n��������+%������w��{.n����j� ����{ay� ʇڙ���f���h������_�(�階�ݢj"��������G����?���&��
