On 07.12.2022 12:41, Jan Beulich wrote:
> On 03.10.2022 18:21, Marek Marczykowski-Górecki wrote:
>> Documentation for credit2_runqueue=all says it should create one queue
>> for all pCPUs on the host. But since introduction
>> sched_credit2_max_cpus_runqueue, it actually created separate runqueue
>> per socket, even if the CPUs count is below
>> sched_credit2_max_cpus_runqueue.
>>
>> Adjust the condition to skip syblink check in case of
>> credit2_runqueue=all.
>>
>> Fixes: 8e2aa76dc167 ("xen: credit2: limit the max number of CPUs in a
>> runqueue")
>> Signed-off-by: Marek Marczykowski-Górecki <[email protected]>
>> Reviewed-by: Juergen Gross <[email protected]>
>> ---
>> Changes in v2:
>> - fix indentation
>> - adjust doc
>>
>> The whole thing is under cpu_runqueue_match() already, so maybe
>> cpu_runqueue_siblings_match() isn't needed at all?
>> ---
>> docs/misc/xen-command-line.pandoc | 5 +++++
>> xen/common/sched/credit2.c | 9 +++++++--
>> 2 files changed, 12 insertions(+), 2 deletions(-)
>
> George, Dario - any chance of an ack (or reasons not to)?
Another two months later I'm inclined to commit this with just Jürgen's R-b
(assuming it still applies cleanly). I'll give it a day or two more ...
Jan
