Re: [Xen-devel] [PATCH] x86/S3: Fix cpu pool scheduling after suspend/resume (v3)

[Ben Guthro <Ben.Guthro@xxxxxxxxxx>]

On Apr 19, 2013, at 8:50 AM, "Jan Beulich" <JBeulich@xxxxxxxx> wrote:

>>>> On 19.04.13 at 14:27, Ben Guthro <Ben.Guthro@xxxxxxxxxx> wrote:
> 
>> On Apr 19, 2013, at 5:40 AM, Jürgen Groß <juergen.gross@xxxxxxxxxxxxxx> 
>> wrote:
>> 
>>> Am 17.04.2013 23:16, schrieb Ben Guthro:
>>>> This review is another S3 scheduler problem with the system_state variable
>> introduced with the following changeset:
>> http://xenbits.xen.org/gitweb/?p=xen.git;a=commit;h=269f543ea750ed567d18f2e81
>>  
>> 9e5d5ce58eda5c5
>>>> 
>>>> Specifically, the cpu_callback function that takes the CPU down during
>> suspend, and back up during resume.
>>>> We were seeing situations where, after S3, only CPU0 was in cpupool0. Guest
>> performance suffered greatly, since all vcpus were only on a single pcpu. 
>> Guests under high CPU load showed the problem much more quickly than an idle 
>> guest.
>>>> 
>>>> Removing this if condition forces the CPUs to go through the expected
>> online/offline state, and be properly scheduled after S3.
>>>> 
>>>> This also includes a necessary partial change proposed earlier by Tomasz
>> Wroblewski here:
>>>> http://lists.xen.org/archives/html/xen-devel/2013-01/msg02206.html 
>>>> 
>>>> It should also resolve the issues discussed in this thread:
>>>> http://lists.xen.org/archives/html/xen-devel/2012-11/msg01801.html 
>>>> 
>>>> v2:
>>>> Address concerns from Juergen Gross about the cpus not being put back into
>> the pool they were in prior to suspend
>>>> 
>>>> v3:
>>>> Addressed leak of cpu_suspended, clean up hard tabs
>>>> 
>>>> Signed-off-by: Ben Guthro <benjamin.guthro@xxxxxxxxxx>
>>> 
>>> Not tested, as I'm on vacation, but looks okay, so:
>>> 
>>> Acked-by: Juergen Gross <juergen.gross@xxxxxxxxxxxxxx>
>> 
>> Thanks for the review Jürgen.
>> 
>> Jan - is this a candidate for commit to 4.3, or will this be pushed out 
>> because of the code freeze?
> 
> This fixing a bug I already committed it now that Jürgen acked it.
> 
> Jan

Thanks. 

This will also apply cleanly to the 4.2 tree, and should be considered for a 
backport, IMO
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel