Re: [RFC PATCH v3 00/16] Core scheduling v3

[Tim Chen]

On 10/29/19 1:40 PM, Julien Desfossez wrote:
> On 18-Sep-2019 01:40:58 PM, Tim Chen wrote:
>> I think the test that's of interest is to see my load balancing added on top
>> of Aaron's fairness patch, instead of using my previous version of
>> forced idle approach in coresched-v3-v5.1.5-test-tim branch. 
>>  
>> I've added my two load balance patches on top of Aaron's patches
>> in coresched-v3-v5.1.5-test-core_vruntime branch and put it in
>>
>> https://github.com/pdxChen/gang/tree/coresched-v3-v5.1.5-test-core_vruntime-lb
> 
> We have been trying to benchmark with the load balancer patches and have
> experienced some hard lockups with the saturated test cases, but we
> don't have traces for now.
> 
> Since we are mostly focused on testing the rebased v4 currently, we will
> post it without those patches and then we can try to debug more.
> 

Aubrey has been experimenting with a couple of patches that tries to move
task to cpu with matching cookie on wake up and load balance.  They are
much simpler than mine and got better performance on the workload he was
testing. He'll rebase those patches on v4 and post them.

Tim