Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1701521
| From | Shivappa Vikas <vikas.shivappa@intel.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH 16/28] x86/intel_rdt: Prepare to add RDT monitor cpus file support |
| Date | 2017-08-01 23:40 +0200 |
| Message-ID | <u9N3r-Rr-5@gated-at.bofh.it> (permalink) |
| References | <u7fpf-86t-3@gated-at.bofh.it> <u7fpi-86t-81@gated-at.bofh.it> <u9Ll0-8cw-31@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Tue, 1 Aug 2017, Thomas Gleixner wrote:
> On Tue, 25 Jul 2017, Vikas Shivappa wrote:
>> /*
>> * The cached intel_pqr_state is strictly per CPU and can never be
>> * updated from a remote CPU. Functions which modify the state
>> @@ -49,6 +47,8 @@
>> */
>> DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
>>
>> +DEFINE_PER_CPU_READ_MOSTLY(struct intel_pqr_state, rdt_cpu_default);
>
> Cacheline wise this is suboptimal. You have to touch two cachelines on each
> context switch (at least for read).
>
> If you make that:
>
> struct intel_pqr_state {
> u32 default_cosid;
> u32 default_rmid;
> u32 cur_cosid;
> u32 cur_rmid;
> };
>
> DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
>
> then it's all together and you spare one cache line.
Will fix..
Thanks,
Vikas
>
> Thanks,
>
> tglx
>
Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread
Re: [PATCH 16/28] x86/intel_rdt: Prepare to add RDT monitor cpus file support Thomas Gleixner <tglx@linutronix.de> - 2017-08-01 21:50 +0200 Re: [PATCH 16/28] x86/intel_rdt: Prepare to add RDT monitor cpus file support Shivappa Vikas <vikas.shivappa@intel.com> - 2017-08-01 23:40 +0200
csiph-web