Messages in this thread | | | From | "Huang, Ying" <> | Subject | Re: [mm/migrate] 9eeb73028c: stress-ng.memhotplug.ops_per_sec -53.8% regression | Date | Mon, 06 Sep 2021 16:31:41 +0800 |
| |
Chen Yu <yu.c.chen@intel.com> writes:
> On Mon, Sep 06, 2021 at 01:57:56PM +0800, Huang, Ying wrote: >> Dave Hansen <dave.hansen@intel.com> writes: >> >> > On 9/5/21 6:53 PM, Huang, Ying wrote: >> >>> in testcase: stress-ng >> >>> on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 192G memory >> >>> with following parameters: >> >>> >> >>> nr_threads: 10% >> >>> disk: 1HDD >> >>> testtime: 60s >> >>> fs: ext4 >> >>> class: os >> >>> test: memhotplug >> >>> cpufreq_governor: performance >> >>> ucode: 0x5003006 >> >>> >> >> Because we added some operations during online/offline CPU, it's >> >> expected that the performance of online/offline CPU will decrease. In >> >> most cases, the performance of CPU hotplug isn't a big problem. But >> >> then I remembers that the performance of the CPU hotplug may influence >> >> suspend/resume performance :-( >> >> >> >> It appears that it is easy and reasonable to enclose the added >> >> operations inside #ifdef CONFIG_NUMA. Is this sufficient to restore the >> >> performance of suspend/resume? >> > >> > It's "memhotplug", not CPUs, right? >> >> Yes. Thanks for pointing that out! >> >> We will update node_demotion[] in CPU hotplug too. Because the status >> that whether a node has CPU may change after CPU hotplug. And CPU >> online/offline performance may be relevant for suspend/resume. >> > Rui and I took a look at the default kernel config, it seems that CONFIG_NUMA is > enabled on laptops on some distributions. Maybe a runtime detecting flag indicating > that whether this system has enabled NUMA (static key eg) would be an option too, so as > not to enable node_demotion[] on non-NUMA laptops/desktops.
Got it! Thanks for your information. Maybe we can try Dave's method firstly and check whether that's OK for suspend/resume.
Best Regards, Huang, Ying
| |