Re: High latency while CPU is at full load
"Joseph D. Wagner" <[email protected]> Tue, 07 Oct 2014 18:15:16 -0700
| Newsgroups | org.kernel.vger.linux-newbie |
|---|---|
| Message-ID | <[email protected]> |
On 10/07/2014 12:12 pm, Grozdan wrote: > Hi, > > I went through the Majordomo list but was not able to find an > appropriate list so I'm trying here. > > Basically, my problem is this: > > I'm doing a lot of audio/video encoding on an AMD FX8350. The encoder > process always runs at nice 10. Even so, my whole system feels very > sluggish. Switching between different app windows and/or virtual > desktops takes up usually 3-5 seconds giving the impression that there > is not enough processing power. Browsing the web is also severely > impacted. > > I had to tune CFS in order to be (much) more responsive during an > encoding session. This has worked out pretty well thus far, but it is > my opinion that the user should *not* need to fiddle with buttons to > make his system respond fluently even under high load. The below is > what I had to do in order to get a snappy system during such load > > kernel.sched_nr_migrate = 64 > kernel.sched_latency_ns = 65000000 > kernel.sched_wakeup_granularity_ns = 100000 > kernel.sched_min_granularity_ns = 100000 > kernel.sched_migration_cost_ns = 7000000 > > PS: If this is not the right list, please forward this mail to the > appropriate one I think your question may be too advanced for the newbie list. I recommend posting this to linux-kernel. Be sure to include your exact kernel version (/proc/version), total RAM, which desktop environment you are using (including version), and the specific software you are using for the encoding. Output from /proc/sched_debug, /proc/schedstat, and /proc/*PID*/sched would be useful as well. (where *PID* is the process id of your encoding process). Joseph D. Wagner -- To unsubscribe from this list: send the line "unsubscribe linux-newbie" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.linux-learn.org/faqs