tag:blogger.com,1999:blog-6469704299235308349.post7527016919664868291..comments2024-03-28T15:50:13.644+11:00Comments on -ck hacking: BFS 0.430, -ck1 for linux-3.9.xckhttp://www.blogger.com/profile/02904761195451530213noreply@blogger.comBlogger42125tag:blogger.com,1999:blog-6469704299235308349.post-35396074938362430532013-07-02T01:26:26.229+10:002013-07-02T01:26:26.229+10:00Personally I usually wait for 3.x.1 before install...Personally I usually wait for 3.x.1 before installing a new kernel unless it fixes some issue I'm having.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-91198900836122538742013-06-29T20:33:13.917+10:002013-06-29T20:33:13.917+10:00Have you also tried with the official 3.9 (not ck)...Have you also tried with the official 3.9 (not ck)? Do the same errors appear?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-57035702831907813962013-06-28T23:01:04.275+10:002013-06-28T23:01:04.275+10:00thanks for sharing the article. i had been looking...thanks for sharing the article. i had been looking for this!<br /><a href="http://www.qualitywebprogrammers.com/" rel="nofollow">Affordable Web Programmer</a><br />M.Smithhttps://www.blogger.com/profile/07396536297083977323noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-37866102921481963192013-06-28T22:45:07.292+10:002013-06-28T22:45:07.292+10:00Hello,
I have several problems with the new kerne...Hello,<br /><br />I have several problems with the new kernel version (3.9)<br />Any help provided is appreciated :)<br />https://bbs.archlinux.org/viewtopic.php?pid=1293535ttouchhttps://www.blogger.com/profile/07846572088455727193noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-44994888971223513732013-06-27T10:15:40.264+10:002013-06-27T10:15:40.264+10:00I second that:
would be nice to know, yeah
CFS i...I second that:<br /><br />would be nice to know, yeah<br /><br />CFS is significantly less efficient than BFS and there are regularly from time to time small interruptions in e.g. audio playback - even when heavily tuned ...<br /><br />thanks !Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-54026048919918899092013-06-26T00:29:46.006+10:002013-06-26T00:29:46.006+10:00Any resyncs against 3.10 tree?Any resyncs against 3.10 tree?Oleksandr Natalenkohttps://www.blogger.com/profile/12098091624630953604noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-22477377468166500942013-06-16T04:33:58.596+10:002013-06-16T04:33:58.596+10:00For those of you also using the BFQ I/O scheduler....For those of you also using the BFQ I/O scheduler...<br /><br />they've brought out a new release: "v6r2 for 2.6.38 - 3.9.0" containing quite a bunch of fixes<br /><br />Announcement: https://groups.google.com/forum/?fromgroups=#!topic/bfq-iosched/BcT3HBmQO5M<br /><br />Patches: http://algo.ing.unimo.it/people/paolo/disk_sched/patches/3.9.0-v6r2/<br />(for older kernels browse the parent directory)<br /><br />Best regards, ManuelAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-5198185127723058252013-06-13T17:33:59.080+10:002013-06-13T17:33:59.080+10:00I was reading about some power-efficiency schedule...I was reading about some power-efficiency scheduler patches who haven't been merged in mainline yet (at http://lwn.net/Articles/546664/ and http://lwn.net/Articles/552885/)<br /><br />I wonder if BFS needs something like this too and how does it compare in terms of power usage with cfs?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-82389206563882948152013-06-13T00:32:48.535+10:002013-06-13T00:32:48.535+10:00It's silly because I guess it's better to ...It's silly because I guess it's better to use perf subsystem.<br /><br />kernelat launches child process and measures time from calling system() to entering child's main(). Launching more children at the same time can give us some responsiveness value.Oleksandr Natalenkohttps://www.blogger.com/profile/12098091624630953604noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-37398552960258152652013-06-12T06:58:35.554+10:002013-06-12T06:58:35.554+10:00Sounds more like a race condition in the unmaintai...Sounds more like a race condition in the unmaintained mencoder code brought out by BFS rather than a BFS problem itself.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-33667696340038319002013-06-11T03:59:12.716+10:002013-06-11T03:59:12.716+10:00@Manuel
No, no log message, just mencoder stoppin...@Manuel<br /><br />No, no log message, just mencoder stopping dead in its encoding and sitting there, using 0% CPU forever. It was always during the second pass of a 2 passes encoding (VBR).<br />And no, I'm not using any other kernel patch, just the vanilla Linux kernel...<br /><br />Thierry.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-7130258768777887772013-06-10T07:52:20.258+10:002013-06-10T07:52:20.258+10:00@Thierry:
Have you had any relevant log messages r...@Thierry:<br />Have you had any relevant log messages related to this issue? Would be a great help if you posted them. And... are you using additional patches?<br /><br />Thanks, ManuelAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-85570029073698647802013-06-10T07:45:51.080+10:002013-06-10T07:45:51.080+10:00@post-factum:
Thank you for providing your work to...@post-factum:<br />Thank you for providing your work to us. Can you, please, provide a more detailed description of what it does before I use it (on the page and in a in-tree readme) and why you call it "silly".<br /><br />Manuel<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-30785972943071651592013-06-08T03:48:12.212+10:002013-06-08T03:48:12.212+10:00Greetings,
Just to let you know that I tested you...Greetings,<br /><br />Just to let you know that I tested your BFS patch v0.430 during a couple of weeks, but had to revert to a vanilla kernel because BFS causes mencoder to deadlock when using multiple cores to encode some videos (about 1 in 3 videos)...<br /><br />Thierry.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-40537644941660184012013-06-07T16:01:57.809+10:002013-06-07T16:01:57.809+10:00Responsiveness-Benchmark? Try this one: https://gi...Responsiveness-Benchmark? Try this one: https://github.com/pfactum/kernelat/Oleksandr Natalenkohttps://www.blogger.com/profile/12098091624630953604noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-26741741205204806222013-06-07T08:18:02.807+10:002013-06-07T08:18:02.807+10:00It's the old give some and get some topic. Int...It's the old give some and get some topic. Interactivity for throughput in I/O or vice versa. The 300 Hz don't make ALL things better on my old system, it stays old. The same is valid for the BFQ I/O scheduler. You need to test it for yourself. <br />For now we even don't have a 'Responsiveness-Benchmark' so far, what is a real shame!<br /><br />ManuelAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-78769786268199616792013-06-05T18:45:50.401+10:002013-06-05T18:45:50.401+10:00I thought 1000 + nohz was better for responsivity?...I thought 1000 + nohz was better for responsivity? Is 300 better for bfs on recent mobile cpus?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-29246827236022424292013-06-04T08:17:20.113+10:002013-06-04T08:17:20.113+10:00Ralph,
thanks for remembering me of CONFIG_HZ_300...Ralph,<br /><br />thanks for remembering me of CONFIG_HZ_300. I know, you've proposed this some months or even a year or more ago. Dunno, why I've abandonned that setting. But what I definitely remember is I got better scores in WCG (www.worldcommunitygrid.org) with CONFIG_HZ_300.<br /><br />I completely don't understand your second paragraph beginning with "Isn't a possible...".<br /><br />But currently I'm running a 3.9.4 with my optimizations and your 300 Hz. Let's see.<br /><br />BTW: My htop (openSUSE 12.3) seems to have problems, that top doesn't show up: Orphaned processes that display, but that really aren't running any more. Maybe htop is dead? Or at least unusable?!<br /><br />Manuel<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-29177744803248111092013-06-03T19:58:22.785+10:002013-06-03T19:58:22.785+10:00Manuel,
NO_HZ is proposed to spare energy: When id...Manuel,<br />NO_HZ is proposed to spare energy: When idle do no more irq wakeups. But I do instead:<br />- no NO_HZ<br />- CONFIG_HZ_1000 down to CONFIG_HZ_300<br />This also safes energy when idle 70 percentage and without the problems of NO_HZ set. And - unsure about - it provides a better throughput on highload, because the less irq context switches !?<br /><br />Isn't a possible intervention of 300 times a second enough for me as user? I mean, even case of playing games? The unreasonable high 1000 Hz was introduced because of worst case experience of waiting times of over a second. But this prevents BFS as the scheduler!<br /><br />I set CONFIG_RCU_BOOST_PRIO=18 , which results a process rcub/0 with prio -19. I need this lower abs number than the process irq/21-b43 with prio -51, because I have seen my wify connection got unreliable otherwise. Manuel, htop shows with push F6 and select sorting column your system priorities.<br /><br />Ralph Ulrich<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-15141579821432923852013-06-03T03:49:25.827+10:002013-06-03T03:49:25.827+10:00Hi Ralph,
nice reading you again!
What does the 3...Hi Ralph,<br />nice reading you again!<br /><br />What does the 300 ticks vs. 1000 (=BFS default) better?<br /><br />Regarding the RCU boosting, I've made good experiences with the following:<br />[CONFIG_TINY_PREEMPT_RCU=y is appropriate for my uniprocessor/-core system, btw.]<br />CONFIG_RCU_BOOST=y<br />CONFIG_RCU_BOOST_PRIO=99 <-- making it realtime<br />CONFIG_RCU_BOOST_DELAY=331 <-- using a prime number to avoid reoccurrences, smaller than default=500<br /><br />Greets,<br /><br />Manuel<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-4029841047357944522013-06-02T20:47:11.313+10:002013-06-02T20:47:11.313+10:00Hi Manuel
I think these special patches target spe...Hi Manuel<br />I think these special patches target special use cases (battery life etc). I myself don't use them but use my own optimizations:<br />rcu boost up<br />no no-hertz<br />300 ticks instead of thousand ticks.<br /><br />Greetings from Hamburg, from where in sunshine I can see the flooding bad weather in the east.<br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-61089298718873792922013-06-01T09:02:51.700+10:002013-06-01T09:02:51.700+10:00@ck:
I don't like seeing you dropping patches....@ck:<br />I don't like seeing you dropping patches. But when you're on the run...<br /><br />The following sub-patches seem to harm performance/ interactivity on my old computer:<br />mm-kswapd_inherit_prio-1.patch<br />mm-idleprio_prio-1.patch<br /><br />I'm making heavy use of /dev/shm that gets partially swapped out, as I use it as a ramdisk.<br />2GB RAM<br />4GB swap (on 2nd disk)<br />3GB /dev/shm<br />(Read the other setup from my previous postings, please.)<br /><br />With your 2 patches mentioned above, I'd get glitches and stuttering in video-playback while using /dev/shm with swapping in parallel. <br /><br />Maybe, I'm the last Unicorn you have, to test your patches with an old machine.<br /><br />Best regards,<br /><br />ManuelAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-72372287310129715482013-05-29T02:41:08.827+10:002013-05-29T02:41:08.827+10:00Your error is just this one:
/home/gorneman/Build...Your error is just this one:<br /><br />/home/gorneman/Builds/Kernel39/linux-3.9.4/kernel/sched/bfs.c: In function ‘irqtime_account_hi_si’:<br />/home/gorneman/Builds/Kernel39/linux-3.9.4/kernel/sched/bfs.c:2333:2: error: implicit declaration of function ‘nsecs_to_cputime64’Anonymoushttps://www.blogger.com/profile/11469174621439712081noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-60931298415844470582013-05-29T02:40:07.371+10:002013-05-29T02:40:07.371+10:00This comment has been removed by the author.Anonymoushttps://www.blogger.com/profile/11469174621439712081noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-88228278080445499522013-05-28T17:47:49.560+10:002013-05-28T17:47:49.560+10:00Hello, I try to compile kernel 3.9.4 in ubuntu 12....Hello, I try to compile kernel 3.9.4 in ubuntu 12.10 with ck patchset and BFQ but get this error http://pastebin.com/rJSitgZb. Someonbe can help me? ThanksAnonymousnoreply@blogger.com