tag:blogger.com,1999:blog-6469704299235308349.post1946491224068457708..comments2024-02-09T16:24:46.087+11:00Comments on -ck hacking: 3.3.0-ck1ckhttp://www.blogger.com/profile/02904761195451530213noreply@blogger.comBlogger91125tag:blogger.com,1999:blog-6469704299235308349.post-91150848237155772532012-06-12T09:58:48.458+10:002012-06-12T09:58:48.458+10:00Hi Manuel,
linux-3.4.2-12queuePatches-bfs423-full...Hi Manuel,<br /><br />linux-3.4.2-12queuePatches-bfs423-full-ck2<br />runs now for some hours: good experience!<br /><br />We hat linux-3.2-bfs at siduction.org for some time without any complains from users. This one was a real difference to mainline!<br />Now linux-3.4-bfs is good. No slowdown for some hours. But mainline scheduler has improved also. I cannot feel the difference any more. As this was the case with linux-3.2-bfs.<br /><br />I need to learn benchmarking ...<br />Greetings from Hamburg, Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-13960160981560693892012-06-12T04:00:05.106+10:002012-06-12T04:00:05.106+10:00@Ralph: I didn't like the 3.[0..2]ers.
And the...@Ralph: I didn't like the 3.[0..2]ers.<br />And the 3.4.2 did me a complete system abort when reading from shm/tmpfs.<br />Best experience ever was 3.3.8 with D.H.s patches. But that did show this slowdown, too.<br /><br />Have you re-tested with kernels & BFS prior to the 3.3 series that there's really no slowdown?<br /><br />I already said, I only can see it after a longer uptime, say 12 to 48h. But it is fact.<br /><br />And it doesn't imply, that the CPU scheduler is wrong<br /><br />ManuelAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-56899520196922719382012-06-11T04:51:45.225+10:002012-06-11T04:51:45.225+10:00@Manuel,
sure there are Window Managers and other...@Manuel, <br />sure there are Window Managers and other programs with flaws. But ever before linux-3.3 there was significant better behavior of the BFScheduler...<br /><br />code.google is ok, we should open a google group for discussions about schedulers there!<br /><br />Ralph Ulrich<br />PS: You can find me as ralul at siduction.orgAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-30051337375060248792012-06-11T02:15:47.290+10:002012-06-11T02:15:47.290+10:00Hi, Ralph!
Many thanks for answering. (I already t...Hi, Ralph!<br />Many thanks for answering. (I already thought you got lost.^^ :-? )<br /><br />For the slowdown experience - it's the same for me (window switching) but I also use the same GUI. KDE 4.8.3 ATM. Maybe that's the culprit. Or, just a moment, you also use firefox with more tabs open? Do you have a lag, over longer uptime, when switching from tab to another tab?! I have it.<br /><br />Regarding H.D.s patches, I already proposed him the way Mou Chen went, posting his patches to a code.google.com page. I don't know anything about github nor how to use it. But I'll let him know about your proposal.<br /><br />I never had any problems with reediting those patches and they did work well in the final stage (as of 3.3.8).<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-59539520670017190582012-06-10T03:44:08.621+10:002012-06-10T03:44:08.621+10:00Hi Manuel,
I cannot explain my slow down experienc...Hi Manuel,<br />I cannot explain my slow down experience after some hours using linux-3.3-bfs. It is like a kind of resistance switching windows (kde-4.8).<br /><br />Also linux-3.4-bfs doesn't gain much. This was different with previous versions: Using linux-3.2-bfs was "feelable" better than mainline linux-3.2.<br /><br />If you are contacting to H.D. please tell him to use github. It is not feasable to guess what of his numerous patches in what special sequence need to be applied. Also there are problems with whitespace and special japanese characters (Easter Eggs in Con Kolivas code) when I tried to get H.D. patches through the web.<br /><br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-49998544477456437522012-06-06T19:21:51.107+10:002012-06-06T19:21:51.107+10:00@ Ralph Ulrich,
can you, please, explain more abo...@ Ralph Ulrich,<br /><br />can you, please, explain more about the "slowing" you do experience? I experience it, too.<br /><br />Please, feel free to post to my email posted earlier on here. I keep contact to Hillf Damon, as he's interested in this, too.<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-23172264693937746032012-06-02T01:37:39.339+10:002012-06-02T01:37:39.339+10:00Cool: insanity feature rich
/me waiting still for...Cool: insanity feature rich<br /><br />/me waiting still for a fix: <br />USE="bull" emerge cow<br />(in case you didnt know the oldest gentoo bug) <br />RalphAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-71514668056340189752012-06-02T01:26:58.347+10:002012-06-02T01:26:58.347+10:00Hillf thought he could grab some very easy fruits....Hillf thought he could grab some very easy fruits. But there are real documentation bugs in Cons code. Which didn't matter as long Con was a single "team". I hope he gets some motivation, if he reads Cons words.<br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-15273218577516920182012-06-01T21:34:42.942+10:002012-06-01T21:34:42.942+10:00And for Hilff, please do not release something tha...And for Hilff, please do not release something that is broken. Going into broken patchs means s**king your head into a pool of sh*t.You should post benchmarks if you want to claim that your things are better. <br /> ChenXhttps://www.blogger.com/profile/08096886089147792760noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-89614737766935092612012-06-01T21:30:54.539+10:002012-06-01T21:30:54.539+10:00Except Hilff's broken one, all of them work.
...Except Hilff's broken one, all of them work.<br /><br />BFS is very fair, RIFS can treat the interactive task well even with big workload. Eh..I can't say anything that is good about CFS.If you really want to get something good comment about CFS, I would say CFS can support insane configuration(***IT IS NOT NECESSARY FOR DESKTOP***)<br /><br /> ChenXhttps://www.blogger.com/profile/08096886089147792760noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-2636632680126337042012-06-01T21:19:30.913+10:002012-06-01T21:19:30.913+10:00Con, please check the mailbox, thanks. ;-)
Subject...Con, please check the mailbox, thanks. ;-)<br />Subject: [PATCH 06/01]BFS O(1) improvement.The mail included a diff.I 'm trying it already.<br /><br />Also I want to give an advice to Hilff here. Please check that your code ***REALLY WORK*** before posting it. Posting the ***BROKEN PATCH*** means wasting the others' time and sucking your head into a dish of shit, also you will lost your credit! If you want to post something and you say that your work is better, please, paste a benchmark result. No people want their box to become a tool for experiment. Scheduler is a critical part of any kind of OS!<br /><br />Here I also want to post something that is interesting.<br /><br /><br />* Chen wrote:<br /><br />> Totally about 17000 lines of code for RT sched, CFS sched, and MODULAR<br /><br />As I said it's 20 KLOC, you are probably looking at an older<br />tree.<br /><br />At 20 KLOC, as I explained, the scheduler is one of the smaller<br />kernel subsystems.<br /><br />Thanks,<br /> Ingo<br /><br />You must realise something from this mail. :D<br /> ChenXhttps://www.blogger.com/profile/08096886089147792760noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-45642070731430972762012-06-01T17:47:51.090+10:002012-06-01T17:47:51.090+10:00If we now get 4 versions of a working Linux schedu...If we now get 4 versions of a working Linux scheduler in place<br />(con,hillf,chen,mainline)<br />perhaps there is a chance to get mainline a compile time plugin infrastructure. If not this was ridiculous once more ...<br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-3593967237009645412012-06-01T16:29:46.410+10:002012-06-01T16:29:46.410+10:00Good luck Con.
And wait for new BFS.
thnaks for yo...Good luck Con.<br />And wait for new BFS.<br />thnaks for your hard work !Micronhttps://www.blogger.com/profile/00612104081287508741noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-66079107006299477832012-06-01T13:56:37.798+10:002012-06-01T13:56:37.798+10:00I will also wait. Good luck on the interview, I ha...I will also wait. Good luck on the interview, I have two myself tomorrow lolAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-39789461850330318162012-06-01T00:05:08.110+10:002012-06-01T00:05:08.110+10:00Thanks. I'll wait for BFS for 3.4, no need for...Thanks. I'll wait for BFS for 3.4, no need for BFS forks :)Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-67449909186169117712012-05-31T23:53:43.795+10:002012-05-31T23:53:43.795+10:00ck said: "Alas the first does nothing since t...ck said: "Alas the first does nothing since the first argument is there for consistency only and is optimised"<br />The real bug is documentation then:<br />+ /* p->parent seems right, but we don't need p anyway */<br />Sure, documentation was not needed as long as there was a single developerAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-20247055179162226132012-05-31T23:53:38.724+10:002012-05-31T23:53:38.724+10:00Sigh... I've tried to be reserved and
He'...Sigh... I've tried to be reserved and <br /><br />He's made the hot path of the enqueue task slower by passing it more arguments and adding more compares thinking he cleaned up a rarely used function. He completely broke nice functioning at all. Preemption broke and would cause lots of unnecessary reschedules for the wrong tasks. A vast amount of cpu cache warmth effects were broken that would adversely affect throughput. He put extra code into the expensive task taking code path with schedstats that doesn't work that way on BFS from CFS. He put fixes in that fixed nothing and sometimes broke what works. He was inconsistent about removing features yet leaving parts of them behind.<br /><br />But, if you don't believe what the code does and are quite happy to think it's going to be performant, be my guest and use it for yourself. <br /><br />As much as I would like to encourage people to hack on BFS, this is not the way to go about it, and especially without even involving me. But if he wants to maintain a fork of BFS, then that's his business. <br /><br />I've been busy preparing for a work interview, so to be honest, I've had trouble caring about code for a while. I will be syncing up BFS with 3.4 once I have more time, which is not far away.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-92012026428074652182012-05-31T23:48:50.505+10:002012-05-31T23:48:50.505+10:00I don't have THP & Co. enabled, as I thoug...I don't have THP & Co. enabled, as I thought it to be too time consuming for my lowest-end CPU (in nowadays' measurements). Same for mem compaction, zcache, cleancache, frontswap, o. dgl.<br /><br />I don't get out of RAM since some kernel revisions ago. (Can't say exactly.)<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-71295188508403494662012-05-31T23:37:40.611+10:002012-05-31T23:37:40.611+10:00Yes, doesnt boot. Emmanuel Benisty just showed:
ht...Yes, doesnt boot. Emmanuel Benisty just showed:<br />http://ompldr.org/vZTE1eQ/IMG_20120531_200543.jpg<br />But I hope Hillf Danton keeps trying, <br />because I would like to have a feature poor but error free and performant working BFS. Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-22758541926823091522012-05-31T23:33:19.895+10:002012-05-31T23:33:19.895+10:00But, dear Con Kolivas, you also should explain the...But, dear Con Kolivas, you also should explain the "missed point", "naive" & "wrong" things to us -- at least to get a little more of insight.<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-36847556558583665632012-05-31T23:26:32.440+10:002012-05-31T23:26:32.440+10:00"drop_swap_cache_aggressively"
Do you ha..."drop_swap_cache_aggressively"<br />Do you have TransparentHugePageTables activated, and don't you consider it's defragmentation feature needs some aggressivly space hold free, just in case you get out of free RAM space?<br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-5600329285849251832012-05-31T23:16:54.365+10:002012-05-31T23:16:54.365+10:00Yes. Doesn't boot ;-) BFS 420 does. MKYes. Doesn't boot ;-) BFS 420 does. MKAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-61152452771819452742012-05-31T23:15:13.839+10:002012-05-31T23:15:13.839+10:00As turns out Con says below these H.D. patches don...As turns out Con says below these H.D. patches dont fix anything. No need to work about that ...<br /><br />I was hot about H.D. patches, because I had observed some retarding when running my linux-3.3.x-bfs420 gentoo system for hours. Ever less performance after some hours... <br /><br />But such issues could be introduced by "tainting" proprietary software (nvidia,broadcom-wl)....<br />Ralph UlrichAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-45756424672297985092012-05-31T23:04:11.885+10:002012-05-31T23:04:11.885+10:00Manuel, then we need a fork: Out there - mainline ...Manuel, then we need a fork: Out there - mainline CFS - is highly configurable. And must be configured (as distributions do hopefully). We need a not-need-to-know Scheduler for the most people.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-33883430393385694172012-05-31T22:58:55.134+10:002012-05-31T22:58:55.134+10:00Doesnt work, because copy-paste adds up a thousend...Doesnt work, because copy-paste adds up a thousends of blanks and tabs into the copied text.<br />Saving the html page also doesnt work, because there are lots of html inserted characters.<br />Ralph UlrichAnonymousnoreply@blogger.com