tag:blogger.com,1999:blog-6469704299235308349.post4806674638596977598..comments2024-02-09T16:24:46.087+11:00Comments on -ck hacking: 3.1.0-ck2, BFS 0.415ckhttp://www.blogger.com/profile/02904761195451530213noreply@blogger.comBlogger47125tag:blogger.com,1999:blog-6469704299235308349.post-32097868703445595062012-01-05T19:31:59.817+11:002012-01-05T19:31:59.817+11:00Linux 3.2 is out!Linux 3.2 is out!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-53445709000999220042012-01-03T02:04:21.323+11:002012-01-03T02:04:21.323+11:00Happy new year, and thanks for your very good job ...Happy new year, and thanks for your very good job !!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-69318168767999975312011-12-26T01:41:37.922+11:002011-12-26T01:41:37.922+11:00Happy Holidays, CK, everyone :)Happy Holidays, CK, everyone :)Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-68729345100591564532011-12-20T03:28:56.683+11:002011-12-20T03:28:56.683+11:00That bug has annoyd me for a few weeks.That bug has annoyd me for a few weeks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-26781414634889695032011-12-19T19:17:52.036+11:002011-12-19T19:17:52.036+11:00Perhaps someone knowledgeable enough here could lo...Perhaps someone knowledgeable enough here could look into it?<br /><br />Hope you can find the time to release a 3.2-based BFS though :)Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-30397452660326066942011-12-19T11:48:26.773+11:002011-12-19T11:48:26.773+11:00Yep looks like there's some silly accounting b...Yep looks like there's some silly accounting bug in there. Don't know if/when/how I'll be able to fix it any time soon, sorry.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-70283590100776592082011-12-19T04:02:24.700+11:002011-12-19T04:02:24.700+11:00— Recently I've noticed some really insane val...— Recently I've noticed some really insane values in sys part of timing: http://poige.livejournal.com/520776.htmlpoigehttps://www.blogger.com/profile/14290248818990453110noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-8579739927311205272011-12-17T19:13:31.751+11:002011-12-17T19:13:31.751+11:00Great! it's been merged in 3.2, see for exampl...Great! it's been merged in 3.2, see for example Wu's code in https://github.com/torvalds/linux/blob/v3.2-rc6/mm/page-writeback.cAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-18691040625355555512011-12-17T13:21:20.957+11:002011-12-17T13:21:20.957+11:00Anyways, for running 3.1.* kernels, it's a wor...Anyways, for running 3.1.* kernels, it's a worthy trial.<br /><br />Whether 3.2 comes @ X-Mas with it or without,<br /><br />Many thanks to Con!<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-45168564670547730042011-12-17T12:58:10.535+11:002011-12-17T12:58:10.535+11:00I wrote to Wu Fengguang now with a 'short'...I wrote to Wu Fengguang now with a 'short' explanation. Let's wait for his possible comment. This Combo works well, maybe I should increase file sizes over 1.3GB @shmfs ;-)<br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-76320975057654261602011-12-17T12:57:13.607+11:002011-12-17T12:57:13.607+11:00Yes, according to http://lwn.net/Articles/465537/ ...Yes, according to <a href="http://lwn.net/Articles/465537/" rel="nofollow">http://lwn.net/Articles/465537/</a> it has been merged.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-35650241669851895012011-12-17T10:57:10.206+11:002011-12-17T10:57:10.206+11:00@CK: Thanks for informing me about these facts.
M...@CK: Thanks for informing me about these facts. <br />My "testcase" is no benchmark at all and would/must fluctuate from day to day with files I need to decode+reencode (missing disk space). So the results would never be scientifically reproducible or "safe of proof" even on here. <br />Though I don't have only just "subjective feelings" that things got much better with that patchset, I just looked at the clock and watched a video and that tells all about the progress. That's no environment+result kernel developers would ever accept. (I know that they bite from early reiserfs development.)<br /><br />Whom do I need to contact next before posting to LKML? Wu Fengguang, perhaps? Please, advise me!<br /><br />Also, I thought, these patches are already included into 3.2-rcs. Did I read too fast? <br /><br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-34969088108871156842011-12-17T09:40:41.276+11:002011-12-17T09:40:41.276+11:00Thanks for reporting back Manuel. You know you cou...Thanks for reporting back Manuel. You know you could actually help these I/O patches get into mainline linux kernel by reporting your testcase and results with/without this patchset applied to the linux kernel mailing list. The author of these patches is having trouble getting enough people to report that they're helpful. This is a common problem of course with regular user issues and linux kernel development. Don't be shy, they won't bite if you have a clear testcase like yours.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-7359949394833237962011-12-17T09:25:10.360+11:002011-12-17T09:25:10.360+11:00@CK: I want to thank you very much for the link to...@CK: I want to thank you very much for the link to these 11+(!) patches for IO-less-dirty-throttling, too! In version v12 they apply to 3.1.4 from openSUSE with CK2 and BFQ patches and compile and work fine.<br /><br />They are a great effort! Though they don't resolve my described issues with loaded shmfs+swap completely -- hickups in vlc-played videos appear less often and with much shorter delays when processing the huge video files as described above at the same time. Also the overall processing time gets reduced greatly as there are much fewer and also shorter stalls.<br /><br />Just wanted to let you know my first experience to that combo,<br />Manuel KrauseAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-60873821842054632262011-12-16T04:28:47.194+11:002011-12-16T04:28:47.194+11:00Interesting patch (IO-less dirty throttling v12), ...Interesting patch (IO-less dirty throttling v12), thanks for the link!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-12721046702032899902011-12-16T03:56:49.552+11:002011-12-16T03:56:49.552+11:00[Ralph Ulrich] By the way, not even a kernel hacke...[Ralph Ulrich] By the way, not even a kernel hacker, I ever saw this complicatedness. This is why I never trusted out of mainline tree patches regarding IO (also no ck-mm patches for me). Also tuxonice project has just quited ...Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-31745008643100012322011-12-15T20:40:12.082+11:002011-12-15T20:40:12.082+11:00Not directly, but there are definitely mainline VM...Not directly, but there are definitely mainline VM patches that I'm looking forward to, like this <a href="http://lwn.net/Articles/456904/" rel="nofollow">No-I/O dirty throttling</a>. Though it worries me seeing how complex this solution is :\ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-89535482677114779042011-12-15T19:14:37.875+11:002011-12-15T19:14:37.875+11:00[Ralph Ulrich] Also regarding the mm mv thing (I a...[Ralph Ulrich] Also regarding the mm mv thing (I am not a kernel hacker):<br />I mentioned above that I was hit by heavy IO, also I didn't experinced this before. I wonder if I had this because of the HugeTable feature: Was this relative new to linux? Due to the following artikel this is because of some background task delivering these huge pages. Though servers might profit, but me as desktop user, should I disable config-huge-pages?<br />But this issue should be better with linux-3.2:<br />http://lwn.net/Articles/467328/<br /><br />CK, is this something your mm patches are about?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-11945778048408980482011-12-15T13:28:03.174+11:002011-12-15T13:28:03.174+11:00At this stage I'm considering abandoning the V...At this stage I'm considering abandoning the VM patches altogether in the future as the virtual memory subsystem is so messy and complex that it's getting impossible to predict how it's going to behave. So unfortunately the answer to that would be no.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-82418760372051714112011-12-15T13:20:08.957+11:002011-12-15T13:20:08.957+11:00@CK: Many thanks for your answer!
Can there be an ...@CK: Many thanks for your answer!<br />Can there be an additional patch to reduce to-and-forth-swapping (in cases it won't be needed at all) with shmfs/swap relations?!<br /><br />Best regards,<br />[Manuel Krause]Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-30122815667584149212011-12-15T10:04:01.883+11:002011-12-15T10:04:01.883+11:00[Ralph Ulrich] "The very scheduler specific&q...[Ralph Ulrich] "The very scheduler specific" features of cgroups, such that the "famous" crgroup patch which Linus T. applauded for his compile jobs, are of no interest for systemd. Or, do I miss something in this regard?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-11078824562732417172011-12-15T09:39:14.432+11:002011-12-15T09:39:14.432+11:00Perhaps if you have NO cgroups enabled in your ker...Perhaps if you have NO cgroups enabled in your kernel then systemd will fail to load. Many of the cgroups features still work with BFS, except for some of the very scheduler specific ones.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-15814601497750575222011-12-15T09:34:12.836+11:002011-12-15T09:34:12.836+11:00[Ralph Ulrich]Systemd is a service-management util...[Ralph Ulrich]Systemd is a service-management utility, BFS a scheduler. What features do you talk about?<br /><br />I do use an Linux-3.1.5 BFS patched kernel on a Debian-unstable with systemd as init in this moment of writing ...Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-62744576859161797222011-12-15T08:34:04.133+11:002011-12-15T08:34:04.133+11:00No config options that are available should have a...No config options that are available should have any bad effects on BFS. If systemd makes cgroup support for features that BFS does not support a mandatory requirement then systemd becomes mutually exclusive with BFS. I can enable stubs that pretend the support is there in BFS but then that will just break things when systemd tries to use these interfaces. Systemd will be yet another one of those polarising technologies... sigh.ckhttps://www.blogger.com/profile/02904761195451530213noreply@blogger.comtag:blogger.com,1999:blog-6469704299235308349.post-3196497092651165072011-12-14T23:44:06.799+11:002011-12-14T23:44:06.799+11:00[Ralph Ulrich]
There is some discussion at
https:/...[Ralph Ulrich]<br />There is some discussion at<br />https://wiki.archlinux.org/index.php/Talk:Systemd<br />cited there: CK says:<br /> "The cgroup features that aren't available with BFS will not appear when BFS is enabled. The rest of the cgroup features still work."<br /><br />As I understand this meant: BFS as a scheduler doesnt want to regard any cgroup setting for doing cpu core jobs priorities. But this does not mean cgroups as needed by systemd are not possible!<br /><br />In this arch-linux wiki about using systemd there is stated: "not supported BFS" patched Linux kernel.<br /><br />Systemd as a service manager is not about interfering any scheduler priorities! This misunderstanding should be clearified!<br /><br />Are there any cgroup config settings thinkable in /usr/src/linux/.config that could have bad influence on BFS?Anonymousnoreply@blogger.com