Announcement

Collapse
No announcement yet.

Two Years With Linux BFS, The Brain Fuck Scheduler

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Two Years With Linux BFS, The Brain Fuck Scheduler

    Phoronix: Two Years With Linux BFS, The Brain Fuck Scheduler

    This month marks the two-year anniversary of the release of BFS, the Brain Fuck Scheduler, for the Linux kernel. While BFS has not been merged into the mainline Linux kernel, the scheduler is still actively maintained by Con Kolivas and patches are updated for new kernel releases. The BFS scheduler has also reached mild success and adoption over the past two years. In this article is a fresh look at the Brain Fuck Scheduler along with a fresh round of benchmarks from the Linux 3.0 kernel.

    http://www.phoronix.com/vr.php?view=16302

  • #2
    this benchmarks are totally inadequate. BFS scheduler is designed to reduce LATENCY in desktop applications.

    i'd check for amount of frames dropped in some FPS game or quality of video capture framerate-wise, as this is where the scheduler latency matters. but these things cannot really be measured with a benchmark ( i think ).

    before CFS epsxe emulator would stall randomly for ~0.5 second now and then. on CFS i sometimes get 0.1 sec delays, which is not the case with BFS at all. that is what should be measured, not performance of webserver or how much FPS can you squeeze of a game.

    Phoronix staff - please, read again this post http://lkml.org/lkml/2009/9/6/231 and think about this article again.
    Last edited by yoshi314; 08-16-2011, 03:14 AM.

    Comment


    • #3
      fail!

      BFS is about latency, not throughput!

      Comment


      • #4
        Well, don't openarena and unigine benches also list the min fps? That should be a good indicator.

        Comment


        • #5
          Kernel 3.0 is unusable for me without BFS. I mean really, a total piece of crap experience. Benchmark THAT.

          Comment


          • #6
            Would someone care to explain how somebody like Con-man Kolivas who goes out of his way to burn bridges and insult players... still manages to get press releases?

            Oh, and RealNC, don't make me step back in here and smack you around some more. Seriously, if all you can come up with is a one liner retort that such and such a kernel version is "insert explicative here" you haven't learned anything over the years.

            Comment


            • #7
              Originally posted by Saist View Post
              Would someone care to explain how somebody like Con-man Kolivas who goes out of his way to burn bridges and insult players... still manages to get press releases?
              Because he wrote a scheduler that improved Desktop Linux for a lot of people. About the insults, surely, when you're treated with so much ignorance you tend to tell all the ignorants to go fuck themselves. Which is only something that raised my respect for CK and what he's doing even more. He's like the lone hacker who accomplishes tremendous tasks and throws the results at the face of the corrupt establishment. In other words, a software hero.

              Oh, and RealNC, don't make me step back in here and smack you around some more.
              Please do. It will be the usual offensive stuff that attacks people on a personal level with lots of bigotry in it. Seriously, go ahead.

              Seriously, if all you can come up with is a one liner retort that such and such a kernel version is "insert explicative here" you haven't learned anything over the years.
              What I have learned over the years is that one guy, alone, improved my Linux experience a hell of a lot while his contributions were never acknowledged properly. And also have learned that people like you will continue to spread FUD because you simply can't stand being wrong. But I've got some bad news for you: You're not the pope.

              Comment


              • #8
                it's just too bad that BFS + systemd is still a no go :/ (no cgroup support).

                Comment


                • #9
                  although in this case favorable, I think raw performance benchmarks send the wrong message. What BFS is optimizing for is user experience, UI latency, sometimes that can come at the expense at total throughput, and that's ok.

                  Comment


                  • #10
                    Con Kolivas commented on his blog about the new Phoronix benchmarks:

                    http://ck-hack.blogspot.com/2011/08/...isits-bfs.html

                    Edit:

                    The graph about the 8000 processes server is surely slamming at the face of CFS. And that, ladies and gentlemen (and Michael, most importantly), is how you would benchmark a CPU scheduler. The Phoronix article misses the point almost entirely. If you can't produce appropriate benchmarks, why did you bother at all? It was an article that serves no purpose. So why did you write it then?
                    Last edited by RealNC; 08-16-2011, 07:41 AM.

                    Comment


                    • #11
                      Originally posted by RealNC View Post
                      Kernel 3.0 is unusable for me without BFS. I mean really, a total piece of crap experience. Benchmark THAT.
                      Care to explain what's wrong? I know CFS doesn't allow you to use millions Hz as a timer frequency, but some people explained it's a dumb stupid idea. Last time you were bashing KDE just because your home made and messed up by yourself distro had some problems with it - you were using unstable graphic drivers... maybe this time it's the same?

                      Comment


                      • #12
                        Originally posted by kraftman View Post
                        Care to explain what's wrong? I know CFS doesn't allow you to use millions Hz as a timer frequency, but some people explained it's a dumb stupid idea.
                        Why the FUD? BFS recommends 1000Hz, not a million. Please show me where BFS recommends more than that. It's not even freakin' possible to use more than 1000Hz with BFS.

                        Ah, you mean the -ck patch, not BFS. You have no clue (again) what BFS is. And even the -ck patch in question even says that more than 1000Hz is only used for some broken software that depend on timer frequency and should not be used without a strong reason because it can break things.

                        You're a FUD spreader, kraftman. And the worst part is you know it, but simply don't give a shit.

                        Last time you were bashing KDE just because your home made and messed up by yourself distro had some problems with it - you were using unstable graphic drivers... maybe this time it's the same?
                        More FUD. Those problems were fixed as soon as the kernel 3.0 BFS came out. It was the CFS scheduler that fucked up the performance of my system. With BFS + 3.0.1, everything is fine again. Oh, and my system is configured perfectly.

                        Kraftman: clueless and ignorant as ever. And with proof, as is evident from the above.
                        Last edited by RealNC; 08-16-2011, 07:48 AM.

                        Comment


                        • #13
                          Originally posted by curaga View Post
                          Well, don't openarena and unigine benches also list the min fps? That should be a good indicator.
                          That would almost be good.
                          What is needed is a way to print a graph that shows how the framerate is moving per second. Like one of those stock marked price graphs you see in those papers.
                          At the same time there should be a way of figuring out when there is a I/O timeout, which is even more essential. That should also be printed into some graph.

                          And there should be a second stress test: A simple "the gui lags" test done via a recording camera where you attempt to do something while the linux kernel is compiling in the background with too many threads.

                          Comment


                          • #14
                            Originally posted by RealNC View Post
                            Why the FUD? BFS recommends 1000Hz, not a million. Please show me where BFS recommends more than that.
                            It's not the FUD. Con allowed you to use at least 10kHz which was stupid. I'm not talking about recommendations, but about ability.

                            Ah, you mean the -ck patch, not BFS. You have no clue (again) what BFS is. And even the -ck patch in question even says that more than 1000Hz is only used for some broken software that depend on timer frequency and should not be used without a strong reason because it can break things.
                            It seems you don't have a clue or your logic fails, because I didn't even mention BFS, but CFS. As far I can see it's you who does FUD here. You didn't even care to explain what's so terribly wrong with CFS in Linux 3.0. You were also FUDing about KDE while the problems you were experiencing were your fault, but let's focus on schedulers.

                            You're a FUD spreader, kraftman. And the worst part is you know it, but simply don't give a shit.
                            Care to explain? It seems you didn't realize what I'm talking about.

                            More FUD. Those problems were fixed as soon as the kernel 3.0 BFS came out. It was the CFS scheduler that fucked up the performance of my system. With BFS + 3.0.1, everything is fine again.
                            As far as I remember your problems were related to unstable graphic drivers. How CFS could mess up your performance with KDE? Again, care to explain what was wrong? 3.0.1 and 3.0 is not the same, so maybe it wasn't BFS which fixed your problems, but DRM or something. Your "proof" is no more.

                            Kraftman: clueless and ignorant as ever. And with proof, as is evident from the above.
                            You're making me laugh. While you didn't even know what I was talking about and you started your biased talk about BFS (which I didn't even mention) it's you who's clueless (as ever).

                            Comment


                            • #15
                              Originally posted by RealNC View Post
                              It's not even freakin' possible to use more than 1000Hz with BFS.
                              http://www.phoronix.com/scan.php?pag...item&px=ODAxOQ

                              Not true. Con allowed you to use 10KHz patch with BFS.

                              Comment

                              Working...
                              X