Announcement

Collapse
No announcement yet.

RIFS-ES Linux Kernel Scheduler Released

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

  • #31
    Originally posted by ulenrich View Post
    Chen,
    could you look into the sleepy thingy once more?
    I recently had a little annoyance with my wlan, this happened two times :
    - doing something not internet related (watching soccer dvb-t using kaffeine) longer than an hour
    - lost my wlan internet connection
    The same happened directly after this a second time the same conditions.

    Why I think it is RIFS related: On Gentoo, normaly loosing connection it is sufficient to
    rc-service dhcpcd restart

    But I had to do:
    rc-service dhcpcd stop
    rc-service wpa_supplicant restart
    rc-service dhcpcd start

    Which indicates a more deeply my broadcom-sta-wl module involved ...
    I think this is not related to the scheduler.(Maybe I have to do a test to prove)
    Actually Linux kernel sucks with wireless

    Comment


    • #32
      Chen,
      really? Please look closely into wakeup features before publishing!

      more generally I meant:
      If a connection I have to reassure in certain time frames,
      could this be a side effect of the RIFS:
      Missing an answer in a timely manner?
      Which disconnected my wlan because of a timeout?

      Comment


      • #33
        Originally posted by ulenrich View Post
        Chen,
        really? Please look closely into wakeup features before publishing!

        more generally I meant:
        If a connection I have to reassure in certain time frames,
        could this be a side effect of the RIFS:
        Missing an answer in a timely manner?
        Which disconnected my wlan because of a timeout?
        I would try to made the scheduler in modular form and find whether it can be solved.

        Comment


        • #34
          Chen,
          I just wanted to say, could you test more closely if
          RIFS suits needs and requirements of wakeup threads in general terms.

          Comment


          • #35
            Originally posted by ulenrich View Post
            Chen,
            I just wanted to say, could you test more closely if
            RIFS suits needs and requirements of wakeup threads in general terms.
            If you have time please contact with me by mail and it could be better for me to solve and test.
            Chen

            Comment


            • #36
              Originally posted by kernelOfTruth View Post
              ++

              I second that


              will try it next week - by then additional fixes for btrfs probably will get in and the kernel should be pretty usable/stable
              Originally posted by TAXI View Post
              Would you please share the patch? Would love to test it.
              Here is RIFS.ES-V1 patch For kernel 3.5.x:

              I am now using this

              Comment


              • #37
                Originally posted by 3766691 View Post
                Here is RIFS.ES-V1 patch For kernel 3.5.x
                There seems to be an error with NO_HZ enabled:

                kernel/time/tick-sched.c: In Funktion ?tick_nohz_idle_exit?:
                kernel/time/tick-sched.c:584:2: Fehler: Implizite Deklaration der Funktion ?update_cpu_load_nohz? [-Werror=implicit-function-declaration]

                Also with CGROUPS it won't compile:

                LD vmlinux
                kernel/built-in.o.data+0x43e0): undefined reference to `cpu_cgroup_subsys'
                make: *** [vmlinux] Fehler 1

                Comment


                • #38
                  Originally posted by TAXI View Post
                  There seems to be an error with NO_HZ enabled:

                  kernel/time/tick-sched.c: In Funktion ?tick_nohz_idle_exit?:
                  kernel/time/tick-sched.c:584:2: Fehler: Implizite Deklaration der Funktion ?update_cpu_load_nohz? [-Werror=implicit-function-declaration]

                  Also with CGROUPS it won't compile:

                  LD vmlinux
                  kernel/built-in.o.data+0x43e0): undefined reference to `cpu_cgroup_subsys'
                  make: *** [vmlinux] Fehler 1
                  the problem with cgroups is a known issue - afaik RIFS doesn't support cgroups (yet)

                  Comment


                  • #39
                    Originally posted by TAXI View Post
                    There seems to be an error with NO_HZ enabled:

                    kernel/time/tick-sched.c: In Funktion ?tick_nohz_idle_exit?:
                    kernel/time/tick-sched.c:584:2: Fehler: Implizite Deklaration der Funktion ?update_cpu_load_nohz? [-Werror=implicit-function-declaration]

                    Also with CGROUPS it won't compile:

                    LD vmlinux
                    kernel/built-in.o.data+0x43e0): undefined reference to `cpu_cgroup_subsys'
                    make: *** [vmlinux] Fehler 1
                    Please disable them. Yes desktop doesn't need these

                    EDIT 2:
                    Now I post a new one.
                    Last edited by 3766691; 22 June 2012, 03:17 PM.

                    Comment


                    • #40
                      Originally posted by kernelOfTruth View Post
                      the problem with cgroups is a known issue - afaik RIFS doesn't support cgroups (yet)
                      OK Now I totally disabled cgroups and non-preemptible and voluntary-sleep preemption model, only preemptible option is left.Tickless is also disabled. These are the feature that desktop users won't care about

                      Comment

                      Working...
                      X