Announcement

Collapse
No announcement yet.

ULatencyD Enters The Linux World

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

  • #31
    Originally posted by kbios View Post
    Hi, I would like to try ULatencyD, but on the FAQ I read "You will not be able to run a different cgroups agent in parallel." Does this mean I will have problems with the linux-containers I'm using?
    Thanks
    I just installed a testing machine to write rules against the current container programs. But currently I can't say what will happen :-)

    Comment


    • #32
      Originally posted by poelzi View Post
      I just installed a testing machine to write rules against the current container programs. But currently I can't say what will happen :-)
      Thanks, that's very appreciated. Count on me for testing :-)

      Comment


      • #33
        Originally posted by TiborB View Post
        1) What if I start (by mistake or by chance) second instance of ulatencyd?
        The worst thing that could happen ist that they move processes arround all the time, but that should not cause much trouble except more load.

        Originally posted by TiborB View Post
        2) what if there are two Xservers run on one box?
        He should connect to all of them. I'm currently rewriting this module for better connection and lesser crude code ;-)

        Originally posted by TiborB View Post
        3) I must admit I'm not much familiar with cgroups and even what exactly your tool is doing. So I dont understand how your tool knows which application is "good" and which is "bad". For example, how it distinguishes opera from linuxdcpp or from some mp3 playing program... The active windows is not allways the right test, because mp3 player might not be in active window yet it needs some preference. Or do you have some list of applications split into some groups?
        1. A program is only 'bad' when resources run into limitation. Currently only a memory protector exists and if he detects memory pressure, the largest programs are put into memory limitations.
        I documented the default scheduler. As you can see, it does not say: this process is bad, but tries to find groups that belong together and gives each group an amount of cpu shares. As opposed the normal: each process gets the same amount of cpu share.
        The rules in rules/media.lua schould set a flag on your mp3 program, so it gets more cpu share because it fits the requirements of the media group.


        Originally posted by TiborB View Post
        4) Do you trust ulatencyd that it would not do any serious harm? In other words, can I put it in the list of services started after boot of my box?
        I'm running it all the time, but i will not suggest running it on a server currently. But for a desktop box it's fine.

        Originally posted by TiborB View Post
        5) Is it possible to measure effect of ulatencyd? Probably not I think...
        Sure. If you run ulatencyd you can run tests/memleak for example without your box crashing. Or try something creazy like compiling the linux kernel with make -j 40 ;-)

        I personally find by desktop much more smoother when it's running.

        Originally posted by TiborB View Post
        For your information - perhaps you can mentioned it somewhere - I found that for Arch Linux two PKGBUILDS were created in AUR (arch linux users will understand what it means) - ulatencyd and ulatencyd-git (http://aur.archlinux.org/packages.php)
        Added it to the wiki, thanks.

        Comment


        • #34
          Poelzi

          I just want to thank you for your answers, I'm satisfied with them... thanks

          Comment

          Working...
          X