daneel wrote: > I was trying this patch in Arch Linux and reading some clarifications > in the forum (https://bbs.archlinux.org/viewtopic.php?id=108516). > Apparently, this patch is not about IO performance, but only the > scheduling of process in different tty. So, if you launch all in the > same tty is not going to help at all.
True. But as it produces such a difference for tasks which are in different ttys (i.e. inside terminal windows, and initial daemons), perhaps it would be good to create scheduling groups for other things too, such as daemons (do they go in their own group when they detach from a tty with the patch, or keep the group they had when they were created?), different classes of background process (especially I/O kernel tasks), and maybe different X applications? I presume it's possible to create new scheduling groups manually, to test the effect on desktop responsiveness? If it's shown to make a good difference, then it'd be possible to look into whether the kernel should do so automatically. Also, there are I/O CFQ cgroups (CONFIG_CFQ_GROUP_IOSCHED) in current kernels. That may be worth looking into in a similar way. -- Heavy Disk I/O harms desktop responsiveness https://bugs.launchpad.net/bugs/131094 You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
