similar to: Stolen and degraded time and schedulers

I've been thinking a bit more about how useful an absolute timeout is for a oneshot timer in a virtual environment. In principle, absolute times are generally preferable. A relative timeout means "timeout in X ns from now", but the meaning of "now" is ambiguous, particularly if the vcpu can be preempted at any time, which means the determination of "now" can be

I've been thinking a bit more about how useful an absolute timeout is for a oneshot timer in a virtual environment. In principle, absolute times are generally preferable. A relative timeout means "timeout in X ns from now", but the meaning of "now" is ambiguous, particularly if the vcpu can be preempted at any time, which means the determination of "now" can be

Hey, folks, Sometimes my workstation bogs down... slows to a crawl. Using gkrellm, it's obvious the CPU is the laggard. The top utility confirms: the load average gets up over 4 at times. But this occurs when cpu stepping pegs the speed at 600MHz. This processor is capable of 1.5GHz and when it's allowed to run at that speed, the load average is under 2, which is fine. So the

Hello, I was thinking of creating a wiki page about Xen clocksources and timekeeping.. including dom0, PV guests and HVM guests. Dan and Jeremy: You guys might have some ideas for this page.. please let me know your thoughts :) Subjects to cover: - Xen hypervisor clocksources (hpet, acpi_pm, pit) - Xen dom0 clocksource, ntpd, etc - Xen PV guest clocksources, independent_wallclock, ntpd,

Existing credit scheduler is not power aware. To achieve better power saving ability with negligible performance impact, following areas may be tweaked and listed here for comments first. Goal is not to silly save power with sacrifice of performance, e.g. we don''t want to prevent migration when there''re free cpus with some pending runqueues. But when free computing power is

Hello, I guess it possible distro specific issue but is it resolvable? I have one node(testing purpose) ganeti 2.0.1 cluster installed over Debian5 Lenny. Almost everything from distro repositories. Only ganeti 2.0.1 and ganeti-debootstrap are from sources. I have it successful run with vmlinuz-2.6.26-2-xen-686 and initrd.img-2.6.26-2-xen-686 from repositories. Both Dom0 and DomU are use the

here is my problem: Parsing config file vir2.cfg Daemon running with PID 11570 Initializing cgroup subsys cpuset Initializing cgroup subsys cpu Linux version 3.0.0 (root@localhost.localdomain) (gcc version 4.4.7 20120313 (Red Hat 4.4.7-3) (GCC) ) #1 SMP Mon Oct 28 00:35:01 CST 2013 Command line: root=/dev/hda1 ro ACPI in unprivileged domain disabled released 0 pages

On a selection of boxes, ntpd running in Xen Dom0 reproducibly exhibits extermely high noise/jitter. Switching back to -default, non-xen kernel ntpd runs with very low jitter/noise. Question -- how can I ''tame'' ntpd noise & jitter when running in Dom0? Is the problem a config issue, or a bug? Already reported this downstream; everybody''s "stumped".

On a selection of boxes, ntpd running in Xen Dom0 reproducibly exhibits extermely high noise/jitter. Switching back to -default, non-xen kernel ntpd runs with very low jitter/noise. Question -- how can I ''tame'' ntpd noise & jitter when running in Dom0? Is the problem a config issue, or a bug? Already reported this downstream; everybody''s "stumped".

My wife's Windows XP laptop was stolen a couple days ago. Every night the computer automatically preforms an rsync to a Debian Linux computer (the dumb-dumbs didn't steal that). My question: if the laptop successfully connects to the Linux box can you think of anyway I can use this fact to track the computer (maybe an IP address from its location., etc.)? By they way I could really care

Hi everyone, I''m working in a firm that monitor wan networks. We have several nagios installed on virtual machines. Recently we noticed that the DomU''s clocks are not synced with the Dom0 and the clocks are wrong. So we tried to sync DomU''s via openntpd but it generates errors in nagios. Logs indicate "Time goes back". So we want to sync DomU with Dom0 and

Here's a quick-but-I-guess-tidy-fix for faulty behaviour someone reported in NVAF. I'm just not sure if the check for nvaa/nvac should still be in nv50_pm_clocks_pre... I believe this is wrong as they can reclock perfectly well (except the non-existing memory). Anyone has a definite answer to that?

Ingo Molnar wrote: > * Ingo Molnar <mingo@elte.hu> wrote: > > >> no, that's not the case: next_timer_interrupt() is the NO_IDLE_HZ >> method of doing things - while in the NO_HZ case you are supposed to >> use clockevent devices to program timer hardware. >> We don't have a clockevent device. But we need NO_IDLE_HZ support, which NO_HZ

Ingo Molnar wrote: > * Ingo Molnar <mingo@elte.hu> wrote: > > >> no, that's not the case: next_timer_interrupt() is the NO_IDLE_HZ >> method of doing things - while in the NO_HZ case you are supposed to >> use clockevent devices to program timer hardware. >> We don't have a clockevent device. But we need NO_IDLE_HZ support, which NO_HZ

Convert VMI timer to use clock events, making it properly able to use the NO_HZ infrastructure. On UP systems, with no local APIC, we just continue to route these events through the PIT. On systems with a local APIC, or SMP, we provide a single source interrupt chip which creates the local timer IRQ. It actually gets delivered by the APIC hardware, but we don't want to use the same local

Convert VMI timer to use clock events, making it properly able to use the NO_HZ infrastructure. On UP systems, with no local APIC, we just continue to route these events through the PIT. On systems with a local APIC, or SMP, we provide a single source interrupt chip which creates the local timer IRQ. It actually gets delivered by the APIC hardware, but we don't want to use the same local

The softlockup watchdog is currently a nuisance in a virtual machine, since the whole system could have the CPU stolen from it for a long period of time. While it would be unlikely for a guest domain to be denied timer interrupts for over 10s, it could happen and any softlockup message would be completely spurious. Earlier I proposed that sched_clock() return time in unstolen nanoseconds, which

The softlockup watchdog is currently a nuisance in a virtual machine, since the whole system could have the CPU stolen from it for a long period of time. While it would be unlikely for a guest domain to be denied timer interrupts for over 10s, it could happen and any softlockup message would be completely spurious. Earlier I proposed that sched_clock() return time in unstolen nanoseconds, which

gday gurus, could someone please help me with this one? Can't find it in the doco. summary of my lm object gives "Pr(>|t|)" but coef doesn't. How do I get hold of these probabilities within an object? There doesn't seem to be an appropriate attribute within the object - I was hoping for something like "my.lm$probabilies". I was hoping to grab the best t

On 09/23/2017 03:52 AM, hw wrote: > Thank you very much for the notice!? Looking at a couple machines, I found > that the automatic choice of profile isn?t what I would want. > > Now I wonder how everyone deals with this, i. e. do you set a profile once > and never change it, or do you keep changing the profile according to > circumstances?? Is changing it even advisable, i. e.