Re: [PATCH RFC V2 0/5] Separate consigned (expected steal) from steal time.
On 10/22/2012 10:33 AM, Rik van Riel wrote: On 10/16/2012 10:23 PM, Michael Wolf wrote: In the case of where you have a system that is running in a capped or overcommitted environment the user may see steal time being reported in accounting tools such as top or vmstat. This can cause confusion for the end user. How do s390 and Power systems deal with reporting that kind of information? IMHO it would be good to see what those do, so we do not end up re-inventing the wheel, and confusing admins with yet another way of reporting the information... Sorry for the delay in the response. I'm assuming you are asking about s390 and Power lpars. In the case of lpar on POWER systems they simply report steal time and do not alter it in any way. They do however report how much processor is assigned to the partition and that information is in /proc/ppc64/lparcfg. Mike -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH RFC V2 0/5] Separate consigned (expected steal) from steal time.
On 10/16/2012 10:23 PM, Michael Wolf wrote: In the case of where you have a system that is running in a capped or overcommitted environment the user may see steal time being reported in accounting tools such as top or vmstat. This can cause confusion for the end user. How do s390 and Power systems deal with reporting that kind of information? IMHO it would be good to see what those do, so we do not end up re-inventing the wheel, and confusing admins with yet another way of reporting the information... -- All rights reversed -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH RFC V2 0/5] Separate consigned (expected steal) from steal time.
On 10/17/2012 06:23 AM, Michael Wolf wrote: In the case of where you have a system that is running in a capped or overcommitted environment the user may see steal time being reported in accounting tools such as top or vmstat. This can cause confusion for the end user. To ease the confusion this patch set adds the idea of consigned (expected steal) time. The host will separate the consigned time from the steal time. The consignment limit passed to the host will be the amount of steal time expected within a fixed period of time. Any other steal time accruing during that period will show as the traditional steal time. TODO: * Change native_clock to take params and not return a value * Change update_rq_clock_task Changes from V1: * Removed the steal time allowed percentage from the guest * Moved the separation of consigned (expected steal) and steal time to the host. * No longer include a sysctl interface. You are showing this in the guest somewhere, but tools like top will still not show it. So for quite a while, it achieves nothing. Of course this is a barrier that any new statistic has to go through. So while annoying, this is per-se ultimately not a blocker. What I still fail to see, is how this is useful information to be shown in the guest. Honestly, if I'm in a guest VM or container, any time during which I am not running is time I lost. It doesn't matter if this was expected or not. This still seems to me as a host-side problem, to be solved entirely by tooling. -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH RFC V2 0/5] Separate consigned (expected steal) from steal time.
On Wed, 2012-10-17 at 21:14 +0400, Glauber Costa wrote: On 10/17/2012 06:23 AM, Michael Wolf wrote: In the case of where you have a system that is running in a capped or overcommitted environment the user may see steal time being reported in accounting tools such as top or vmstat. This can cause confusion for the end user. To ease the confusion this patch set adds the idea of consigned (expected steal) time. The host will separate the consigned time from the steal time. The consignment limit passed to the host will be the amount of steal time expected within a fixed period of time. Any other steal time accruing during that period will show as the traditional steal time. TODO: * Change native_clock to take params and not return a value * Change update_rq_clock_task Changes from V1: * Removed the steal time allowed percentage from the guest * Moved the separation of consigned (expected steal) and steal time to the host. * No longer include a sysctl interface. You are showing this in the guest somewhere, but tools like top will still not show it. So for quite a while, it achieves nothing. Of course this is a barrier that any new statistic has to go through. So while annoying, this is per-se ultimately not a blocker. What I still fail to see, is how this is useful information to be shown in the guest. Honestly, if I'm in a guest VM or container, any time during which I am not running is time I lost. It doesn't matter if this was expected or not. This still seems to me as a host-side problem, to be solved entirely by tooling. What tools like top and vmstat will show is altered. When I put time in the consign bucket it does not show up in steal. So now as long as the system is performing as expected the user will see 100% and 0% steal. I added the consign field to /proc/stat so that all time accrued in the period is accounted for and also for debugging purposes. The user wont care about consign and will not see it. -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH RFC V2 0/5] Separate consigned (expected steal) from steal time.
In the case of where you have a system that is running in a capped or overcommitted environment the user may see steal time being reported in accounting tools such as top or vmstat. This can cause confusion for the end user. To ease the confusion this patch set adds the idea of consigned (expected steal) time. The host will separate the consigned time from the steal time. The consignment limit passed to the host will be the amount of steal time expected within a fixed period of time. Any other steal time accruing during that period will show as the traditional steal time. TODO: * Change native_clock to take params and not return a value * Change update_rq_clock_task Changes from V1: * Removed the steal time allowed percentage from the guest * Moved the separation of consigned (expected steal) and steal time to the host. * No longer include a sysctl interface. --- Michael Wolf (5): Alter the amount of steal time reported by the guest. Expand the steal time msr to also contain the consigned time. Add the code to send the consigned time from the host to the guest Add a timer to allow the separation of consigned from steal time. Add an ioctl to communicate the consign limit to the host. arch/x86/include/asm/kvm_host.h | 11 + arch/x86/include/asm/kvm_para.h |3 ++ arch/x86/include/asm/paravirt.h |4 ++- arch/x86/kernel/kvm.c |8 ++ arch/x86/kvm/x86.c | 50 ++- fs/proc/stat.c |9 +-- include/linux/kernel_stat.h |2 ++ include/linux/kvm.h |2 ++ include/linux/kvm_host.h|2 ++ kernel/sched/cputime.c | 21 +++- kernel/sched/sched.h|2 ++ virt/kvm/kvm_main.c |7 + 12 files changed, 108 insertions(+), 13 deletions(-) -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html