[RFC][PATCH] KVM: APPLES can improve the performance of applications and virtualized systems by up to 49%

Dear all, Recently, we made a few improvements on effectively utilizing Pause Loop Exiting (PLE) support for higher throughput on virtualized systems. Basically, it solves two problems: 1) how to adjust PLE_Window; 2) how to select virtual CPUs to schedule on VM_EXITs caused by PLE. Our tests with

Re: [RFC] blkio_delay_total is calculated mistakenly

Ping? Can anyone please add some comments for this change? Thank you. Best, Weiwei Jia On Tue, Feb 14, 2017 at 8:27 PM, Weiwei Jia wrote: > Hi, > > When I read Linux Kernel source codes about how "blkio_delay_total" > (delay waiting for synchronous block I/O to com

Re: [RFC] blkio_delay_total is calculated mistakenly

On Tue, Feb 14, 2017 at 10:00 PM, Greg KH wrote: > On Tue, Feb 14, 2017 at 08:27:36PM -0500, Weiwei Jia wrote: >> Hi, >>Balbir Singh >> When I read Linux Kernel source codes about how "blkio_delay_total" >> (delay waiting for synchronous block I/O to compl

[RFC] blkio_delay_total is calculated mistakenly

elayacct.c?v=4.7#L121 [2] http://lxr.free-electrons.com/source/kernel/delayacct.c?v=4.7#L52 Thanks, Weiwei Jia From 8c290bce66f0ef2b117c8f47a13bbf2d80c500f0 Mon Sep 17 00:00:00 2001 From: Weiwei Jia Date: Tue, 14 Feb 2017 20:18:34 -0500 Subject: [PATCH] fix the mistake blkio_delay_total calculation

[PATCH] remove unused parameter

Remove unused parameter in wakeup_gran function for Completely Fair Scheduling (CFS). Signed-off-by: Weiwei Jia --- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c242944..f4375d4 100644 --- a/kernel

Re: Timeslice of vCPU thread in QEMU/KVM is not stable

Hi Pankaj Gupta, Thanks for your reply. I have found the problem after debug Linux Kernel. The problem is once there is I/O thread upon vCPU2 thread of VM1, there will be some mutex (synchronization) produced so that it will be preempted by vCPU2 thread of VM2. After I set "/proc/sys/kernel/sched_

Timeslice of vCPU thread in QEMU/KVM is not stable

Hi everyone, I am testing the timeslice of vCPU thread in QEMU/KVM. In principle, the timeslice should be stable under following workload but it is unstable after I do experiments with following workload. I appreciate it if you can give me some suggestions. Thanks in advance. Workload settings: I

Re: [PATCH] Documentation:Update Documentation/zh_CN/arm64/booting.txt

t;9d372c9f", "6d32ab2d". > And improve the format of documentation. > > Signed-off-by: Fu Wei Reviewed-by: Weiwei Jia > --- > Documentation/zh_CN/arm64/booting.txt | 93 > ++- > 1 file changed, 58 insertions(+), 35 deletio

Re: [PATCH] Documentation: Chinese translation of arm64/silicon-errata.txt

2016-02-15 12:57 GMT+08:00 Fu Wei : > Hi Harry, Hi Wei Fu, > > Thanks for your rapid response :-) > > > On 02/15/2016 03:23 AM, Weiwei Jia wrote: >> >> 2016-02-14 3:40 GMT+08:00 : >>> >>> From: Fu Wei >>> >>> This is a Chines

Re: [PATCH] Documentation: Chinese translation of arm64/silicon-errata.txt

2016-02-14 3:40 GMT+08:00 : > From: Fu Wei > > This is a Chinese translated version of Documentation/arm64/silicon-errata.txt > > Signed-off-by: Fu Wei Reviewed-by: Weiwei Jia > --- > Documentation/zh_CN/arm64/silicon-errata.txt | 74 > ++