On Mon, Jun 13, 2022 at 09:03:24PM +0530, manish.mishra wrote:
>
> On 13/06/22 8:03 pm, Peter Xu wrote:
> > On Mon, Jun 13, 2022 at 03:28:34PM +0530, manish.mishra wrote:
> > > On 26/05/22 8:21 am, Jason Wang wrote:
> > > > On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
> > > > > On Wed, May 25
On 13/06/22 8:03 pm, Peter Xu wrote:
On Mon, Jun 13, 2022 at 03:28:34PM +0530, manish.mishra wrote:
On 26/05/22 8:21 am, Jason Wang wrote:
On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
2. Also this algorithm only control or li
On Mon, Jun 13, 2022 at 03:28:34PM +0530, manish.mishra wrote:
>
> On 26/05/22 8:21 am, Jason Wang wrote:
> > On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
> > > On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
> > > > > 2. Also this algorithm only control or limits dirty rate by g
On 26/05/22 8:21 am, Jason Wang wrote:
On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
2. Also this algorithm only control or limits dirty rate by guest
writes. There can be some memory dirtying done by virtio based devices
which i
On 26/05/22 8:21 am, Jason Wang wrote:
On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
2. Also this algorithm only control or limits dirty rate by guest
writes. There can be some memory dirtying done by virtio based devices
which
On Wed, May 25, 2022 at 11:56 PM Peter Xu wrote:
>
> On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
> > > 2. Also this algorithm only control or limits dirty rate by guest
> > > writes. There can be some memory dirtying done by virtio based devices
> > > which is accounted only at qe
On Wed, May 25, 2022 at 11:38:26PM +0800, Hyman Huang wrote:
> > 2. Also this algorithm only control or limits dirty rate by guest
> > writes. There can be some memory dirtying done by virtio based devices
> > which is accounted only at qemu level so may not be accounted through
> > dirty rings so
在 2022/5/24 0:44, manish.mishra 写道:
On 17/05/22 1:49 pm, Hyman Huang wrote:
Thanks Manish for the comment, i'll give my explanation and any
supplement are welcomed.
Really sorry for such late reply Hyman, this slipped my mind.
在 2022/5/17 1:13, manish.mishra 写道:
Hi Hyman Huang,
I had fe
On 17/05/22 1:49 pm, Hyman Huang wrote:
Thanks Manish for the comment, i'll give my explanation and any supplement are
welcomed.
Really sorry for such late reply Hyman, this slipped my mind.
在 2022/5/17 1:13, manish.mishra 写道:
Hi Hyman Huang,
I had few doubts regarding this patch series.
Thanks Manish for the comment, i'll give my explanation and any
supplement are welcomed.
在 2022/5/17 1:13, manish.mishra 写道:
Hi Hyman Huang,
I had few doubts regarding this patch series.
For the first point, m'm rudely guessing that you want to figure out how
should we set the vcpu dirty limi
Hi Hyman Huang,
I had few doubts regarding this patch series.
1. Why we choose for dirty rate limit per vcpu. I mean it becomes very hard for
user to decide per
vcpu dirty rate limit. For e.g. we have 1Gbps network and 10 vcpu vm. Now
if someone wants to
keep criteria for convergence
From: Hyman Huang(黄勇)
Setup a negative feedback system when vCPU thread
handling KVM_EXIT_DIRTY_RING_FULL exit by introducing
throttle_us_per_full field in struct CPUState. Sleep
throttle_us_per_full microseconds to throttle vCPU
if dirtylimit is in service.
Signed-off-by: Hyman Huang(黄勇)
Revie
12 matches
Mail list logo
