On Thu, Nov 25, 2021 at 09:28:59AM +0100, David Hildenbrand wrote:
> On 25.11.21 03:20, Jason Wang wrote:
> > We only process the first in sg which may lead to the bitmap of the
> > pages belongs to following sgs were not cleared. This may result more
> > pages to be migrated. Fixing this by proces
On Thu, Nov 25, 2021 at 09:34:32AM +0100, Philippe Mathieu-Daudé wrote:
> On 11/25/21 03:20, Jason Wang wrote:
> > We only process the first in sg which may lead to the bitmap of the
> > pages belongs to following sgs were not cleared. This may result more
> > pages to be migrated. Fixing this by p
On 25.11.21 17:09, Michael S. Tsirkin wrote:
> On Thu, Nov 25, 2021 at 09:28:59AM +0100, David Hildenbrand wrote:
>> On 25.11.21 03:20, Jason Wang wrote:
>>> We only process the first in sg which may lead to the bitmap of the
>>> pages belongs to following sgs were not cleared. This may result more
On Thu, Nov 25, 2021 at 10:20:46AM +0800, Jason Wang wrote:
> Spec said:
>
> "and len the total of bytes written into the buffer."
>
> For inflateq, deflateq and statsq, we don't process in_sg so the used
> length should be zero. For free_page_vq, since the pages could be
> changed in the destina
From: Hyman Huang(黄勇)
v6:
- rebase on master
- fix dirtylimit setup crash found by Markus
- polish the comments according to the advice given by Markus
- adjust the qemu qmp command tag to 7.0
v5:
- rebase on master
- adjust the throttle algorithm by removing the tuning in
RESTRAINT_RATIO cas
From: Hyman Huang(黄勇)
Impose dirty restraint on vCPU by kicking it and sleep
as the auto-converge does during migration, but just
kick the specified vCPU instead, not all vCPUs of vm.
Start a thread to track the dirtylimit status and adjust
the throttle pencentage dynamically depend on current
a
From: Hyman Huang(黄勇)
Implement dirtyrate calculation periodically basing on
dirty-ring and throttle vCPU until it reachs the quota
dirty page rate given by user.
Introduce qmp commands set-dirty-limit/cancel-dirty-limit to
set/cancel dirty page limit on vCPU.
Signed-off-by: Hyman Huang(黄勇)
--
From: Hyman Huang(黄勇)
Introduce the third method GLOBAL_DIRTY_LIMIT of dirty
tracking for calculate dirtyrate periodly.
Implement thread for calculating dirtyrate periodly, which will
be used for for vCPU throttle implementation.
Add dirtylimit.h to introduce the util function for dirty page li
On Thu, Nov 11 2021, Yishai Hadas wrote:
> Upon reading/writing the migration data there is no real reason to limit
> the read/write system call from the file to be 8 bytes.
>
> In addition, there is no reason to depend on the file offset alignment.
> The offset is just some logical value which d
On 19/11/2021 13:47, Chao Peng wrote:
> Signed-off-by: Yu Zhang
> Signed-off-by: Chao Peng
> ---
> virt/kvm/kvm_main.c | 23 +++
> 1 file changed, 19 insertions(+), 4 deletions(-)
>
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 271cef8d1cd0..b8673490d301 1
* Juan Quintela (quint...@redhat.com) wrote:
> "Dr. David Alan Gilbert" wrote:
> > * Juan Quintela (quint...@redhat.com) wrote:
> >> We will need to split it later in zero_num (number of zero pages) and
> >> normal_num (number of normal pages). This name is better.
> >>
> >> Signed-off-by: Juan
When updating the R bit of a PTE, the Hash64 MMU was using a wrong byte
offset, causing the first byte of the adjacent PTE to be corrupted.
This caused a panic when booting FreeBSD, using the Hash MMU.
Fixes: a2dd4e83e76b ("ppc/hash64: Rework R and C bit updates")
Signed-off-by: Leandro Lupori
--
* Juan Quintela (quint...@redhat.com) wrote:
> Signed-off-by: Juan Quintela
Pretty obvious, but I guess to have the complete set of comments:
Reviewed-by: Dr. David Alan Gilbert
> ---
> migration/multifd-zlib.c | 2 ++
> migration/multifd-zstd.c | 2 ++
> migration/multifd.c | 1 +
> 3
* Juan Quintela (quint...@redhat.com) wrote:
> Signed-off-by: Juan Quintela
Reviewed-by: Dr. David Alan Gilbert
> ---
> migration/multifd.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/migration/multifd.c b/migration/multifd.c
> index cdeffdc4c5..ce7101cf9d 10064
* Juan Quintela (quint...@redhat.com) wrote:
> It is already there as p->pages->num.
>
> Signed-off-by: Juan Quintela
Reviewed-by: Dr. David Alan Gilbert
> ---
> migration/multifd.h | 2 +-
> migration/multifd-zlib.c | 7 +++
> migration/multifd-zstd.c | 7 +++
> migration/multif
* Juan Quintela (quint...@redhat.com) wrote:
> It is already there as p->pages->num.
>
> Signed-off-by: Juan Quintela
Reviewed-by: Dr. David Alan Gilbert
> ---
> migration/multifd.h | 2 +-
> migration/multifd-zlib.c | 9 -
> migration/multifd-zstd.c | 7 +++
> migration/mult
On 11/25/21 15:33, Leandro Lupori wrote:
When updating the R bit of a PTE, the Hash64 MMU was using a wrong byte
offset, causing the first byte of the adjacent PTE to be corrupted.
This caused a panic when booting FreeBSD, using the Hash MMU.
Fixes: a2dd4e83e76b ("ppc/hash64: Rework R and C b
* Juan Quintela (quint...@redhat.com) wrote:
> We were using the iov directly, but we will need this info on the
> following patch.
Yes I think so; have you considered that really need to check the
fields of MultiFD*Params to see which fields you're actually using?
Reviewed-by: Dr. David Alan
* Juan Quintela (quint...@redhat.com) wrote:
> "Dr. David Alan Gilbert" wrote:
> > * Juan Quintela (quint...@redhat.com) wrote:
> >> We are divining by page_size to multiply again in the only use.
> > ^--- typo
> >> Once there, impreve the comments.
> > ^--- typo
> >
On Thu, Nov 25, 2021 at 05:36:29PM +0530, Ani Sinha wrote:
> x-native-hotplug property, when used in order to disable HPC bit on the PCIE
> root ports, can lead to unexpected results from the guest operating system.
> Users are strongly advised not to touch this property in order to manipulte
> th
If one tries to use -machine powernv9,accel=kvm in a Power9 host, a
cryptic error will be shown:
qemu-system-ppc64: Register sync failed... If you're using kvm-hv.ko, only
"-cpu host" is possible
qemu-system-ppc64: kvm_init_vcpu: kvm_arch_init_vcpu failed (0): Invalid
argument
Appending '-cpu h
On Friday, November 26, 2021 12:11 AM, David Hildenbrand wrote:
> On 25.11.21 17:09, Michael S. Tsirkin wrote:
> > On Thu, Nov 25, 2021 at 09:28:59AM +0100, David Hildenbrand wrote:
> >> On 25.11.21 03:20, Jason Wang wrote:
> >>> We only process the first in sg which may lead to the bitmap of the
>
On Fri, Nov 26, 2021 at 01:21:46AM +, Wang, Wei W wrote:
> On Friday, November 26, 2021 12:11 AM, David Hildenbrand wrote:
> > On 25.11.21 17:09, Michael S. Tsirkin wrote:
> > > On Thu, Nov 25, 2021 at 09:28:59AM +0100, David Hildenbrand wrote:
> > >> On 25.11.21 03:20, Jason Wang wrote:
> > >>
On Thu, Nov 25, 2021 at 03:33:22PM -0300, Leandro Lupori wrote:
> When updating the R bit of a PTE, the Hash64 MMU was using a wrong byte
> offset, causing the first byte of the adjacent PTE to be corrupted.
> This caused a panic when booting FreeBSD, using the Hash MMU.
>
> Fixes: a2dd4e83e76b ("
On Thu, Nov 25, 2021 at 07:42:02PM -0300, Daniel Henrique Barboza wrote:
> If one tries to use -machine powernv9,accel=kvm in a Power9 host, a
> cryptic error will be shown:
>
> qemu-system-ppc64: Register sync failed... If you're using kvm-hv.ko, only
> "-cpu host" is possible
> qemu-system-ppc6
TARGET_SIGSTKSZ is not used, we should remove it.
Signed-off-by: Song Gao
---
linux-user/alpha/target_signal.h | 1 -
linux-user/generic/signal.h | 1 -
linux-user/hppa/target_signal.h | 1 -
linux-user/mips/target_signal.h | 1 -
linux-user/mips64/target_signal.h | 1 -
linux-user/sp
Hi all,
This seris:
- Move target_signal.h generic defintions to generic/signal.h,
- target_syscall.h remove TARGET_MINSIGSTKSZ
- Remove unused definitions TARGET_SIGSTKSZ.
Song Gao (3):
linux-user: Move target_signal.h generic definitions to
generic/signal.h
linux-user: target_syscal
No code change
Suggested-by: Richard Henderson
Signed-off-by: Song Gao
Reviewed-by: Laurent Vivier
---
linux-user/aarch64/target_signal.h| 18 --
linux-user/arm/target_signal.h| 18 --
linux-user/cris/target_signal.h | 18 --
li
TARGET_MINSIGSTKSZ has been defined in generic/signal.h
or target_signal.h, We don't need to define it again.
Signed-off-by: Song Gao
Reviewed-by: Laurent Vivier
Reviewed-by: Philippe Mathieu-Daudé
---
linux-user/aarch64/target_syscall.h| 1 -
linux-user/alpha/target_syscall.h | 1 -
On Fri, Nov 26, 2021 at 9:21 AM Wang, Wei W wrote:
>
> On Friday, November 26, 2021 12:11 AM, David Hildenbrand wrote:
> > On 25.11.21 17:09, Michael S. Tsirkin wrote:
> > > On Thu, Nov 25, 2021 at 09:28:59AM +0100, David Hildenbrand wrote:
> > >> On 25.11.21 03:20, Jason Wang wrote:
> > >>> We on
On Friday, November 26, 2021 10:31 AM, Jason Wang wrote:
>
> I've tested the code with migration before sending the patches, I see the hint
> works fine.
>
That's great (assume you saw great reduction in the migration time as well).
Reviewed-by: Wei Wang
Thanks,
Wei
On Fri, Nov 26, 2021 at 12:10 AM Michael S. Tsirkin wrote:
>
> On Thu, Nov 25, 2021 at 09:34:32AM +0100, Philippe Mathieu-Daudé wrote:
> > On 11/25/21 03:20, Jason Wang wrote:
> > > We only process the first in sg which may lead to the bitmap of the
> > > pages belongs to following sgs were not cl
On Fri, Nov 26, 2021 at 10:40 AM Wang, Wei W wrote:
>
> On Friday, November 26, 2021 10:31 AM, Jason Wang wrote:
> >
> > I've tested the code with migration before sending the patches, I see the
> > hint
> > works fine.
> >
>
> That's great (assume you saw great reduction in the migration time as
Turn on pre-defined feature VIRTIO_BLK_F_SIZE_MAX virtio blk device
to avoid guest DMA request size is too large to exceed hardware spec.
Signed-off-by: Andy Pei
---
hw/block/vhost-user-blk.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.
On Fri, Nov 26, 2021 at 12:14 AM Michael S. Tsirkin wrote:
>
> On Thu, Nov 25, 2021 at 10:20:46AM +0800, Jason Wang wrote:
> > Spec said:
> >
> > "and len the total of bytes written into the buffer."
> >
> > For inflateq, deflateq and statsq, we don't process in_sg so the used
> > length should be
On Thu, Nov 25, 2021 at 6:16 PM Eugenio Pérez wrote:
>
> Qemu falls back on userland handlers even if vhost-user and vhost-vdpa
> cases. These assumes a tap device can handle the packets.
>
> If a vdpa device fail to start, it can trigger a sigsegv because of
> that. Add dummy receiver that return
On Thu, Nov 25, 2021 at 6:16 PM Eugenio Pérez wrote:
>
> The message has never been true in the case of non tap networking, so
> only tell that userland networking will be used if possible.
>
> Signed-off-by: Eugenio Pérez
Acked-by: Jason Wang
> ---
> hw/net/virtio-net.c | 11 ++-
> 1
On Thu, 25 Nov 2021, Michael S. Tsirkin wrote:
> On Thu, Nov 25, 2021 at 05:36:29PM +0530, Ani Sinha wrote:
> > x-native-hotplug property, when used in order to disable HPC bit on the PCIE
> > root ports, can lead to unexpected results from the guest operating system.
> > Users are strongly adv
Orginal qemu commit hash:14d02cfbe4adaeebe7cb833a8cc71191352cf03b
In function pcie_add_capability, an assert contains the
"offset < offset + size" expression.
Both variable offset and variable size are uint16_t,
the comparison is always true due to type promotion.
The next expression may be t
The purpose of dbus_get_proxies to construct the proxies corresponding to the
IDs registered to dbus-vmstate.
Currenty, this function returns an error in case there is any failure
while instantiating proxy for "all" the names on dbus.
Ideally this function should error out only if it is not able
huang...@chinatelecom.cn writes:
> From: Hyman Huang(黄勇)
>
> Implement dirtyrate calculation periodically basing on
> dirty-ring and throttle vCPU until it reachs the quota
> dirty page rate given by user.
>
> Introduce qmp commands set-dirty-limit/cancel-dirty-limit to
> set/cancel dirty page li
The use of atomics in this patch and the previous requires careful
review by an expert on proper use of atomics.
The use of atomics in this patch and the previous requires careful
review by an expert on proper use of atomics.
On Fri, Nov 26, 2021 at 10:45:43AM +0800, Jason Wang wrote:
> On Fri, Nov 26, 2021 at 12:14 AM Michael S. Tsirkin wrote:
> >
> > On Thu, Nov 25, 2021 at 10:20:46AM +0800, Jason Wang wrote:
> > > Spec said:
> > >
> > > "and len the total of bytes written into the buffer."
> > >
> > > For inflateq,
101 - 144 of 144 matches
Mail list logo
