vcpu thread.
However, during we wait vcpu thread to be created, the bql is
unlocked, and other thread is allowed to call resume_all_vcpus(),
which will resume the un-realized vcpu.
This fixes the issue by filter out un-realized vcpu during
resume_all_vcpus().
Signed-off-by: Keqian Zhu
---
system
so we
must retry.
Signed-off-by: Keqian Zhu
---
system/cpus.c | 29 -
1 file changed, 24 insertions(+), 5 deletions(-)
diff --git a/system/cpus.c b/system/cpus.c
index 68d161d96b..4e41abe23e 100644
--- a/system/cpus.c
+++ b/system/cpus.c
@@ -571,12 +571,14 @@ static
I hit these bugs when I test the RFC patch of ARM vCPU hotplug feature.
This patch has been verified valid.
Keqian Zhu (2):
system/cpus: Fix pause_all_vcpus() under concurrent environment
system/cpus: Fix resume_all_vcpus() under vCPU hotplug condition
system/cpus.c | 32
The following points sometimes can reduce much data
to copy:
1. When width matches, we can transfer data with one
call of iov_to_buf().
2. Only the required height need to transfer, not
whole image.
Signed-off-by: Keqian Zhu
---
hw/display/virtio-gpu.c | 22 +++---
1 file
b62075021a ("hw/acpi: Add ACPI Generic Event Device Support")
Signed-off-by: Keqian Zhu
---
hw/acpi/generic_event_device.c | 8
1 file changed, 8 insertions(+)
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index e28457a7d1..a3d31631fe
ned-off-by: Keqian Zhu
---
hw/acpi/generic_event_device.c | 8
1 file changed, 8 insertions(+)
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index e28457a7d1..a3d31631fe 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -267
Constify vmstate_ecc_state and vmstate_x86_cpu.
Signed-off-by: Keqian Zhu
---
hw/block/ecc.c | 2 +-
include/hw/block/flash.h | 2 +-
target/i386/cpu.h| 2 +-
target/i386/machine.c| 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/hw/block/ecc.c b/hw
On 2021/4/8 21:22, Philippe Mathieu-Daudé wrote:
> On 3/15/21 10:05 AM, Keqian Zhu wrote:
>> Hi Philippe,
>>
>> It seems that vmstate_ecc_state and vmstate_x86_cpu can also be constified.
>> Found by .
>
> Correct (I only searched for the static ones).
>
Peter,
On 2021/3/24 23:09, Peter Xu wrote:
> On Wed, Mar 24, 2021 at 10:56:22AM +0800, Keqian Zhu wrote:
>> Hi Peter,
>>
>> On 2021/3/23 22:34, Peter Xu wrote:
>>> Keqian,
>>>
>>> On Tue, Mar 23, 2021 at 02:40:43PM +0800, Keqian Zhu wrote:
>&g
Hi Peter,
On 2021/3/23 22:34, Peter Xu wrote:
> Keqian,
>
> On Tue, Mar 23, 2021 at 02:40:43PM +0800, Keqian Zhu wrote:
>>>> The second question is that you observed longer migration time (55s->73s)
>>>> when guest
>>>> has 24G ram and dirty rat
Hi Peter,
On 2021/3/23 3:45, Peter Xu wrote:
> On Mon, Mar 22, 2021 at 10:02:38PM +0800, Keqian Zhu wrote:
>> Hi Peter,
>
> Hi, Keqian,
>
> [...]
>
>> You emphasize that dirty ring is a "Thread-local buffers", but dirty bitmap
>> is global
On 2021/3/23 2:52, Peter Xu wrote:
> On Mon, Mar 22, 2021 at 09:37:19PM +0800, Keqian Zhu wrote:
>>> +/* Should be with all slots_lock held for the address spaces. */
>>> +static void kvm_dirty_ring_mark_page(KVMState *s, uint32_t as_id,
>>> +
Hi Peter,
On 2021/3/11 4:32, Peter Xu wrote:
> This is v5 of the qemu dirty ring interface support.
>
>
>
> v5:
>
> - rebase
>
> - dropped patch "update-linux-headers: Include const.h" after rebase
>
> - dropped patch "KVM: Fixup kvm_log_clear_one_slot() ioctl return check" since
>
> simi
On 2021/3/11 4:33, Peter Xu wrote:
> KVM dirty ring is a new interface to pass over dirty bits from kernel to the
> userspace. Instead of using a bitmap for each memory region, the dirty ring
> contains an array of dirtied GPAs to fetch (in the form of offset in slots).
> For each vcpu there wi
Hi Peter,
On 2021/3/11 4:32, Peter Xu wrote:
> Per-kml slots_lock will bring some trouble if we want to take all slots_lock
> of
> all the KMLs, especially when we're in a context that we could have taken some
> of the KML slots_lock, then we even need to figure out what we've taken and
> what we
Hi Peter,
On 2021/3/11 4:33, Peter Xu wrote:
> KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is for KVM_CLEAR_DIRTY_LOG, which is only
> useful for KVM_GET_DIRTY_LOG. Skip enabling it for kvm dirty ring.
>
> More importantly, KVM_DIRTY_LOG_INITIALLY_SET will not wr-protect all the
> pages
> initially, whic
Hi Philippe,
It seems that vmstate_ecc_state and vmstate_x86_cpu can also be constified.
Found by .
Thanks,
Keqian
On 2021/3/14 1:11, Philippe Mathieu-Daudé wrote:
> VMStateDescription isn't supposed to be modified.
>
>
>
> Philippe Mathieu-Daudé (3):
>
> hw/arm: Constify VMStateDescriptio
Hi,
I don't dig into code logic, just some nit below.
On 2021/3/1 0:10, Minwoo Im wrote:
> Given that now we have nvme-subsys device supported, we can manage
> namespace allocated, but not attached: detached. This patch introduced
s/introduced/introduces
> a parameter for nvme-ns device named '
Hi Alex,
On 2021/3/11 4:24, Alex Williamson wrote:
> On Wed, 10 Mar 2021 15:19:33 +0800
> Kunkun Jiang wrote:
>
>> Hi Alex,
>>
>> On 2021/3/10 7:17, Alex Williamson wrote:
>>> On Thu, 4 Mar 2021 21:34:46 +0800
>>> Kunkun Jiang wrote:
>>>
The cpu_physical_memory_set_dirty_lebitmap() can q
On 2021/3/10 0:08, Peter Xu wrote:
> On Tue, Mar 09, 2021 at 02:57:53PM +, Dr. David Alan Gilbert wrote:
>> * Thomas Huth (th...@redhat.com) wrote:
>>> On 09/03/2021 15.05, Keqian Zhu wrote:
>>>>
>>>>
>>>> On 2021/3/9 21:48, Thomas H
Hi Alex,
On 2021/3/10 7:17, Alex Williamson wrote:
> On Thu, 4 Mar 2021 21:34:46 +0800
> Kunkun Jiang wrote:
>
>> The cpu_physical_memory_set_dirty_lebitmap() can quickly deal with
>> the dirty pages of memory by bitmap-traveling, regardless of whether
>> the bitmap is aligned correctly or not.
On 2021/3/9 21:48, Thomas Huth wrote:
> On 17/12/2020 02.49, Keqian Zhu wrote:
>> The parameters start and size are transfered from QEMU memory
>> emulation layer. It can promise that they are TARGET_PAGE_SIZE
>> aligned. However, KVM needs they are qemu_real_page_size ali
the switch of vfio dirty_page_tracking into vfio_memory_listener
can solve above problems. Besides, Do not require devices in SAVING
state for vfio_sync_dirty_bitmap().
[1] https://www.spinics.net/lists/kvm/msg229967.html
Reported-by: Zenghui Yu
Signed-off-by: Keqian Zhu
Suggested-by: Pao
Hi,
This patch is still not queued. Who can help to do this? Thanks :)
Keqian
On 2020/12/17 9:49, Keqian Zhu wrote:
> Hi all,
>
> This series fixes memory waste and adds alignment check for unmatched
> qemu_real_host_page_size and TARGET_PAGE_SIZE.
>
> Thanks.
>
> K
Hi Kirti,
What's your opinion about this? Thanks.
Keqian
On 2021/1/30 14:30, Keqian Zhu wrote:
> Hi Kirti,
>
> On 2021/1/28 5:03, Kirti Wankhede wrote:
>>
>>
>> On 1/11/2021 1:04 PM, Keqian Zhu wrote:
>>> For now the switch of vfio dirty
Hi Philippe,
On 2021/2/1 23:14, Philippe Mathieu-Daudé wrote:
> Hi,
>
> On 12/17/20 2:49 AM, Keqian Zhu wrote:
>> The parameters start and size are transfered from QEMU memory
>> emulation layer. It can promise that they are TARGET_PAGE_SIZE
>> aligned.
Hi All,
Kindly Ping ;-) ...
On 2021/1/25 15:51, Keqian Zhu wrote:
> Hi Paolo,
>
> Any suggestions on this patch series :-) ? Thanks,
>
> Keqian
>
> On 2020/12/17 9:49, Keqian Zhu wrote:
>> Hi all,
>>
>> This series fixes memory waste
Hi Kirti,
On 2021/1/28 5:03, Kirti Wankhede wrote:
>
>
> On 1/11/2021 1:04 PM, Keqian Zhu wrote:
>> For now the switch of vfio dirty page tracking is integrated into
>> the vfio_save_handler, it causes some problems [1].
>>
>
> Sorry, I missed [1] mail, som
On 2021/1/29 15:49, Paolo Bonzini wrote:
> On 28/01/21 21:02, Dr. David Alan Gilbert wrote:
>> * Paolo Bonzini (pbonz...@redhat.com) wrote:
>>> On 11/01/21 08:34, Keqian Zhu wrote:
>>>> +static void vfio_listener_log_
Hi Paolo and Kirti,
Many thanks for reply. I am busy today and will reply you tomorrow, Thanks.
Keqian.
On 2021/1/28 5:03, Kirti Wankhede wrote:
>
>
> On 1/11/2021 1:04 PM, Keqian Zhu wrote:
>> For now the switch of vfio dirty page tracking is integrated into
>> the
Hi Paolo,
Any suggestions on this patch series :-) ? Thanks,
Keqian
On 2020/12/17 9:49, Keqian Zhu wrote:
> Hi all,
>
> This series fixes memory waste and adds alignment check for unmatched
> qemu_real_host_page_size and TARGET_PAGE_SIZE.
>
> Thanks.
>
> Keqian Zhu
es in SAVING
state for vfio_sync_dirty_bitmap().
[1] https://www.spinics.net/lists/kvm/msg229967.html
Reported-by: Zenghui Yu
Signed-off-by: Keqian Zhu
---
hw/vfio/common.c| 53 +
hw/vfio/migration.c | 35 --
2 files change
Correct sample code to avoid confusing readers.
Signed-off-by: Keqian Zhu
Cc: qemu-triv...@nongnu.org
Reviewed-by: Paolo Bonzini
Reviewed-by: Peter Xu
---
v2:
- Add Cc and R-b.
---
docs/devel/rcu.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/devel/rcu.txt b
Friendly ping ...
Hi, please queue this well reviewed series, Thanks :-)
Keqian
On 2020/12/17 9:49, Keqian Zhu wrote:
> Hi all,
>
> This series fixes memory waste and adds alignment check for unmatched
> qemu_real_host_page_size and TARGET_PAGE_SIZE.
>
> Thanks.
>
> K
[...]
>>> -for (j = old_num_blocks; j < new_num_blocks; j++) {
>>> -new_blocks->blocks[j] = bitmap_new(DIRTY_MEMORY_BLOCK_SIZE);
>>> +if (extend) {
>>> +for (j = cpy_num_blocks; j < new_num_blocks; j++) {
>>> +new_blocks->blocks[j] =
>>> b
Correct sample code to avoid confusing readers.
Signed-off-by: Keqian Zhu
---
docs/devel/rcu.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/devel/rcu.txt b/docs/devel/rcu.txt
index cdf002edd8..2e6cc607a1 100644
--- a/docs/devel/rcu.txt
+++ b/docs/devel/rcu.txt
On 2020/12/17 18:05, Stefan Hajnoczi wrote:
> On Mon, Nov 30, 2020 at 09:11:03PM +0800, Keqian Zhu wrote:
>> @@ -1839,15 +1841,26 @@ static void dirty_memory_extend(ram_addr_t
>> old_ram_size,
>> new_blocks = g_malloc(sizeof(*new_blocks) +
>>
Hi Peter,
Friendly ping :-) Are you going to queue this?
Thanks,
Keqian
On 2020/12/10 15:52, Keqian Zhu wrote:
> In host_memory_backend_get_host_nodes, we build host_nodes
> list and output it to v (a StringOutputVisitor) but forget
> to free the list. This fixes the memory leak.
lot dirty_bmap
may waste memory. For example, when qemu_real_host_page_size is
64K and TARGET_PAGE_SIZE is 4K, it wastes 93.75% (15/16) memory.
Signed-off-by: Keqian Zhu
Reviewed-by: Andrew Jones
Reviewed-by: Peter Xu
---
accel/kvm/kvm-all.c | 6 +-
1 file changed, 5 insertions(+), 1 delet
avoid future breaking.
Signed-off-by: Keqian Zhu
---
accel/kvm/kvm-all.c | 7 +++
1 file changed, 7 insertions(+)
---
v2
- Address Andrew's commment (Use assert instead of return err).
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f6b16a8df8..73b195cc41 100644
--- a/acc
Hi all,
This series fixes memory waste and adds alignment check for unmatched
qemu_real_host_page_size and TARGET_PAGE_SIZE.
Thanks.
Keqian Zhu (2):
accel: kvm: Fix memory waste under mismatch page size
accel: kvm: Add aligment assert for kvm_log_clear_one_slot
accel/kvm/kvm-all.c | 13
On 2020/12/17 4:48, Peter Xu wrote:
> On Wed, Dec 16, 2020 at 04:21:17PM +0800, Keqian Zhu wrote:
>> One more thing, we should consider whether @start and @size is psize aligned
>> (my second
>> patch). Do you agree to add assert on them directly?
>
> Yes I think
Hi Peter,
On 2020/12/16 1:57, Peter Xu wrote:
> On Tue, Dec 15, 2020 at 03:19:47PM +0800, Keqian Zhu wrote:
>> When handle dirty log, we face qemu_real_host_page_size and
>> TARGET_PAGE_SIZE. The first one is the granule of KVM dirty
>> bitmap, and the second one is the
On 2020/12/16 15:23, Andrew Jones wrote:
> On Tue, Dec 15, 2020 at 12:55:50PM +0100, Andrew Jones wrote:
>> On Tue, Dec 15, 2020 at 03:19:48PM +0800, Keqian Zhu wrote:
>>> The parameters start and size are transfered from QEMU memory
>>> emulation layer. I
On 2020/12/15 19:55, Andrew Jones wrote:
> On Tue, Dec 15, 2020 at 03:19:48PM +0800, Keqian Zhu wrote:
>> The parameters start and size are transfered from QEMU memory
>> emulation layer. It can promise that they are TARGET_PAGE_SIZE
>> aligned. However, KVM needs they ar
Hi drew,
On 2020/12/15 19:20, Andrew Jones wrote:
> On Tue, Dec 15, 2020 at 03:19:47PM +0800, Keqian Zhu wrote:
>> When handle dirty log, we face qemu_real_host_page_size and
>> TARGET_PAGE_SIZE. The first one is the granule of KVM dirty
>> bitmap, and the second one is the
Keqian Zhu (2):
accel: kvm: Fix memory waste under mismatch page size
accel: kvm: Add aligment check for kvm_log_clear_one_slot
accel/kvm/kvm-all.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
--
2.23.0
avoid future breaking.
Signed-off-by: Keqian Zhu
---
accel/kvm/kvm-all.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index c5e06288eb..3d0e3aa872 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -701,6 +701,11 @@ stati
lot dirty_bmap may waste
memory. For example, when qemu_real_host_page_size is 64K and
TARGET_PAGE_SIZE is 4K, this bugfix can save 93.75% memory.
Signed-off-by: Keqian Zhu
---
accel/kvm/kvm-all.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/
: Keqian Zhu
---
backends/hostmem.c | 1 +
1 file changed, 1 insertion(+)
---
v2:
- Update commit message.
- Add Chen Qun's T.b.
- Add Igor's R.b.
diff --git a/backends/hostmem.c b/backends/hostmem.c
index 4bde00e8e7..9f9ac95edd 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
) ??:?
#19 0xaaac0c82ed5f (/usr/libexec/qemu-kvm+0x88ed5f) ??:?
SUMMARY: AddressSanitizer: 32 byte(s) leaked in 2 allocation(s).
Fixes: 4cf1b76bf1e2 (hostmem: add properties for NUMA memory policy)
Reported-by: Euler Robot
Signed-off-by: Keqian Zhu
---
backends/hostmem.c | 1 +
1 file changed, 1
Keqian Zhu (2):
ramlist: Make dirty bitmap blocks of ramlist resizable
ramlist: Resize dirty bitmap blocks after remove ramblock
softmmu/physmem.c | 37 +
1 file changed, 29 insertions(+), 8 deletions(-)
--
2.23.0
296 byte(s) leaked in 9 allocation(s).
Reported-by: Euler Robot
Signed-off-by: Keqian Zhu
little concern:
According to code, my bugfix can solve two problems:
1. Lose reference to dirty bitmap of deleted ramblock, because the reference is
covered by dirty bitmap of newly added ramblock.
2.
When we remove a ramblock, we should decrease the dirty bitmap blocks
of ramlist to avoid memory leakage. This patch rebuilds dirty_memory_
extend to support both "extend" and "decrease".
Reported-by: Euler Robot
Signed-off-by: Keqian Zhu
---
so
Fixes: 63c4db4c2e6d (net: relocate paths to helpers and scripts)
Signed-off-by: Keqian Zhu
---
net/tap.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/tap.c b/net/tap.c
index c46ff66184..b8e5cca51c 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -951,7 +951,8 @@ free_fail
Use the new "dirty_bitmap_resize" interface to reduce dirty bitmap
blocks after we remove a ramblock from ramlist.
Signed-off-by: Keqian Zhu
---
softmmu/physmem.c | 8
1 file changed, 8 insertions(+)
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index f6ff78378e..
When we remove a ramblock, we should decrease the dirty bitmap blocks
of ramlist to avoid memory leakage. This patch rebuilds dirty_memory_
extend to support both "extend" and "decrease".
Signed-off-by: Keqian Zhu
---
softmmu/physmem.c | 28
Hi all,
I failed to find where we free dirty bitmap blocks of ramlist. If this is a
memory leakage problem, I hope this patch series can fix it properly :-).
Thanks,
Keqian.
Keqian Zhu (2):
ramlist: Make dirty bitmap blocks of ramlist resizable
ramlist: Resize dirty bitmap blocks after
Avoid covering object refcount of qemu_irq, otherwise it may causes
memory leak.
Signed-off-by: Keqian Zhu
---
hw/core/irq.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/core/irq.c b/hw/core/irq.c
index fb3045b912..59af4dfc74 100644
--- a/hw/core/irq.c
+++ b/hw/core
In migration_shutdown, global var current_migration is freed but not
assigned to NULL, which may cause heap-use-after-free problem if the
following code logic is abnormal.
Signed-off-by: Keqian Zhu
---
migration/migration.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/migration
ned-off-by: Keqian Zhu
---
Changelog:
v3:
- Address Dave's comments.
v2:
- Use new_dirty_pages instead of accu_dirty_pages.
- Adjust commit messages.
---
include/exec/ram_addr.h | 5 +
migration/ram.c | 8 +---
2 files changed, 6 insertions(+), 7 deletions(-)
diff --git
d
of first ram save iteration.
Signed-off-by: Keqian Zhu
---
Changelog:
v2:
- use new_dirty_pages instead of accu_dirty_pages.
- adjust commit messages.
---
include/exec/ram_addr.h | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/include/exec/ram_addr.h b/include/exec/
"real dirty rate" is less
than real "real dirty rate".
Signed-off-by: Keqian Zhu
---
include/exec/ram_addr.h | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index 5e59a3d8d7..af9677e291 100644
--- a/inc
make migration time longer, and is disabled by default.
Signed-off-by: Keqian Zhu
---
Cc: Juan Quintela
Cc: "Dr. David Alan Gilbert"
Cc: Eric Blake
Cc: Markus Armbruster
---
migration/migration.c | 13
migration/ram.c | 25 +-
monitor/hmp
The KVM_VGIC_ATTR macro expect the second parameter as gicr_typer,
of which high 32bit is constructed by mp_affinity. For most case,
the high 32bit of mp_affinity is zero, so it will always access the
ICC_CTLR_EL1 of CPU0.
Signed-off-by: Keqian Zhu
---
hw/intc/arm_gicv3_kvm.c | 4 +---
1 file
Replace kvm_device_access with kvm_gicc_access to simplify
code.
Signed-off-by: Keqian Zhu
---
hw/intc/arm_gicv3_kvm.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c
index ca43bf87ca..85f6420498 100644
--- a/hw/intc
Hi all,
This patch-set contains trivial bugfix and typo fix.
Thanks,
Keqian
Keqian Zhu (3):
bugfix: Use gicr_typer in arm_gicv3_icc_reset
intc/gicv3_kvm: use kvm_gicc_access to get ICC_CTLR_EL1
Typo: Correct the name of CPU hotplug memory region
hw/acpi/cpu.c | 2 +-
hw/intc
Replace "acpi-mem-hotplug" with "acpi-cpu-hotplug"
Signed-off-by: Keqian Zhu
---
hw/acpi/cpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c
index e2c957ce00..3d6a500fb7 100644
--- a/hw/acpi/cpu.c
+++ b/hw/acpi/cpu.c
@@ -
ation time longer, and is disabled by default.
Signed-off-by: Keqian Zhu
---
Cc: Juan Quintela
Cc: "Dr. David Alan Gilbert"
Cc: Eric Blake
Cc: Markus Armbruster
---
migration/migration.c | 13
migration/ram.c | 25 +-
monitor/hmp-cmds.c| 8
ram_addr_t
allocation on long boundaries. So currently we wont "updated the total
dirty page count for both".
By removing the alignment constraint of length in fast path, we can always
use fast dirty sync path if start_global is aligned to word page.
Signed-off-by: Keqian Zhu
---
include/e
In the cpu_physical_memory_sync_dirty_bitmap func, use start_global
variable to make code more clear. And the addr variable is only used
in slow path, so move it to slow path.
Signed-off-by: Keqian Zhu
---
include/exec/ram_addr.h | 11 +--
1 file changed, 5 insertions(+), 6 deletions
This patch series including code style change and performace fix
about dirty bitmap sync.
---
changelogs:
v2:
- split code style change and performace fix.
Keqian Zhu (2):
memory: Introduce start_global variable in dirty bitmap sync
migration: not require length align when choose fast
nd we can always use fast
dirty sync path.
Signed-off-by: Keqian Zhu
---
Cc: Paolo Bonzini
Cc: "Dr. David Alan Gilbert"
Cc: qemu-devel@nongnu.org
---
include/exec/ram_addr.h | 15 ++-
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/include/exec/ram_addr.h b
time.
We can make this parameter configurable to switch between mig-
ration time first or guest performance first.
The default value is 50 and valid range is 1 to 100.
Signed-off-by: Keqian Zhu
---
Changelog:
v1->v2
-Use full name for parameter. Suggested by Eric Blake.
-Change the upper bo
time.
We can make this parameter configurable to switch between mig-
ration time first or guest performance first.
The default value is 50 and valid range is 1 to 100.
Signed-off-by: Keqian Zhu
---
Changelog:
v1->v2
-Use full name for parameter. Suggested by Eric Blake.
-Change the upper bo
time.
We can configure this parameter to switch between migration time
firt or guest performance first. The default value is 50.
Signed-off-by: Keqian Zhu
---
Cc: Juan Quintela
Cc: "Dr. David Alan Gilbert"
Cc: Eric Blake
Cc: Markus Armbruster
---
migration/migrat
At the tail stage of throttle, VM is very sensitive to
CPU percentage. We just throttle 30% of remaining CPU
when throttle is more than 80 percentage.
This doesn't conflict with cpu_throttle_increment.
This may make migration time longer, and is disabled
by default.
Signed-off-by: Keqia
), once hit a
unplug-pending failover device, then it can return true right
now to save cpu time.
Signed-off-by: Keqian Zhu
---
Cc: jfreim...@redhat.com
Cc: Juan Quintela
Cc: "Dr. David Alan Gilbert"
---
migration/migration.c | 2 +-
migration/savevm.c| 24 +++-
m
We can use existing helper function to trigger hotplug handler
plug, which makes code clearer.
Reviewed-by: Igor Mammedov
Signed-off-by: Keqian Zhu
---
hw/arm/virt.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 39ab5f47e0
There is extra indent in ACPI GED hotplug cb that should be
deleted.
Reviewed-by: Igor Mammedov
Signed-off-by: Keqian Zhu
---
hw/acpi/generic_event_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index
This removes extra indent and makes some code refactor related to
memory hotplug.
Changelog:
v2 -> v3
- Addressed Peter's comments.
v1 -> v2
- Add Igor's R-b.
Keqian Zhu (2):
hw/acpi: Remove extra indent in ACPI GED hotplug cb
hw/arm: Use helper function to trigger hotp
From: zhukeqian
There is extra indent in ACPI GED plug cb. And we can use
existing helper function to trigger hotplug handler plug.
Reviewed-by: Igor Mammedov
Signed-off-by: Keqian Zhu
---
v1->v2:
- Add Igor's R-b
Cc: Shameer Kolothum
Cc: "Michael S. Tsirkin"
Cc: Igor M
From: zhukeqian
There is extra indent in ACPI GED plug cb. And we can use
existing helper function to trigger hotplug handler plug.
Signed-off-by: Keqian Zhu
Cc: Shameer Kolothum
Cc: "Michael S. Tsirkin"
Cc: Igor Mammedov
---
hw/acpi/generic_event_device.c | 2 +-
hw/
83 matches
Mail list logo
