at least two individual
tasks. There are times we need to submit a single task and hence a
single DSA task submission is also required.
Signed-off-by: Hao Xiang
Signed-off-by: Bryan Zhang
---
include/qemu/dsa.h | 16 +++
util/dsa.c | 252 +
2
Test hook is disabled by default. To set it, a normal page ratio
between 0 and 100 are valid. If the ratio is set to 50, it means
at least 50% of all pages are sent as normal pages.
Signed-off-by: Hao Xiang
---
include/qemu/dsa.h | 7 ++-
migration/migration-hmp-cmds.c | 7
to be sent as a normal page. This
is useful for live migration performance analysis and optimization.
Signed-off-by: Hao Xiang
---
migration/options.c | 31 +++
migration/options.h | 1 +
qapi/migration.json | 17 ++---
3 files changed, 46 insertions(+), 3
Juan Quintela had a patchset enabling zero page checking in multifd
threads.
https://lore.kernel.org/all/20220802063907.18882-13-quint...@redhat.com/
Some of the changes in that patchset has already made to upstream but
a few are still being reviewed. This patch contains the changes from
the
Idxd is the device driver for DSA (Intel Data Streaming
Accelerator). The driver is fully functioning since Linux
kernel 5.19. This change adds the driver's header file used
for userspace development.
Signed-off-by: Hao Xiang
---
linux-headers/linux/idxd.h | 356
* Add test case to start and complete multifd live migration with DSA
offloading enabled.
* Add test case to start and cancel multifd live migration with DSA
offloading enabled.
Signed-off-by: Bryan Zhang
Signed-off-by: Hao Xiang
---
tests/qtest/migration-test.c | 66
size is useful for performance tuning.
Signed-off-by: Hao Xiang
---
migration/migration-hmp-cmds.c | 7 +++
migration/multifd-zlib.c | 4 ++--
migration/multifd-zstd.c | 4 ++--
migration/multifd.c| 6 --
migration/multifd.h| 3 ---
5 files changed, 15
* Test DSA start and stop path.
* Test DSA configure and cleanup path.
* Test DSA task submission and completion path.
Signed-off-by: Bryan Zhang
Signed-off-by: Hao Xiang
---
tests/unit/meson.build | 6 +
tests/unit/test-dsa.c | 448 +
2 files changed
Enable instruction set enqcmd in build.
Signed-off-by: Hao Xiang
---
meson.build | 2 ++
meson_options.txt | 2 ++
scripts/meson-buildoptions.sh | 3 +++
3 files changed, 7 insertions(+)
diff --git a/meson.build b/meson.build
index bd65a111aa..6ea859829c 100644
using DSA
offloading.
* Patchset
Apply this patchset on top of commit
800485762e6564e04e2ab315132d477069562d91
Hao Xiang (16):
Cherry pick a set of patches that enables multifd zero page feature.
meson: Introduce new instruction set enqcmd to the build system.
util/dsa: Add depende
.
Signed-off-by: Hao Xiang
---
util/dsa.c | 243 -
1 file changed, 242 insertions(+), 1 deletion(-)
diff --git a/util/dsa.c b/util/dsa.c
index f82282ce99..0e68013ffb 100644
--- a/util/dsa.c
+++ b/util/dsa.c
@@ -44,6 +44,7 @@
#define DSA_WQ_SIZE
Intel DSA offloading is an optional feature that turns on if
proper hardware and software stack is available. To turn on
DSA offloading in multifd live migration:
multifd-dsa-accel="[dsa_dev_path1] ] [dsa_dev_path2] ... [dsa_dev_pathX]"
This feature is turned off by default.
Signed-o
The current multifd packet size is 128 * 4kb. This change adds
an option to set the packet size. Both sender and receiver needs
to set the same packet size for things to work.
Signed-off-by: Hao Xiang
---
migration/options.c | 34 ++
migration/options.h | 1
* Use a safe thread queue for DSA task enqueue/dequeue.
* Implement DSA task submission.
* Implement DSA batch task submission.
Signed-off-by: Hao Xiang
---
include/qemu/dsa.h | 35
util/dsa.c | 196 +
2 files changed, 231 insertions
. The sender thread submits a batch of pages to DSA
hardware and waits for the DSA completion thread to signal for work
completion.
Signed-off-by: Hao Xiang
---
migration/multifd.c | 101 +---
migration/multifd.h | 3 ++
2 files changed, 89 insertions(+), 15
* DSA device open and close.
* DSA group contains multiple DSA devices.
* DSA group configure/start/stop/clean.
Signed-off-by: Hao Xiang
Signed-off-by: Bryan Zhang
---
include/qemu/dsa.h | 49 +++
util/dsa.c | 338 +
util/meson.build
* Add a DSA task completion callback.
* DSA completion thread will call the tasks's completion callback
on every task/batch task completion.
* DSA submission path to wait for completion.
* Implement CPU fallback if DSA is not able to complete the task.
Signed-off-by: Hao Xiang
Signed-off
On Fri, Oct 27, 2023 at 5:30 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > Juan Quintela had a patchset enabling zero page checking in multifd
> > threads.
> >
> > https://lore.kernel.org/all/20220802063907.18882-13-quint...@redhat.com/
>
> Hmm, risk
On Fri, Oct 27, 2023 at 6:22 AM Peter Maydell wrote:
>
> On Fri, 27 Oct 2023 at 13:32, Fabiano Rosas wrote:
> >
> > Hao Xiang writes:
> >
> > > Juan Quintela had a patchset enabling zero page checking in multifd
> > > threads.
> > >
> &
On Mon, Oct 30, 2023 at 8:26 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > * Background:
> > I posted an RFC about DSA offloading in QEMU:
> > https://patchew.org/QEMU/20230529182001.2232069-1-hao.xi...@bytedance.com/
> >
> > This patchset imp
On Mon, Oct 30, 2023 at 6:58 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > On Fri, Oct 27, 2023 at 5:30 AM Fabiano Rosas wrote:
> >>
> >> Hao Xiang writes:
> >>
> >> > Juan Quintela had a patchset enabling zero page c
On Mon, Oct 30, 2023 at 7:41 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > Intel DSA offloading is an optional feature that turns on if
> > proper hardware and software stack is available. To turn on
> > DSA offloading in multifd live migration:
> >
>
Hi everyone,
I am looking into using the new Data Streaming Accelerator (DSA)
hardware acceleration feature built into the Intel Sapphire Rapids
system. One of the scenarios I am investigating is the QEMU live
migration feature. I noticed that during live migration, there is
pretty busy work
Hi all, this is meant to be an RFC. Sorry I didn't put that in the email
subject correctly.
From: "Hao Xiang"
Date: Mon, May 29, 2023, 11:20
Subject: [PATCH 0/4] Add Intel Data Streaming Accelerator offloading
To: , ,
Cc: "Hao Xiang"
* Idea:
Intel Data Streaming Accelerato
1. Adds a memory comparison function by submitting
the work to the idxd driver.
2. Add interface to set bufferiszero accel function
to DSA offloading.
3. Fallback to use CPU accel function if DSA offloading
fails due to page fault.
Signed-off-by: Hao Xiang
---
include/qemu/cutils.h | 6
1. Enable instruction set enqcmd in build.
2. Enable instruction set movdir64b in build.
Signed-off-by: Hao Xiang
---
meson.build | 3 +++
meson_options.txt | 4
scripts/meson-buildoptions.sh | 6 ++
3 files changed, 13 insertions(+)
diff --git
This change adds a new argument --dsa-accelerate to qemu.
Signed-off-by: Hao Xiang
---
qemu-options.hx | 10 ++
softmmu/runstate.c | 4
softmmu/vl.c | 22 ++
storage-daemon/qemu-storage-daemon.c
Idxd is the device driver for DSA (Intel Data Streaming
Accelerator). The driver is fully functioning since Linux
kernel 5.19. This change adds the driver's header file used
for userspace development.
Signed-off-by: Hao Xiang
---
linux-headers/linux/idxd.h | 356
e interrupt for true async completion.
4. The DSA device can also offload other operations.
* memcpy
* xbzrle encoding/decoding
* crc32
base-commit: ac84b57b4d74606f7f83667a0606deef32b2049d
Hao Xiang (4):
Introduce new instruction set enqcmd/mmovdir64b to the build system.
Add dependency id
Hi,
After pulling in the QEMU latest commits, I can no longer run the
"configure" command. Below is the error message I am seeing. I believe this
is related to this change "configure: create a python venv
unconditionally".
I am running on Debian GNU/Linux 11 (bullseye) and 5.15 kernel version.
On Tue, May 30, 2023 at 2:26 AM Duan, Zhenzhong
wrote:
>
> Hi Hao,
>
> > +memset(, 0, sizeof(descriptor));
> > +
> > +descriptor.opcode = DSA_OPCODE_COMPARE;
>
> What about using DSA_OPCODE_COMPVAL with zero?
> DSA_OPCODE_COMPARE consumes double bandwidth by reading
> from both src and
Hi Paolo, I have applied this patch locally and I am able to run
"configure" now.
From: "Paolo Bonzini"
Date: Fri, May 19, 2023, 1:31 AM
Subject: [External] Re: Configure no longer works after pulling in the
latest QEMU commits
To: "Hao Xiang", "qemu-devel@nongn
On Tue, Jan 23, 2024 at 7:11 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > On Sun, Jan 14, 2024 at 10:02 PM Shivam Kumar
> > wrote:
> >>
> >>
> >>
> >> > On 04-Jan-2024, at 6:14 AM, Hao Xiang wrote:
> >> >
> &g
On Sun, Jan 14, 2024 at 11:01 PM Shivam Kumar wrote:
>
>
>
> > On 04-Jan-2024, at 6:14 AM, Hao Xiang wrote:
> >
> > From: Juan Quintela
> >
> > This implements the zero page dection and handling.
> >
> > Signed-off-by:
On Sun, Jan 14, 2024 at 10:02 PM Shivam Kumar wrote:
>
>
>
> > On 04-Jan-2024, at 6:14 AM, Hao Xiang wrote:
> >
> > From: Juan Quintela
> >
> > We have to enable it by default until we introduce the new code.
> >
> > Signed-off-by:
On Thu, Nov 16, 2023 at 7:14 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > From: Juan Quintela
> >
> > Signed-off-by: Juan Quintela
> > Reviewed-by: Leonardo Bras
> > ---
> > migration/multifd.c | 7 ---
> > migration/options
On Sun, Jan 14, 2024 at 10:46 PM Shivam Kumar wrote:
>
>
>
> > On 04-Jan-2024, at 6:14 AM, Hao Xiang wrote:
> >
> > 1. Refactor multifd_send_thread function.
> > 2. Implement buffer_is_zero_use_cpu to handle CPU based zero page
> > checking.
&g
On Tue, Feb 6, 2024 at 8:25 PM Peter Xu wrote:
>
> On Tue, Feb 06, 2024 at 11:19:05PM +0000, Hao Xiang wrote:
> > diff --git a/migration/multifd.c b/migration/multifd.c
> > index 25cbc6dc6b..a20d0ed10e 100644
> > --- a/migration/multifd.c
> > +++ b/migration/
On Fri, Feb 2, 2024 at 2:30 AM wrote:
>
> From: Peter Xu
>
> This array is redundant when p->pages exists. Now we extended the life of
> p->pages to the whole period where pending_job is set, it should be safe to
> always use p->pages->offset[] rather than p->normal[]. Drop the array.
>
>
On Fri, Feb 9, 2024 at 4:20 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > On Fri, Feb 2, 2024 at 2:30 AM wrote:
> >>
> >> From: Peter Xu
> >>
> >> This array is redundant when p->pages exists. Now we extended the life of
>
This change adds zero page counters and updates multifd send/receive
tracing format to track the newly added counters.
Signed-off-by: Hao Xiang
---
migration/multifd.c| 43 ++
migration/multifd.h| 21 -
migration/ram.c
+
|multifd-2-threads | 4643 |
++
|multifd-4-threads | 4143 |
++
Apply this patchset on top of commit
5767815218efd3cbfd409505ed824d5f356044ae
Hao Xiang (7):
migration/multifd: Add new migration option zero-page-detectio
main thread.
Signed-off-by: Hao Xiang
---
migration/multifd.c | 1 +
migration/options.c | 2 +-
migration/ram.c | 53 ++---
3 files changed, 42 insertions(+), 14 deletions(-)
diff --git a/migration/multifd.c b/migration/multifd.c
index fbb40ea10b
This change extends the MigrationStatus interface to track zero pages
and zero bytes counter.
Signed-off-by: Hao Xiang
---
migration/migration-hmp-cmds.c | 4
migration/migration.c | 2 ++
qapi/migration.json | 15 ++-
tests/migration
This new parameter controls where the zero page checking is running.
1. If this parameter is set to 'legacy', zero page checking is
done in the migration main thread.
2. If this parameter is set to 'none', zero page checking is disabled.
Signed-off-by: Hao Xiang
---
hw/core/qdev-properties
migration main thread.
Signed-off-by: Hao Xiang
---
tests/qtest/migration-test.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 8a5bb1752e..c27083110a 100644
--- a/tests/qtest/migration-te
off-by: Hao Xiang
---
migration/meson.build | 1 +
migration/multifd-zero-page.c | 59 +++
migration/multifd-zlib.c | 26 ---
migration/multifd-zstd.c | 25 ---
migration/multifd.c |
Add myself to maintain multifd zero page checking acceleration function.
Signed-off-by: Hao Xiang
---
MAINTAINERS | 5 +
1 file changed, 5 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index a24c2b51b6..3ca407cb58 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3403,6 +3403,11 @@ F
thread.
Signed-off-by: Hao Xiang
---
tests/qtest/migration-test.c | 26 ++
1 file changed, 26 insertions(+)
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 7675519cfa..2c13df04c3 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest
This change adds zero page counters and updates multifd send/receive
tracing format to track the newly added counters.
Signed-off-by: Hao Xiang
---
migration/migration-hmp-cmds.c | 4
migration/multifd.c| 43 ++
migration/multifd.h
This implements the zero page detection and handling on the multifd
threads.
Signed-off-by: Hao Xiang
---
migration/multifd.c | 62 +
migration/multifd.h | 5
2 files changed, 62 insertions(+), 5 deletions(-)
diff --git a/migration/multifd.c b
This new parameter controls where the zero page checking is running. If
this parameter is set to true, zero page checking is done in the multifd
sender threads. If this parameter is set to false, zero page checking is
done in the migration main thread.
Signed-off-by: Hao Xiang
---
migration
| 21.53GB/s |
+--+
|multifd-4-threads | 4143 | 24.13GB/s |
+--+
Apply this patchset on top of commit
39a6e4f87e7b75a45b08d6dc8b8b7c2954c87440
Hao Xiang (6):
migration/multifd: Add new migration
This change extends the MigrationStatus interface to track zero pages
and zero bytes counter.
Signed-off-by: Hao Xiang
---
qapi/migration.json | 15 ++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/qapi/migration.json b/qapi/migration.json
index ff033a0344
main thread.
Signed-off-by: Hao Xiang
---
migration/multifd.c | 3 ++-
migration/ram.c | 49 -
2 files changed, 42 insertions(+), 10 deletions(-)
diff --git a/migration/multifd.c b/migration/multifd.c
index c031f947c7..c6833ccb07 100644
On Wed, Feb 7, 2024 at 12:41 AM Jiri Denemark wrote:
>
> On Wed, Feb 07, 2024 at 12:37:15 +0800, Peter Xu wrote:
> > On Wed, Feb 07, 2024 at 12:13:10PM +0800, Peter Xu wrote:
> > > On Tue, Feb 06, 2024 at 11:19:04PM +, Hao Xiang wrote:
> > > > This change exte
On Tue, Feb 6, 2024 at 7:39 PM Peter Xu wrote:
>
> On Tue, Feb 06, 2024 at 11:19:02PM +0000, Hao Xiang wrote:
> > This patchset is based on Juan Quintela's old series here
> > https://lore.kernel.org/all/20220802063907.18882-1-quint...@redhat.com/
> >
> > In th
On Tue, Feb 6, 2024 at 7:45 PM Peter Xu wrote:
>
> On Tue, Feb 06, 2024 at 11:19:03PM +0000, Hao Xiang wrote:
> > diff --git a/qapi/migration.json b/qapi/migration.json
> > index 819708321d..ff033a0344 100644
> > --- a/qapi/migration.json
> > +++ b/qapi/migrat
riginal Message-
> > From: Peter Xu
> > Sent: Wednesday, February 7, 2024 4:10 PM
> > To: Bryan Zhang ; Hao Xiang
> > ; Liu, Yuan1
> > Cc: Fabiano Rosas ; QEMU Devel Mailing List > de...@nongnu.org>
> > Subject: Regarding to the recent Intel IAA/DSA/QAT
On Sun, Dec 17, 2023 at 7:11 PM Wang, Lei wrote:
>
> On 11/14/2023 13:40, Hao Xiang wrote:> * Create a dedicated thread for DSA
> task
> completion.
> > * DSA completion thread runs a loop and poll for completed tasks.
> > * Start and stop DSA completion thread d
On Mon, Dec 11, 2023 at 11:44 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > Intel DSA offloading is an optional feature that turns on if
> > proper hardware and software stack is available. To turn on
> > DSA offloading in multifd live migration:
> >
>
On Mon, Dec 18, 2023 at 5:34 PM Wang, Lei wrote:
>
> On 12/19/2023 2:57, Hao Xiang wrote:> On Sun, Dec 17, 2023 at 7:11 PM Wang,
> Lei
> wrote:
> >>
> >> On 11/14/2023 13:40, Hao Xiang wrote:> * Create a dedicated thread for DSA
> >> task
> &
On Mon, Dec 11, 2023 at 1:28 PM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > * DSA device open and close.
> > * DSA group contains multiple DSA devices.
> > * DSA group configure/start/stop/clean.
> >
> > Signed-off-by: Hao Xiang
> > Signed-o
On Mon, Dec 11, 2023 at 7:41 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > Enable instruction set enqcmd in build.
> >
> > Signed-off-by: Hao Xiang
> > ---
> > meson.build | 2 ++
> > meson_options.txt | 2 ++
>
On Tue, Dec 12, 2023 at 8:10 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > * Use a safe thread queue for DSA task enqueue/dequeue.
> > * Implement DSA task submission.
> > * Implement DSA batch task submission.
> >
> > Signed-off-by: Hao Xiang
On Tue, Dec 19, 2023 at 5:19 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> >>
> >> > +}
> >> > +
> >> > +void dsa_start(void) {}
> >> > +
> >> > +void dsa_stop(void) {}
> >> > +
> >&
On Wed, Dec 13, 2023 at 6:01 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > * Add a DSA task completion callback.
> > * DSA completion thread will call the tasks's completion callback
> > on every task/batch task completion.
> > * DSA submission path to wai
On Wed, Dec 13, 2023 at 9:33 AM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > During live migration, if the latency between sender and receiver
> > is high but bandwidth is high (a long and fat pipe), using a bigger
> > packet size can help reduce migration tot
From: Juan Quintela
This implements the zero page dection and handling.
Signed-off-by: Juan Quintela
---
migration/multifd.c | 41 +++--
migration/multifd.h | 5 +
2 files changed, 44 insertions(+), 2 deletions(-)
diff --git a/migration/multifd.c
Intel DSA offloading is an optional feature that turns on if
proper hardware and software stack is available. To turn on
DSA offloading in multifd live migration:
multifd-dsa-accel="[dsa_dev_path1] [dsa_dev_path2] ... [dsa_dev_pathX]"
This feature is turned off by default.
Signed-o
1. Refactor multifd_send_thread function.
2. Implement buffer_is_zero_use_cpu to handle CPU based zero page
checking.
3. Introduce the batch task structure in MultiFDSendParams.
Signed-off-by: Hao Xiang
---
include/qemu/dsa.h | 43 +++--
migration/multifd.c | 77
* Use a safe thread queue for DSA task enqueue/dequeue.
* Implement DSA task submission.
* Implement DSA batch task submission.
Signed-off-by: Hao Xiang
---
include/qemu/dsa.h | 28 +++
util/dsa.c | 201 +
2 files changed, 229 insertions
Enable instruction set enqcmd in build.
Signed-off-by: Hao Xiang
---
meson.build | 14 ++
meson_options.txt | 2 ++
scripts/meson-buildoptions.sh | 3 +++
3 files changed, 19 insertions(+)
diff --git a/meson.build b/meson.build
index 6c77d9687d
From: Juan Quintela
Signed-off-by: Juan Quintela
Reviewed-by: Leonardo Bras
---
migration/multifd.c | 7 ---
migration/options.c | 17 +
migration/ram.c | 45 ++---
qapi/migration.json | 1 -
4 files changed, 51 insertions(+),
* Test DSA start and stop path.
* Test DSA configure and cleanup path.
* Test DSA task submission and completion path.
Signed-off-by: Bryan Zhang
Signed-off-by: Hao Xiang
---
tests/unit/meson.build | 6 +
tests/unit/test-dsa.c | 475 +
2 files changed
From: Juan Quintela
We have to enable it by default until we introduce the new code.
Signed-off-by: Juan Quintela
---
migration/options.c | 15 +++
migration/options.h | 1 +
qapi/migration.json | 8 +++-
3 files changed, 23 insertions(+), 1 deletion(-)
diff --git
the packet size is useful for performance tuning.
Set the option:
migrate_set_parameter multifd-packet-size 4190208
Signed-off-by: Hao Xiang
---
migration/migration-hmp-cmds.c | 7 +++
migration/multifd-zlib.c | 6 --
migration/multifd-zstd.c | 6 --
migration/multifd.c
* Add a DSA task completion callback.
* DSA completion thread will call the tasks's completion callback
on every task/batch task completion.
* DSA submission path to wait for completion.
* Implement CPU fallback if DSA is not able to complete the task.
Signed-off-by: Hao Xiang
Signed-off
Apply this patchset on top of commit
7425b6277f12e82952cede1f531bfc689bf77fb1
Hao Xiang (16):
meson: Introduce new instruction set enqcmd to the build system.
util/dsa: Add dependency idxd.
util/dsa: Implement DSA device start and stop logic.
util/dsa: Implement DSA task enqueue and dequeue.
at least two individual
tasks. There are times we need to submit a single task and hence a
single DSA task submission is also required.
Signed-off-by: Hao Xiang
Signed-off-by: Bryan Zhang
---
include/qemu/dsa.h | 18
util/dsa.c | 247 +
2
. The sender thread submits a batch of pages to DSA
hardware and waits for the DSA completion thread to signal for work
completion.
Signed-off-by: Hao Xiang
---
migration/multifd.c | 51 -
1 file changed, 46 insertions(+), 5 deletions(-)
diff --git a/migration
* Add test case to start and complete multifd live migration with DSA
offloading enabled.
* Add test case to start and cancel multifd live migration with DSA
offloading enabled.
Signed-off-by: Bryan Zhang
Signed-off-by: Hao Xiang
---
tests/qtest/migration-test.c | 77
to be sent as a normal page. This
is useful for live migration performance analysis and optimization.
Signed-off-by: Hao Xiang
---
migration/options.c | 32
migration/options.h | 1 +
qapi/migration.json | 18 +++---
3 files changed, 48 insertions(+), 3
Idxd is the device driver for DSA (Intel Data Streaming
Accelerator). The driver is fully functioning since Linux
kernel 5.19. This change adds the driver's header file used
for userspace development.
Signed-off-by: Hao Xiang
---
linux-headers/linux/idxd.h | 356
From: Juan Quintela
This patch adds counters and similar. Logic will be added on the
following patch.
Signed-off-by: Juan Quintela
---
migration/multifd.c| 37 ++---
migration/multifd.h| 17 -
migration/trace-events | 8
3
.
Signed-off-by: Hao Xiang
---
include/qemu/dsa.h | 1 +
util/dsa.c | 274 -
2 files changed, 274 insertions(+), 1 deletion(-)
diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
index 37cae8d9d2..2513192a2b 100644
--- a/include/qemu/dsa.h
+++ b
The current multifd packet size is 128 * 4kb. This change adds
an option to set the packet size. Both sender and receiver needs
to set the same packet size for things to work.
Signed-off-by: Hao Xiang
---
migration/options.c | 36
migration/options.h | 1
Test hook is disabled by default. To set it, a normal page ratio
between 0 and 100 are valid. If the ratio is set to 50, it means
at least 50% of all pages are sent as normal pages.
Set the option:
migrate_set_parameter multifd-normal-page-ratio 60
Signed-off-by: Hao Xiang
---
include/qemu
* DSA device open and close.
* DSA group contains multiple DSA devices.
* DSA group configure/start/stop/clean.
Signed-off-by: Hao Xiang
Signed-off-by: Bryan Zhang
---
include/qemu/dsa.h | 72 +++
util/dsa.c | 316 +
util/meson.build
On Mon, Jan 8, 2024 at 9:15 AM Gregory Price wrote:
>
> On Fri, Jan 05, 2024 at 09:59:19PM -0800, Hao Xiang wrote:
> > On Wed, Jan 3, 2024 at 1:56 PM Gregory Price
> > wrote:
> > >
> > > For a variety of performance reasons, this will not work the way you
&g
On Mon, Jan 8, 2024 at 2:47 PM Hao Xiang wrote:
>
> On Mon, Jan 8, 2024 at 9:15 AM Gregory Price
> wrote:
> >
> > On Fri, Jan 05, 2024 at 09:59:19PM -0800, Hao Xiang wrote:
> > > On Wed, Jan 3, 2024 at 1:56 PM Gregory Price
> > > wrote:
> > >
On Mon, Jan 8, 2024 at 6:26 PM Liu, Yuan1 wrote:
>
> > -Original Message-
> > From: Fabiano Rosas
> > Sent: Tuesday, January 9, 2024 4:28 AM
> > To: Liu, Yuan1 ; Hao Xiang
> > Cc: Bryan Zhang ; qemu-devel@nongnu.org;
> > marcandre.lur.
On Mon, Jan 8, 2024 at 12:39 PM Fabiano Rosas wrote:
>
> Hao Xiang writes:
>
> > From: Juan Quintela
> >
> > We have to enable it by default until we introduce the new code.
> >
> > Signed-off-by: Juan Quintela
> > ---
> > migration/options.c
On Mon, Jan 8, 2024 at 12:28 PM Fabiano Rosas wrote:
>
> "Liu, Yuan1" writes:
>
> >> -Original Message-
> >> From: Hao Xiang
> >> Sent: Saturday, January 6, 2024 7:53 AM
> >> To: Fabiano Rosas
> >> Cc: Bryan Zhan
On Mon, Jan 8, 2024 at 5:13 PM Gregory Price wrote:
>
> On Mon, Jan 08, 2024 at 05:05:38PM -0800, Hao Xiang wrote:
> > On Mon, Jan 8, 2024 at 2:47 PM Hao Xiang wrote:
> > >
> > > On Mon, Jan 8, 2024 at 9:15 AM Gregory Price
> > > wrote:
> > > &g
On Tue, Jan 9, 2024 at 11:58 AM Gregory Price
wrote:
>
> On Tue, Jan 09, 2024 at 11:33:04AM -0800, Hao Xiang wrote:
> > On Mon, Jan 8, 2024 at 5:13 PM Gregory Price
> > wrote:
> >
> > Sounds like the technical details are explained on the other thread.
> &g
On Tue, Jan 9, 2024 at 2:13 PM Gregory Price wrote:
>
> On Tue, Jan 09, 2024 at 01:27:28PM -0800, Hao Xiang wrote:
> > On Tue, Jan 9, 2024 at 11:58 AM Gregory Price
> > wrote:
> > >
> > > If you drop this line:
> > >
> > > -numa no
methods effectively unimplemented. This is in preparation of a
> > subsequent commit that will implement actually using QAT for compression
> > and decompression.
> >
> > Signed-off-by: Bryan Zhang
> > Signed-off-by: Hao Xiang
> > ---
> > hw/core/q
On Tue, Jan 2, 2024 at 5:04 AM David Hildenbrand wrote:
>
> On 01.01.24 08:53, Ho-Ren (Jack) Chuang wrote:
> > Introduce a new configuration option 'host-mem-type=' in the
> > '-object memory-backend-ram', allowing users to specify
> > from which type of memory to allocate.
> >
> > Users can
On Wed, Jan 3, 2024 at 1:56 PM Gregory Price wrote:
>
> On Sun, Dec 31, 2023 at 11:53:15PM -0800, Ho-Ren (Jack) Chuang wrote:
> > Introduce a new configuration option 'host-mem-type=' in the
> > '-object memory-backend-ram', allowing users to specify
> > from which type of memory to allocate.
> >
1 - 100 of 204 matches
Mail list logo