From: Alexander Antonov
After a "make -C tools/perf", git reports the following untracked file:
perf-iostat
Add this generated file to perf's .gitignore file.
Acked-by: Namhyung Kim
Signed-off-by: Alexander Antonov
---
tools/perf/.gitignore | 1 +
1 file changed, 1 insertion(+)
From: Alexander Antonov
Add basic flow for a new iostat mode in perf. Mode is intended to
provide four I/O performance metrics per each PCIe root port: Inbound Read,
Inbound Write, Outbound Read, Outbound Write.
The actual code to compute the metrics and attribute it to
root port is in follow
From: Alexander Antonov
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Acked-by: Namhyung Kim
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iostat.c | 110 ++
1 file changed, 110
From: Alexander Antonov
This functionality is based on recently introduced sysfs attributes
for Intel® Xeon® Scalable processor family (code name Skylake-SP):
Commit bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore unit to
IIO PMON mapping")
Mode is intended to provid
From: Alexander Antonov
Resending V5 with added Acked-by: Namhyung Kim tag.
Thanks,
Alexander
The previous version can be found at:
v4:
https://lkml.kernel.org/r/20210203135830.38568-1-alexander.anto...@linux.intel.com/
Changes in this revision are:
v4 -> v5:
- Addressed comments f
The following commit has been merged into the perf/core branch of tip:
Commit-ID: cface0326a6c2ae5c8f47bd466f07624b3e348a7
Gitweb:
https://git.kernel.org/tip/cface0326a6c2ae5c8f47bd466f07624b3e348a7
Author:Alexander Antonov
AuthorDate:Tue, 23 Mar 2021 18:05:07 +03:00
After a "make -C tools/perf", git reports the following untracked file:
perf-iostat
Add this generated file to perf's .gitignore file.
Signed-off-by: Alexander Antonov
---
tools/perf/.gitignore | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/.gitignore b/tools/perf/
ach metric requiries only one uncore event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
#EventCount * 4B / (1024 * 1024)
Signed-off-by: Alexander Antonov
---
tools/perf/Documentation/perf-iostat.txt | 88 ++
tools/perf/Mak
Inbound Read(MB)Inbound Write(MB)Outbound
Read(MB) Outbound Write(MB)
:17 358559 440
22
:3a320
0
197.081983
-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 21 +-
tools/perf/util/Build | 1 +
tools/perf/util/iostat.c | 53 ++
tools/perf/util/iostat.h | 47 ++
tools/perf/util/stat-display.c | 40
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iostat.c | 110 ++
1 file changed, 110 insertions(+)
create mode 100644 tools/perf/arch/x86
he segment in skx_iio_get_topology() function.
Reported-by: kernel test robot
Tested-by: Kyle Meyer
Reviewed-by: Andi Kleen
Reviewed-by: Kan Liang
Signed-off-by: Alexander Antonov
---
arch/x86/events/intel/uncore.c | 12 ++
arch/x86/events/intel/uncore.h | 9 -
arch/x86/events/intel/unco
On 3/9/2021 10:51 AM, liuqi (BA) wrote:
Hi Alexander,
On 2021/2/3 21:58, Alexander Antonov wrote:
This functionality is based on recently introduced sysfs attributes
for Intel® Xeon® Scalable processor family (code name Skylake-SP):
Commit bb42b3d39781 ("perf/x86/intel/uncore: E
On 2/4/2021 3:32 PM, Namhyung Kim wrote:
On Wed, Feb 3, 2021 at 10:58 PM Alexander Antonov
wrote:
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iostat.c | 124
On 2/4/2021 3:22 PM, Namhyung Kim wrote:
On Wed, Feb 3, 2021 at 10:58 PM Alexander Antonov
wrote:
Add basic flow for a new iostat mode in perf. Mode is intended to
provide four I/O performance metrics per each PCIe root port: Inbound Read,
Inbound Write, Outbound Read, Outbound Write
On 2/4/2021 3:07 PM, Namhyung Kim wrote:
Hello,
On Wed, Feb 3, 2021 at 10:58 PM Alexander Antonov
wrote:
Adding AGGR_PCIE_PORT mode to be able to distinguish aggr_mode
for root ports in following patches.
I'm not sure adding the AGGR_PCIE_PORT is the right way.
In my understanding, the aggr
After a "make -C tools/perf", git reports the following untracked file:
perf-iostat
Add this generated file to perf's .gitignore file.
Signed-off-by: Alexander Antonov
---
tools/perf/.gitignore | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/.gitignore b/tools/perf/
ach metric requiries only one uncore event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
#EventCount * 4B / (1024 * 1024)
Signed-off-by: Alexander Antonov
---
tools/perf/Documentation/perf-iostat.txt | 88 ++
tools/perf/Mak
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iostat.c | 124 ++
1 file changed, 124 insertions(+)
create mode 100644 tools/perf/arch/x86
-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 31 ++
tools/perf/util/iostat.h | 32 +++
tools/perf/util/stat-display.c | 40 +-
tools/perf/util/stat-shadow.c | 11 +-
tools/perf/util/stat.h
0
22
:3a320
0
197.081983474 seconds time elapsed
Alexander Antonov (5):
perf stat: Add AGGR_PCIE_PORT mode
perf stat: Basic support for iostat in perf
perf stat: Helper functions for PCIe
Adding AGGR_PCIE_PORT mode to be able to distinguish aggr_mode
for root ports in following patches.
Signed-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 5 -
.../util/scripting-engines/trace-event-python.c | 3 ++-
tools/perf/util/stat-display.c
On 1/29/2021 11:26 AM, Namhyung Kim wrote:
Hello,
On Tue, Jan 26, 2021 at 5:06 PM Alexander Antonov
wrote:
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
[SNIP]
+static int
Introduce helper functions to control PCIe root ports list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iostat.c | 127 ++
1 file changed, 127 insertions(+)
create mode 100644 tools/perf/arch/x86
After a "make -C tools/perf", git reports the following untracked file:
perf-iostat
Add this generated file to perf's .gitignore file.
Signed-off-by: Alexander Antonov
---
tools/perf/.gitignore | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/.gitignore b/tools/perf/
ach metric requiries only one uncore event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
#EventCount * 4B / (1024 * 1024)
Signed-off-by: Alexander Antonov
---
tools/perf/Documentation/perf-iostat.txt | 88 ++
tools/perf/Mak
-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 31 ++
tools/perf/util/iostat.h | 32 +++
tools/perf/util/stat-display.c | 40 +-
tools/perf/util/stat-shadow.c | 11 +-
tools/perf/util/stat.h
440
22
:3a320
0
197.081983474 seconds time elapsed
Alexander Antonov (5):
perf stat: Add AGGR_PCIE_PORT mode
perf stat: Basic support for iostat in perf
Adding AGGR_PCIE_PORT mode to be able to distinguish aggr_mode
for root ports in following patches.
Signed-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 5 -
.../util/scripting-engines/trace-event-python.c | 3 ++-
tools/perf/util/stat-display.c
On 1/15/2021 10:33 AM, Namhyung Kim wrote:
On Fri, Jan 15, 2021 at 1:41 AM Alexander Antonov
wrote:
On 1/14/2021 6:39 AM, Namhyung Kim wrote:
On Wed, Jan 13, 2021 at 9:08 PM Alexander Antonov
wrote:
On 1/6/2021 12:02 PM, Namhyung Kim wrote:
On Wed, Dec 23, 2020 at 10:03 PM Alexander
On 1/14/2021 6:39 AM, Namhyung Kim wrote:
On Wed, Jan 13, 2021 at 9:08 PM Alexander Antonov
wrote:
On 1/6/2021 12:02 PM, Namhyung Kim wrote:
On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
wrote:
This functionality is based on recently introduced sysfs attributes
for Intel® Xeon
On 1/14/2021 6:34 AM, Namhyung Kim wrote:
Hello,
On Wed, Jan 13, 2021 at 8:34 PM Alexander Antonov
wrote:
On 1/6/2021 11:56 AM, Namhyung Kim wrote:
On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
wrote:
Add basic flow for a new iiostat mode in perf. Mode is intended to
provide four I
On 1/6/2021 12:02 PM, Namhyung Kim wrote:
On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
wrote:
This functionality is based on recently introduced sysfs attributes
for Intel® Xeon® Scalable processor family (code name Skylake-SP):
Commit bb42b3d39781 ("perf/x86/intel/uncore: E
On 1/6/2021 11:56 AM, Namhyung Kim wrote:
On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
wrote:
Add basic flow for a new iiostat mode in perf. Mode is intended to
provide four I/O performance metrics per each IIO stack: Inbound Read,
Inbound Write, Outbound Read, Outbound Write
On 1/6/2021 11:44 AM, Namhyung Kim wrote:
Hi,
On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
wrote:
Adding evsel::perf_device void pointer.
For performance monitoring purposes, an evsel can have a related device.
These changes allow to attribute, for example, I/O performance metrics
Adding evsel::perf_device void pointer.
For performance monitoring purposes, an evsel can have a related device.
These changes allow to attribute, for example, I/O performance metrics
to IIO stack.
Signed-off-by: Alexander Antonov
---
tools/perf/util/evsel.h | 1 +
1 file changed, 1 insertion
Adding AGGR_IIO_STACK mode to be able to distinguish aggr_mode
for IIO stacks in following patches.
Signed-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 7 +--
.../util/scripting-engines/trace-event-python.c | 2 +-
tools/perf/util/stat-display.c
After a "make -C tools/perf", git reports the following untracked file:
perf-iiostat
Add this generated file to perf's .gitignore file.
Signed-off-by: Alexander Antonov
---
tools/perf/.gitignore | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/.gitignore b/tools/perf/
requiries only one IIO event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
#EventCount * 4B / (1024 * 1024)
Signed-off-by: Alexander Antonov
---
tools/perf/Documentation/perf-iiostat.txt | 89 ++
tools/perf/Mak
Introduce helper functions to control IIO stacks list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iiostat.c | 125 +
1 file changed, 125 insertions(+)
create mode 100644 tools/perf/arch/x86/util
Outbound Write(MB)
:17 358559 440
22
:3a320
0
197.081983474 seconds time elapsed
Alexander Antonov (6):
perf stat: Add AGGR
-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 33 -
tools/perf/util/iiostat.h | 33 +
tools/perf/util/stat-display.c | 38 +-
tools/perf/util/stat-shadow.c | 11 +-
tools/perf/util
On 12/15/2020 4:58 PM, Arnaldo Carvalho de Melo wrote:
Em Mon, Dec 14, 2020 at 07:04:30PM -0800, Andi Kleen escreveu:
My first thought was: Why not have a 'perf iiostat' subcommand?
Same would apply to a lot of options in perf stat.
I guess you could add some aliases to "perf" that give
requiries only one IIO event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
#EventCount * 4B / (1024 * 1024)
Signed-off-by: Alexander Antonov
---
tools/perf/Documentation/perf-stat.txt | 31 +++
tools/perf/arch/x86/util/Build
Introduce helper functions to control IIO stacks list.
These helpers will be used in the follow-up patch.
Signed-off-by: Alexander Antonov
---
tools/perf/arch/x86/util/iiostat.c | 125 +
1 file changed, 125 insertions(+)
create mode 100644 tools/perf/arch/x86/util
.
Signed-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 33 -
tools/perf/util/iiostat.h | 33 +
tools/perf/util/stat-display.c | 38 +-
tools/perf/util/stat-shadow.c | 11 +-
tools
Adding evsel::perf_device void pointer.
For performance monitoring purposes, an evsel can have a related device.
These changes allow to attribute, for example, I/O performance metrics
to IIO stack.
Signed-off-by: Alexander Antonov
---
tools/perf/util/evsel.h | 1 +
1 file changed, 1 insertion
Adding AGGR_IIO_STACK mode to be able to distinguish aggr_mode
for IIO stacks in following patches.
Signed-off-by: Alexander Antonov
---
tools/perf/builtin-stat.c | 5 -
.../util/scripting-engines/trace-event-python.c | 2 +-
tools/perf/util/stat-display.c
22
:3a320
0
197.081983474 seconds time elapsed
Alexander Antonov (5):
perf stat: Add AGGR_IIO_STACK mode
perf evsel: Introduce an observed performance device
perf stat: Basic supp
...@linux.intel.com; Meyer, Kyle; Anderson, Russ
Subject: [PATCH] perf/x86/intel/uncore: Fix for iio mapping on Skylake Server
From: Alexander Antonov
Introduced early attributes /sys/devices/uncore_iio_/die* are
initialized by skx_iio_set_mapping(), however, for example, for multiple
segment platforms
The following commit has been merged into the perf/core branch of tip:
Commit-ID: f797f05d917ffef94249ee0aec4c14a5b50517b2
Gitweb:
https://git.kernel.org/tip/f797f05d917ffef94249ee0aec4c14a5b50517b2
Author:Alexander Antonov
AuthorDate:Mon, 28 Sep 2020 13:21:33 +03:00
From: Alexander Antonov
Introduced early attributes /sys/devices/uncore_iio_/die* are
initialized by skx_iio_set_mapping(), however, for example, for multiple
segment platforms skx_iio_get_topology() returns -EPERM before a list of
attributes in skx_iio_mapping_group will have been initialized
architecture.
Usage example:
ls /sys/devices/uncore__/die*
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
Signed-off-by: Roman Sudarikov
Reviewed-by: Kan Liang
Reviewed-by: Alexander Shishkin
---
arch/x86/events/intel/uncore.c | 8
arch/x86/events/intel
From: Roman Sudarikov
The accessor to return number of dies on the platform.
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
Signed-off-by: Roman Sudarikov
Reviewed-by: Kan Liang
Reviewed-by: Alexander Shishkin
---
arch/x86/events/intel/uncore.c | 13
is file which holds "Segment:Root Bus" for PCIe root port,
which can be monitored by that IIO PMON block.
Details are explained in Documentation/ABI/testing/sysfs-devices-mapping
Reported-by: kbuild test robot
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
From: Alexander Antonov
The previous version can be found at:
v9:
https://lkml.kernel.org/r/20200525080554.21313-1-alexander.anto...@linux.intel.com/
Changes in this revision are:
v9 -> v10:
- Addressed comment from CI Test Service:
1. Fixed coding style issues (old style declarat
architecture.
Usage example:
ls /sys/devices/uncore__/die*
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
Signed-off-by: Roman Sudarikov
Reviewed-by: Kan Liang
Reviewed-by: Alexander Shishkin
---
arch/x86/events/intel/uncore.c | 8
arch/x86/events/intel
From: Alexander Antonov
The previous version can be found at:
v8:
https://lkml.kernel.org/r/20200320073110.4761-1-roman.sudari...@linux.intel.com/
Changes in this revision are:
v8 -> v9:
- Addressed comments from Alexander Shishkin:
1. Improved comments and commit messages
2. Replac
is file which holds "Segment:Root Bus" for PCIe root port,
which can be monitored by that IIO PMON block.
Details are explained in Documentation/ABI/testing/sysfs-devices-mapping
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
Signed-off-by: Roman Sudarikov
Review
From: Roman Sudarikov
The accessor to return number of dies on the platform.
Co-developed-by: Alexander Antonov
Signed-off-by: Alexander Antonov
Signed-off-by: Roman Sudarikov
Reviewed-by: Kan Liang
Reviewed-by: Alexander Shishkin
---
arch/x86/events/intel/uncore.c | 13
60 matches
Mail list logo