* RE: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
@ 2022-03-15 12:10 Cristian Marussi
2022-04-08 17:30 ` James Morse
0 siblings, 1 reply; 10+ messages in thread
From: Cristian Marussi @ 2022-03-15 12:10 UTC (permalink / raw)
To: 'James Morse', x86, linux-kernel
Cc: Fenghua Yu, Reinette Chatre, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang, cristian.marussi
[-- Attachment #1: Type: text/plain, Size: 3022 bytes --]
Hi James,
I tested this on an Intel(R) Xeon(R) Gold 5120T trying to compare gathered
resctrl monitor data with and without your series and see if results
were consistent.
I started from this paper [0] from Intel itself for my basic setup with
some minor variations: basically, using the attached test_monitors.sh
my test setup is as follows:
- a cpuset shield is created upfront isolating all the cpus belonging
to node1 (14-27,42-55)
- 2 resctrl CoS are created:
+ 1 process (tar on a big file) act as a LC LatencyCritical actor
and is run on one of the shielded CPUs with taskset (48)
+ other 3 processes instead runs stress-ng, supposedly acting as
BE BestEffort noisy neighbours and are pinned to other 3 distinct
cpus (49,50,51)
The script then triggers 4 different runs of the above crowd with different
cache allocation masks setup in lc/be CoS schemata for node1: ranging
basically from no dedicated allocation (7ff 7ff) to a cache allocation
highly unbalanced in favour of the LC task (7fe 001).
While doing that I collect in background (and out of node1 processors) all
the mon_data from the lc_cos group every 100ms and dump those in a file one
for each cache allocation mask. (mondata_LC_7f0_00f.txt etc)
I tested first against a v5.17-rc1 mainline without your series (named as
5.17.0-rc1-mainline in the results) and then again with your series on top
(named as 5.17.0-rc1-00021-g21c69a5706a5). Got your series from [1].
Then I used gnuplot to see what was the 'profile' of this data with and
without your series by plotting the LC process llc_occupancy data against
time for each one of the runs with the differerent cache allocated.
(each colored graphs represent a different run with a different
cache allocation as reported)
Note that during each run:
- at first the LC process is run without any noisy BEs
- then BEs neighbours are spawned and let to settle for 5s
- finally LC is run again while BEs are making a mess in bg
As a consequence in the plotted graphs, you can see a clear break between
the first part of the run and the last one with BEs.
Looking at the graphs it seems to me that the resctrl counters with and
without you series report a highly similar data profile, as expected
(and hoped :D).
I attach as references:
- a tarball of the raw data (test_mon_data.gz)
- the test_monitors.sh script (not nice but working)
- draw_resctrl.gp gnuplot script
- two PNG of the LC llc_occupancy graphs (all cachemasks runs)
- with your series: LC_llc_occupancy_5.17.0-rc1-00021-g21c69a5706a5.png
- without your series: LC_llc_occupancy_5.17.0-rc1-mainline.png
Gnuplot is run as:
gnuplot -e "filedir='results/5.17.0-rc1-00021-g21c69a5706a5" draw_resctrl.gp
Hope this helps...
Thanks,
Cristian
[0] https://www.intel.com/content/www/us/en/developer/articles/technical/use-intel-resource-director-technology-to-allocate-last-level-cache-llc.html
[1] git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git mpam/resctrl_monitors_in_bytes/v3
[-- Attachment #2: draw_resctrl.gp --]
[-- Type: text/plain, Size: 445 bytes --]
#!/usr/bin/gnuplot --persist
set title filedir
set xlabel "Time (s)"
set ylabel "LLC Occupancy"
cd filedir
plot './mondata_LC_7ff_7ff.txt' using 1:2 t "(LC)7ff <--> 7ff(BE)" with linespoint,\
'./mondata_LC_700_0ff.txt' using 1:2 t "(LC)700 <--> 0ff(BE)" with linespoint,\
'./mondata_LC_7f0_00f.txt' using 1:2 t "(LC)7f0 <--> 00f(BE)" with linespoint,\
'./mondata_LC_7fe_001.txt' using 1:2 t "(LC)7fe <--> 001(BE)" with linespoint
pause -1
[-- Attachment #3: test_mon_data.gz --]
[-- Type: application/gzip, Size: 38676 bytes --]
[-- Attachment #4: test_monitors.sh --]
[-- Type: application/x-sh, Size: 3171 bytes --]
[-- Attachment #5: LC_llc_occupancy_5.17.0-rc1-mainline.png --]
[-- Type: image/png, Size: 131515 bytes --]
[-- Attachment #6: LC_llc_occupancy_5.17.0-rc1-00021-g21c69a5706a5.png --]
[-- Type: image/png, Size: 134354 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-03-15 12:10 [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes Cristian Marussi
@ 2022-04-08 17:30 ` James Morse
2022-04-11 9:45 ` Cristian Marussi
0 siblings, 1 reply; 10+ messages in thread
From: James Morse @ 2022-04-08 17:30 UTC (permalink / raw)
To: 20220217182110.7176-1-james.morse, x86, linux-kernel
Cc: Fenghua Yu, Reinette Chatre, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang, cristian.marussi
Hi Cristian,
On 15/03/2022 12:10, Cristian Marussi wrote:
> I tested this on an Intel(R) Xeon(R) Gold 5120T trying to compare gathered
> resctrl monitor data with and without your series and see if results
> were consistent.
>
> I started from this paper [0] from Intel itself for my basic setup with
> some minor variations:
[..]
> While doing that I collect in background (and out of node1 processors) all
> the mon_data from the lc_cos group every 100ms and dump those in a file one
> for each cache allocation mask. (mondata_LC_7f0_00f.txt etc)
>
> I tested first against a v5.17-rc1 mainline without your series (named as
> 5.17.0-rc1-mainline in the results) and then again with your series on top
> (named as 5.17.0-rc1-00021-g21c69a5706a5). Got your series from [1].
>
> Then I used gnuplot to see what was the 'profile' of this data with and
> without your series by plotting the LC process llc_occupancy data against
> time for each one of the runs with the differerent cache allocated.
> (each colored graphs represent a different run with a different
> cache allocation as reported)
> Hope this helps...
This is great, thanks!
Can I take this as a Tested-by?
Thanks,
James
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-04-08 17:30 ` James Morse
@ 2022-04-11 9:45 ` Cristian Marussi
0 siblings, 0 replies; 10+ messages in thread
From: Cristian Marussi @ 2022-04-11 9:45 UTC (permalink / raw)
To: James Morse
Cc: 20220217182110.7176-1-james.morse, x86, linux-kernel, Fenghua Yu,
Reinette Chatre, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
H Peter Anvin, Babu Moger, shameerali.kolothum.thodi, Jamie Iles,
D Scott Phillips OS, lcherian, bobo.shaobowang
On Fri, Apr 08, 2022 at 06:30:40PM +0100, James Morse wrote:
> Hi Cristian,
>
> On 15/03/2022 12:10, Cristian Marussi wrote:
> > I tested this on an Intel(R) Xeon(R) Gold 5120T trying to compare gathered
> > resctrl monitor data with and without your series and see if results
> > were consistent.
> >
> > I started from this paper [0] from Intel itself for my basic setup with
> > some minor variations:
>
> [..]
>
> > While doing that I collect in background (and out of node1 processors) all
> > the mon_data from the lc_cos group every 100ms and dump those in a file one
> > for each cache allocation mask. (mondata_LC_7f0_00f.txt etc)
> >
> > I tested first against a v5.17-rc1 mainline without your series (named as
> > 5.17.0-rc1-mainline in the results) and then again with your series on top
> > (named as 5.17.0-rc1-00021-g21c69a5706a5). Got your series from [1].
> >
> > Then I used gnuplot to see what was the 'profile' of this data with and
> > without your series by plotting the LC process llc_occupancy data against
> > time for each one of the runs with the differerent cache allocated.
> > (each colored graphs represent a different run with a different
> > cache allocation as reported)
>
> > Hope this helps...
>
Hi James,
> This is great, thanks!
>
> Can I take this as a Tested-by?
>
Sure, sorry to have forgot that :D
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Thanks,
Cristian
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
@ 2022-02-17 18:20 James Morse
2022-03-07 12:56 ` Jamie Iles
` (2 more replies)
0 siblings, 3 replies; 10+ messages in thread
From: James Morse @ 2022-02-17 18:20 UTC (permalink / raw)
To: x86, linux-kernel
Cc: Fenghua Yu, Reinette Chatre, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, H Peter Anvin, Babu Moger, James Morse,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang, tan.shaopeng
Changes in this version? Expanded the commit message of patch 12, and
made a few things static, as reported by the kbuild robot.
---
The aim of this series is to insert a split between the parts of the monitor
code that the architecture must implement, and those that are part of the
resctrl filesystem. The eventual aim is to move all filesystem parts out
to live in /fs/resctrl, so that resctrl can be wired up for MPAM.
What's MPAM? See the cover letter of a previous series. [1]
The series adds domain online/offline callbacks to allow the filesystem to
manage some of its structures itself, then moves all the 'mba_sc' behaviour
to be part of the filesystem.
This means another architecture doesn't need to provide an mbps_val array.
As its all software, the resctrl filesystem should be able to do this without
any help from the architecture code.
Finally __rmid_read() is refactored to be the API call that the architecture
provides to read a counter value. All the hardware specific overflow detection,
scaling and value correction should occur behind this helper.
This series is based on v5.17-rc1, and can be retrieved from:
git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git mpam/resctrl_monitors_in_bytes/v3
[0] git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git mpam/resctrl_merge_cdp/v7
[1] https://lore.kernel.org/lkml/20210728170637.25610-1-james.morse@arm.com/
[v1] https://lore.kernel.org/lkml/20210729223610.29373-1-james.morse@arm.com/
[v2] https://lore.kernel.org/lkml/20211001160302.31189-1-james.morse@arm.com/
Thanks,
James Morse (21):
x86/resctrl: Kill off alloc_enabled
x86/resctrl: Merge mon_capable and mon_enabled
x86/resctrl: Add domain online callback for resctrl work
x86/resctrl: Group struct rdt_hw_domain cleanup
x86/resctrl: Add domain offline callback for resctrl work
x86/resctrl: Remove set_mba_sc()s control array re-initialisation
x86/resctrl: Create mba_sc configuration in the rdt_domain
x86/resctrl: Switch over to the resctrl mbps_val list
x86/resctrl: Remove architecture copy of mbps_val
x86/resctrl: Abstract and use supports_mba_mbps()
x86/resctrl: Allow update_mba_bw() to update controls directly
x86/resctrl: Calculate bandwidth from the previous __mon_event_count()
chunks
x86/recstrl: Add per-rmid arch private storage for overflow and chunks
x86/recstrl: Allow per-rmid arch private storage to be reset
x86/resctrl: Abstract __rmid_read()
x86/resctrl: Pass the required parameters into
resctrl_arch_rmid_read()
x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()
x86/resctrl: Move get_corrected_mbm_count() into
resctrl_arch_rmid_read()
x86/resctrl: Rename and change the units of resctrl_cqm_threshold
x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's
boot_cpu_data
x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
arch/x86/kernel/cpu/resctrl/core.c | 117 ++++--------
arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 75 +++++---
arch/x86/kernel/cpu/resctrl/internal.h | 61 +++----
arch/x86/kernel/cpu/resctrl/monitor.c | 211 ++++++++++++++--------
arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +-
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 205 +++++++++++++++++----
include/linux/resctrl.h | 62 ++++++-
7 files changed, 478 insertions(+), 255 deletions(-)
--
2.30.2
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-02-17 18:20 James Morse
@ 2022-03-07 12:56 ` Jamie Iles
2022-04-04 16:36 ` James Morse
2022-03-15 6:41 ` Xin Hao
2022-03-15 8:16 ` tan.shaopeng
2 siblings, 1 reply; 10+ messages in thread
From: Jamie Iles @ 2022-03-07 12:56 UTC (permalink / raw)
To: James Morse
Cc: x86, linux-kernel, Fenghua Yu, Reinette Chatre, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang, tan.shaopeng
On Thu, Feb 17, 2022 at 06:20:49PM +0000, James Morse wrote:
> Changes in this version? Expanded the commit message of patch 12, and
> made a few things static, as reported by the kbuild robot.
>
> ---
> The aim of this series is to insert a split between the parts of the monitor
> code that the architecture must implement, and those that are part of the
> resctrl filesystem. The eventual aim is to move all filesystem parts out
> to live in /fs/resctrl, so that resctrl can be wired up for MPAM.
>
> What's MPAM? See the cover letter of a previous series. [1]
>
> The series adds domain online/offline callbacks to allow the filesystem to
> manage some of its structures itself, then moves all the 'mba_sc' behaviour
> to be part of the filesystem.
> This means another architecture doesn't need to provide an mbps_val array.
> As its all software, the resctrl filesystem should be able to do this without
> any help from the architecture code.
>
> Finally __rmid_read() is refactored to be the API call that the architecture
> provides to read a counter value. All the hardware specific overflow detection,
> scaling and value correction should occur behind this helper.
>
>
> This series is based on v5.17-rc1, and can be retrieved from:
> git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git mpam/resctrl_monitors_in_bytes/v3
>
> [0] git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git mpam/resctrl_merge_cdp/v7
> [1] https://lore.kernel.org/lkml/20210728170637.25610-1-james.morse@arm.com/
>
> [v1] https://lore.kernel.org/lkml/20210729223610.29373-1-james.morse@arm.com/
> [v2] https://lore.kernel.org/lkml/20211001160302.31189-1-james.morse@arm.com/
>
> Thanks,
>
> James Morse (21):
> x86/resctrl: Kill off alloc_enabled
> x86/resctrl: Merge mon_capable and mon_enabled
> x86/resctrl: Add domain online callback for resctrl work
> x86/resctrl: Group struct rdt_hw_domain cleanup
> x86/resctrl: Add domain offline callback for resctrl work
> x86/resctrl: Remove set_mba_sc()s control array re-initialisation
> x86/resctrl: Create mba_sc configuration in the rdt_domain
> x86/resctrl: Switch over to the resctrl mbps_val list
> x86/resctrl: Remove architecture copy of mbps_val
> x86/resctrl: Abstract and use supports_mba_mbps()
> x86/resctrl: Allow update_mba_bw() to update controls directly
> x86/resctrl: Calculate bandwidth from the previous __mon_event_count()
> chunks
> x86/recstrl: Add per-rmid arch private storage for overflow and chunks
> x86/recstrl: Allow per-rmid arch private storage to be reset
> x86/resctrl: Abstract __rmid_read()
> x86/resctrl: Pass the required parameters into
> resctrl_arch_rmid_read()
> x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()
> x86/resctrl: Move get_corrected_mbm_count() into
> resctrl_arch_rmid_read()
> x86/resctrl: Rename and change the units of resctrl_cqm_threshold
> x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's
> boot_cpu_data
> x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
>
> arch/x86/kernel/cpu/resctrl/core.c | 117 ++++--------
> arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 75 +++++---
> arch/x86/kernel/cpu/resctrl/internal.h | 61 +++----
> arch/x86/kernel/cpu/resctrl/monitor.c | 211 ++++++++++++++--------
> arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +-
> arch/x86/kernel/cpu/resctrl/rdtgroup.c | 205 +++++++++++++++++----
> include/linux/resctrl.h | 62 ++++++-
> 7 files changed, 478 insertions(+), 255 deletions(-)
Reviewed-by: Jamie Iles <quic_jiles@quicinc.com>
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-03-07 12:56 ` Jamie Iles
@ 2022-04-04 16:36 ` James Morse
0 siblings, 0 replies; 10+ messages in thread
From: James Morse @ 2022-04-04 16:36 UTC (permalink / raw)
To: Jamie Iles
Cc: x86, linux-kernel, Fenghua Yu, Reinette Chatre, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang, tan.shaopeng
Hi Jamie,
On 3/7/22 12:56, Jamie Iles wrote:
> On Thu, Feb 17, 2022 at 06:20:49PM +0000, James Morse wrote:
>> Changes in this version? Expanded the commit message of patch 12, and
>> made a few things static, as reported by the kbuild robot.
[...]
> Reviewed-by: Jamie Iles <quic_jiles@quicinc.com>
Thanks!
James
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-02-17 18:20 James Morse
2022-03-07 12:56 ` Jamie Iles
@ 2022-03-15 6:41 ` Xin Hao
2022-04-04 16:36 ` James Morse
2022-03-15 8:16 ` tan.shaopeng
2 siblings, 1 reply; 10+ messages in thread
From: Xin Hao @ 2022-03-15 6:41 UTC (permalink / raw)
To: james.morse
Cc: Babu.Moger, bobo.shaobowang, bp, fenghua.yu, hpa, jamie,
lcherian, linux-kernel, mingo, reinette.chatre, scott,
shameerali.kolothum.thodi, tan.shaopeng, tglx, x86, Baolin Wang,
Erik Yuan
Hi james,
I have done some verification on x86 machine(Intel(R) Xeon(R) Platinum
8269CY), and "CAT, CMT, MBA, MBM" have been tested,
They all work well.
So please add Tested-by: Xin Hao <xhao@linux.alibaba.com>
--
Best Regards!
Xin Hao
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-03-15 6:41 ` Xin Hao
@ 2022-04-04 16:36 ` James Morse
0 siblings, 0 replies; 10+ messages in thread
From: James Morse @ 2022-04-04 16:36 UTC (permalink / raw)
To: xhao
Cc: Babu.Moger, bobo.shaobowang, bp, fenghua.yu, hpa, jamie,
lcherian, linux-kernel, mingo, reinette.chatre, scott,
shameerali.kolothum.thodi, tan.shaopeng, tglx, x86, Baolin Wang,
Erik Yuan
Hello!
On 3/15/22 06:41, Xin Hao wrote:
> I have done some verification on x86 machine(Intel(R) Xeon(R) Platinum 8269CY), and "CAT, CMT, MBA, MBM" have been tested,
>
> They all work well.
>
> So please add Tested-by: Xin Hao <xhao@linux.alibaba.com>
Great, thanks!
James
^ permalink raw reply [flat|nested] 10+ messages in thread
* RE: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-02-17 18:20 James Morse
2022-03-07 12:56 ` Jamie Iles
2022-03-15 6:41 ` Xin Hao
@ 2022-03-15 8:16 ` tan.shaopeng
2022-04-04 16:35 ` James Morse
2 siblings, 1 reply; 10+ messages in thread
From: tan.shaopeng @ 2022-03-15 8:16 UTC (permalink / raw)
To: 'James Morse', x86, linux-kernel
Cc: Fenghua Yu, Reinette Chatre, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang
Hi James,
> Changes in this version? Expanded the commit message of patch 12, and made
> a few things static, as reported by the kbuild robot.
>
> ---
> The aim of this series is to insert a split between the parts of the monitor code
> that the architecture must implement, and those that are part of the resctrl
> filesystem. The eventual aim is to move all filesystem parts out to live in
> /fs/resctrl, so that resctrl can be wired up for MPAM.
>
> What's MPAM? See the cover letter of a previous series. [1]
>
> The series adds domain online/offline callbacks to allow the filesystem to
> manage some of its structures itself, then moves all the 'mba_sc' behaviour to
> be part of the filesystem.
> This means another architecture doesn't need to provide an mbps_val array.
> As its all software, the resctrl filesystem should be able to do this without any
> help from the architecture code.
>
> Finally __rmid_read() is refactored to be the API call that the architecture
> provides to read a counter value. All the hardware specific overflow detection,
> scaling and value correction should occur behind this helper.
>
>
> This series is based on v5.17-rc1, and can be retrieved from:
> git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git
> mpam/resctrl_monitors_in_bytes/v3
>
> [0] git://git.kernel.org/pub/scm/linux/kernel/git/morse/linux.git
> mpam/resctrl_merge_cdp/v7 [1]
> https://lore.kernel.org/lkml/20210728170637.25610-1-james.morse@arm.com
> /
>
> [v1]
> https://lore.kernel.org/lkml/20210729223610.29373-1-james.morse@arm.com
> /
> [v2]
> https://lore.kernel.org/lkml/20211001160302.31189-1-james.morse@arm.com
> /
>
> Thanks,
>
> James Morse (21):
> x86/resctrl: Kill off alloc_enabled
> x86/resctrl: Merge mon_capable and mon_enabled
> x86/resctrl: Add domain online callback for resctrl work
> x86/resctrl: Group struct rdt_hw_domain cleanup
> x86/resctrl: Add domain offline callback for resctrl work
> x86/resctrl: Remove set_mba_sc()s control array re-initialisation
> x86/resctrl: Create mba_sc configuration in the rdt_domain
> x86/resctrl: Switch over to the resctrl mbps_val list
> x86/resctrl: Remove architecture copy of mbps_val
> x86/resctrl: Abstract and use supports_mba_mbps()
> x86/resctrl: Allow update_mba_bw() to update controls directly
> x86/resctrl: Calculate bandwidth from the previous __mon_event_count()
> chunks
> x86/recstrl: Add per-rmid arch private storage for overflow and chunks
> x86/recstrl: Allow per-rmid arch private storage to be reset
> x86/resctrl: Abstract __rmid_read()
> x86/resctrl: Pass the required parameters into
> resctrl_arch_rmid_read()
> x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()
> x86/resctrl: Move get_corrected_mbm_count() into
> resctrl_arch_rmid_read()
> x86/resctrl: Rename and change the units of resctrl_cqm_threshold
> x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's
> boot_cpu_data
> x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
>
> arch/x86/kernel/cpu/resctrl/core.c | 117 ++++--------
> arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 75 +++++---
> arch/x86/kernel/cpu/resctrl/internal.h | 61 +++----
> arch/x86/kernel/cpu/resctrl/monitor.c | 211
> ++++++++++++++--------
> arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +-
> arch/x86/kernel/cpu/resctrl/rdtgroup.c | 205
> +++++++++++++++++----
> include/linux/resctrl.h | 62 ++++++-
> 7 files changed, 478 insertions(+), 255 deletions(-)
>
> --
> 2.30.2
I tested this patch series on Intel(R) Xeon(R) Gold 6254 CPU with resctrl selftest.
It is no problem.
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
2022-03-15 8:16 ` tan.shaopeng
@ 2022-04-04 16:35 ` James Morse
0 siblings, 0 replies; 10+ messages in thread
From: James Morse @ 2022-04-04 16:35 UTC (permalink / raw)
To: tan.shaopeng, x86, linux-kernel
Cc: Fenghua Yu, Reinette Chatre, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, H Peter Anvin, Babu Moger,
shameerali.kolothum.thodi, Jamie Iles, D Scott Phillips OS,
lcherian, bobo.shaobowang
Hello!
On 3/15/22 08:16, tan.shaopeng@fujitsu.com wrote:
>> Changes in this version? Expanded the commit message of patch 12, and made
>> a few things static, as reported by the kbuild robot.
[...]
> I tested this patch series on Intel(R) Xeon(R) Gold 6254 CPU with resctrl selftest.
> It is no problem.
>
> Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
> Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Thanks!
James
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2022-04-11 9:46 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-03-15 12:10 [PATCH v3 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes Cristian Marussi
2022-04-08 17:30 ` James Morse
2022-04-11 9:45 ` Cristian Marussi
-- strict thread matches above, loose matches on Subject: below --
2022-02-17 18:20 James Morse
2022-03-07 12:56 ` Jamie Iles
2022-04-04 16:36 ` James Morse
2022-03-15 6:41 ` Xin Hao
2022-04-04 16:36 ` James Morse
2022-03-15 8:16 ` tan.shaopeng
2022-04-04 16:35 ` James Morse
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).