perf: New start period for the freq mode
RFC PATCH 1/1 perf: New start period for the freq mode
From: Kan Liang <[email protected]>
The freq mode is the current default mode of Linux perf. 1 period is used as a start period. The period is auto-adjusted in each tick or an overflow to meet the frequency target.
The start period 1 is too low and may trigger some issues.
- Many HWs do not support period 1 well.
https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/
- For an event that occurs frequently, period 1 is too far away from the real period. Lots of the samples are generated at the beginning. The distribution of samples may not be even.
It's hard to find a universal start period for all events. The idea is only to give an estimate for the popular HW and HW cache events. For the rest of the events, start from the lowest possible recommended value.
Only the Intel event list JSON file provides the recommended SAV (sample after value) for each event. The estimation is based on the Intel's SAV.
This patch implements a generic perf_freq_start_period() which impacts all ARCHs.
If the other ARCHs don't like the start period, a per-pmu (*freq_start_period) may be introduced instead. Or make it a __weak function.
The other option would be exposing a start_period knob in the sysfs or a per-event config. So the end users can set their preferred start period. Please let me know your thoughts.
SW events may need to be specially handled, which is not implemented in the patch.
--- kernel/events/core.c | 65 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 64 insertions(+), 1 deletion(-)
kernel/events/core.c +64 -1
@@ -12017,6 +12017,69 @@ static void account_event(struct perf_event *event)account_pmu_sb_event (event); } +static u64 perf_freq_start_period (struct perf_event *event) +{ +int type = event->attr.type; +u64 config, factor; + +/* +* The 127 is the lowest possible recommended SAV (sample after value) +* for a 4000 freq (default freq), according to Intel event list JSON +* file, which is the only JSON file that provides a recommended value. +*/ + factor =127 *4000 ; +if (type !=PERF_TYPE_HARDWARE && type !=PERF_TYPE_HW_CACHE ) + goto end; + +/* +* The estimation of the start period in the freq mode is +* based on the below assumption. +* +* For a cycles or an instructions event, 1GHZ of the +* underlying platform, 1 IPC. The workload is idle 50% time. +* The start period = 1,000,000,000 * 1 / freq / 2. +* = 500,000,000 / freq +* +* Usually, the branch-related events occur less than the +* instructions event. According to the Intel event list JSON +* file, the SAV (sample after value) of a branch-related event +* is usually 1/4 of an instruction event. +* The start period of branch-related events = 125,000,000 / freq. +* +* The cache-related events occurs even less. The SAV is usually +* 1/20 of an instruction event. +* The start period of cache-related events = 25,000,000 / freq. +*/ + config = event->attr.config &PERF_HW_EVENT_MASK ; +if (type ==PERF_TYPE_HARDWARE ) { +switch (config) { +case PERF_COUNT_HW_CPU_CYCLES : +case PERF_COUNT_HW_INSTRUCTIONS : +case PERF_COUNT_HW_BUS_CYCLES : +case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND : +case PERF_COUNT_HW_STALLED_CYCLES_BACKEND : +case PERF_COUNT_HW_REF_CPU_CYCLES : + factor =500000000 ; +break ; +case PERF_COUNT_HW_BRANCH_INSTRUCTIONS : +case PERF_COUNT_HW_BRANCH_MISSES : + factor =125000000 ; +break ; +case PERF_COUNT_HW_CACHE_REFERENCES : +case PERF_COUNT_HW_CACHE_MISSES : + factor =25000000 ; +break ; +default : + goto end; + } + } + +if (type ==PERF_TYPE_HW_CACHE ) + factor =25000000 ; +end: +return DIV_ROUND_UP_ULL (factor, event->attr.sample_freq); +} +/* * Allocate and initialize an event structure */
@@ -12140,7 +12203,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, hwc = &event->hw; hwc->sample_period = attr->sample_period;if (attr->freq && attr->sample_freq) - hwc->sample_period =1 ; + hwc->sample_period =perf_freq_start_period (event); hwc->last_period = hwc->sample_period;local64_set (&hwc->period_left, hwc->sample_period);
Signature · 1 line
2.38.1
Namhyung Kim
maintainerHi Kan,
Quoted 30 lines · On Thu, Aug 29, 2024 at 08:20:36AM -0700, [email protected] wrote:
From: Kan Liang <[email protected]>
The freq mode is the current default mode of Linux perf. 1 period is used as a start period. The period is auto-adjusted in each tick or an overflow to meet the frequency target.
The start period 1 is too low and may trigger some issues.
- Many HWs do not support period 1 well.
https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/
- For an event that occurs frequently, period 1 is too far away from the real period. Lots of the samples are generated at the beginning. The distribution of samples may not be even.It's hard to find a universal start period for all events. The idea is only to give an estimate for the popular HW and HW cache events. For the rest of the events, start from the lowest possible recommended value.
Only the Intel event list JSON file provides the recommended SAV (sample after value) for each event. The estimation is based on the Intel's SAV.
This patch implements a generic
perf_freq_start_period()which impacts all ARCHs.
If the other ARCHs don't like the start period, a per-pmu (*freq_start_period) may be introduced instead. Or make it a__weakfunction.
The other option would be exposing astart_periodknob in the sysfs or a per-event config. So the end users can set their preferred start period. Please let me know your thoughts.
Quoted 2 lines
SW events may need to be specially handled, which is not implemented in the patch.
Sounds like a per-pmu callback is fine. PMUs don't have the callback (including SW) can use 1 same as of now.
Thanks,
Namhyung
Quoted 92 lines
Signed-off-by Kan Liang <[email protected]>--- kernel/events/core.c | 65 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 64 insertions(+), 1 deletion(-)kernel/events/core.c +64
-1@@ -12017,6 +12017,69 @@ static void account_event(struct perf_event *event)account_pmu_sb_event (event); } +static u64 perf_freq_start_period (struct perf_event *event) +{ +int type = event->attr.type; +u64 config, factor; + +/* +* The 127 is the lowest possible recommended SAV (sample after value) +* for a 4000 freq (default freq), according to Intel event list JSON +* file, which is the only JSON file that provides a recommended value. +*/ + factor =127 *4000 ; +if (type !=PERF_TYPE_HARDWARE && type !=PERF_TYPE_HW_CACHE ) + goto end; + +/* +* The estimation of the start period in the freq mode is +* based on the below assumption. +* +* For a cycles or an instructions event, 1GHZ of the +* underlying platform, 1 IPC. The workload is idle 50% time. +* The start period = 1,000,000,000 * 1 / freq / 2. +* = 500,000,000 / freq +* +* Usually, the branch-related events occur less than the +* instructions event. According to the Intel event list JSON +* file, the SAV (sample after value) of a branch-related event +* is usually 1/4 of an instruction event. +* The start period of branch-related events = 125,000,000 / freq. +* +* The cache-related events occurs even less. The SAV is usually +* 1/20 of an instruction event. +* The start period of cache-related events = 25,000,000 / freq. +*/ + config = event->attr.config &PERF_HW_EVENT_MASK ; +if (type ==PERF_TYPE_HARDWARE ) { +switch (config) { +case PERF_COUNT_HW_CPU_CYCLES : +case PERF_COUNT_HW_INSTRUCTIONS : +case PERF_COUNT_HW_BUS_CYCLES : +case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND : +case PERF_COUNT_HW_STALLED_CYCLES_BACKEND : +case PERF_COUNT_HW_REF_CPU_CYCLES : + factor =500000000 ; +break ; +case PERF_COUNT_HW_BRANCH_INSTRUCTIONS : +case PERF_COUNT_HW_BRANCH_MISSES : + factor =125000000 ; +break ; +case PERF_COUNT_HW_CACHE_REFERENCES : +case PERF_COUNT_HW_CACHE_MISSES : + factor =25000000 ; +break ; +default : + goto end; + } + } + +if (type ==PERF_TYPE_HW_CACHE ) + factor =25000000 ; +end: +return DIV_ROUND_UP_ULL (factor, event->attr.sample_freq); +} +/* * Allocate and initialize an event structure */ @@ -12140,7 +12203,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, hwc = &event->hw; hwc->sample_period = attr->sample_period;if (attr->freq && attr->sample_freq) - hwc->sample_period =1 ; + hwc->sample_period =perf_freq_start_period (event); hwc->last_period = hwc->sample_period;local64_set (&hwc->period_left, hwc->sample_period);Signature · 1 line
2.38.1
Quoted 33 lines · Namhyung Kim
Hi Kan,
Quoted 30 lines · On Thu, Aug 29, 2024 at 08:20:36AM -0700, [email protected] wrote:
From: Kan Liang <[email protected]>
The freq mode is the current default mode of Linux perf. 1 period is used as a start period. The period is auto-adjusted in each tick or an overflow to meet the frequency target.
The start period 1 is too low and may trigger some issues.
- Many HWs do not support period 1 well.
https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/
- For an event that occurs frequently, period 1 is too far away from the real period. Lots of the samples are generated at the beginning. The distribution of samples may not be even.It's hard to find a universal start period for all events. The idea is only to give an estimate for the popular HW and HW cache events. For the rest of the events, start from the lowest possible recommended value.
Only the Intel event list JSON file provides the recommended SAV (sample after value) for each event. The estimation is based on the Intel's SAV.
This patch implements a generic
perf_freq_start_period()which impacts all ARCHs.
If the other ARCHs don't like the start period, a per-pmu (*freq_start_period) may be introduced instead. Or make it a__weakfunction.
The other option would be exposing astart_periodknob in the sysfs or a per-event config. So the end users can set their preferred start period. Please let me know your thoughts.
Quoted 5 lines
Quoted 2 lines
SW events may need to be specially handled, which is not implemented in the patch.
Sounds like a per-pmu callback is fine. PMUs don't have the callback (including SW) can use 1 same as of now.
I once hope the new start period can benefit more ARCHs. But yes, a per-pmu setting should be more practical.
Thanks,
Kan
Quoted 97 lines
Thanks,
NamhyungQuoted 92 lines
Signed-off-by Kan Liang <[email protected]>--- kernel/events/core.c | 65 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 64 insertions(+), 1 deletion(-)kernel/events/core.c +64
-1@@ -12017,6 +12017,69 @@ static void account_event(struct perf_event *event)account_pmu_sb_event (event); } +static u64 perf_freq_start_period (struct perf_event *event) +{ +int type = event->attr.type; +u64 config, factor; + +/* +* The 127 is the lowest possible recommended SAV (sample after value) +* for a 4000 freq (default freq), according to Intel event list JSON +* file, which is the only JSON file that provides a recommended value. +*/ + factor =127 *4000 ; +if (type !=PERF_TYPE_HARDWARE && type !=PERF_TYPE_HW_CACHE ) + goto end; + +/* +* The estimation of the start period in the freq mode is +* based on the below assumption. +* +* For a cycles or an instructions event, 1GHZ of the +* underlying platform, 1 IPC. The workload is idle 50% time. +* The start period = 1,000,000,000 * 1 / freq / 2. +* = 500,000,000 / freq +* +* Usually, the branch-related events occur less than the +* instructions event. According to the Intel event list JSON +* file, the SAV (sample after value) of a branch-related event +* is usually 1/4 of an instruction event. +* The start period of branch-related events = 125,000,000 / freq. +* +* The cache-related events occurs even less. The SAV is usually +* 1/20 of an instruction event. +* The start period of cache-related events = 25,000,000 / freq. +*/ + config = event->attr.config &PERF_HW_EVENT_MASK ; +if (type ==PERF_TYPE_HARDWARE ) { +switch (config) { +case PERF_COUNT_HW_CPU_CYCLES : +case PERF_COUNT_HW_INSTRUCTIONS : +case PERF_COUNT_HW_BUS_CYCLES : +case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND : +case PERF_COUNT_HW_STALLED_CYCLES_BACKEND : +case PERF_COUNT_HW_REF_CPU_CYCLES : + factor =500000000 ; +break ; +case PERF_COUNT_HW_BRANCH_INSTRUCTIONS : +case PERF_COUNT_HW_BRANCH_MISSES : + factor =125000000 ; +break ; +case PERF_COUNT_HW_CACHE_REFERENCES : +case PERF_COUNT_HW_CACHE_MISSES : + factor =25000000 ; +break ; +default : + goto end; + } + } + +if (type ==PERF_TYPE_HW_CACHE ) + factor =25000000 ; +end: +return DIV_ROUND_UP_ULL (factor, event->attr.sample_freq); +} +/* * Allocate and initialize an event structure */ @@ -12140,7 +12203,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, hwc = &event->hw; hwc->sample_period = attr->sample_period;if (attr->freq && attr->sample_freq) - hwc->sample_period =1 ; + hwc->sample_period =perf_freq_start_period (event); hwc->last_period = hwc->sample_period;local64_set (&hwc->period_left, hwc->sample_period);Signature · 1 line
2.38.1
Peter Zijlstra
maintainerQuoted 12 lines · Namhyung Kim
Hi Kan,
Quoted 9 lines · On Thu, Aug 29, 2024 at 08:20:36AM -0700, [email protected] wrote:
From: Kan Liang <[email protected]>
The freq mode is the current default mode of Linux perf. 1 period is used as a start period. The period is auto-adjusted in each tick or an overflow to meet the frequency target.
The start period 1 is too low and may trigger some issues.
- Many HWs do not support period 1 well.
https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/
So we already have x86_pmu::limit_period and pmu::check_period to deal with this. Don't they already capture the 1 and increase it where appropriate?
Quoted 3 lines
Quoted 3 lines
- For an event that occurs frequently, period 1 is too far away from the real period. Lots of the samples are generated at the beginning. The distribution of samples may not be even.
Which is why samples include a WEIGHT option IIRC.
Quoted 2 lines
Sounds like a per-pmu callback is fine. PMUs don't have the callback (including SW) can use 1 same as of now.
This, but also, be very careful to not over-estimate, because ramping up is fast, but having to adjust down can take a while.
Quoted 10 lines · Peter Zijlstra
Quoted 9 lines · Namhyung Kim
Hi Kan,
Quoted 6 lines · On Thu, Aug 29, 2024 at 08:20:36AM -0700, [email protected] wrote:
From: Kan Liang <[email protected]>
The freq mode is the current default mode of Linux perf. 1 period is used as a start period. The period is auto-adjusted in each tick or an overflow to meet the frequency target.
Quoted 7 lines
Quoted 3 lines
Quoted 3 lines
The start period 1 is too low and may trigger some issues.
- Many HWs do not support period 1 well.
https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/So we already have
x86_pmu::limit_periodandpmu::check_periodto deal with this. Don't they already capture the 1 and increase it where appropriate?
The limit_period only checks the minimum acceptable value for HW. If the value is lower than that, I think HW errors may be triggered. It's a mandatory request.
However, it doesn't make it a perfect start value, which perf uses in the default freq mode.
As you can see in Thomas's experiment, it doesn't trigger HW issue to set the start period to 1. But the message "perf: interrupt took too long (2503 > 2500), lowering ..." is printed. That should be a false alarm. To avoid it, 32 is finally used for the limit_period.
https://lore.kernel.org/lkml/87plq9l5d2.ffs@tglx/
We cannot always use this way to address the above issue.
- It's impossible to test all the platforms to find a perfect "32" for each platform.
- Some events may need a very low period. We cannot set the limit_period too high.
Furthermore, a low start period for the frequently occurring event challenges both HW and virtualization, which has a longer path to handle a PMI.
I think we need a better start period for the default freq mode.
Yes, there is already a pmu::check_period which is period related. I will check if it can be modified to feedback a start value somehow.
Quoted 7 lines
Quoted 4 lines
Quoted 4 lines
- For an event that occurs frequently, period 1 is too far away from the real period. Lots of the samples are generated at the beginning. The distribution of samples may not be even.
Which is why samples include a WEIGHT option IIRC.
The WEIGHT gives all kinds of latency to understand it. But it doesn't help changing the distribution.
Quoted 5 lines
Quoted 2 lines
Sounds like a per-pmu callback is fine. PMUs don't have the callback (including SW) can use 1 same as of now.
This, but also, be very careful to not over-estimate, because ramping up is fast, but having to adjust down can take a while.
Sure.
Thanks,
Kan