Messages in this thread | | | Date | Wed, 28 Sep 2022 11:05:43 -0400 | From | "Liang, Kan" <> | Subject | Re: [PATCH v1 00/22] Improvements to Intel perf metrics |
| |
On 2022-09-28 10:04 a.m., Ian Rogers wrote: > On Wed, Sep 28, 2022 at 5:56 AM Liang, Kan <kan.liang@linux.intel.com> wrote: >> >> >> >> On 2022-09-28 3:21 a.m., Ian Rogers wrote: >>> For consistency with: >>> https://github.com/intel/perfmon-metrics >>> rename of topdown TMA metrics from Frontend_Bound to tma_frontend_bound. >>> >> >> If so, all the scripts with the old name must be broken on the existing >> platforms. Can we keep both old name and new name for the existing >> platforms? >> >> For the event naming, if we want to rename an event. We still keep the >> old name and mark it as deprecated in the existing platforms to maintain >> compatibility. >> >> Can we do the similar thing for metrics? >> For the existing platforms, just add all the metrics from the >> perfmon-metrics and don't change the existing metrics unless they have >> errors. >> >> Thanks, >> Kan > > Thanks Kan, > > Do we have examples of scripts that will be impacted by this? My > thoughts are that such scripts are likely using TopdownL1 as a metric > group, the metrics within that group vary and names may change over > time. For example, on hybrid there is Backend_Bound_Aux. Given the > existing state, such compatibility is only required for level 1 > metrics on CNL CPX CLX KBLR/CFL/CML SKX SKL/KBL BDX BDW HSX HSW IVT > IVB JKT/SNB-EP SNB. Injecting either a metric group or an aliasing > metric is messy and when can we stop carrying the patch? There hasn't > been discussion of doing this in the context of: > https://github.com/intel/perfmon-metrics > I'd suggest that this is a good time for script writers to change how > they use particular metrics and derive the information instead from > groups like TopdownL1.
So the rename only impacts the Topdown metrics, right? We still keep the old group name, TopdownL1.
If so, I agree. It only makes sense when collect in a Top-down group, not specific metrics.
Thanks, Kan
> This will also make them robust to changes in > the TMA metrics CSV files, another win. > > Thanks, > Ian > > >>> Remove _SMT suffix metrics are dropped as the #SMT_On and #EBS_Mode >>> are correctly expanded in the single main metric. Fix perf expr to >>> allow a double if to be correctly processed. >>> >>> Add all 6 levels of TMA metrics. Child metrics are placed in a group >>> named after their parent allowing children of a metric to be >>> easily measured using the metric name with a _group suffix. >>> >>> Don't drop TMA metrics if they contain topdown events. >>> >>> The ## and ##? operators are correctly expanded. >>> >>> The locate-with column is added to the long description describing a >>> sampling event. >>> >>> Metrics are written in terms of other metrics to reduce the expression >>> size and increase readability. >>> >>> Following this the pmu-events/arch/x86 directories match those created >>> by the script at: >>> https://github.com/intel/event-converter-for-linux-perf/blob/master/download_and_gen.py >>> with updates at: >>> https://github.com/captain5050/event-converter-for-linux-perf >>> >>> Ian Rogers (22): >>> perf expr: Allow a double if expression >>> perf expr: Remove jevents case workaround >>> perf metrics: Don't scale counts going into metrics >>> perf vendor events: Update Intel skylakex >>> perf vendor events: Update Intel alderlake >>> perf vendor events: Update Intel broadwell >>> perf vendor events: Update Intel broadwellx >>> perf vendor events: Update Intel cascadelakex >>> perf vendor events: Update elkhartlake cpuids >>> perf vendor events: Update Intel haswell >>> perf vendor events: Update Intel haswellx >>> perf vendor events: Update Intel icelake >>> perf vendor events: Update Intel icelakex >>> perf vendor events: Update Intel ivybridge >>> perf vendor events: Update Intel ivytown >>> perf vendor events: Update Intel jaketown >>> perf vendor events: Update Intel sandybridge >>> perf vendor events: Update Intel sapphirerapids >>> perf vendor events: Update silvermont cpuids >>> perf vendor events: Update Intel skylake >>> perf vendor events: Update Intel tigerlake >>> perf vendor events: Update Intel broadwellde >>> >>> .../arch/x86/alderlake/adl-metrics.json | 1215 ++++++++++++++++- >>> .../pmu-events/arch/x86/alderlake/cache.json | 129 +- >>> .../arch/x86/alderlake/frontend.json | 12 + >>> .../pmu-events/arch/x86/alderlake/memory.json | 22 + >>> .../pmu-events/arch/x86/alderlake/other.json | 22 + >>> .../arch/x86/alderlake/pipeline.json | 14 +- >>> .../arch/x86/broadwell/bdw-metrics.json | 603 ++++++-- >>> .../arch/x86/broadwellde/bdwde-metrics.json | 639 +++++++-- >>> .../arch/x86/broadwellx/bdx-metrics.json | 644 +++++++-- >>> .../arch/x86/broadwellx/uncore-cache.json | 10 +- >>> .../x86/broadwellx/uncore-interconnect.json | 18 +- >>> .../arch/x86/broadwellx/uncore-memory.json | 18 +- >>> .../arch/x86/cascadelakex/clx-metrics.json | 893 ++++++++---- >>> .../arch/x86/cascadelakex/uncore-memory.json | 18 +- >>> .../arch/x86/cascadelakex/uncore-other.json | 10 +- >>> .../pmu-events/arch/x86/haswell/cache.json | 4 +- >>> .../pmu-events/arch/x86/haswell/frontend.json | 12 +- >>> .../arch/x86/haswell/hsw-metrics.json | 502 +++++-- >>> .../pmu-events/arch/x86/haswellx/cache.json | 2 +- >>> .../arch/x86/haswellx/frontend.json | 12 +- >>> .../arch/x86/haswellx/hsx-metrics.json | 707 +++++++--- >>> .../x86/haswellx/uncore-interconnect.json | 18 +- >>> .../arch/x86/haswellx/uncore-memory.json | 18 +- >>> .../pmu-events/arch/x86/icelake/cache.json | 6 +- >>> .../arch/x86/icelake/icl-metrics.json | 725 +++++++++- >>> .../pmu-events/arch/x86/icelake/pipeline.json | 2 +- >>> .../pmu-events/arch/x86/icelakex/cache.json | 6 +- >>> .../arch/x86/icelakex/icx-metrics.json | 794 ++++++++++- >>> .../arch/x86/icelakex/pipeline.json | 2 +- >>> .../arch/x86/icelakex/uncore-other.json | 2 +- >>> .../arch/x86/ivybridge/ivb-metrics.json | 525 +++++-- >>> .../pmu-events/arch/x86/ivytown/cache.json | 4 +- >>> .../arch/x86/ivytown/floating-point.json | 2 +- >>> .../pmu-events/arch/x86/ivytown/frontend.json | 18 +- >>> .../arch/x86/ivytown/ivt-metrics.json | 558 ++++++-- >>> .../arch/x86/ivytown/uncore-cache.json | 58 +- >>> .../arch/x86/ivytown/uncore-interconnect.json | 84 +- >>> .../arch/x86/ivytown/uncore-memory.json | 2 +- >>> .../arch/x86/ivytown/uncore-other.json | 6 +- >>> .../arch/x86/ivytown/uncore-power.json | 8 +- >>> .../arch/x86/jaketown/jkt-metrics.json | 291 ++-- >>> tools/perf/pmu-events/arch/x86/mapfile.csv | 18 +- >>> .../arch/x86/sandybridge/snb-metrics.json | 279 +++- >>> .../arch/x86/sapphirerapids/cache.json | 4 +- >>> .../arch/x86/sapphirerapids/frontend.json | 11 + >>> .../arch/x86/sapphirerapids/pipeline.json | 4 +- >>> .../arch/x86/sapphirerapids/spr-metrics.json | 858 +++++++++++- >>> .../arch/x86/skylake/skl-metrics.json | 774 ++++++++--- >>> .../arch/x86/skylakex/skx-metrics.json | 859 +++++++++--- >>> .../arch/x86/skylakex/uncore-memory.json | 18 +- >>> .../arch/x86/skylakex/uncore-other.json | 19 +- >>> .../arch/x86/tigerlake/tgl-metrics.json | 727 +++++++++- >>> tools/perf/tests/expr.c | 4 + >>> tools/perf/util/expr.c | 11 +- >>> tools/perf/util/expr.y | 2 +- >>> tools/perf/util/stat-shadow.c | 9 +- >>> 56 files changed, 10103 insertions(+), 2129 deletions(-) >>>
| |