[PATCH v1 42/51] perf doc: Refresh topdown documentation
Ian Rogers
irogers at google.com
Sun Feb 19 01:28:39 PST 2023
perf stat now supports --topdown for any platform with the TopdownL1
metric group including Intel before Icelake. Tweak the documentation
to reflect this.
Signed-off-by: Ian Rogers <irogers at google.com>
---
tools/perf/Documentation/perf-stat.txt | 27 +++++-----
tools/perf/Documentation/topdown.txt | 70 +++++++++++---------------
2 files changed, 44 insertions(+), 53 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 18abdc1dce05..29bdcfa93f04 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -394,10 +394,10 @@ See perf list output for the possible metrics and metricgroups.
Do not aggregate counts across all monitored CPUs.
--topdown::
-Print complete top-down metrics supported by the CPU. This allows to
-determine bottle necks in the CPU pipeline for CPU bound workloads,
-by breaking the cycles consumed down into frontend bound, backend bound,
-bad speculation and retiring.
+Print top-down metrics supported by the CPU. This allows to determine
+bottle necks in the CPU pipeline for CPU bound workloads, by breaking
+the cycles consumed down into frontend bound, backend bound, bad
+speculation and retiring.
Frontend bound means that the CPU cannot fetch and decode instructions fast
enough. Backend bound means that computation or memory access is the bottle
@@ -430,15 +430,18 @@ CPUs the workload runs on. If needed the CPUs can be forced using
taskset.
--td-level::
-Print the top-down statistics that equal to or lower than the input level.
-It allows users to print the interested top-down metrics level instead of
-the complete top-down metrics.
+Print the top-down statistics that equal the input level. It allows
+users to print the interested top-down metrics level instead of the
+level 1 top-down metrics.
+
+As the higher levels gather more metrics and use more counters they
+will be less accurate. By convention a metric can be examined by
+appending '_group' to it and this will increase accuracy compared to
+gathering all metrics for a level. For example, level 1 analysis may
+highlight 'tma_frontend_bound'. This metric may be drilled into with
+'tma_frontend_bound_group' with
+'perf stat -M tma_frontend_bound_group...'.
-The availability of the top-down metrics level depends on the hardware. For
-example, Ice Lake only supports L1 top-down metrics. The Sapphire Rapids
-supports both L1 and L2 top-down metrics.
-
-Default: 0 means the max level that the current hardware support.
Error out if the input is higher than the supported max level.
--no-merge::
diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt
index a15b93fdcf50..ae0aee86844f 100644
--- a/tools/perf/Documentation/topdown.txt
+++ b/tools/perf/Documentation/topdown.txt
@@ -1,46 +1,35 @@
-Using TopDown metrics in user space
------------------------------------
+Using TopDown metrics
+---------------------
-Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
-methodology to break down CPU pipeline execution into 4 bottlenecks:
-frontend bound, backend bound, bad speculation, retiring.
+TopDown metrics break apart performance bottlenecks. Starting at level
+1 it is typical to get metrics on retiring, bad speculation, frontend
+bound, and backend bound. Higher levels provide more detail in to the
+level 1 bottlenecks, such as at level 2: core bound, memory bound,
+heavy operations, light operations, branch mispredicts, machine
+clears, fetch latency and fetch bandwidth. For more details see [1][2][3].
-For more details on Topdown see [1][5]
+perf stat --topdown implements this using available metrics that vary
+per architecture.
-Traditionally this was implemented by events in generic counters
-and specific formulas to compute the bottlenecks.
-
-perf stat --topdown implements this.
-
-Full Top Down includes more levels that can break down the
-bottlenecks further. This is not directly implemented in perf,
-but available in other tools that can run on top of perf,
-such as toplev[2] or vtune[3]
+% perf stat -a --topdown -I1000
+# time % tma_retiring % tma_backend_bound % tma_frontend_bound % tma_bad_speculation
+ 1.001141351 11.5 34.9 46.9 6.7
+ 2.006141972 13.4 28.1 50.4 8.1
+ 3.010162040 12.9 28.1 51.1 8.0
+ 4.014009311 12.5 28.6 51.8 7.2
+ 5.017838554 11.8 33.0 48.0 7.2
+ 5.704818971 14.0 27.5 51.3 7.3
+...
-New Topdown features in Ice Lake
-===============================
+New Topdown features in Intel Ice Lake
+======================================
With Ice Lake CPUs the TopDown metrics are directly available as
fixed counters and do not require generic counters. This allows
to collect TopDown always in addition to other events.
-% perf stat -a --topdown -I1000
-# time retiring bad speculation frontend bound backend bound
- 1.001281330 23.0% 15.3% 29.6% 32.1%
- 2.003009005 5.0% 6.8% 46.6% 41.6%
- 3.004646182 6.7% 6.7% 46.0% 40.6%
- 4.006326375 5.0% 6.4% 47.6% 41.0%
- 5.007991804 5.1% 6.3% 46.3% 42.3%
- 6.009626773 6.2% 7.1% 47.3% 39.3%
- 7.011296356 4.7% 6.7% 46.2% 42.4%
- 8.012951831 4.7% 6.7% 47.5% 41.1%
-...
-
-This also enables measuring TopDown per thread/process instead
-of only per core.
-
-Using TopDown through RDPMC in applications on Ice Lake
-======================================================
+Using TopDown through RDPMC in applications on Intel Ice Lake
+=============================================================
For more fine grained measurements it can be useful to
access the new directly from user space. This is more complicated,
@@ -301,8 +290,8 @@ This "opens" a new measurement period.
A program using RDPMC for TopDown should schedule such a reset
regularly, as in every few seconds.
-Limits on Ice Lake
-==================
+Limits on Intel Ice Lake
+========================
Four pseudo TopDown metric events are exposed for the end-users,
topdown-retiring, topdown-bad-spec, topdown-fe-bound and topdown-be-bound.
@@ -318,8 +307,8 @@ a sampling read group. Since the SLOTS event must be the leader of a TopDown
group, the second event of the group is the sampling event.
For example, perf record -e '{slots, $sampling_event, topdown-retiring}:S'
-Extension on Sapphire Rapids Server
-===================================
+Extension on Intel Sapphire Rapids Server
+=========================================
The metrics counter is extended to support TMA method level 2 metrics.
The lower half of the register is the TMA level 1 metrics (legacy).
The upper half is also divided into four 8-bit fields for the new level 2
@@ -338,7 +327,6 @@ other four level 2 metrics by subtracting corresponding metrics as below.
[1] https://software.intel.com/en-us/top-down-microarchitecture-analysis-method-win
-[2] https://github.com/andikleen/pmu-tools/wiki/toplev-manual
-[3] https://software.intel.com/en-us/intel-vtune-amplifier-xe
+[2] https://sites.google.com/site/analysismethods/yasin-pubs
+[3] https://perf.wiki.kernel.org/index.php/Top-Down_Analysis
[4] https://github.com/andikleen/pmu-tools/tree/master/jevents
-[5] https://sites.google.com/site/analysismethods/yasin-pubs
--
2.39.2.637.g21b0678d19-goog
More information about the linux-arm-kernel
mailing list