Received-SPF: pass (google.com: domain of linux-kernel+bounces-85913-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Wed, 28 Feb 2024 16:18:05 -0800
In-Reply-To: <20240229001806.4158429-1-irogers@google.com>
Message-Id: <20240229001806.4158429-21-irogers@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240229001806.4158429-1-irogers@google.com>
Subject: [PATCH v1 20/20] perf jevents: Add upi_bw metric for Intel
From: Ian Rogers <irogers@google.com>
To: Perry Taylor <perry.taylor@intel.com>, Samantha Alt <samantha.alt@intel.com>, 
	Caleb Biggers <caleb.biggers@intel.com>, Weilin Wang <weilin.wang@intel.com>, 
	Edward Baker <edward.baker@intel.com>, Andi Kleen <ak@linux.intel.com>, 
	Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>, 
	Arnaldo Carvalho de Melo <acme@kernel.org>, Namhyung Kim <namhyung@kernel.org>, 
	Mark Rutland <mark.rutland@arm.com>, 
	Alexander Shishkin <alexander.shishkin@linux.intel.com>, Jiri Olsa <jolsa@kernel.org>, 
	Ian Rogers <irogers@google.com>, Adrian Hunter <adrian.hunter@intel.com>, 
	John Garry <john.g.garry@oracle.com>, Kan Liang <kan.liang@linux.intel.com>, 
	Jing Zhang <renyu.zj@linux.alibaba.com>, Thomas Richter <tmricht@linux.ibm.com>, 
	James Clark <james.clark@arm.com>, linux-kernel@vger.kernel.org, 
	linux-perf-users@vger.kernel.org, Stephane Eranian <eranian@google.com>
Content-Type: text/plain; charset="UTF-8"

Break down UPI read and write bandwidth using uncore_upi counters.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/intel_metrics.py | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index cdeb58e17c5e..219541a30450 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -1006,6 +1006,27 @@ def UncoreMemBw() -> Optional[MetricGroup]:
   ], description = "Memory Bandwidth")
 
 
+def UncoreUpiBw() -> Optional[MetricGroup]:
+  try:
+    upi_rds = Event("UNC_UPI_RxL_FLITS.ALL_DATA")
+    upi_wrs = Event("UNC_UPI_TxL_FLITS.ALL_DATA")
+  except:
+    return None
+
+  upi_total = upi_rds + upi_wrs
+
+  # From "Uncore Performance Monitoring": When measuring the amount of
+  # bandwidth consumed by transmission of the data (i.e. NOT including
+  # the header), it should be .ALL_DATA / 9 * 64B.
+  scale = (64 / 9) / 1_000_000
+  return MetricGroup("upi_bw", [
+      Metric("upi_bw_read", "UPI read bandwidth",
+             d_ratio(upi_rds, interval_sec), f"{scale}MB/s"),
+      Metric("upi_bw_write", "DDR memory write bandwidth",
+             d_ratio(upi_wrs, interval_sec), f"{scale}MB/s"),
+  ], description = "UPI Bandwidth")
+
+
 all_metrics = MetricGroup("", [
     Cycles(),
     Idle(),
@@ -1026,6 +1047,7 @@ all_metrics = MetricGroup("", [
     UncoreDir(),
     UncoreMem(),
     UncoreMemBw(),
+    UncoreUpiBw(),
 ])
 
 if args.metricgroups:
-- 
2.44.0.278.ge034bb2e1d-goog