[PATCH v1 27/49] perf python: Port rw-by-file from Perl to perf module

[Ian Rogers]

Replace the legacy Perl script rw-by-file.pl with a standalone Python
script in tools/perf/python/rw-by-file.py using the perf Python module.

Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Encapsulate per-file-descriptor read/write byte and call count
  aggregation in an RwByFile class using perf.session and resolve thread
  command names via session.find_thread(pid, sample_tid).
- Add argparse CLI support (-i/--input and target program filter) and
  full type annotations.

Add a shell test
(test_rw_by_file_python.sh) to verify the standalone script.

Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/python/rw-by-file.py               | 109 ++++++++++++++++++
 .../tests/shell/test_rw_by_file_python.sh     |  70 +++++++++++
 2 files changed, 179 insertions(+)
 create mode 100755 tools/perf/python/rw-by-file.py
 create mode 100755 tools/perf/tests/shell/test_rw_by_file_python.sh

diff --git a/tools/perf/python/rw-by-file.py b/tools/perf/python/rw-by-file.py
new file mode 100755
index 000000000000..562ee7f7fd7e
--- /dev/null
+++ b/tools/perf/python/rw-by-file.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+"""Display r/w activity for files read/written to for a given program."""
+from __future__ import annotations
+
+import argparse
+from collections import defaultdict
+import sys
+from typing import Optional, Dict
+import perf
+
+class RwByFile:
+    """Tracks and displays read/write activity by file descriptor."""
+    def __init__(self, comm: str) -> None:
+        self.for_comm = comm
+        self.reads: Dict[int, Dict[str, int]] = defaultdict(
+            lambda: {"bytes_requested": 0, "total_reads": 0}
+        )
+        self.writes: Dict[int, Dict[str, int]] = defaultdict(
+            lambda: {"bytes_written": 0, "total_writes": 0}
+        )
+        self.unhandled: Dict[str, int] = defaultdict(int)
+        self.session: Optional[perf.session] = None
+
+    def process_event(self, sample: perf.sample_event) -> None:
+        """Process events."""
+        raw_name = str(sample.evsel)
+        event_name = raw_name[6:-1] if raw_name.startswith("evsel(") else raw_name
+
+        pid = sample.sample_pid
+        assert self.session is not None
+        try:
+            thread = self.session.find_thread(pid, sample.sample_tid)
+            comm = (thread.comm() if thread else None) or "unknown"
+        except (TypeError, AttributeError):
+            comm = "unknown"
+
+        if comm != self.for_comm:
+            return
+
+        if event_name == "syscalls:sys_enter_read":
+            try:
+                fd = sample.fd
+                count = sample.count
+                self.reads[fd]["bytes_requested"] += count
+                self.reads[fd]["total_reads"] += 1
+            except AttributeError:
+                self.unhandled[event_name] += 1
+        elif event_name == "syscalls:sys_enter_write":
+            try:
+                fd = sample.fd
+                count = sample.count
+                self.writes[fd]["bytes_written"] += count
+                self.writes[fd]["total_writes"] += 1
+            except AttributeError:
+                self.unhandled[event_name] += 1
+        else:
+            self.unhandled[event_name] += 1
+
+    def print_totals(self) -> None:
+        """Print summary tables."""
+        print(f"file read counts for {self.for_comm}:\n")
+        print(f"{'fd':>6s}  {'# reads':>10s}  {'bytes_requested':>15s}")
+        print(f"{'-'*6}  {'-'*10}  {'-'*15}")
+
+        for fd, data in sorted(self.reads.items(),
+                               key=lambda kv: kv[1]["bytes_requested"], reverse=True):
+            print(f"{fd:6d}  {data['total_reads']:10d}  {data['bytes_requested']:15d}")
+
+        print(f"\nfile write counts for {self.for_comm}:\n")
+        print(f"{'fd':>6s}  {'# writes':>10s}  {'bytes_written':>15s}")
+        print(f"{'-'*6}  {'-'*10}  {'-'*15}")
+
+        for fd, data in sorted(self.writes.items(),
+                               key=lambda kv: kv[1]["bytes_written"], reverse=True):
+            print(f"{fd:6d}  {data['total_writes']:10d}  {data['bytes_written']:15d}")
+
+        if self.unhandled:
+            print("\nunhandled events:\n")
+            print(f"{'event':<40s}  {'count':>10s}")
+            print(f"{'-'*40}  {'-'*10}")
+            for event_name, count in self.unhandled.items():
+                print(f"{event_name:<40s}  {count:10d}")
+
+    def run(self, input_file: str) -> None:
+        """Run the session."""
+        self.session = perf.session(perf.data(input_file), sample=self.process_event)
+        try:
+            self.session.process_events()
+        finally:
+            self.session = None
+        self.print_totals()
+
+def main() -> None:
+    """Main function."""
+    parser = argparse.ArgumentParser(description="Trace r/w activity by file")
+    parser.add_argument("comm", help="Filter by command name")
+    parser.add_argument("-i", "--input", default="perf.data", help="Input file")
+    args = parser.parse_args()
+
+    analyzer = RwByFile(args.comm)
+    try:
+        analyzer.run(args.input)
+    except IOError as e:
+        print(e, file=sys.stderr)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/perf/tests/shell/test_rw_by_file_python.sh b/tools/perf/tests/shell/test_rw_by_file_python.sh
new file mode 100755
index 000000000000..a305d5eded75
--- /dev/null
+++ b/tools/perf/tests/shell/test_rw_by_file_python.sh
@@ -0,0 +1,70 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# rw-by-file python test
+
+set -e
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+if ! "$PYTHON" -c 'import perf' > /dev/null 2>&1; then
+	echo "Skipping test, perf python module not found"
+	exit 2
+fi
+
+script_dir="$(dirname "$0")/../../python"
+script_path="${script_dir}/rw-by-file.py"
+
+if ! perf check feature -q libtraceevent > /dev/null 2>&1; then
+	echo "Skipping test, libtraceevent is disabled"
+	exit 2
+fi
+
+
+if [ ! -f "$script_path" ]; then
+	echo "Skipping test, rw-by-file.py not found at $script_path"
+	exit 2
+fi
+
+err=0
+cleanup() {
+	rm -f "${temp_data}" "${temp_out}"
+}
+trap 'cleanup' EXIT TERM INT
+temp_data=$(mktemp /tmp/perf.data.XXXXXX)
+temp_out=$(mktemp /tmp/perf.out.XXXXXX)
+
+echo "Testing rw-by-file.py..."
+
+# Create a perf.data file. Try to get tracepoint data.
+if perf list | grep -q "syscalls:sys_enter_read"; then
+	perf record -e syscalls:sys_enter_read,syscalls:sys_enter_write -a -o "${temp_data}" \
+		-- dd if=/dev/urandom of=/dev/null bs=1M count=10 >/dev/null 2>&1 || \
+		{ echo "Skipping test, perf record failed"; exit 2; }
+else
+	echo "Skipping test, no syscalls:sys_enter_read event"
+	exit 2
+fi
+
+
+if [ ! -s "${temp_data}" ]; then
+	echo "Skipping test, perf record failed to create data"
+	exit 2
+fi
+
+# Check that the script executes - filtering for "dd" since that's what we ran
+if ! "$PYTHON" "$script_path" -i "${temp_data}" "dd" > "${temp_out}"; then
+	echo "rw-by-file.py test failed"
+	err=1
+else
+	if ! grep -E -q "^ *[0-9]+" "${temp_out}"; then
+		echo "Failed to find metric data rows"
+		err=1
+	else
+		echo "rw-by-file test passed."
+	fi
+fi
+rm -f "${temp_out}"
+
+exit $err
-- 
2.55.0.1082.g2b9226bbc0-goog