[PATCH v5 48/58] perf rw-by-file: Port rw-by-file to use python module

[Ian Rogers]

Port the legacy Perl script rw-by-file.pl to a python script using the
perf module in tools/perf/python.

The new script uses a class-based architecture and leverages the
perf.session API for event processing.

It tracks read and write activity by file descriptor for a given
program name, aggregating bytes requested/written and total counts.

Complications:
- Had to split long lines in __init__ to satisfy pylint.
- pylint warns about the module name not being snake_case, but it is
  kept for consistency with the original script name.

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers at google.com>
---
v2:

 - Fixed Substring Matching: Replaced if "sys_enter_read" in
   event_name: with an exact match against syscalls:sys_enter_read and
   raw_syscalls:sys_enter_read using sample.evsel.name . This prevents
   variants like readv or readlink from incorrectly triggering the
   read logic. Similar fixes were applied for write events.

 - Fixed Silent Error Dropping: Instead of silently returning when
   expected fields are missing (causing AttributeError ), the script
   now increments the self.unhandled counter for that event. This
   ensures that missing data or unexpected event variants are reported
   to the user instead of quietly skewing the results.
---
 tools/perf/python/rw-by-file.py | 103 ++++++++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100755 tools/perf/python/rw-by-file.py

diff --git a/tools/perf/python/rw-by-file.py b/tools/perf/python/rw-by-file.py
new file mode 100755
index 000000000000..f71e0b21f64e
--- /dev/null
+++ b/tools/perf/python/rw-by-file.py
@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+"""Display r/w activity for files read/written to for a given program."""
+
+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."""
+        event_name = sample.evsel.name  # type: ignore
+
+        pid = sample.sample_pid
+        assert self.session is not None
+        try:
+            comm = self.session.process(pid).comm()
+        except Exception: # pylint: disable=broad-except
+            comm = "unknown"
+
+        if comm != self.for_comm:
+            return
+
+        if event_name in ("syscalls:sys_enter_read", "raw_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 in ("syscalls:sys_enter_write", "raw_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)
+        self.session.process_events()
+        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()
-- 
2.54.0.545.g6539524ca2-goog