[PATCH v1 28/58] perf syscall-counts-by-pid: Port syscall-counts-by-pid to use python module

[Ian Rogers]

Rewrite tools/perf/scripts/python/syscall-counts-by-pid.py to use the
python module and various style changes. By avoiding the overheads in
the `perf script` execution the performance improves by more than 3.8x
as shown in the following (with PYTHON_PATH and PERF_EXEC_PATH set as
necessary):

```
$ perf record -e raw_syscalls:sys_enter -a sleep 1
...
$ time perf script tools/perf/scripts/python/syscall-counts-by-pid.py perf
Install the python-audit package to get syscall names.
For example:
  # apt-get install python3-audit (Ubuntu)
  # yum install python3-audit (Fedora)
  etc.

Press control+C to stop and show the summary
Warning:
1 out of order events recorded.

syscall events for perf:

comm [pid]/syscalls                            count
 ---------------------------------------  ----------

perf [3886080]
  1                                           538989
  16                                              32
  203                                             17
  3                                                2
  257                                              1
  204                                              1
  15                                               1
  0                                                1

perf [3886082]
  7                                                1

real    0m3.852s
user    0m3.512s
sys     0m0.336s
$ time python3 tools/perf/python/syscall-counts-by-pid.py perf
Warning:
1 out of order events recorded.

syscall events for perf:

comm [pid]/syscalls                           count
 --------------------------------------- -----------

perf [3886080]
  write                                      538989
  ioctl                                          32
  sched_setaffinity                              17
  close                                           2
  openat                                          1
  sched_getaffinity                               1
  rt_sigreturn                                    1
  read                                            1

perf [3886082]
  poll                                            1

real    0m1.011s
user    0m0.963s
sys     0m0.048s
```

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/python/syscall-counts-by-pid.py | 57 ++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100755 tools/perf/python/syscall-counts-by-pid.py

diff --git a/tools/perf/python/syscall-counts-by-pid.py b/tools/perf/python/syscall-counts-by-pid.py
new file mode 100755
index 000000000000..a5d91060b18d
--- /dev/null
+++ b/tools/perf/python/syscall-counts-by-pid.py
@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# Displays system-wide system call totals, broken down by syscall.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+import argparse
+from collections import defaultdict
+import perf
+
+syscalls = defaultdict(lambda: defaultdict(lambda: defaultdict(int)))
+for_comm = None
+session = None
+
+
+def print_syscall_totals():
+    if for_comm is not None:
+        print(f"\nsyscall events for {for_comm}:\n")
+    else:
+        print("\nsyscall events:\n")
+
+    print(f"{'comm [pid]/syscalls':<40} {'count':>10}")
+    print("---------------------------------------- -----------")
+
+    comm_keys = syscalls.keys()
+    for comm in comm_keys:
+        pid_keys = syscalls[comm].keys()
+        for pid in pid_keys:
+            print(f"\n{comm} [{pid}]")
+            id_keys = syscalls[comm][pid].keys()
+            for id, val in sorted(syscalls[comm][pid].items(),
+                                  key=lambda kv: (kv[1], kv[0]), reverse=True):
+                print(f"  {perf.syscall_name(id):<38} {val:>10}")
+
+
+def process_event(sample):
+    event_name = str(sample.evsel)
+    if event_name == "evsel(raw_syscalls:sys_enter)":
+        id = sample.id
+    elif event_name.startswith("evsel(syscalls:sys_enter_"):
+        id = sample.__syscall_nr
+    else:
+        return
+    pid = sample.sample_pid
+    comm = session.process(pid).comm()
+    if for_comm and comm != for_comm:
+        return
+    syscalls[comm][pid][id] += 1
+
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser()
+    ap.add_argument("comm", nargs="?", help="Only report syscalls for comm")
+    args = ap.parse_args()
+    for_comm = args.comm
+    session = perf.session(perf.data("perf.data"), sample=process_event)
+    session.process_events()
+    print_syscall_totals()
-- 
2.54.0.rc1.513.gad8abe7a5a-goog