mirror of
https://github.com/torvalds/linux.git
synced 2026-11-10 17:11:02 +01:00
perf python: Port failed-syscalls-by-pid to perf module
Port failed-syscalls-by-pid.py to a standalone script in tools/perf/python/ using the perf module: - Resolve architecture-aware syscall names using perf.syscall_name(id, session.e_machine) instead of host python-audit tables, supporting cross-architecture perf.data files without external dependencies. - Translate negative syscall return values into symbolic E* error names using perf.arch_strerrno(ret, session.e_machine), leveraging the auto-generated trace beauty architecture errno tables. - Encapsulate aggregation in a SyscallAnalyzer class using collections.defaultdict and add argparse filtering by comm, PID, and -i/--input. Add a shell test (test_failed_syscalls_by_pid_python.sh) to verify the standalone script. Assisted-by: Antigravity:gemini-3.1-pro Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Ian Rogers
Arnaldo Carvalho de Melo
parent
712af96a53
commit
b76c43d09b
161
tools/perf/python/failed-syscalls-by-pid.py
Executable file
161
tools/perf/python/failed-syscalls-by-pid.py
Executable file
|
|
@ -0,0 +1,161 @@
|
|||
#!/usr/bin/env python3
|
||||
# SPDX-License-Identifier: GPL-2.0
|
||||
"""
|
||||
Displays system-wide failed system call totals, broken down by pid.
|
||||
If a [comm] or [pid] arg is specified, only syscalls called by it are displayed.
|
||||
|
||||
Ported from tools/perf/scripts/python/failed-syscalls-by-pid.py
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
from collections import defaultdict
|
||||
import os
|
||||
import sys
|
||||
from typing import Optional
|
||||
import perf
|
||||
|
||||
|
||||
def strerror(nr: int, e_machine: Optional[int] = None) -> str:
|
||||
"""Return error string for a given errno, accounting for target e_machine."""
|
||||
return perf.arch_strerrno(nr, e_machine) or f"Unknown {nr} errno"
|
||||
|
||||
|
||||
class SyscallAnalyzer:
|
||||
"""Analyzes failed syscalls and aggregates counts."""
|
||||
|
||||
def __init__(self, for_comm: Optional[str] = None, for_pid: Optional[int] = None):
|
||||
self.for_comm = for_comm
|
||||
self.for_pid = for_pid
|
||||
self.session: Optional[perf.session] = None
|
||||
self.syscalls: dict[tuple[str, int, int, int], int] = defaultdict(int)
|
||||
machine = os.uname().machine
|
||||
self.host_64_bit = ("64" in machine or machine in ("s390x", "alpha")
|
||||
or sys.maxsize > 0xffffffff)
|
||||
|
||||
def process_event(self, sample: perf.sample_event) -> None:
|
||||
"""Process raw_syscalls:sys_exit and syscalls:sys_exit events."""
|
||||
event_name = str(sample.evsel)
|
||||
if "raw_syscalls:sys_exit" not in event_name and "syscalls:sys_exit" not in event_name:
|
||||
return
|
||||
|
||||
pid = sample.sample_tid
|
||||
comm = "Unknown"
|
||||
if hasattr(self, 'session') and self.session:
|
||||
try:
|
||||
thread = self.session.find_thread(sample.sample_pid, pid)
|
||||
if thread:
|
||||
comm = thread.comm() or "Unknown"
|
||||
except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError):
|
||||
pass
|
||||
|
||||
if self.for_comm is not None and comm != self.for_comm:
|
||||
return
|
||||
if self.for_pid is not None and pid != self.for_pid:
|
||||
return
|
||||
|
||||
ret = getattr(sample, "ret", 0)
|
||||
is_64_bit = (getattr(self.session, "is_64_bit", self.host_64_bit)
|
||||
if self.session else self.host_64_bit)
|
||||
# Tracepoint fields may be exposed as unsigned 32-bit or 64-bit integers.
|
||||
# Guard the 32-bit 0xfffff000..0xffffffff conversion with 'not is_64_bit' so valid
|
||||
# 64-bit user-space addresses in that range (e.g. mmap/brk) are not misclassified.
|
||||
if ret > 0:
|
||||
if not is_64_bit and 0xfffff000 <= ret <= 0xffffffff:
|
||||
ret -= 0x100000000
|
||||
elif ret >= 0xfffffffffffff000:
|
||||
ret -= 0x10000000000000000
|
||||
|
||||
# Linux kernel syscalls only return error codes in the [-4095, -1] (-MAX_ERRNO)
|
||||
# range; other negative signed values are valid unsigned user-space pointers.
|
||||
if -4095 <= ret < 0:
|
||||
syscall_id = getattr(sample, "__syscall_nr", -1)
|
||||
if not (0 <= (syscall_id & ~0x40000000) <= 0xffff):
|
||||
syscall_id = getattr(sample, "nr", -1)
|
||||
if not (0 <= (syscall_id & ~0x40000000) <= 0xffff):
|
||||
syscall_id = getattr(sample, "sys_id", -1)
|
||||
if not (0 <= (syscall_id & ~0x40000000) <= 0xffff):
|
||||
syscall_id = getattr(sample, "id", -1)
|
||||
|
||||
# Mask out the x86_64 x32 ABI bit (__X32_SYSCALL_BIT = 0x40000000).
|
||||
raw_sc_id = syscall_id & ~0x40000000
|
||||
if 0 <= raw_sc_id <= 0xffff:
|
||||
self.syscalls[(comm, pid, syscall_id, ret)] += 1
|
||||
|
||||
def print_summary(self) -> None:
|
||||
"""Print aggregated statistics."""
|
||||
if self.for_comm is not None:
|
||||
print(f"\nsyscall errors for {self.for_comm}:\n")
|
||||
elif self.for_pid is not None:
|
||||
print(f"\nsyscall errors for PID {self.for_pid}:\n")
|
||||
else:
|
||||
print("\nsyscall errors:\n")
|
||||
|
||||
print(f"{'comm [pid]':<30} {'count':>10}")
|
||||
print(f"{'-' * 30:<30} {'-' * 10:>10}")
|
||||
|
||||
sorted_keys = sorted(
|
||||
self.syscalls.keys(),
|
||||
key=lambda k: (k[0], k[1], k[2], -self.syscalls[k])
|
||||
)
|
||||
current_comm_pid = None
|
||||
current_syscall = None
|
||||
emach = getattr(self.session, "e_machine", 0) or 0
|
||||
for comm, pid, syscall_id, ret in sorted_keys:
|
||||
if current_comm_pid != (comm, pid):
|
||||
print(f"\n{comm} [{pid}]")
|
||||
current_comm_pid = (comm, pid)
|
||||
current_syscall = None
|
||||
if current_syscall != syscall_id:
|
||||
raw_sc_id = syscall_id & ~0x40000000
|
||||
try:
|
||||
if emach:
|
||||
name = perf.syscall_name(raw_sc_id, emach) or str(syscall_id)
|
||||
else:
|
||||
name = perf.syscall_name(raw_sc_id) or str(syscall_id)
|
||||
except AttributeError:
|
||||
name = str(syscall_id)
|
||||
print(f" syscall: {name:<16}")
|
||||
current_syscall = syscall_id
|
||||
err_str = strerror(ret, emach)
|
||||
count = self.syscalls[(comm, pid, syscall_id, ret)]
|
||||
print(f" err = {err_str:<20} {count:10d}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
ap = argparse.ArgumentParser(
|
||||
description="Displays system-wide failed system call totals, "
|
||||
"broken down by pid.")
|
||||
ap.add_argument("-i", "--input", default="perf.data",
|
||||
help="Input file name")
|
||||
ap.add_argument("filter", nargs="?", help="COMM or PID to filter by")
|
||||
args = ap.parse_args()
|
||||
|
||||
F_COMM = None
|
||||
F_PID = None
|
||||
|
||||
if args.filter:
|
||||
try:
|
||||
F_PID = int(args.filter)
|
||||
except ValueError:
|
||||
F_COMM = args.filter
|
||||
|
||||
analyzer = SyscallAnalyzer(F_COMM, F_PID)
|
||||
session = None
|
||||
|
||||
try:
|
||||
print("Press control+C to stop and show the summary")
|
||||
session = perf.session(perf.data(args.input), sample=analyzer.process_event)
|
||||
analyzer.session = session
|
||||
session.process_events()
|
||||
analyzer.print_summary()
|
||||
except KeyboardInterrupt:
|
||||
analyzer.print_summary()
|
||||
except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e:
|
||||
print(f"Error processing events: {e}")
|
||||
sys.exit(1)
|
||||
finally:
|
||||
# Break reference cycles between perf.session and analyzer.process_event
|
||||
# because perf.session is a C extension type without cyclic GC (tp_traverse).
|
||||
analyzer.session = None
|
||||
session = None
|
||||
95
tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
Executable file
95
tools/perf/tests/shell/test_failed_syscalls_by_pid_python.sh
Executable file
|
|
@ -0,0 +1,95 @@
|
|||
#!/bin/bash
|
||||
# SPDX-License-Identifier: GPL-2.0
|
||||
# failed-syscalls-by-pid 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}/failed-syscalls-by-pid.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, failed-syscalls-by-pid.py not found at $script_path"
|
||||
exit 2
|
||||
fi
|
||||
|
||||
err=0
|
||||
temp_dir=$(mktemp -d /tmp/perf-failed-syscalls-by-pid-XXXXXX)
|
||||
temp_data="${temp_dir}/perf.data"
|
||||
temp_out="${temp_dir}/perf.out"
|
||||
|
||||
cleanup() {
|
||||
rm -rf "${temp_dir}"
|
||||
}
|
||||
|
||||
trap 'cleanup' EXIT TERM INT
|
||||
|
||||
test_file_mode() {
|
||||
echo "Testing failed-syscalls-by-pid.py..."
|
||||
|
||||
# Check if syscalls:sys_exit is supported/readable
|
||||
if ! perf record -e syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
|
||||
if ! perf record -e raw_syscalls:sys_exit -o /dev/null -- true >/dev/null 2>&1; then
|
||||
echo "Skipping test, no syscalls:sys_exit or raw_syscalls:sys_exit event"
|
||||
exit 2
|
||||
else
|
||||
EVENT="raw_syscalls:sys_exit"
|
||||
fi
|
||||
else
|
||||
EVENT="syscalls:sys_exit"
|
||||
fi
|
||||
|
||||
# Generate some events by running a command that should fail at least some syscall
|
||||
# (e.g. failing stat on non-existent file).
|
||||
# Using '|| true' because 'perf record' returns the exit code of 'ls',
|
||||
# which fails with ENOENT
|
||||
perf record -e "${EVENT}" -o "${temp_data}" -- ls /does_not_exist >/dev/null 2>&1 || true
|
||||
if [ ! -s "${temp_data}" ]; then
|
||||
echo "Skipping test, perf record failed to create data"
|
||||
exit 2
|
||||
fi
|
||||
|
||||
# Run the script and check output
|
||||
if ! "$PYTHON" "$script_path" -i "${temp_data}" > "${temp_out}"; then
|
||||
echo "failed-syscalls-by-pid test failed."
|
||||
err=1
|
||||
elif ! grep -n -q "err = ENOENT" "${temp_out}"; then
|
||||
echo "Failed to find expected failed syscalls"
|
||||
cat "${temp_out}"
|
||||
err=1
|
||||
elif ! "$PYTHON" "$script_path" -i "${temp_data}" "ls" > "${temp_out}.comm" || \
|
||||
! grep -q "err = ENOENT" "${temp_out}.comm"; then
|
||||
echo "failed-syscalls-by-pid comm filter test failed."
|
||||
cat "${temp_out}.comm"
|
||||
err=1
|
||||
else
|
||||
ls_pid=$(sed -n 's/^ls \[\([0-9][0-9]*\)\].*/\1/p' "${temp_out}.comm" | head -n 1)
|
||||
if [ -z "${ls_pid}" ] || \
|
||||
! "$PYTHON" "$script_path" -i "${temp_data}" "${ls_pid}" > "${temp_out}.pid" || \
|
||||
! grep -q "err = ENOENT" "${temp_out}.pid"; then
|
||||
echo "failed-syscalls-by-pid PID filter test failed."
|
||||
cat "${temp_out}.pid" 2>/dev/null || true
|
||||
err=1
|
||||
else
|
||||
echo "failed-syscalls-by-pid test passed."
|
||||
fi
|
||||
fi
|
||||
rm -f "${temp_out}" "${temp_out}.comm" "${temp_out}.pid"
|
||||
}
|
||||
|
||||
test_file_mode
|
||||
|
||||
exit $err
|
||||
Loading…
Reference in New Issue
Block a user