| Age | Commit message (Collapse) | Author |
|---|
|
optparse is deprecated since Python 3.2 and triggers a pylint
deprecated-module warning on newer versions of pylint.
Replace optparse.OptionParser in tools/perf/tests/shell/lib/attr.py with
argparse.ArgumentParser.
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>
|
|
'perf probe' names the event after the function and binary, so concurrent
runs, as with 'perf test -r3', all add probe_testfile:foo and all but one
fail with 'event "foo" already exists'. Name the event foo_$$.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
Now it's safe to run multiple 'perf trace' commands at the same time.
Let's make them non-exclusive so that they can run in parallel.
$ sudo perf test 'perf trace'
113: Check open filename arg using perf trace + vfs_getname : Skip
114: perf trace enum augmentation tests : Ok
115: perf trace BTF general tests : Ok
116: perf trace exit race : Ok
117: perf trace record and replay : Ok
118: perf trace summary : Ok
[ irogers: Keep trace+probe_vfs_getname.sh exclusive, as without BPF every
'perf trace' opens its probe:vfs_getname* probe. ]
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250814071754.193265-6-namhyung@kernel.org
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>
|
|
With --max-events=1 an unrelated event can end perf trace before the
command's syscall is seen. Trace the whole command and grep for the
expected line, as trace_btf_enum.sh does, and remove the exclusive tag.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
On a mismatch print the command, the match count, the matching lines and
the end of the output.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
Scope the uprobe name to the pid, retry adding and deleting it as
concurrent uprobe_events writes can fail with EBUSY, and delete it from
an exit trap. Create the temporary files with mktemp rather than reserving
names with mktemp -u. Remove the exclusive tag.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
The fixed vfs_getname probe name collides between parallel tests, and the
cleanup deletes every probe:vfs_getname* probe. Name the probe
getname_flags_$$, match it exactly, and remove it from an exit trap. Not
starting with vfs_getname also stops perf trace, which opens every
probe:vfs_getname* event, from pinning it.
Remove the exclusive tag from probe_vfs_getname.sh and
record+script_probe_vfs_getname.sh. trace+probe_vfs_getname.sh needs perf
trace to find its probe, so it uses vfs_getname_$$ and stays exclusive.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
Writing 0 to events/enable disables every tracepoint, breaking perf
sessions running in parallel. Disable just the kprobes and uprobes, an
enabled one would make clearing kprobe_events or uprobe_events fail with
EBUSY.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
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>
|
|
The before and after records are paired by list position. If a CPU or
domain disappears, counters can be subtracted from a different record
or left as absolute values. An extra record can also advance the cursor
past the list.
Identify the second snapshot by its timestamp or CPU ordering, and
require matching CPU/domain IDs and versions before subtracting. Check
that every record has a counterpart before printing, and propagate
errors from either input of diff.
Add a shell test with synthetic snapshots, including equal timestamps,
CPU filtering, and missing or reordered CPU/domain records.
Fixes: 5a357ae6ad63fd10 ("perf sched stats: Add support for report subcommand")
Reviewed-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Assisted-by: LLM
Signed-off-by: Tianyi Chen <hi@tychen.cc>
Tested-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
When -d/--db is not specified, event_analyzing_sample.py created a
temporary file in /tmp via tempfile.mkstemp() and deleted it in
trace_end(). As noted during review, creating the database in a shared
/tmp directory does not reserve SQLite's auxiliary sidecar filenames
(-journal or -wal), and a temporary on-disk file is unnecessary when the
caller did not ask to persist the database.
Default to sqlite3.connect(":memory:") when db_path is not provided,
removing the temporary file creation and cleanup logic, and test both
the default in-memory mode and explicit -d file mode in
test_event_analyzing_sample_python.sh.
Fixes: eeb70645a8097437 ("perf python: Port event_analyzing_sample to perf module")
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>
|
|
When all Python shell tests run concurrently during 'perf test' under
heavy load:
1. Unfiltered 'perf list' initializes all hardware PMUs and metrics in
each test process; use 'perf list tracepoint' when checking for
tracepoint events.
2. Running 'perf record' without '-B -N --no-bpf-event' synthesizes BPF
events across the system and caches build-ids into ~/.debug; add
'-B -N --no-bpf-event' to all Python shell test recordings.
3. Drop '-a' in test_check_perf_trace_python.sh,
test_rw_by_file_python.sh, test_rw_by_pid_python.sh,
test_rwtop_python.sh, and test_syscall_counts_by_pid_python.sh where
only a single child workload ('dd' or 'sleep') is tested, avoiding
system-wide /proc synthesis and ringbuffer contention.
4. Add '-W 1' to 'ping -c 1' in test_net_dropmonitor_python.sh and
test_netdev_times_python.sh, and narrow 'compaction:*' to
'compaction:mm_compaction_begin,compaction:mm_compaction_end' in
test_compaction_times_python.sh.
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>
|
|
When running 'perf test' in parallel under heavy system load, a one-shot
'perf record -e ... -- ls /does_not_exist' without '-B -N --no-bpf-event'
can exit in under 300 microseconds before 'ls's PERF_RECORD_COMM and
ENOENT sys_exit events are captured, while also contending on ~/.debug
build-id caching and BPF event synthesis.
Pass '-B -N --no-bpf-event' to 'perf record', sleep 0.05s in a subshell
after 'ls' so its events are flushed before the parent subshell exits,
and wrap the record and check steps in a bounded retry loop (up to 5
attempts).
Fixes: b76c43d09b06da1b ("perf python: Port failed-syscalls-by-pid to perf module")
Fixes: 4e3fe6987cbad8ab ("perf python: Port failed-syscalls from Perl to perf module")
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>
|
|
In test_intel_pt_events_python.sh, test_export_to_sqlite_python.sh, and
test_export_to_postgresql_python.sh, 'sh -c "uname; true"' uses the
shell builtin 'true' and exits within microseconds of 'uname', sending
SIGCHLD to 'perf record' before the Intel PT AUX buffer is always
flushed under heavy parallel load (~5-10% drop rate).
Sleep 0.05s in the subshell after 'uname' ('sh -c "uname; sleep 0.05"')
so 'uname' completely exits and flushes its AUX trace before 'sh' exits,
and wrap the record and verification step in a bounded retry loop (up to
5 attempts). Also pass '-B -N --no-bpf-event' to 'perf record -g' in
test_export_to_sqlite_python.sh and test_export_to_postgresql_python.sh
to avoid build-id cache and BPF synthesis overhead.
Fixes: d4ce72e9e238fd70 ("perf python: Port intel-pt-events and libxed to perf module")
Fixes: 62d350135e676a11 ("perf python: Port export-to-sqlite to perf module")
Fixes: b1f968c9656a8a87 ("perf python: Port export-to-postgresql to perf module")
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>
|
|
In test_stat_cpi_python.sh, 'perf test -w noploop &' defaults to a
1-second duration and can exit under heavy parallel load before
'perf stat -p' and 'perf script stat-cpi' finish starting up. In
addition, the fixed 'sleep 0.5' before sending SIGINT can fire before
Python finishes importing the perf module, opening the live evlist, and
flushing the first interval.
In stat-cpi.py, register SIGINT and SIGTERM handlers before calling
_open_live_evlist() and pass flush=True when printing live output so
redirected stdout is flushed immediately after each interval.
In test_stat_cpi_python.sh, run 'perf test -w noploop 60 &' so the
target workload stays alive until killed, and poll the output file for
'cpi' (up to 5 seconds) before sending SIGINT.
Fixes: 4425182d426b ("perf python: Port stat-cpi to perf module")
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>
|
|
In sctop.py:
- If an earlier interval elapsed and printed an empty table before the
target comm ('sleep') executed any syscalls, analyzer.printed became
True and the final partial interval containing the target comm's
syscalls was never flushed at EOF. Flush print_current_totals() in
finally when analyzer.syscalls is non-empty as well as when nothing
has been printed yet.
- Initialize analyzer.e_machine after creating perf.session rather than
when session is still None.
In test_sctop_python.sh:
- Use a private temporary directory via 'mktemp -d'.
- Drop '-a' and pass '-B -N --no-bpf-event' to 'perf record', and sleep
briefly in the subshell ('sh -c "sleep 0.1; sleep 0.05"') with a
bounded retry loop so 'sleep's PERF_RECORD_COMM and sys_enter events
are reliably captured under heavy load.
Fixes: b83f0bacf5e4f936 ("perf python: Port sctop to perf module")
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>
|
|
Since commit 9fa3ec84587c ("allow incomplete imports of filenames"), in
v7.0, getname_flags() only calls do_getname(). None of the lines the
vfs_getname tests search for are in getname_flags() any more, so the
tests always skip. Fall back to the initname() call in do_getname().
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>
|
|
The CoreSight callchain test traces both userspace and kernel execution
and checks the callchain across a syscall.
Add --kcore to perf record to save the running kernel image alongside
the trace data so perf script can use it to decode the kernel trace.
If kcore is not available, the test will be skipped.
Add a Fixes tag so the change can be backported to stable kernels and
improve the test reliability.
Fixes: ca0e19074bd6afcb ("perf test: Add Arm CoreSight callchain test")
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Refactor 'perf script' to launch standalone scripts directly via fork()
and execvp() and remove the legacy embedded Perl and Python scripting
engines:
- Remove the embedded Perl scripting engine
(util/scripting-engines/trace-event-perl.c), Perl scripts, bin
wrappers, and Trace-Util library
(scripts/perl/Perf-Trace-Util/), and script_perl.sh test.
- Remove libperl feature checks from Makefile.config, Makefile.perf,
builtin-check.c, and Documentation/perf-check.txt.
- Remove -g / --gen-script option and scripting_ops dispatch table from
builtin-script.c and trace-event-scripting.c.
- Hide the legacy -s / --script option and update script discovery in
find_script() and list_available_scripts() to prioritize the system
'python' directory over bare filenames in the current directory.
- Update the Python script shell tests (test_arm_coresight_disasm.sh,
test_task_analyzer.sh, and test_*_python.sh) to invoke scripts via
'perf script <script>' rather than running the Python interpreter
directly on the script file path.
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>
|
|
Remove embedded Python interpreter support (libpython) from perf, as
all Python scripts have been migrated to standalone scripts using the
perf Python extension module.
Changes include:
- Remove libpython detection and build flags from Makefile.config.
- Remove legacy Python script installation rules from Makefile.perf.
- Delete tools/perf/util/scripting-engines/trace-event-python.c and
tools/perf/scripts/python/Perf-Trace-Util/Context.c.
- Remove Python scripting engine registration from
trace-event-scripting.c.
- Remove libpython from the supported features list in builtin-check.c
and Documentation/perf-check.txt.
- Delete the legacy Python scripts and bin wrappers in
tools/perf/scripts/python/ and update shell tests.
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>
|
|
Move parallel-perf.py from tools/perf/scripts/python/ to
tools/perf/python/ as it is a standalone Python utility that invokes
'perf script' in parallel across time slices and CPUs. Update
tools/perf/tests/shell/script.sh accordingly.
Also fix bugs and clean up the script to pass mypy and pylint without
suppression comments:
- Fix Work.command() to return the shlex.quote()-escaped command string
(previously sh_cmd was computed with shlex.quote() and discarded in
favor of unquoted self.cmd).
- Close self.popen.stdout in the parent process after spawning the
consumer subprocess in Work.start() when --pipe-to is used, ensuring
the producer receives SIGPIPE if the consumer exits early and avoiding
leaking the pipe file descriptor.
- Convert method and function names to snake_case, specify utf-8 file
encodings, and add type annotations and docstrings.
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>
|
|
Port export-to-postgresql.py to a standalone script in
tools/perf/python/ using the perf module and libpq via ctypes.
Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql for database creation and DDL
execution by driving libpq directly via ctypes (PQconnectdb, PQexec,
PQputCopyData, PQputCopyEnd) and streaming binary PostgreSQL COPY
files in PostgresExporter, enabling export on headless servers without
Qt installed.
- Harden database connection and SQL identifier handling by rejecting
URI ('://') and connection-parameter ('=') injection strings in
setup_db() and connect(), escaping single quotes and backslashes in
connection strings, and quoting SQL identifiers (quote_ident).
- Support Intel PT and instruction trace export via
perf.session(itrace=...) and perf.call_return callbacks, reconstructing
relational call_paths and calls tables (including id=0 placeholder
rows and callfk/returnfk foreign keys) and unpacking synthesized PT
payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Use a dedicated context_switch ID counter so context-switch exports
do not advance sample database IDs out of sync with call_return
references.
Update Documentation/db-export.txt and add a shell test
(test_export_to_postgresql_python.sh) to verify the standalone exporter.
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>
|
|
Port export-to-sqlite.py to a standalone script in tools/perf/python/
using the perf module and Python's standard library sqlite3 module.
Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql by using Python's built-in
sqlite3 module in DatabaseExporter, allowing SQLite export on headless
and minimal systems without Qt installed.
- Support Intel PT and hardware instruction trace export via
perf.session(itrace=...) and perf.call_return callbacks, reconstructing
relational call_paths and calls tables and decoding synthesized PT
payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Export context_switches via perf.session's context_switch callback
and map thread and comm IDs to their relational database keys.
- Manage temporary staging files inside an isolated tempfile.mkdtemp()
directory with guaranteed cleanup in a finally block.
Update Documentation/db-export.txt and add a shell test
(test_export_to_sqlite_python.sh) to verify the standalone exporter.
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>
|
|
Migrate the Intel PT virtual LBR test from generating an inline legacy
perf script callback to using a standalone Python script
(perf_brstack_max.py) with the brstack iterator API in the perf Python
module.
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>
|
|
Port intel-pt-events.py and libxed.py from tools/perf/scripts/python/
to standalone modules in tools/perf/python/:
- Refactor intel-pt-events.py into an IntelPTAnalyzer class with full
type annotations to encapsulate trace state and stashed output.
- Configure instruction trace decoding directly via perf.session's
itrace option and context_switch callback.
- Dynamically select 32-bit vs 64-bit disassembly mode in libxed.py
using session.is_64_bit and annotate instructions with source lines
via sample.srccode().
- Rename methods in libxed.py to snake_case (instruction, set_mode,
disassemble_one) and remove Python 2 compatibility code.
Add a shell test (test_intel_pt_events_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>
|
|
Port powerpc-hcalls.py from tools/perf/scripts/python/ to a standalone
script in tools/perf/python/:
- Refactor the script into an HCallAnalyzer class with full type
annotations to encapsulate per-CPU hypervisor call entry/exit state.
- Use perf.session for event processing to track hypervisor call entry
and exit timestamps and aggregate min/max/average duration statistics
against HCALL_TABLE.
- Add argparse CLI support (-i/--input) and remove Python 2
compatibility code.
Add a shell test (test_powerpc_hcalls_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>
|
|
Port arm-cs-trace-disasm.py to a standalone script in tools/perf/python/
using the perf module directly.
Improvements compared to the legacy script:
- Encapsulate trace disassembly state in a TraceDisasm class.
- Default to itrace="b" when creating perf.session() (overridable via
--itrace or PERF_ITRACE) so all CoreSight branch samples are
synthesized without requiring --itrace=b on the command line.
- Automatically search standard kernel debug paths (find_vmlinux())
when -k/--vmlinux is not specified, and query
perf.config_get("annotate.objdump") for the default objdump binary.
- Bound DISASM_CACHE memory consumption by evicting the cache at 1024
entries and skipping caching of oversized (> 512 lines) objdump
outputs.
- Use sample.srccode() from the perf extension module to annotate
disassembly output with source filenames, line numbers, and source
lines.
Update the ARM CoreSight disassembly shell test
(test_arm_coresight_disasm.sh) to invoke the standalone script.
Assisted-by: Antigravity:gemini-3.1-pro
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Port check-perf-trace.py to a standalone script in tools/perf/python/
using the perf module directly.
Improvements compared to the legacy script:
- Access tracepoint fields directly as attributes on perf.sample_event
instead of per-event dictionaries and legacy Perf-Trace-Util helpers.
- Decode symbolic flag and enum masks for irq:softirq_entry and
kmem:kmalloc directly in Python and add -i/--input CLI support via
argparse.
- Add full type annotations and clean up Python 2 idioms.
Add a shell test (test_check_perf_trace_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>
|
|
Port netdev-times.py from tools/perf/scripts/python/ to a standalone
script in tools/perf/python/:
- Refactor the script into a NetDevTimesAnalyzer class with full type
annotations to encapsulate state.
- Collect events via perf.session and sort them in timestamp order
before analysis so multi-CPU TX and RX packet timelines are
reconstructed deterministically.
- Replace custom argument parsing with argparse (-i/--input, --tx,
--rx, --dev, --debug), extract tracepoint fields directly from sample
attributes, and remove Python 2 compatibility artifacts.
Add a shell test (test_netdev_times_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>
|
|
Port net_dropmonitor.py from tools/perf/scripts/python/ to a standalone
script in tools/perf/python/:
- Refactor the script into a DropMonitor class with full type
annotations to encapsulate state.
- Use perf.session for skb:kfree_skb event processing and add argparse
CLI support (-i/--input and -k/--kallsyms).
- Resolve kernel drop addresses via perf.session symbols/callchains and
binary search over /proc/kallsyms, ignoring zeroed kptr_restrict
addresses with graceful fallback when kallsyms is unavailable.
- Remove Python 2 compatibility code.
Add a shell test (test_net_dropmonitor_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>
|
|
Port compaction-times.py to a standalone script in tools/perf/python/
using the perf module directly to analyze mm_compaction tracepoints.
Improvements compared to the legacy script:
- Replace Python 2 constructs (such as sys.maxint and raw integer
bitmasks) with Python 3 enum.IntEnum (Popt) and enum.IntFlag (Topt)
types.
- Access tracepoint fields directly on perf.sample_event and add
-i/--input CLI option support via argparse.
- Add full type annotations passing mypy and pylint without suppression
comments.
Add a shell test (test_compaction_times_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>
|
|
Replace the legacy Perl script wakeup-latency.pl with a standalone
Python script in tools/perf/python/wakeup-latency.py using the perf
Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Track wakeup timestamps per-task (keyed by the wakee PID on
sched:sched_wakeup and matched against next_pid on sched:sched_switch)
rather than per-CPU, avoiding mixed latencies when multiple wakeups
occur on a CPU before a context switch.
- Guard print_totals() when total_wakeups == 0 (printing 'N/A' instead
of dividing by zero when a trace contains no matched wakeup/switch
pairs).
- Add argparse CLI options (-i/--input) and full type annotations.
Add a shell test
(test_wakeup_latency_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>
|
|
Port sched-migration.py and SchedGui.py from tools/perf/scripts/python/
to standalone modules in tools/perf/python/:
- Refactor sched-migration.py into a SchedMigrationAnalyzer class using
perf.session for event processing and add argparse CLI support
(-i/--input, -v/--verbose, --gui, --no-gui).
- Port SchedGui.py to tools/perf/python/ as a local module dependency.
- Load wxPython dynamically via importlib only when GUI mode (--gui) is
requested so text-mode analysis, testing on headless systems, and
static analysis (mypy/pylint) succeed without wx installed.
- Remove Python 2 compatibility code.
Add a shell test (test_sched_migration_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>
|
|
Port task-analyzer.py from tools/perf/scripts/python/ to a standalone
script in tools/perf/python/ refactored into a class-based architecture.
Improvements compared to the legacy script:
- Support both offline perf.data file analysis (using perf.session) and
live trace capture (using evlist.read_on_cpu), accessing
sched:sched_switch tracepoint fields directly from sample objects.
- Automatically disable ANSI terminal color escape sequences when --csv
or --csv-summary is enabled so CSV column headers ('Comm,',
'Time Out-Out,', etc.) are never polluted by color codes when running
interactively on a TTY (e.g. as root).
- Sanitize non-printable characters and leading CSV formula characters
(=, +, -, @) in task comm strings.
- Emit a one-time warning to stderr if sched:sched_switch samples are
missing tracepoint fields (such as when recorded without libtraceevent
support).
Update test_task_analyzer.sh to invoke 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>
|
|
Port tools/perf/scripts/python/futex-contention.py to a standalone
script in tools/perf/python/ using the perf module. Avoiding the
embedded interpreter overhead improves execution speed by ~3.2x:
```
$ perf record -e syscalls:sys_*_futex -a sleep 1
...
$ time perf script tools/perf/scripts/python/futex-contention.py
...
real 0m1.007s
user 0m0.935s
sys 0m0.072s
$ time python3 tools/perf/python/futex-contention.py
...
real 0m0.314s
user 0m0.259s
sys 0m0.056s
```
Additional improvements compared to the legacy script:
- Consolidate per-(tid, uaddr) contention count, total_time, min_time,
and max_time into a single LockStats class instead of maintaining
three separate dictionaries.
- Validate that uaddr and op tracepoint attributes are present on
syscalls:sys_enter_futex samples rather than silently attributing
missing fields to uaddr=0, op=0 (FUTEX_WAIT).
- Add -i/--input CLI option support via argparse and full type
annotations.
Add a shell test (test_futex_contention_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>
|
|
Replace the legacy Perl script rwtop.pl with a standalone Python script
in tools/perf/python/rwtop.py using the perf Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Support both offline perf.data files (via perf.session) and live
recording (via LiveSession with --live), driving periodic interval
summaries from event timestamps rather than wall-clock SIGALRM timers
so both live and offline runs produce deterministic output.
- Convert unsigned 32-bit and 64-bit error return values
(0xfffff000..0xffffffff and >= 0x8000000000000000) to negative errnos
so failed read/write syscalls are recorded in the error table rather
than inflating bytes_read / bytes_written.
- Sanitize non-printable characters in /proc/<pid>/comm to prevent
terminal control sequence injection.
Add a shell test
(test_rwtop_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>
|
|
Replace the legacy Perl script rw-by-pid.pl with a standalone Python
script in tools/perf/python/rw-by-pid.py using the perf Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Convert unsigned 32-bit and 64-bit error return values
(0xfffff000..0xffffffff and >= 0x8000000000000000) to negative errnos
so failed read/write syscalls are recorded in the error table rather
than inflating bytes_read / bytes_written.
- Add argparse CLI support (-i/--input) and full type annotations.
Add a shell test
(test_rw_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>
|
|
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@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Port sctop.py from tools/perf/scripts/python/ to a standalone script in
tools/perf/python/ using an SCTopAnalyzer class structure.
Improvements compared to the legacy script:
- Support both offline perf.data analysis (via perf.session, advancing
display intervals deterministically using event timestamps) and live
monitoring (via LiveSession with automatic tracepoint fallback from
raw_syscalls:sys_enter to syscalls:sys_enter_*).
- Resolve architecture-aware syscall names via
perf.syscall_name(id, session.e_machine) without requiring
python-audit.
- Replace unsafe signal.SIGALRM dictionary mutation and os.popen("clear")
subshell spawning with a synchronized threading.Lock / threading.Event
timer and direct ANSI terminal escape sequences ('\x1b[2J\x1b[H').
Add a shell test (test_sctop_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>
|
|
Replace the legacy Perl script failed-syscalls.pl with a standalone
Python script in tools/perf/python/failed-syscalls.py using the perf
Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Support both syscalls:sys_exit_* and raw_syscalls:sys_exit events (the
legacy script only handled raw_syscalls::sys_exit).
- Use session.is_64_bit to distinguish 32-bit vs 64-bit unsigned error
return ranges (0xfffff000..0xffffffff vs >= 0xfffffffffffff000) so
valid 64-bit syscalls returning ~4GB values are not misclassified as
32-bit negative errors.
- Add argparse CLI support (-i/--input and optional comm filter) and
full type annotations.
Add a shell test
(test_failed_syscalls_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>
|
|
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>
|
|
Port tools/perf/scripts/python/syscall-counts-by-pid.py to a standalone
script in tools/perf/python/ using the perf module. Avoiding the
embedded interpreter and per-event dictionary overhead improves
execution speed by ~3.8x:
```
$ perf record -e raw_syscalls:sys_enter -a sleep 1
...
$ time perf script tools/perf/scripts/python/syscall-counts-by-pid.py perf
...
real 0m3.852s
user 0m3.512s
sys 0m0.336s
$ time python3 tools/perf/python/syscall-counts-by-pid.py perf
...
real 0m1.011s
user 0m0.963s
sys 0m0.048s
```
Additional improvements compared to the legacy script:
- Resolve architecture-specific syscall names via
perf.syscall_name(id, session.e_machine) instead of host python-audit
tables.
- Support both raw_syscalls:sys_enter and individual syscalls:sys_enter_*
tracepoints, and filter out invalid (> 0xffff or negative) syscall IDs.
- Support filtering by numeric PID as well as command name (comm), and
resolve process command names via session.find_thread(pid).
Add a shell test (test_syscall_counts_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>
|
|
Port tools/perf/scripts/python/syscall-counts.py to a standalone script
in tools/perf/python/ using the perf module. Avoiding the embedded
interpreter and per-event dictionary allocation overhead improves
execution speed by ~4x:
```
$ perf record -e raw_syscalls:sys_enter -a sleep 1
...
$ time perf script tools/perf/scripts/python/syscall-counts.py perf
...
real 0m3.887s
user 0m3.578s
sys 0m0.308s
$ time python3 tools/perf/python/syscall-counts.py perf
...
real 0m0.953s
user 0m0.905s
sys 0m0.048s
```
Additional improvements compared to the legacy script:
- Resolve syscall names using perf.syscall_name(id, session.e_machine)
instead of host python-audit / Util.py tables, enabling accurate
cross-architecture perf.data analysis without external dependencies.
- Support both raw_syscalls:sys_enter (sample.id) and individual
syscalls:sys_enter_* tracepoints (sample.__syscall_nr / sample.nr),
filtering out invalid/corrupt (> 0xffff or negative) syscall numbers.
- Add argparse CLI options (-i/--input and optional comm filter).
Add a shell test (test_syscall_counts_python.sh) to verify the
standalone script. The legacy script and its bin wrapper are retained
temporarily during the transition to maintain bisectability and are
removed once all scripts are migrated.
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>
|
|
Port event_analyzing_sample.py to a standalone script in
tools/perf/python/ using the perf module and standard library sqlite3
module.
Improvements compared to the legacy script:
- Encapsulate database state in a _DB container instead of mutating
module-level globals, and ensure temporary SQLite database files are
cleaned up on exit.
- Add argparse CLI options (-i/--input and -d/--db) while preserving
PerfEvent, PebsEvent, and PebsNHM binary raw_buf unpacking and
symbol/DSO histogram reporting.
- Remove Python 2 compatibility code and add type annotations.
Add a shell test (test_event_analyzing_sample_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>
|
|
Port gecko.py to a standalone script in tools/perf/python/ that uses
the perf module directly to convert perf.data profiles into Firefox
Gecko profile format.
Improvements compared to the legacy script:
- Encapsulate profiler state in GeckoCLI and CategoryData classes with
full type annotations, removing global variables.
- Harden the local HTTP server in _write_and_launch(): write the
temporary profile to an isolated tempfile.TemporaryDirectory() with a
randomized UUID filename instead of the current working directory,
bind HTTPServer exclusively to 127.0.0.1 on an OS-assigned ephemeral
port (0), restrict CORS Access-Control-Allow-Origin to
'https://profiler.firefox.com' instead of '*', and restrict HTTP GET
requests exclusively to the randomized profile filename (returning
HTTP 403 for directory listings and any other path).
- Add -i/--input and -e/--event CLI options via argparse.
Add a shell test (test_gecko_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>
|
|
Port flamegraph.py to a standalone script in tools/perf/python/ that
uses the perf module directly, avoiding intermediate dictionary
allocations for event fields.
Improvements compared to the legacy script:
- Add Subresource Integrity (integrity="sha256-...") and
crossorigin="anonymous" attributes to external CDN stylesheet and
script tags in MINIMAL_HTML.
- Upgrade CDN HTML template hash verification from weak MD5
(hashlib.md5) to cryptographic SHA-256 (hashlib.sha256).
- Escape '<', '>', and '&' ('\u003c', '\u003e', '\u0026') in embedded
JSON payloads (stacks_json and options_json) to prevent HTML script
injection / XSS when rendering untrusted symbol or command names.
- Skip invoking 'perf report --header-only' when the input is stdin
('-'), a FIFO pipe, or a character device (S_ISFIFO / S_ISCHR) so
non-seekable streams do not hang or fail.
Add a shell test (test_flamegraph_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>
|
|
Port stackcollapse.py from tools/perf/scripts/python/ to a standalone
script in tools/perf/python/ refactored into a StackCollapseAnalyzer
class.
Improvements compared to the legacy script:
- Traverse sample.callchain directly from perf.session without
allocating per-event dictionaries, and fall back to sample.symbol when
a sample has no callchain.
- Replace deprecated optparse with argparse, adding -i/--input alongside
--include-tid, --include-pid, --no-comm, --tidy-java, and --kernel.
- Handle BrokenPipeError cleanly when output is piped into downstream
tools (such as head or flamegraph.pl).
Add a shell test (test_stackcollapse_python.sh) using a CPU workload
(perf test -w noploop) 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>
|
|
Port mem-phys-addr.py to a standalone script in tools/perf/python/
using the perf.session API to read perf.data files and profile physical
memory access types against /proc/iomem.
Improvements compared to the legacy script:
- Parse the full indentation hierarchy of /proc/iomem into a parent-child
tree of frozen IomemEntry dataclasses (instead of only top-level
indent-0 ranges), resolving physical addresses to the most specific
sub-range (such as Kernel code/data/bss inside System RAM) and rolling
child counts up into parent totals.
- Support profiling multiple memory events in a single perf.data session
(keyed by evsel name) instead of assuming a single global event.
- Add argparse CLI options (-i/--input and --iomem to allow supplying an
offline /proc/iomem snapshot from a target system).
Add a shell test (test_mem_phys_addr_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>
|
|
Port stat-cpi.py from the legacy embedded scripting framework to a
standalone Python script in tools/perf/python/ to calculate Cycles Per
Instruction (CPI) per interval per CPU or thread.
Improvements compared to the legacy script:
- Support both perf.data file mode (via perf.session stat callbacks)
and live counter collection mode (using perf.parse_events,
evlist.open, and evsel.read across intervals), with automatic fallback
to user-space (:u) and self-process monitoring when perf_event_paranoid
restricts system-wide events (EACCES).
- Compute per-interval counter deltas (val, ena, run) keyed by raw event
name so cumulative PERF_RECORD_STAT snapshots and hybrid PMU events
(e.g. cpu_core/cycles/, cpu_atom/cycles/) are accumulated accurately,
and scale counts by time_enabled / time_running when multiplexed.
- Replace hard-coded CPU ([0, 1]) and thread ([0]) arrays with dynamic
CPU and thread discovery so arbitrary system topologies work
automatically.
- Add CLI option handling (-i, -I, -p) via argparse and type annotations
passing mypy and pylint.
Add a shell test (test_stat_cpi_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>
|
|
Clean up mypy type errors and pylint errors/warnings in
tools/perf/tests/shell/lib/ (attr.py, perf_json_output_lint.py, and
perf_metric_validation.py):
- Fix E0606 (possibly-used-before-assignment) in perf_metric_validation.py
by importing sys at module level.
- Add type annotations for stack, second_results, collectlist,
get_bounds(), and main() in perf_metric_validation.py.
- Avoid assigning -1 to list[int] expected_items in
perf_json_output_lint.py, rename shadowing variables, and remove
redundant lambdas.
- Remove unnecessary semicolons, use lazy logging arguments, specify
exception types and file encodings, and initialize module-level logger
in attr.py.
Also update tools/perf/tests/shell/lib/setup_python.sh to:
- Avoid x-prefix string comparisons.
- Export PYTHON and resolve PYTHONPATH and PERF_EXEC_PATH from
BASH_SOURCE[0], ../../../python (for nested test directories such as
coresight/), and the directory containing the perf binary so out-of-tree
builds and standalone perf python scripts work seamlessly.
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>
|
|
IBS events with exclude_{user,kernel} bits, as used for per-thread
recording when kernel samples are not allowed, are rejected on hardware
without the privilege filter, so per-thread 'perf mem record' fails on
AMD:
$ perf mem record -o /dev/null -- true
Failure to open event 'ibs_op/ldlat=0/u' on PMU 'ibs_op' which will be removed.
Kernel v6.14 added swfilt, a software privilege filter exposed as the
'swfilt' format term, making those events usable per-thread. Give the
ibs_op memory events extra tables with the term, selected in
perf_pmu__arch_init() when the PMU exposes it, keeping the names that
need system wide mode otherwise; the knowledge that IBS needs this
stays in the arch code.
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
