| Age | Commit message (Collapse) | Author |
|---|
|
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>
|
|
The grep to match cgroup name in metric output assumes no leading / on
the cgroup name, however, cgroups in /proc/self/cgroup may have a
leading /. Strip the / if it exists to avoid failures to match the
cgroup name in the perf stat output.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Exercise the function view without driving a terminal now that it has
a stdio path. Keep the existing datasym record/report coverage and make a
separate recording of the contended locks used by the futex hash benchmark.
Always check the function table headers, table replacement, missing-iaddr
diagnostic, and conflicting options. A machine can support c2c recording
without capturing a contended sample, so report a skip when the hierarchy
is empty rather than treating hardware sampling variance as a failure.
When samples are available, check generic row shapes for all three
hierarchy levels, their expanded fold signs, cacheline addresses, and the
absence of trailing whitespace in the table body.
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The workload path leaves err at 0 and returns, so the test exits 0 and is
reported as a pass even though nothing was recorded and neither report
invocation ran. The check_c2c_support() path above it already sets err=2.
Set err=2 there as well so a failing workload is reported as a skip.
Fixes: ac881007c4bf7be4 ("perf tests c2c: Add a basic c2c")
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Currently the leader sampling test looks for "cycles:" string to match
the event and retrieve the value before the event name. But it won't
work on hybrid systems as the event name is different like below.
$ perf script | grep -m 10 brstack
perf 3322152 1873980.978431: 625379 cpu_atom/cycles/: 558200cc40cf brstack_bench+0x31 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978431: 625379 cpu_atom/cycles/: 558200cc40cf brstack_bench+0x31 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978598: 612177 cpu_atom/cycles/: 558200cc4082 brstack_foo+0x17 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978598: 612177 cpu_atom/cycles/: 558200cc4082 brstack_foo+0x17 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978762: 591859 cpu_atom/cycles/: 558200cc403d brstack_bar+0x0 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978762: 591859 cpu_atom/cycles/: 558200cc403d brstack_bar+0x0 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978948: 628505 cpu_atom/cycles/: 558200cc403e brstack_bar+0x1 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.978948: 628505 cpu_atom/cycles/: 558200cc403e brstack_bar+0x1 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.979146: 669816 cpu_atom/cycles/: 558200cc40e5 brstack_bench+0x47 (/home/namhyung/project/linux/tools/perf/perf)
perf 3322152 1873980.979146: 669816 cpu_atom/cycles/: 558200cc40e5 brstack_bench+0x47 (/home/namhyung/project/linux/tools/perf/perf)
But we can control the output format of perf script using -F option. So
we knows where the period is in the output. To filter by symbol name,
"ip" and "sym" fields are required as well.
$ perf script -F period,ip,sym | grep -m 10 brstack
625379 558200cc40cf brstack_bench
625379 558200cc40cf brstack_bench
612177 558200cc4082 brstack_foo
612177 558200cc4082 brstack_foo
591859 558200cc403d brstack_bar
591859 558200cc403d brstack_bar
628505 558200cc403e brstack_bar
628505 558200cc403e brstack_bar
669816 558200cc40e5 brstack_bench
669816 558200cc40e5 brstack_bench
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
I noticed it failed for leader sampling tests on Broadwell. It's
because the period of groups members are a little bit different. Maybe
there's an hardware issue but anyway it's close enough to treat them as
same. I printed the value like below.
$ perf test record
...
prev: 462507, curr: 462506
prev: 494783, curr: 494782
prev: 454350, curr: 454349
prev: 502782, curr: 502781
prev: 566693, curr: 566692
prev: 606558, curr: 606557
prev: 559770, curr: 559769
prev: 595737, curr: 595736
prev: 643386, curr: 643385
prev: 663672, curr: 663671
prev: 620622, curr: 620621
prev: 650419, curr: 650418
Leader sampling [Failed inconsistent cycles count]
Let's update the logic to compare values to allow 1% of errors.
Also I think it should compare only if sees the non-leader samples so
split the check of (($index % 2)).
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
'perf record' with multithreads would create a data directory instead of
a file. But the cleanup and retry logic expect a file and try to delete
them with 'rm -f' which would fail. Add '-r' flag to remove
directories.
rm: cannot remove '/tmp/__perf_test.perf.data.ZVHTw.old': Is a directory
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The minimum required shellcheck version treats paths with leading
variables as starting from the script's current directory, so shellcheck
is able to source all of these files without needing the extra
directives:
v0.7.2 - 2021-04-19
Changed
* SC1090: A leading $x/ or $(x)/ is now treated as ./ when locating files
Remove them to avoid future copy pasting and confusion that they are
required. Because the paths weren't actually followed, they didn't have
to be accurate and accepted any string to silence the warning.
Signed-off-by: James Clark <james.clark@linaro.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a "Hybrid event merging" test that checks evlist__can_merge_hybrid()
and evlist__merge_hybrid() directly, covering the events a wildcard
expanded to over two core PMUs, the same over three, and events that
must not be merged.
Add a report_hybrid_merge.sh shell test that records and then reports
with --hybrid-merge, and extend top.sh to cover perf top with it.
Signed-off-by: Ian Rogers <irogers@google.com>
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The test's only guard matches "failed: no PMU supports the memory
events", but a PMU that has memory events and refuses them per-thread,
such as AMD IBS on kernels without the swfilt filter, falls through:
the script runs under 'set -e' and the bare 'perf mem record' aborts it
through the EXIT trap, reporting a signal that never happened and
turning "this PMU cannot record these events" into a test failure.
Skip when a trivial per-thread 'perf mem record' fails, and put the
record and annotate calls in the condition of an 'if', where 'set -e'
leaves them alone, so the remaining cases report their own failures
instead of the first one aborting the run.
Fixes: f60a5c22967b ("perf tests: Test annotate with data type profiling and rust")
Acked-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Validate that SIMD registers (XMM/YMM/ZMM/OPMASK on x86) can be sampled
correctly with hardware support.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Validate that eGPRs (extended general purpose registers) and SSP
(shadow stack pointer) registers can be sampled correctly on x86
platforms.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Cleanup function was removed by writing to /dev/null rather than
temporary files. The exit path still had a call.
Fixes: 44f6b44027910eb9 ("perf test: Fix hybrid testing of event fallback test")
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The waiting helpers implement timeouts using:
date +%s%1N
This relies on GNU coreutils date truncating %N to the specified width,
so %1N yields tenths of a second.
Rust coreutils (uutils) interprets the width differently and does not
truncate the nanoseconds field. Consequently "date +%1N" returns all
nine nanosecond digits, causing the elapsed-time calculation to be done
in nanoseconds while timeout values remain in tenths of a second.
As a result, timeout comparisons succeed immediately and the waiting
helpers time out on their first iteration. This causes
test_intel_pt.sh to fail on systems using uutils "date".
Avoid implementation-specific date formatting entirely. Instead, wait
for 100 ms on each iteration and count the timeout down. Besides fixing
the portability issue, this removes the busy-waiting behaviour in
wait_for_perf_to_start(), which could otherwise consume CPU while
waiting for perf record to start.
Since the timeout is now based on repeated sleeps, it is only
approximate. Update the comments accordingly. Also make is_running()
wait for exactly the documented number of tenths by changing its timeout
test from -gt to the new logic, and quote tm_out in the modified code.
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
The test case 'perf stat tests' fails on s390 z/VM machines. The
root cause is the unsupported CPU measurement facility on z/VM.
Therefore the events cycles and instructions do not exist and
are unsupported. This cause the subtest
Hide zero events stat test
to fail.
Output before:
# perf test 116
116: perf stat tests : FAILED!
=== Test Summary ===
Passed main tests : 0
Passed subtests : 0
Skipped tests : 0
Failed tests : 1
List of failed tests:
116: perf stat tests
#
Output after:
# ./perf test 116
116: perf stat tests : Ok
=== Test Summary ===
Passed main tests : 1
Passed subtests : 0
Skipped tests : 0
Failed tests : 0
#
Fixes: 64724095a33fbee8 ("perf stat: Add --hide-zero-events option to suppress zero-count events")
Reviewed-by: Aaron Tomlin <atomlin@atomlin.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Aaron Tomlin <atomlin@atomlin.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a test case to check if --stdio weight annotation works
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Assisted-by: omp:GPT-5.6-Luna
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Add a dedicated shell test script, trace_ksym_beautifier.sh, to verify
that 'perf trace' properly symbolises kernel virtual addresses (e.g.
call_site in kmem:kmalloc) and function pointer fields (e.g. function in
timer:hrtimer_start) using the kernel symbol beautifier (SCA_KSYM).
Committer testing:
root@number:~# perf test "kernel sym"
145: perf trace kernel symbol beautifier tests : Ok
=== Test Summary ===
Passed main tests : 1
Passed subtests : 0
Skipped tests : 0
Failed tests : 0
root@number:~# perf test -vv "kernel sym"
145: perf trace kernel symbol beautifier tests:
---- start ----
test child forked, pid 920749
Testing perf trace kernel symbol beautifier (call_site)
Testing perf trace kernel symbol beautifier (function pointer)
---- end(0) ----
145: perf trace kernel symbol beautifier tests : Ok
=== Test Summary ===
Passed main tests : 1
Passed subtests : 0
Skipped tests : 0
Failed tests : 0
root@number:~# perf test -vvv "kernel sym"
145: perf trace kernel symbol beautifier tests:
---- start ----
test child forked, pid 920784
Testing perf trace kernel symbol beautifier (call_site)
Testing perf trace kernel symbol beautifier (function pointer)
---- end(0) ----
145: perf trace kernel symbol beautifier tests : Ok
=== Test Summary ===
Passed main tests : 1
Passed subtests : 0
Skipped tests : 0
Failed tests : 0
root@number:~#
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
While 'perf sched latency' reports task runtime and delay statistics
(average and maximum delay), it does not provide a visual representation
of how task wait times are distributed across latency ranges between
snapshots (start and finish of the analysis window).
The --histogram option collects CPU wait latencies (time between when
a task becomes runnable and when it gets scheduled onto a CPU) into 22
latency buckets, displaying an ASCII bar chart distribution.
The --hist-mode option configures the bucketing scheme:
- log (default). Logarithmic latency buckets ranging from
sub-microsecond (< 1 us) up to >= 1.05 seconds
- linear. Equal-width linear latency buckets
(i.e., 100 us steps up to >= 2.1 ms)
The --time option allows filtering trace event processing to a
specific time interval [start,stop].
Example histogram output excerpt:
❯ sudo perf sched latency --histogram --CPU 0
CPU Wait Latency Distribution Histogram (between snapshots) (total samples: 36114)
-------------------------------------------------------------------
Latency Range | Count | Pct | Histogram Graph
-------------------------------------------------------------------
< 1 us | 17 | 0.0% | #
2 - 4 us | 673 | 1.9% | #
4 - 8 us | 6237 | 17.3% | ######
8 - 16 us | 3224 | 8.9% | ###
16 - 32 us | 1388 | 3.8% | #
32 - 64 us | 709 | 2.0% | #
64 - 128 us | 690 | 1.9% | #
128 - 256 us | 789 | 2.2% | #
256 - 512 us | 541 | 1.5% | #
512 - 1024 us | 2256 | 6.2% | ##
1 - 2 ms | 3577 | 9.9% | ###
2 - 4 ms | 13259 | 36.7% | ##############
4 - 8 ms | 2523 | 7.0% | ##
8 - 16 ms | 222 | 0.6% | #
16 - 32 ms | 10 | 0.0% | #
>= 1.05 s | 3 | 0.0% | #
-------------------------------------------------------------------
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
The libdw callback API has two levels: dwfl_getthread_frames() first finds
the requested thread using the next_thread() or get_thread() callback and
then walks its stack.
Since perf only has a snapshot of the stack of a single thread, it
provides a stubbed-out API that always returns the pid the Dwfl was
attached with (i.e. whatever was passed to dwfl_attach_state()), rather
than the actual sampled thread's TID.
Commit 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF
after every unwind") changed libdw unwinding from recreating the Dwfl
object for each sample to caching it in struct maps, which is shared by
every thread in the process. It left next_thread() unchanged.
Since the pid passed to dwfl_attach_state() is only set at creation, only
the thread of the first sample is ever found. As a result,
dwfl_getthread_frames() fails with ESRCH when asked to unwind a sample
from another thread.
Make next_thread() return the current sample's TID, provide get_thread()
so libdw can find it directly, and pass the process PID expected by
dwfl_attach_state(). This allows libdw to unwind samples from every thread
in a multi-threaded process.
Add a shell regression test that records a four-thread workload and
verifies that libdw recovers the worker callchain for every worker TID.
Fixes: 6b2658b3f36a ("perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind")
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Alessio Podda <aleph.pi.gh@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
When monitoring a large number of events (e.g., with wildcards such as
--event 'syscalls:sys_enter_*'), many matched events will return a count
of zero. This clutters the output, making it difficult to spot the
active events.
Add a new option --hide-zero-events to suppress printing events that
have a count of zero.
To prevent formatting and diagnostic issues, the zero-skipping logic
implements the following rules:
1. In metric-only mode (i.e., --metric-only), columns must remain
aligned in the output grid. We evaluate config->metric_only first
to avoid skipping zero-valued columns, preventing values from
shifting left and aligning under incorrect headers
2. For explicitly requested events, we ensure they are not silently
hidden if they are unsupported. We only hide a zero-count event
if counter->supported is true, ensuring that unsupported explicit
events still report "<not supported>"
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
To simply check the number of output lines with and without the option.
Before this series, it failed like below:
$ perf test -v 125
125: perf stat --bpf-counters --for-each-cgroup test:
---- start ----
test child forked, pid 1941516
Normal output has 22 lines, but it now has 54
---- end(-1) ----
125: perf stat --bpf-counters --for-each-cgroup test : FAILED!
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
With Zstd compression enabled ('perf record -z'), a single mmap push
whose compressed output exceeds the maximum record size makes
zstd_compress_stream_to_records() emit several PERF_RECORD_COMPRESSED2
records back to back. record__pushfn() however rewrote only the first
record's header to describe the whole blob as one record:
event->data_size = compressed - sizeof(struct perf_record_compressed2);
event->header.size = PERF_ALIGN(compressed, sizeof(u64));
padding = event->header.size - compressed;
...
record__write(rec, map, &pad, padding);
perf_event_header::size is a __u16, so once the compressed blob no
longer fits in it the header.size assignment truncates and 'padding'
(size_t) underflows. write() is then handed that bogus length and fails
with EFAULT, aborting the recording:
failed to write perf data, error: Bad address
The bytes that did reach the file are mis-framed, so reading it back
cannot be decompressed.
This is easy to hit with a high event rate and a large buffer, e.g.:
perf record -z -F max -m 32M --per-thread -- perf test -w thloop 5 1
The single-record fixup is wrong by construction: because header.size is
16 bits a compressed record cannot exceed 64KB, so the compressor must
split a push into a chain of records, and the session reader already
consumes them as such.
Frame each record where it is produced instead: make
process_comp_header() set the per-record data_size, 8-byte-align
header.size and zero the trailing padding, and let record__pushfn()
write the resulting blob, as the AIO path already does. Reduce
max_record_size by sizeof(u64) so the per-record alignment padding
cannot push header.size past its u16 field. process_comp_header()
returns -1 when that padding would not fit the space left in 'dst', so
the compressor stops instead of overrunning the output buffer.
There is no on-disk format change; a perf.data written by the fixed tool
is still read by existing perf.
Fixes: 208c0e168344 ("perf record: Add 8-byte aligned event type PERF_RECORD_COMPRESSED2")
Reported-by: Farid Zakaria <fmzakari@meta.com>
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
Commit ae42a2a2a3ae ("perf tests: Speed up lock contention analysis shell test")
in linux-next heavily optimized the test runtimes by switching the workload from
the default of 10 process groups down to 1 (`perf bench sched messaging -g 1`).
However, this change inadvertently dropped the original `-p` flag, causing the
benchmark to default to `socketpair()` instead of `pipe()`. While `socketpair()`
still generates some lock events on x86, it fails to trigger enough samples on
architectures like s390, causing the test suite to fail due to lack of captured
data.
Restore the omitted `-p` pipe flag. The test retains the massive speedups
achieved through the `-g 1` scaling, while producing a massive density of lock
events across all architectures to fully satisfy the BPF trace filtering logic.
Fixes: ae42a2a2a3ae ("perf tests: Speed up lock contention analysis shell test")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
Specifying --field-separator option is stating you want CSV output.
Passing both --field-separator and --json-output is then stating
you want output to be in CSV and JSON format at same time.
Currently this combination is not rejected, and the outcome
is a malformed combination of CSV and JSON output.
This is because of inconsistencies in various printing functions,
some of them have if-else chains that start with
"Should I print JSON?", and some start with "Should I print CSV?".
Example of current output:
$ tools/perf/perf stat -x , -j -e cpu-migrations true
{"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 474817, "pcnt-running" : 100.00,,
Instead reject the option combination,
with a helpful error message and non-zero exit code.
Example of new output:
$ tools/perf/perf stat -x , -j true
cannot use both --field-separator and --json-output
Usage: perf stat [<options>] [<command>]
-x, --field-separator <separator>
print counts with custom separator
-j, --json-output print counts in JSON format
Signed-off-by: Ivan Lazaric <ivan.lazaric1@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
Add auto counter reload sampling test to verify that the intended event
records can be captured and the self-reloaded events won't generate any
records.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
Add a CoreSight shell test for synthesized callchains.
The test uses the new callchain workload to generate trace and decodes
it with synthesis callchain. It then verifies that the instruction
samples show the expected callchain push and pop.
Use control FIFOs so tracing starts only around the workload, which
keeps the trace data small. The test is limited to with the cs_etm
event available and root permission.
After:
perf test 138 -vvv
138: CoreSight synthesized callchain:
---- start ----
test child forked, pid 35581
Callchain flow matched:
l1=4642868 l2=4642880 l3=4642895 l4=4642919 l5=4670494 l6=4670500 l7=4670520
---- end(0) ----
138: CoreSight synthesized callchain : Ok
Assisted-by: Codex:GPT-5.5
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
The itrace 'c' and 'r' options request synthesized branch events for
calls and returns only. For perf script the default itrace options are
"--itrace=ce", so CS ETM should emit call branches and error events by
default.
CS ETM currently synthesizes a branch sample for every decoded taken
branch whenever branch synthesis is enabled. This produces redundant
jump and conditional branch samples.
Add a branch filter derived from the itrace calls and returns options.
When neither option is set, keep the existing behavior and synthesize all
branch samples. When calls or returns are requested, emit only branch
samples whose flags match the selected branch type, while preserving trace
begin/end markers.
Also update test_arm_coresight_disasm.sh and arm-cs-trace-disasm.py
to use the --itrace=b option for generating branch samples.
Before:
perf script -F,+flags
callchain_test 6114 [005] 331519.825214: 1 branches: tr strt jmp 0 [unknown] ([unknown]) => ffff8000803a3a68 perf_report_aux_output_id+0x50 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000803a3a74 perf_report_aux_output_id+0x5c ([kernel.kallsyms]) => ffff8000817f4d88 memset+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jmp ffff8000817f4d8c memset+0x4 ([kernel.kallsyms]) => ffff8000817f4c00 __pi_memset_generic+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4c1c __pi_memset_generic+0x1c ([kernel.kallsyms]) => ffff8000817f4c44 __pi_memset_generic+0x44 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4c4c __pi_memset_generic+0x4c ([kernel.kallsyms]) => ffff8000817f4c5c __pi_memset_generic+0x5c ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4c5c __pi_memset_generic+0x5c ([kernel.kallsyms]) => ffff8000817f4cf0 __pi_memset_generic+0xf0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4d30 __pi_memset_generic+0x130 ([kernel.kallsyms]) => ffff8000817f4d68 __pi_memset_generic+0x168 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4d78 __pi_memset_generic+0x178 ([kernel.kallsyms]) => ffff8000817f4d6c __pi_memset_generic+0x16c ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4d78 __pi_memset_generic+0x178 ([kernel.kallsyms]) => ffff8000817f4d6c __pi_memset_generic+0x16c ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000817f4d78 __pi_memset_generic+0x178 ([kernel.kallsyms]) => ffff8000817f4d6c __pi_memset_generic+0x16c ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: return ffff8000817f4d84 __pi_memset_generic+0x184 ([kernel.kallsyms]) => ffff8000803a3a78 perf_report_aux_output_id+0x60 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: jcc ffff8000803a3a98 perf_report_aux_output_id+0x80 ([kernel.kallsyms]) => ffff8000803a3b04 perf_report_aux_output_id+0xec ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000803a3b1c perf_report_aux_output_id+0x104 ([kernel.kallsyms]) => ffff8000803a38f8 __perf_event_header__init_id+0x0 ([kernel.kallsyms])
After:
callchain_test 6114 [005] 331519.825214: 1 branches: tr strt jmp 0 [unknown] ([unknown]) => ffff8000803a3a68 perf_report_aux_output_id+0x50 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000803a3a74 perf_report_aux_output_id+0x5c ([kernel.kallsyms]) => ffff8000817f4d88 memset+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000803a3b1c perf_report_aux_output_id+0x104 ([kernel.kallsyms]) => ffff8000803a38f8 __perf_event_header__init_id+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000803a39c0 __perf_event_header__init_id+0xc8 ([kernel.kallsyms]) => ffff800080105258 __task_pid_nr_ns+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff80008010528c __task_pid_nr_ns+0x34 ([kernel.kallsyms]) => ffff8000801d5610 __rcu_read_lock+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000801052b0 __task_pid_nr_ns+0x58 ([kernel.kallsyms]) => ffff800080192078 lock_acquire+0x0 ([kernel.kallsyms])
callchain_test 6114 [005] 331519.825214: 1 branches: call ffff8000801923f4 lock_acquire+0x37c ([kernel.kallsyms]) => ffff8000801d6da0 rcu_is_watching+0x0 ([kernel.kallsyms])
Fixes: b12235b113cf ("perf tools: Add mechanic to synthesise CoreSight trace packets")
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
It can now pass command line arguments to perf kvm record. Let's pass
'sleep 1' directly and see it doesn't fail.
$ sudo perf test -vv kvm
96: perf kvm tests:
---- start ----
test child forked, pid 3686726
Starting qemu-system-x86_64...
Testing perf kvm stat
Recording kvm events for pid 3686746 (duration 1s)...
perf kvm stat test [Success]
Testing perf kvm record/report
Recording kvm profile for pid 3686746 (duration 1s)...
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.576 MB /tmp/__perf_kvm_test.perf.data.0HgX6 (4009 samples) ]
perf kvm record/report test [Success]
Testing perf kvm buildid-list
perf kvm buildid-list test [Success]
Testing perf kvm stat live
perf kvm stat live test [Success]
Testing perf kvm record default event with command line
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB /dev/null ]
perf kvm record default event [Success]
---- end(0) ----
96: perf kvm tests : Ok
=== Test Summary ===
Passed main tests : 1
Passed subtests : 0
Skipped tests : 0
Failed tests : 0
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
Optimize the execution of the metric validation and metric listing shell
test suites:
1. `stat_metrics_values.sh`:
The Python metric validator runs the `perf bench futex hash` workload
for each validated metric relationship. Reduce the benchmark runtime
limit from `-r 2` (2 seconds) to `-r 1` (1 second). This cuts the
workload duration in half while still generating sufficient PMU events
to satisfy non-zero threshold metric validations.
2. `stat_all_metrics.sh`:
The metric checking test runs `perf stat` sequentially across all
433+ listed metrics. Change the default workload for system-wide runs
from `sleep 0.01` to `true`. This avoids the 10ms sleep delay on each
sequential metric invocation, saving over 4 seconds of total wall
time during full test suite runs.
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
The lock contention analysis test suite (`lock_contention.sh`) performs a
series of 13 separate profiling checks to verify various aggregation and
filtering parameters of `perf lock contention`. Each of these checks runs
the `perf bench sched messaging` messaging benchmark as its workload.
By default, `sched messaging` runs 10 groups of 40 processes (400
processes total) generating substantial task scheduling, context
switching, and IPC message passing. When traced system-wide for lock
events, the tracing overhead (handling millions of lock acquisitions and
releases) slows execution down significantly, causing the test suite to
take over 80 seconds.
Optimize this by introducing a scaled-down messaging benchmark workload:
`perf bench sched messaging -g 1 -p`. Running 1 group (40 processes) takes
only 0.01 seconds natively (instead of 0.08 seconds), drastically reduces
the sheer volume of lock acquire/release trace events, and reduces CPU
context switching during tracing while still generating sufficient lock
events to fully exercise the BPF/record filters.
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
|
The off-cpu profiling test suite runs multiple recording commands with a
default workload of `sleep 1` to test the off-cpu threshold configurations
(specifically, above 999ms and below 1200ms). This adds a mandatory 3.0
seconds of sleep overhead.
Optimize this by scaling down the thresholds and workload durations by a
factor of 10:
- Use `sleep 0.1` as the workload duration.
- Change the above-threshold test to use `--off-cpu-thresh 50` and `sleep
0.1`.
- Change the below-threshold test to use `--off-cpu-thresh 500` and `sleep
0.1`.
- Update the awk period check in the above-threshold test to look for a
period greater than 50,000,000 ns (50ms) instead of 999,000,000 ns
(999ms).
This reduces raw test sleep overhead from 3.0s down to 0.3s, yielding a
~2.7 second speedup for this test.
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
|
