diff options
Diffstat (limited to 'tools/perf/tests/shell/lib')
| -rw-r--r-- | tools/perf/tests/shell/lib/attr.py | 470 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/coresight.sh | 2 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/perf_has_symbol.sh | 2 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/perf_json_output_lint.py | 26 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/perf_metric_validation.py | 251 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/probe_vfs_getname.sh | 27 | ||||
| -rw-r--r-- | tools/perf/tests/shell/lib/stat_output.sh | 27 |
7 files changed, 680 insertions, 125 deletions
diff --git a/tools/perf/tests/shell/lib/attr.py b/tools/perf/tests/shell/lib/attr.py new file mode 100644 index 000000000000..bfccc727d9b2 --- /dev/null +++ b/tools/perf/tests/shell/lib/attr.py @@ -0,0 +1,470 @@ +# SPDX-License-Identifier: GPL-2.0 + +import configparser +import os +import sys +import glob +import optparse +import platform +import tempfile +import logging +import re +import shutil +import subprocess + +def data_equal(a, b): + # Allow multiple values in assignment separated by '|' + a_list = a.split('|') + b_list = b.split('|') + + for a_item in a_list: + for b_item in b_list: + if (a_item == b_item): + return True + elif (a_item == '*') or (b_item == '*'): + return True + + return False + +class Fail(Exception): + def __init__(self, test, msg): + self.msg = msg + self.test = test + def getMsg(self): + return '\'%s\' - %s' % (self.test.path, self.msg) + +class Notest(Exception): + def __init__(self, test, arch): + self.arch = arch + self.test = test + def getMsg(self): + return '[%s] \'%s\'' % (self.arch, self.test.path) + +class Unsup(Exception): + def __init__(self, test): + self.test = test + def getMsg(self): + return '\'%s\'' % self.test.path + +class Event(dict): + terms = [ + 'cpu', + 'flags', + 'type', + 'size', + 'config', + 'sample_period', + 'sample_type', + 'read_format', + 'disabled', + 'inherit', + 'pinned', + 'exclusive', + 'exclude_user', + 'exclude_kernel', + 'exclude_hv', + 'exclude_idle', + 'mmap', + 'comm', + 'freq', + 'inherit_stat', + 'enable_on_exec', + 'task', + 'watermark', + 'precise_ip', + 'mmap_data', + 'sample_id_all', + 'exclude_host', + 'exclude_guest', + 'exclude_callchain_kernel', + 'exclude_callchain_user', + 'wakeup_events', + 'bp_type', + 'config1', + 'config2', + 'branch_sample_type', + 'sample_regs_user', + 'sample_stack_user', + ] + + def add(self, data): + for key, val in data: + log.debug(" %s = %s" % (key, val)) + self[key] = val + + def __init__(self, name, data, base): + log.debug(" Event %s" % name); + self.name = name; + self.group = '' + self.add(base) + self.add(data) + + def equal(self, other): + for t in Event.terms: + log.debug(" [%s] %s %s" % (t, self[t], other[t])); + if t not in self or t not in other: + return False + if not data_equal(self[t], other[t]): + return False + return True + + def optional(self): + if 'optional' in self and self['optional'] == '1': + return True + return False + + def diff(self, other): + for t in Event.terms: + if t not in self or t not in other: + continue + if not data_equal(self[t], other[t]): + log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) + +def parse_version(version): + if not version: + return None + return [int(v) for v in version.split(".")[0:2]] + +# Test file description needs to have following sections: +# [config] +# - just single instance in file +# - needs to specify: +# 'command' - perf command name +# 'args' - special command arguments +# 'ret' - Skip test if Perf doesn't exit with this value (0 by default) +# 'test_ret'- If set to 'true', fail test instead of skipping for 'ret' argument +# 'arch' - architecture specific test (optional) +# comma separated list, ! at the beginning +# negates it. +# 'auxv' - Truthy statement that is evaled in the scope of the auxv map. When false, +# the test is skipped. For example 'auxv["AT_HWCAP"] == 10'. (optional) +# 'kernel_since' - Inclusive kernel version from which the test will start running. Only the +# first two values are supported, for example "6.1" (optional) +# 'kernel_until' - Exclusive kernel version from which the test will stop running. (optional) +# [eventX:base] +# - one or multiple instances in file +# - expected values assignments +class Test(object): + def __init__(self, path, options): + parser = configparser.ConfigParser() + parser.read(path) + + log.warning("running '%s'" % path) + + self.path = path + self.test_dir = options.test_dir + self.perf = options.perf + self.command = parser.get('config', 'command') + self.args = parser.get('config', 'args') + + try: + self.ret = parser.get('config', 'ret') + except: + self.ret = 0 + + self.test_ret = parser.getboolean('config', 'test_ret', fallback=False) + + try: + self.arch = parser.get('config', 'arch') + log.warning("test limitation '%s'" % self.arch) + except: + self.arch = '' + + self.auxv = parser.get('config', 'auxv', fallback=None) + self.kernel_since = parse_version(parser.get('config', 'kernel_since', fallback=None)) + self.kernel_until = parse_version(parser.get('config', 'kernel_until', fallback=None)) + self.expect = {} + self.result = {} + log.debug(" loading expected events"); + self.load_events(path, self.expect) + + def is_event(self, name): + if name.find("event") == -1: + return False + else: + return True + + def skip_test_kernel_since(self): + if not self.kernel_since: + return False + return not self.kernel_since <= parse_version(platform.release()) + + def skip_test_kernel_until(self): + if not self.kernel_until: + return False + return not parse_version(platform.release()) < self.kernel_until + + def skip_test_auxv(self): + def new_auxv(a, pattern): + items = list(filter(None, pattern.split(a))) + # AT_HWCAP is hex but doesn't have a prefix, so special case it + if items[0] == "AT_HWCAP": + value = int(items[-1], 16) + else: + try: + value = int(items[-1], 0) + except: + value = items[-1] + return (items[0], value) + + if not self.auxv: + return False + auxv = subprocess.check_output("LD_SHOW_AUXV=1 sleep 0", shell=True) \ + .decode(sys.stdout.encoding) + pattern = re.compile(r"[: ]+") + auxv = dict([new_auxv(a, pattern) for a in auxv.splitlines()]) + return not eval(self.auxv) + + def skip_test_arch(self, myarch): + # If architecture not set always run test + if self.arch == '': + # log.warning("test for arch %s is ok" % myarch) + return False + + # Allow multiple values in assignment separated by ',' + arch_list = self.arch.split(',') + + # Handle negated list such as !s390x,ppc + if arch_list[0][0] == '!': + arch_list[0] = arch_list[0][1:] + log.warning("excluded architecture list %s" % arch_list) + for arch_item in arch_list: + # log.warning("test for %s arch is %s" % (arch_item, myarch)) + if arch_item == myarch: + return True + return False + + for arch_item in arch_list: + # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch)) + if arch_item == myarch: + return False + return True + + def restore_sample_rate(self, value=10000): + try: + # Check value of sample_rate + with open("/proc/sys/kernel/perf_event_max_sample_rate", "r") as fIn: + curr_value = fIn.readline() + # If too low restore to reasonable value + if not curr_value or int(curr_value) < int(value): + with open("/proc/sys/kernel/perf_event_max_sample_rate", "w") as fOut: + fOut.write(str(value)) + + except IOError as e: + log.warning("couldn't restore sample_rate value: I/O error %s" % e) + except ValueError as e: + log.warning("couldn't restore sample_rate value: Value error %s" % e) + except TypeError as e: + log.warning("couldn't restore sample_rate value: Type error %s" % e) + + def load_events(self, path, events): + parser_event = configparser.ConfigParser() + parser_event.read(path) + + # The event record section header contains 'event' word, + # optionaly followed by ':' allowing to load 'parent + # event' first as a base + for section in filter(self.is_event, parser_event.sections()): + + parser_items = parser_event.items(section); + base_items = {} + + # Read parent event if there's any + if (':' in section): + base = section[section.index(':') + 1:] + parser_base = configparser.ConfigParser() + parser_base.read(self.test_dir + '/' + base) + base_items = parser_base.items('event') + + e = Event(section, parser_items, base_items) + events[section] = e + + def run_cmd(self, tempdir): + junk1, junk2, junk3, junk4, myarch = (os.uname()) + + if self.skip_test_arch(myarch): + raise Notest(self, myarch) + + if self.skip_test_auxv(): + raise Notest(self, "auxv skip") + + if self.skip_test_kernel_since(): + raise Notest(self, "old kernel skip") + + if self.skip_test_kernel_until(): + raise Notest(self, "new kernel skip") + + self.restore_sample_rate() + cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, + self.perf, self.command, tempdir, self.args) + ret = os.WEXITSTATUS(os.system(cmd)) + + log.info(" '%s' ret '%s', expected '%s'" % (cmd, str(ret), str(self.ret))) + + if not data_equal(str(ret), str(self.ret)): + if self.test_ret: + raise Fail(self, "Perf exit code failure") + else: + raise Unsup(self) + + def compare(self, expect, result): + match = {} + + log.debug(" compare"); + + # For each expected event find all matching + # events in result. Fail if there's not any. + for exp_name, exp_event in expect.items(): + exp_list = [] + res_event = {} + log.debug(" matching [%s]" % exp_name) + for res_name, res_event in result.items(): + log.debug(" to [%s]" % res_name) + if (exp_event.equal(res_event)): + exp_list.append(res_name) + log.debug(" ->OK") + else: + log.debug(" ->FAIL"); + + log.debug(" match: [%s] matches %s" % (exp_name, str(exp_list))) + + # we did not any matching event - fail + if not exp_list: + if exp_event.optional(): + log.debug(" %s does not match, but is optional" % exp_name) + else: + if not res_event: + log.debug(" res_event is empty"); + else: + exp_event.diff(res_event) + raise Fail(self, 'match failure'); + + match[exp_name] = exp_list + + # For each defined group in the expected events + # check we match the same group in the result. + for exp_name, exp_event in expect.items(): + group = exp_event.group + + if (group == ''): + continue + + for res_name in match[exp_name]: + res_group = result[res_name].group + if res_group not in match[group]: + raise Fail(self, 'group failure') + + log.debug(" group: [%s] matches group leader %s" % + (exp_name, str(match[group]))) + + log.debug(" matched") + + def resolve_groups(self, events): + for name, event in events.items(): + group_fd = event['group_fd']; + if group_fd == '-1': + continue; + + for iname, ievent in events.items(): + if (ievent['fd'] == group_fd): + event.group = iname + log.debug('[%s] has group leader [%s]' % (name, iname)) + break; + + def run(self): + tempdir = tempfile.mkdtemp(); + + try: + # run the test script + self.run_cmd(tempdir); + + # load events expectation for the test + log.debug(" loading result events"); + for f in glob.glob(tempdir + '/event*'): + self.load_events(f, self.result); + + # resolve group_fd to event names + self.resolve_groups(self.expect); + self.resolve_groups(self.result); + + # do the expectation - results matching - both ways + self.compare(self.expect, self.result) + self.compare(self.result, self.expect) + + finally: + # cleanup + shutil.rmtree(tempdir) + + +def run_tests(options): + for f in glob.glob(options.test_dir + '/' + options.test): + try: + Test(f, options).run() + except Unsup as obj: + log.warning("unsupp %s" % obj.getMsg()) + except Notest as obj: + log.warning("skipped %s" % obj.getMsg()) + +def setup_log(verbose): + global log + level = logging.CRITICAL + + if verbose == 1: + level = logging.WARNING + if verbose == 2: + level = logging.INFO + if verbose >= 3: + level = logging.DEBUG + + log = logging.getLogger('test') + log.setLevel(level) + ch = logging.StreamHandler() + ch.setLevel(level) + formatter = logging.Formatter('%(message)s') + ch.setFormatter(formatter) + log.addHandler(ch) + +USAGE = '''%s [OPTIONS] + -d dir # tests dir + -p path # perf binary + -t test # single test + -v # verbose level +''' % sys.argv[0] + +def main(): + parser = optparse.OptionParser(usage=USAGE) + + parser.add_option("-t", "--test", + action="store", type="string", dest="test") + parser.add_option("-d", "--test-dir", + action="store", type="string", dest="test_dir") + parser.add_option("-p", "--perf", + action="store", type="string", dest="perf") + parser.add_option("-v", "--verbose", + default=0, action="count", dest="verbose") + + options, args = parser.parse_args() + if args: + parser.error('FAILED wrong arguments %s' % ' '.join(args)) + return -1 + + setup_log(options.verbose) + + if not options.test_dir: + print('FAILED no -d option specified') + sys.exit(-1) + + if not options.test: + options.test = 'test*' + + try: + run_tests(options) + + except Fail as obj: + print("FAILED %s" % obj.getMsg()) + sys.exit(-1) + + sys.exit(0) + +if __name__ == '__main__': + main() diff --git a/tools/perf/tests/shell/lib/coresight.sh b/tools/perf/tests/shell/lib/coresight.sh index 11ed2c25ed91..184d62e7e5bd 100644 --- a/tools/perf/tests/shell/lib/coresight.sh +++ b/tools/perf/tests/shell/lib/coresight.sh @@ -18,7 +18,7 @@ BIN="$DIR/$TEST" # If the test tool/binary does not exist and is executable then skip the test if ! test -x "$BIN"; then exit 2; fi # If CoreSight is not available, skip the test -perf list cs_etm | grep -q cs_etm || exit 2 +perf list pmu | grep -q cs_etm || exit 2 DATD="." # If the data dir env is set then make the data dir use that instead of ./ if test -n "$PERF_TEST_CORESIGHT_DATADIR"; then diff --git a/tools/perf/tests/shell/lib/perf_has_symbol.sh b/tools/perf/tests/shell/lib/perf_has_symbol.sh index 5d59c32ae3e7..561c93b75d77 100644 --- a/tools/perf/tests/shell/lib/perf_has_symbol.sh +++ b/tools/perf/tests/shell/lib/perf_has_symbol.sh @@ -3,7 +3,7 @@ perf_has_symbol() { - if perf test -vv "Symbols" 2>&1 | grep "[[:space:]]$1$"; then + if perf test -vv -F "Symbols" 2>&1 | grep "[[:space:]]$1$"; then echo "perf does have symbol '$1'" return 0 fi diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index ea55d5ea1ced..9e772a89ce38 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -15,9 +15,11 @@ ap.add_argument('--event', action='store_true') ap.add_argument('--per-core', action='store_true') ap.add_argument('--per-thread', action='store_true') ap.add_argument('--per-cache', action='store_true') +ap.add_argument('--per-cluster', action='store_true') ap.add_argument('--per-die', action='store_true') ap.add_argument('--per-node', action='store_true') ap.add_argument('--per-socket', action='store_true') +ap.add_argument('--metric-only', action='store_true') ap.add_argument('--file', type=argparse.FileType('r'), default=sys.stdin) args = ap.parse_args() @@ -49,31 +51,39 @@ def check_json_output(expected_items): 'cgroup': lambda x: True, 'cpu': lambda x: isint(x), 'cache': lambda x: True, + 'cluster': lambda x: True, 'die': lambda x: True, 'event': lambda x: True, 'event-runtime': lambda x: isfloat(x), 'interval': lambda x: isfloat(x), 'metric-unit': lambda x: True, 'metric-value': lambda x: isfloat(x), + 'metric-threshold': lambda x: x in ['unknown', 'good', 'less good', 'nearly bad', 'bad'], 'metricgroup': lambda x: True, 'node': lambda x: True, 'pcnt-running': lambda x: isfloat(x), 'socket': lambda x: True, 'thread': lambda x: True, 'unit': lambda x: True, + 'insn per cycle': lambda x: isfloat(x), + 'GHz': lambda x: True, # FIXME: it seems unintended for --metric-only } input = '[\n' + ','.join(Lines) + '\n]' for item in json.loads(input): if expected_items != -1: count = len(item) - if count != expected_items and count >= 1 and count <= 6 and 'metric-value' in item: + if count not in expected_items and count >= 1 and count <= 7 and 'metric-value' in item: # Events that generate >1 metric may have isolated metric # values and possibly other prefixes like interval, core, # aggregate-number, or event-runtime/pcnt-running from multiplexing. pass - elif count != expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: + elif count not in expected_items and count >= 1 and count <= 5 and 'metricgroup' in item: pass - elif count != expected_items: + elif count - 1 in expected_items and 'metric-threshold' in item: + pass + elif count in expected_items and 'insn per cycle' in item: + pass + elif count not in expected_items: raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' f' in \'{item}\'') for key, value in item.items(): @@ -85,11 +95,13 @@ def check_json_output(expected_items): try: if args.no_args or args.system_wide or args.event: - expected_items = 7 + expected_items = [5, 7] elif args.interval or args.per_thread or args.system_wide_no_aggr: - expected_items = 8 - elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cache: - expected_items = 9 + expected_items = [6, 8] + elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cluster or args.per_cache: + expected_items = [7, 9] + elif args.metric_only: + expected_items = [1, 2] else: # If no option is specified, don't check the number of items. expected_items = -1 diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py index 50a34a9cc040..dea8ef1977bf 100644 --- a/tools/perf/tests/shell/lib/perf_metric_validation.py +++ b/tools/perf/tests/shell/lib/perf_metric_validation.py @@ -1,4 +1,4 @@ -#SPDX-License-Identifier: GPL-2.0 +# SPDX-License-Identifier: GPL-2.0 import re import csv import json @@ -6,36 +6,63 @@ import argparse from pathlib import Path import subprocess + +class TestError: + def __init__(self, metric: list[str], wl: str, value: list[float], low: float, up=float('nan'), description=str()): + self.metric: list = metric # multiple metrics in relationship type tests + self.workloads = [wl] # multiple workloads possible + self.collectedValue: list = value + self.valueLowBound = low + self.valueUpBound = up + self.description = description + + def __repr__(self) -> str: + if len(self.metric) > 1: + return "\nMetric Relationship Error: \tThe collected value of metric {0}\n\ + \tis {1} in workload(s): {2} \n\ + \tbut expected value range is [{3}, {4}]\n\ + \tRelationship rule description: \'{5}\'".format(self.metric, self.collectedValue, self.workloads, + self.valueLowBound, self.valueUpBound, self.description) + elif len(self.collectedValue) == 0: + return "\nNo Metric Value Error: \tMetric {0} returns with no value \n\ + \tworkload(s): {1}".format(self.metric, self.workloads) + else: + return "\nWrong Metric Value Error: \tThe collected value of metric {0}\n\ + \tis {1} in workload(s): {2}\n\ + \tbut expected value range is [{3}, {4}]"\ + .format(self.metric, self.collectedValue, self.workloads, + self.valueLowBound, self.valueUpBound) + + class Validator: - def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', workload='true', metrics=''): + def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', + workload='true', metrics='', cputype='cpu'): self.rulefname = rulefname self.reportfname = reportfname self.rules = None - self.collectlist:str = metrics + self.collectlist: str = metrics self.metrics = self.__set_metrics(metrics) self.skiplist = set() self.tolerance = t + self.cputype = cputype self.workloads = [x for x in workload.split(",") if x] - self.wlidx = 0 # idx of current workloads - self.allresults = dict() # metric results of all workload - self.allignoremetrics = dict() # metrics with no results or negative results - self.allfailtests = dict() + self.wlidx = 0 # idx of current workloads + self.allresults = dict() # metric results of all workload self.alltotalcnt = dict() self.allpassedcnt = dict() - self.allerrlist = dict() - self.results = dict() # metric results of current workload + self.results = dict() # metric results of current workload # vars for test pass/failure statistics - self.ignoremetrics= set() # metrics with no results or negative results, neg result counts as a failed test - self.failtests = dict() + # metrics with no results or negative results, neg result counts failed tests + self.ignoremetrics = set() self.totalcnt = 0 self.passedcnt = 0 # vars for errors self.errlist = list() # vars for Rule Generator - self.pctgmetrics = set() # Percentage rule + self.pctgmetrics = set() # Percentage rule # vars for debug self.datafname = datafname @@ -69,10 +96,10 @@ class Validator: ensure_ascii=True, indent=4) - def get_results(self, idx:int = 0): - return self.results[idx] + def get_results(self, idx: int = 0): + return self.results.get(idx) - def get_bounds(self, lb, ub, error, alias={}, ridx:int = 0) -> list: + def get_bounds(self, lb, ub, error, alias={}, ridx: int = 0) -> list: """ Get bounds and tolerance from lb, ub, and error. If missing lb, use 0.0; missing ub, use float('inf); missing error, use self.tolerance. @@ -85,7 +112,7 @@ class Validator: tolerance, denormalized base on upper bound value """ # init ubv and lbv to invalid values - def get_bound_value (bound, initval, ridx): + def get_bound_value(bound, initval, ridx): val = initval if isinstance(bound, int) or isinstance(bound, float): val = bound @@ -113,10 +140,10 @@ class Validator: return lbv, ubv, denormerr - def get_value(self, name:str, ridx:int = 0) -> list: + def get_value(self, name: str, ridx: int = 0) -> list: """ Get value of the metric from self.results. - If result of this metric is not provided, the metric name will be added into self.ignoremetics and self.errlist. + If result of this metric is not provided, the metric name will be added into self.ignoremetics. All future test(s) on this metric will fail. @param name: name of the metric @@ -142,38 +169,43 @@ class Validator: Check if metrics value are non-negative. One metric is counted as one test. Failure: when metric value is negative or not provided. - Metrics with negative value will be added into the self.failtests['PositiveValueTest'] and self.ignoremetrics. + Metrics with negative value will be added into self.ignoremetrics. """ negmetric = dict() pcnt = 0 tcnt = 0 rerun = list() - for name, val in self.get_results().items(): + results = self.get_results() + if not results: + return + for name, val in results.items(): if val < 0: negmetric[name] = val rerun.append(name) else: pcnt += 1 tcnt += 1 + # The first round collect_perf() run these metrics with simple workload + # "true". We give metrics a second chance with a longer workload if less + # than 20 metrics failed positive test. if len(rerun) > 0 and len(rerun) < 20: second_results = dict() self.second_test(rerun, second_results) for name, val in second_results.items(): - if name not in negmetric: continue + if name not in negmetric: + continue if val >= 0: del negmetric[name] pcnt += 1 - self.failtests['PositiveValueTest']['Total Tests'] = tcnt - self.failtests['PositiveValueTest']['Passed Tests'] = pcnt if len(negmetric.keys()): self.ignoremetrics.update(negmetric.keys()) - negmessage = ["{0}(={1:.4f})".format(name, val) for name, val in negmetric.items()] - self.failtests['PositiveValueTest']['Failed Tests'].append({'NegativeValue': negmessage}) + self.errlist.extend( + [TestError([m], self.workloads[self.wlidx], negmetric[m], 0) for m in negmetric.keys()]) return - def evaluate_formula(self, formula:str, alias:dict, ridx:int = 0): + def evaluate_formula(self, formula: str, alias: dict, ridx: int = 0): """ Evaluate the value of formula. @@ -187,10 +219,11 @@ class Validator: sign = "+" f = str() - #TODO: support parenthesis? + # TODO: support parenthesis? for i in range(len(formula)): if i+1 == len(formula) or formula[i] in ('+', '-', '*', '/'): - s = alias[formula[b:i]] if i+1 < len(formula) else alias[formula[b:]] + s = alias[formula[b:i]] if i + \ + 1 < len(formula) else alias[formula[b:]] v = self.get_value(s, ridx) if not v: errs.append(s) @@ -228,49 +261,49 @@ class Validator: alias = dict() for m in rule['Metrics']: alias[m['Alias']] = m['Name'] - lbv, ubv, t = self.get_bounds(rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'], alias, ridx=rule['RuleIndex']) - val, f = self.evaluate_formula(rule['Formula'], alias, ridx=rule['RuleIndex']) + lbv, ubv, t = self.get_bounds( + rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'], alias, ridx=rule['RuleIndex']) + val, f = self.evaluate_formula( + rule['Formula'], alias, ridx=rule['RuleIndex']) + + lb = rule['RangeLower'] + ub = rule['RangeUpper'] + if isinstance(lb, str): + if lb in alias: + lb = alias[lb] + if isinstance(ub, str): + if ub in alias: + ub = alias[ub] + if val == -1: - self.failtests['RelationshipTest']['Failed Tests'].append({'RuleIndex': rule['RuleIndex'], 'Description':f}) + self.errlist.append(TestError([m['Name'] for m in rule['Metrics']], self.workloads[self.wlidx], [], + lb, ub, rule['Description'])) elif not self.check_bound(val, lbv, ubv, t): - lb = rule['RangeLower'] - ub = rule['RangeUpper'] - if isinstance(lb, str): - if lb in alias: - lb = alias[lb] - if isinstance(ub, str): - if ub in alias: - ub = alias[ub] - self.failtests['RelationshipTest']['Failed Tests'].append({'RuleIndex': rule['RuleIndex'], 'Formula':f, - 'RangeLower': lb, 'LowerBoundValue': self.get_value(lb), - 'RangeUpper': ub, 'UpperBoundValue':self.get_value(ub), - 'ErrorThreshold': t, 'CollectedValue': val}) + self.errlist.append(TestError([m['Name'] for m in rule['Metrics']], self.workloads[self.wlidx], [val], + lb, ub, rule['Description'])) else: self.passedcnt += 1 - self.failtests['RelationshipTest']['Passed Tests'] += 1 self.totalcnt += 1 - self.failtests['RelationshipTest']['Total Tests'] += 1 return - # Single Metric Test - def single_test(self, rule:dict): + def single_test(self, rule: dict): """ Validate if the metrics are in the required value range. eg. lower_bound <= metrics_value <= upper_bound One metric is counted as one test in this type of test. One rule may include one or more metrics. Failure: when the metric value not provided or the value is outside the bounds. - This test updates self.total_cnt and records failed tests in self.failtest['SingleMetricTest']. + This test updates self.total_cnt. @param rule: dict with metrics to validate and the value range requirement """ - lbv, ubv, t = self.get_bounds(rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold']) + lbv, ubv, t = self.get_bounds( + rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold']) metrics = rule['Metrics'] passcnt = 0 totalcnt = 0 - faillist = list() failures = dict() rerun = list() for m in metrics: @@ -286,25 +319,20 @@ class Validator: second_results = dict() self.second_test(rerun, second_results) for name, val in second_results.items(): - if name not in failures: continue + if name not in failures: + continue if self.check_bound(val, lbv, ubv, t): passcnt += 1 del failures[name] else: - failures[name] = val + failures[name] = [val] self.results[0][name] = val self.totalcnt += totalcnt self.passedcnt += passcnt - self.failtests['SingleMetricTest']['Total Tests'] += totalcnt - self.failtests['SingleMetricTest']['Passed Tests'] += passcnt if len(failures.keys()) != 0: - faillist = [{'MetricName':name, 'CollectedValue':val} for name, val in failures.items()] - self.failtests['SingleMetricTest']['Failed Tests'].append({'RuleIndex':rule['RuleIndex'], - 'RangeLower': rule['RangeLower'], - 'RangeUpper': rule['RangeUpper'], - 'ErrorThreshold':rule['ErrorThreshold'], - 'Failure':faillist}) + self.errlist.extend([TestError([name], self.workloads[self.wlidx], val, + rule['RangeLower'], rule['RangeUpper']) for name, val in failures.items()]) return @@ -312,19 +340,11 @@ class Validator: """ Create final report and write into a JSON file. """ - alldata = list() - for i in range(0, len(self.workloads)): - reportstas = {"Total Rule Count": self.alltotalcnt[i], "Passed Rule Count": self.allpassedcnt[i]} - data = {"Metric Validation Statistics": reportstas, "Tests in Category": self.allfailtests[i], - "Errors":self.allerrlist[i]} - alldata.append({"Workload": self.workloads[i], "Report": data}) - - json_str = json.dumps(alldata, indent=4) - print("Test validation finished. Final report: ") - print(json_str) + print(self.errlist) if self.debug: - allres = [{"Workload": self.workloads[i], "Results": self.allresults[i]} for i in range(0, len(self.workloads))] + allres = [{"Workload": self.workloads[i], "Results": self.allresults[i]} + for i in range(0, len(self.workloads))] self.json_dump(allres, self.datafname) def check_rule(self, testtype, metric_list): @@ -342,13 +362,13 @@ class Validator: return True # Start of Collector and Converter - def convert(self, data: list, metricvalues:dict): + def convert(self, data: list, metricvalues: dict): """ Convert collected metric data from the -j output to dict of {metric_name:value}. """ for json_string in data: try: - result =json.loads(json_string) + result = json.loads(json_string) if "metric-unit" in result and result["metric-unit"] != "(null)" and result["metric-unit"] != "": name = result["metric-unit"].split(" ")[1] if len(result["metric-unit"].split(" ")) > 1 \ else result["metric-unit"] @@ -359,15 +379,16 @@ class Validator: def _run_perf(self, metric, workload: str): tool = 'perf' - command = [tool, 'stat', '-j', '-M', f"{metric}", "-a"] + command = [tool, 'stat', '--cputype', self.cputype, '-j', '-M', f"{metric}", "-a"] wl = workload.split() command.extend(wl) print(" ".join(command)) cmd = subprocess.run(command, stderr=subprocess.PIPE, encoding='utf-8') data = [x+'}' for x in cmd.stderr.split('}\n') if x] + if data[0][0] != '{': + data[0] = data[0][data[0].find('{'):] return data - def collect_perf(self, workload: str): """ Collect metric data with "perf stat -M" on given workload with -a and -j. @@ -385,14 +406,18 @@ class Validator: if rule["TestType"] == "RelationshipTest": metrics = [m["Name"] for m in rule["Metrics"]] if not any(m not in collectlist[0] for m in metrics): - collectlist[rule["RuleIndex"]] = [",".join(list(set(metrics)))] + collectlist[rule["RuleIndex"]] = [ + ",".join(list(set(metrics)))] for idx, metrics in collectlist.items(): - if idx == 0: wl = "true" - else: wl = workload + if idx == 0: + wl = "true" + else: + wl = workload for metric in metrics: data = self._run_perf(metric, wl) - if idx not in self.results: self.results[idx] = dict() + if idx not in self.results: + self.results[idx] = dict() self.convert(data, self.results[idx]) return @@ -412,13 +437,16 @@ class Validator: 2) create metric name list """ command = ['perf', 'list', '-j', '--details', 'metrics'] - cmd = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, encoding='utf-8') + cmd = subprocess.run(command, stdout=subprocess.PIPE, + stderr=subprocess.PIPE, encoding='utf-8') try: data = json.loads(cmd.stdout) for m in data: if 'MetricName' not in m: print("Warning: no metric name") continue + if 'Unit' in m and m['Unit'] != self.cputype: + continue name = m['MetricName'].lower() self.metrics.add(name) if 'ScaleUnit' in m and (m['ScaleUnit'] == '1%' or m['ScaleUnit'] == '100%'): @@ -453,12 +481,12 @@ class Validator: rules = data['RelationshipRules'] self.skiplist = set([name.lower() for name in data['SkipList']]) self.rules = self.remove_unsupported_rules(rules) - pctgrule = {'RuleIndex':0, - 'TestType':'SingleMetricTest', - 'RangeLower':'0', + pctgrule = {'RuleIndex': 0, + 'TestType': 'SingleMetricTest', + 'RangeLower': '0', 'RangeUpper': '100', 'ErrorThreshold': self.tolerance, - 'Description':'Metrics in percent unit have value with in [0, 100]', + 'Description': 'Metrics in percent unit have value with in [0, 100]', 'Metrics': [{'Name': m.lower()} for m in self.pctgmetrics]} self.rules.append(pctgrule) @@ -469,8 +497,9 @@ class Validator: idx += 1 if self.debug: - #TODO: need to test and generate file name correctly - data = {'RelationshipRules':self.rules, 'SupportedMetrics': [{"MetricName": name} for name in self.metrics]} + # TODO: need to test and generate file name correctly + data = {'RelationshipRules': self.rules, 'SupportedMetrics': [ + {"MetricName": name} for name in self.metrics]} self.json_dump(data, self.fullrulefname) return @@ -482,20 +511,17 @@ class Validator: @param key: key to the dictionaries (index of self.workloads). ''' self.allresults[key] = self.results - self.allignoremetrics[key] = self.ignoremetrics - self.allfailtests[key] = self.failtests self.alltotalcnt[key] = self.totalcnt self.allpassedcnt[key] = self.passedcnt - self.allerrlist[key] = self.errlist - #Initialize data structures before data validation of each workload + # Initialize data structures before data validation of each workload def _init_data(self): - testtypes = ['PositiveValueTest', 'RelationshipTest', 'SingleMetricTest'] + testtypes = ['PositiveValueTest', + 'RelationshipTest', 'SingleMetricTest'] self.results = dict() - self.ignoremetrics= set() + self.ignoremetrics = set() self.errlist = list() - self.failtests = {k:{'Total Tests':0, 'Passed Tests':0, 'Failed Tests':[]} for k in testtypes} self.totalcnt = 0 self.passedcnt = 0 @@ -513,6 +539,9 @@ class Validator: ''' if not self.collectlist: self.parse_perf_metrics() + if not self.metrics: + print("No metric found for testing") + return 0 self.create_rules() for i in range(0, len(self.workloads)): self.wlidx = i @@ -525,33 +554,36 @@ class Validator: testtype = r['TestType'] if not self.check_rule(testtype, r['Metrics']): continue - if testtype == 'RelationshipTest': + if testtype == 'RelationshipTest': self.relationship_test(r) elif testtype == 'SingleMetricTest': self.single_test(r) else: print("Unsupported Test Type: ", testtype) - self.errlist.append("Unsupported Test Type from rule: " + r['RuleIndex']) - self._storewldata(i) print("Workload: ", self.workloads[i]) - print("Total metrics collected: ", self.failtests['PositiveValueTest']['Total Tests']) - print("Non-negative metric count: ", self.failtests['PositiveValueTest']['Passed Tests']) print("Total Test Count: ", self.totalcnt) print("Passed Test Count: ", self.passedcnt) - + self._storewldata(i) self.create_report() - return sum(self.alltotalcnt.values()) != sum(self.allpassedcnt.values()) + return len(self.errlist) > 0 # End of Class Validator def main() -> None: - parser = argparse.ArgumentParser(description="Launch metric value validation") - - parser.add_argument("-rule", help="Base validation rule file", required=True) - parser.add_argument("-output_dir", help="Path for validator output file, report file", required=True) - parser.add_argument("-debug", help="Debug run, save intermediate data to files", action="store_true", default=False) - parser.add_argument("-wl", help="Workload to run while data collection", default="true") + parser = argparse.ArgumentParser( + description="Launch metric value validation") + + parser.add_argument( + "-rule", help="Base validation rule file", required=True) + parser.add_argument( + "-output_dir", help="Path for validator output file, report file", required=True) + parser.add_argument("-debug", help="Debug run, save intermediate data to files", + action="store_true", default=False) + parser.add_argument( + "-wl", help="Workload to run while data collection", default="true") parser.add_argument("-m", help="Metric list to validate", default="") + parser.add_argument("-cputype", help="Only test metrics for the given CPU/PMU type", + default="cpu") args = parser.parse_args() outpath = Path(args.output_dir) reportf = Path.joinpath(outpath, 'perf_report.json') @@ -559,8 +591,8 @@ def main() -> None: datafile = Path.joinpath(outpath, 'perf_data.json') validator = Validator(args.rule, reportf, debug=args.debug, - datafname=datafile, fullrulefname=fullrule, workload=args.wl, - metrics=args.m) + datafname=datafile, fullrulefname=fullrule, workload=args.wl, + metrics=args.m, cputype=args.cputype) ret = validator.test() return ret @@ -569,6 +601,3 @@ def main() -> None: if __name__ == "__main__": import sys sys.exit(main()) - - - diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index bf4c1fb71c4b..58debce9ab42 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -13,9 +13,28 @@ cleanup_probe_vfs_getname() { add_probe_vfs_getname() { add_probe_verbose=$1 if [ $had_vfs_getname -eq 1 ] ; then - line=$(perf probe -L getname_flags 2>&1 | grep -E 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') + result_initname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+initname.*" + line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_initname_re" | sed -r "s/$result_initname_re/\1/") + + # Search the old regular expressions so that this will + # pass on older kernels as well. + if [ -z "$line" ] ; then + result_filename_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*" + line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_filename_re" | sed -r "s/$result_filename_re/\1/") + fi + + if [ -z "$line" ] ; then + result_aname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->aname = NULL;" + line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_aname_re" | sed -r "s/$result_aname_re/\1/") + fi + + if [ -z "$line" ] ; then + echo "Could not find probeable line" + return 2 + fi + perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" + perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" || return 1 fi } @@ -27,7 +46,7 @@ skip_if_no_debuginfo() { # check if perf is compiled with libtraceevent support skip_no_probe_record_support() { if [ $had_vfs_getname -eq 1 ] ; then - perf record --dry-run -e $1 2>&1 | grep "libtraceevent is necessary for tracepoint support" && return 2 - return 1 + perf check feature -q libtraceevent && return 1 + return 2 fi } diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh index 3cc158a64326..c2ec7881ec1d 100644 --- a/tools/perf/tests/shell/lib/stat_output.sh +++ b/tools/perf/tests/shell/lib/stat_output.sh @@ -79,7 +79,7 @@ check_per_thread() echo "[Skip] paranoid and not root" return fi - perf stat --per-thread -a $2 true + perf stat --per-thread -p $$ $2 true commachecker --per-thread echo "[Success]" } @@ -97,6 +97,18 @@ check_per_cache_instance() echo "[Success]" } +check_per_cluster() +{ + echo -n "Checking $1 output: per cluster " + if ParanoidAndNotRoot 0 + then + echo "[Skip] paranoid and not root" + return + fi + perf stat --per-cluster -a $2 true + echo "[Success]" +} + check_per_die() { echo -n "Checking $1 output: per die " @@ -136,6 +148,19 @@ check_per_socket() echo "[Success]" } +check_metric_only() +{ + echo -n "Checking $1 output: metric only " + if [ "$(uname -m)" = "s390x" ] && ! grep '^facilities' /proc/cpuinfo | grep -qw 67 + then + echo "[Skip] CPU-measurement counter facility not installed" + return + fi + perf stat --metric-only $2 -e instructions,cycles true + commachecker --metric-only + echo "[Success]" +} + # The perf stat options for per-socket, per-core, per-die # and -A ( no_aggr mode ) uses the info fetched from this # directory: "/sys/devices/system/cpu/cpu*/topology". For |