Files
linux/tools/perf/tests/shell/record.sh
Namhyung Kim 3662f82f16 perf test: Speed up some tests using perf list
On my system, perf list is very slow to print the whole events.  I think
there's a performance issue in SDT and uprobes event listing.  I noticed
this issue while running perf test on x86 but it takes long to check
some CoreSight event which should be skipped quickly.

Anyway, some test uses perf list to check whether the required event is
available before running the test.  The perf list command can take an
argument to specify event class or (glob) pattern.  But glob pattern is
only to suppress output for unmatched ones after checking all events.

In this case, specifying event class is better to reduce the number of
events it checks and to avoid buggy subsystems entirely.

No functional changes intended.

Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20241016065654.269994-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 09:55:58 -07:00

293 lines
7.5 KiB
Bash
Executable File

#!/bin/bash
# perf record tests
# SPDX-License-Identifier: GPL-2.0
set -e
shelldir=$(dirname "$0")
# shellcheck source=lib/waiting.sh
. "${shelldir}"/lib/waiting.sh
# shellcheck source=lib/perf_has_symbol.sh
. "${shelldir}"/lib/perf_has_symbol.sh
testsym="test_loop"
skip_test_missing_symbol ${testsym}
err=0
perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
script_output=$(mktemp /tmp/__perf_test.perf.data.XXXXX.script)
testprog="perf test -w thloop"
cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
br_cntr_file="/caps/branch_counter_nr"
br_cntr_output="branch stack counters"
br_cntr_script_output="br_cntr: A"
default_fd_limit=$(ulimit -Sn)
# With option --threads=cpu the number of open file descriptors should be
# equal to sum of: nmb_cpus * nmb_events (2+dummy),
# nmb_threads for perf.data.n (equal to nmb_cpus) and
# 2*nmb_cpus of pipes = 4*nmb_cpus (each pipe has 2 ends)
# All together it needs 8*nmb_cpus file descriptors plus some are also used
# outside of testing, thus raising the limit to 16*nmb_cpus
min_fd_limit=$(($(getconf _NPROCESSORS_ONLN) * 16))
cleanup() {
rm -rf "${perfdata}"
rm -rf "${perfdata}".old
trap - EXIT TERM INT
}
trap_cleanup() {
cleanup
exit 1
}
trap trap_cleanup EXIT TERM INT
test_per_thread() {
echo "Basic --per-thread mode test"
if ! perf record -o /dev/null --quiet ${testprog} 2> /dev/null
then
echo "Per-thread record [Skipped event not supported]"
return
fi
if ! perf record --per-thread -o "${perfdata}" ${testprog} 2> /dev/null
then
echo "Per-thread record [Failed record]"
err=1
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "Per-thread record [Failed missing output]"
err=1
return
fi
# run the test program in background (for 30 seconds)
${testprog} 30 &
TESTPID=$!
rm -f "${perfdata}"
wait_for_threads ${TESTPID} 2
perf record -p "${TESTPID}" --per-thread -o "${perfdata}" sleep 1 2> /dev/null
kill ${TESTPID}
if [ ! -e "${perfdata}" ]
then
echo "Per-thread record [Failed record -p]"
err=1
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "Per-thread record [Failed -p missing output]"
err=1
return
fi
echo "Basic --per-thread mode test [Success]"
}
test_register_capture() {
echo "Register capture test"
if ! perf list pmu | grep -q 'br_inst_retired.near_call'
then
echo "Register capture test [Skipped missing event]"
return
fi
if ! perf record --intr-regs=\? 2>&1 | grep -q 'available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15'
then
echo "Register capture test [Skipped missing registers]"
return
fi
if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call \
-c 1000 --per-thread ${testprog} 2> /dev/null \
| perf script -F ip,sym,iregs -i - 2> /dev/null \
| grep -q "DI:"
then
echo "Register capture test [Failed missing output]"
err=1
return
fi
echo "Register capture test [Success]"
}
test_system_wide() {
echo "Basic --system-wide mode test"
if ! perf record -aB --synth=no -o "${perfdata}" ${testprog} 2> /dev/null
then
echo "System-wide record [Skipped not supported]"
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "System-wide record [Failed missing output]"
err=1
return
fi
if ! perf record -aB --synth=no -e cpu-clock,cs --threads=cpu \
-o "${perfdata}" ${testprog} 2> /dev/null
then
echo "System-wide record [Failed record --threads option]"
err=1
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "System-wide record [Failed --threads missing output]"
err=1
return
fi
echo "Basic --system-wide mode test [Success]"
}
test_workload() {
echo "Basic target workload test"
if ! perf record -o "${perfdata}" ${testprog} 2> /dev/null
then
echo "Workload record [Failed record]"
err=1
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "Workload record [Failed missing output]"
err=1
return
fi
if ! perf record -e cpu-clock,cs --threads=package \
-o "${perfdata}" ${testprog} 2> /dev/null
then
echo "Workload record [Failed record --threads option]"
err=1
return
fi
if ! perf report -i "${perfdata}" -q | grep -q "${testsym}"
then
echo "Workload record [Failed --threads missing output]"
err=1
return
fi
echo "Basic target workload test [Success]"
}
test_branch_counter() {
echo "Branch counter test"
# Check if the branch counter feature is supported
for dir in $cpu_pmu_dir
do
if [ ! -e "$dir$br_cntr_file" ]
then
echo "branch counter feature not supported on all core PMUs ($dir) [Skipped]"
return
fi
done
if ! perf record -o "${perfdata}" -e "{branches:p,instructions}" -j any,counter ${testprog} 2> /dev/null
then
echo "Branch counter record test [Failed record]"
err=1
return
fi
if ! perf report -i "${perfdata}" -D -q | grep -q "$br_cntr_output"
then
echo "Branch counter report test [Failed missing output]"
err=1
return
fi
if ! perf script -i "${perfdata}" -F +brstackinsn,+brcntr | grep -q "$br_cntr_script_output"
then
echo " Branch counter script test [Failed missing output]"
err=1
return
fi
echo "Branch counter test [Success]"
}
test_cgroup() {
echo "Cgroup sampling test"
if ! perf record -aB --synth=cgroup --all-cgroups -o "${perfdata}" ${testprog} 2> /dev/null
then
echo "Cgroup sampling [Skipped not supported]"
return
fi
if ! perf report -i "${perfdata}" -D | grep -q "CGROUP"
then
echo "Cgroup sampling [Failed missing output]"
err=1
return
fi
if ! perf script -i "${perfdata}" -F cgroup | grep -q -v "unknown"
then
echo "Cgroup sampling [Failed cannot resolve cgroup names]"
err=1
return
fi
echo "Cgroup sampling test [Success]"
}
test_leader_sampling() {
echo "Basic leader sampling test"
if ! perf record -o "${perfdata}" -e "{branches,branches}:Su" perf test -w brstack 2> /dev/null
then
echo "Leader sampling [Failed record]"
err=1
return
fi
index=0
perf script -i "${perfdata}" > $script_output
while IFS= read -r line
do
# Check if the two branches counts are equal in each record
branches=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="branches:") print $(i-1)}')
if [ $(($index%2)) -ne 0 ] && [ ${branches}x != ${prev_branches}x ]
then
echo "Leader sampling [Failed inconsistent branches count]"
err=1
return
fi
index=$(($index+1))
prev_branches=$branches
done < $script_output
echo "Basic leader sampling test [Success]"
}
test_topdown_leader_sampling() {
echo "Topdown leader sampling test"
if ! perf stat -e "{slots,topdown-retiring}" true 2> /dev/null
then
echo "Topdown leader sampling [Skipped event parsing failed]"
return
fi
if ! perf record -o "${perfdata}" -e "{instructions,slots,topdown-retiring}:S" true 2> /dev/null
then
echo "Topdown leader sampling [Failed topdown events not reordered correctly]"
err=1
return
fi
echo "Topdown leader sampling test [Success]"
}
# raise the limit of file descriptors to minimum
if [[ $default_fd_limit -lt $min_fd_limit ]]; then
ulimit -Sn $min_fd_limit
fi
test_per_thread
test_register_capture
test_system_wide
test_workload
test_branch_counter
test_cgroup
test_leader_sampling
test_topdown_leader_sampling
# restore the default value
ulimit -Sn $default_fd_limit
cleanup
exit $err