forked from Minki/linux
fde59ab161
Due to retpolines, indirect calls are much more expensive than direct
calls. The filters have a select set of functions it uses for the
predicates. Instead of using function pointers to call them, create a
filter_pred_fn_call() function that uses a switch statement to call the
predicate functions directly. This gives almost a 10% speedup to the
filter logic.
Using the histogram benchmark:
Before:
# event histogram
#
# trigger info: hist:keys=delta:vals=hitcount:sort=delta:size=2048 if delta > 0 [active]
#
{ delta: 113 } hitcount: 272
{ delta: 114 } hitcount: 840
{ delta: 118 } hitcount: 344
{ delta: 119 } hitcount: 25428
{ delta: 120 } hitcount: 350590
{ delta: 121 } hitcount: 1892484
{ delta: 122 } hitcount: 6205004
{ delta: 123 } hitcount: 11583521
{ delta: 124 } hitcount: 37590979
{ delta: 125 } hitcount: 108308504
{ delta: 126 } hitcount: 131672461
{ delta: 127 } hitcount: 88700598
{ delta: 128 } hitcount: 65939870
{ delta: 129 } hitcount: 45055004
{ delta: 130 } hitcount: 33174464
{ delta: 131 } hitcount: 31813493
{ delta: 132 } hitcount: 29011676
{ delta: 133 } hitcount: 22798782
{ delta: 134 } hitcount: 22072486
{ delta: 135 } hitcount: 17034113
{ delta: 136 } hitcount: 8982490
{ delta: 137 } hitcount: 2865908
{ delta: 138 } hitcount: 980382
{ delta: 139 } hitcount: 1651944
{ delta: 140 } hitcount: 4112073
{ delta: 141 } hitcount: 3963269
{ delta: 142 } hitcount: 1712508
{ delta: 143 } hitcount: 575941
After:
# event histogram
#
# trigger info: hist:keys=delta:vals=hitcount:sort=delta:size=2048 if delta > 0 [active]
#
{ delta: 103 } hitcount: 60
{ delta: 104 } hitcount: 16966
{ delta: 105 } hitcount: 396625
{ delta: 106 } hitcount: 3223400
{ delta: 107 } hitcount: 12053754
{ delta: 108 } hitcount: 20241711
{ delta: 109 } hitcount: 14850200
{ delta: 110 } hitcount: 4946599
{ delta: 111 } hitcount: 3479315
{ delta: 112 } hitcount: 18698299
{ delta: 113 } hitcount: 62388733
{ delta: 114 } hitcount: 95803834
{ delta: 115 } hitcount: 58278130
{ delta: 116 } hitcount: 15364800
{ delta: 117 } hitcount: 5586866
{ delta: 118 } hitcount: 2346880
{ delta: 119 } hitcount: 1131091
{ delta: 120 } hitcount: 620896
{ delta: 121 } hitcount: 236652
{ delta: 122 } hitcount: 105957
{ delta: 123 } hitcount: 119107
{ delta: 124 } hitcount: 54494
{ delta: 125 } hitcount: 63856
{ delta: 126 } hitcount: 64454
{ delta: 127 } hitcount: 34818
{ delta: 128 } hitcount: 41446
{ delta: 129 } hitcount: 51242
{ delta: 130 } hitcount: 28361
{ delta: 131 } hitcount: 23926
The peak before was 126ns per event, after the peak is 114ns, and the
fastest time went from 113ns to 103ns.
Link: https://lkml.kernel.org/r/20220906225529.781407172@goodmis.org
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
|
||
|---|---|---|
| .. | ||
| bpf | ||
| cgroup | ||
| configs | ||
| debug | ||
| dma | ||
| entry | ||
| events | ||
| futex | ||
| gcov | ||
| irq | ||
| kcsan | ||
| livepatch | ||
| locking | ||
| module | ||
| power | ||
| printk | ||
| rcu | ||
| sched | ||
| time | ||
| trace | ||
| .gitignore | ||
| acct.c | ||
| async.c | ||
| audit_fsnotify.c | ||
| audit_tree.c | ||
| audit_watch.c | ||
| audit.c | ||
| audit.h | ||
| auditfilter.c | ||
| auditsc.c | ||
| backtracetest.c | ||
| bounds.c | ||
| capability.c | ||
| cfi.c | ||
| compat.c | ||
| configs.c | ||
| context_tracking.c | ||
| cpu_pm.c | ||
| cpu.c | ||
| crash_core.c | ||
| crash_dump.c | ||
| cred.c | ||
| delayacct.c | ||
| dma.c | ||
| exec_domain.c | ||
| exit.c | ||
| extable.c | ||
| fail_function.c | ||
| fork.c | ||
| freezer.c | ||
| gen_kheaders.sh | ||
| groups.c | ||
| hung_task.c | ||
| iomem.c | ||
| irq_work.c | ||
| jump_label.c | ||
| kallsyms_internal.h | ||
| kallsyms.c | ||
| kcmp.c | ||
| Kconfig.freezer | ||
| Kconfig.hz | ||
| Kconfig.locks | ||
| Kconfig.preempt | ||
| kcov.c | ||
| kexec_core.c | ||
| kexec_elf.c | ||
| kexec_file.c | ||
| kexec_internal.h | ||
| kexec.c | ||
| kheaders.c | ||
| kmod.c | ||
| kprobes.c | ||
| ksysfs.c | ||
| kthread.c | ||
| latencytop.c | ||
| Makefile | ||
| module_signature.c | ||
| notifier.c | ||
| nsproxy.c | ||
| padata.c | ||
| panic.c | ||
| params.c | ||
| pid_namespace.c | ||
| pid.c | ||
| profile.c | ||
| ptrace.c | ||
| range.c | ||
| reboot.c | ||
| regset.c | ||
| relay.c | ||
| resource_kunit.c | ||
| resource.c | ||
| rseq.c | ||
| scftorture.c | ||
| scs.c | ||
| seccomp.c | ||
| signal.c | ||
| smp.c | ||
| smpboot.c | ||
| smpboot.h | ||
| softirq.c | ||
| stackleak.c | ||
| stacktrace.c | ||
| static_call_inline.c | ||
| static_call.c | ||
| stop_machine.c | ||
| sys_ni.c | ||
| sys.c | ||
| sysctl-test.c | ||
| sysctl.c | ||
| task_work.c | ||
| taskstats.c | ||
| torture.c | ||
| tracepoint.c | ||
| tsacct.c | ||
| ucount.c | ||
| uid16.c | ||
| uid16.h | ||
| umh.c | ||
| up.c | ||
| user_namespace.c | ||
| user-return-notifier.c | ||
| user.c | ||
| usermode_driver.c | ||
| utsname_sysctl.c | ||
| utsname.c | ||
| watch_queue.c | ||
| watchdog_hld.c | ||
| watchdog.c | ||
| workqueue_internal.h | ||
| workqueue.c | ||