d41bc48bfa
Add benchmark to measure overhead of uprobes and uretprobes. Also have a baseline (no uprobe attached) benchmark. On my dev machine, baseline benchmark can trigger 130M user_target() invocations. When uprobe is attached, this falls to just 700K. With uretprobe, we get down to 520K: $ sudo ./bench trig-uprobe-base -a Summary: hits 131.289 ± 2.872M/s # UPROBE $ sudo ./bench -a trig-uprobe-without-nop Summary: hits 0.729 ± 0.007M/s $ sudo ./bench -a trig-uprobe-with-nop Summary: hits 1.798 ± 0.017M/s # URETPROBE $ sudo ./bench -a trig-uretprobe-without-nop Summary: hits 0.508 ± 0.012M/s $ sudo ./bench -a trig-uretprobe-with-nop Summary: hits 0.883 ± 0.008M/s So there is almost 2.5x performance difference between probing nop vs non-nop instruction for entry uprobe. And 1.7x difference for uretprobe. This means that non-nop uprobe overhead is around 1.4 microseconds for uprobe and 2 microseconds for non-nop uretprobe. For nop variants, uprobe and uretprobe overhead is down to 0.556 and 1.13 microseconds, respectively. For comparison, just doing a very low-overhead syscall (with no BPF programs attached anywhere) gives: $ sudo ./bench trig-base -a Summary: hits 4.830 ± 0.036M/s So uprobes are about 2.67x slower than pure context switch. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20211116013041.4072571-1-andrii@kernel.org
62 lines
1.1 KiB
C
62 lines
1.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
// Copyright (c) 2020 Facebook
|
|
|
|
#include <linux/bpf.h>
|
|
#include <asm/unistd.h>
|
|
#include <bpf/bpf_helpers.h>
|
|
#include <bpf/bpf_tracing.h>
|
|
|
|
char _license[] SEC("license") = "GPL";
|
|
|
|
long hits = 0;
|
|
|
|
SEC("tp/syscalls/sys_enter_getpgid")
|
|
int bench_trigger_tp(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("raw_tp/sys_enter")
|
|
int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
|
|
{
|
|
if (id == __NR_getpgid)
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("kprobe/__x64_sys_getpgid")
|
|
int bench_trigger_kprobe(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("fentry/__x64_sys_getpgid")
|
|
int bench_trigger_fentry(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("fentry.s/__x64_sys_getpgid")
|
|
int bench_trigger_fentry_sleep(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|
|
|
|
SEC("fmod_ret/__x64_sys_getpgid")
|
|
int bench_trigger_fmodret(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return -22;
|
|
}
|
|
|
|
SEC("uprobe/self/uprobe_target")
|
|
int bench_trigger_uprobe(void *ctx)
|
|
{
|
|
__sync_add_and_fetch(&hits, 1);
|
|
return 0;
|
|
}
|