基于 libbpf 的 TCP 连贯提早监督工具 tcpconnlat 剖析 – eBPF 基础知识 Part5
《eBPF 基础知识》系列简介:
《eBPF 基础知识》系列指标是整顿一下 BPF 相干的基础知识。次要聚焦程序与内核互动接口局部。文章应用了 libbpf,但如果你不间接应用 libbpf,看本系列还是有肯定意义的,因为它聚焦于程序与内核互动接口局部,而非 libbpf 封装自身。而所有 bpf 开发框架,都要以类似的形式跟内核互动。甚至框架自身就是基于 libbpf。哪怕是 golang/rust/python/BCC/bpftrace。
- 《ELF 格局简述 – eBPF 基础知识 Part1》
- 《BPF 零碎接口 与 libbpf 示例剖析 – eBPF 基础知识 Part2》
- 《经典 libbpf 范例: bootstrap 剖析 – eBPF 基础知识 Part3》
- 《经典 libbpf 范例: uprobe 剖析 – eBPF 基础知识 Part4》
国内习惯:尽量多图少文字。以下假如读者曾经对 BPF 有肯定的理解,或者浏览过之前的《eBPF 基础知识》系列文章。
很少人晓得,eBPF 的利用鼻祖 BCC 除了提供很多基于 python/bpftrace 的工具集之外,最近因为 libbpf 1.0 大大加强了:易用性、性能、执行文件的可移植性 BPF CO-RE (Compile Once – Run Everywhere)
的起因,开始有很多间接用 libbpf 1.0 写的 c 的 工具了。其中一个就是这篇文章要讲的 tcpconnlat。
动机:为何我要钻研 libbpf 版本的 tcpconnlat
开始剖析前,我想说几句废话:为何我要钻研 libbpf 版本的 tcpconnlat?
-
理解这个经典又实用的 BPF 工具,如何与内核互动实现性能的。
内核的 BPF 接口 (syscall) 因为历史和兼容性起因,设计得切实简单和不直观。syscall 设计者是想缩小 syscall 数量,一个 syscall 实现多功能。但同时也减少了应用的复杂度。这里想理解:
- 须要用到哪些内核对象
- 内核对象之间如何 link 起来,组成数据 / 事件流
-
学习如何应用 libbpf。这是主要指标。
- libbpf 如何帮忙简化开发者与内核对话的难度
tcpconnlat 示例程序性能
tcpconnlat 程序通过:
-
内核态 bpf 程序监听用户的 内核的
tcp_v4_connect
与tcp_rcv_state_process
函数,去记录和剖析 socket 连贯建设的用时状况。发送事件到 bpf_perf_event_output。阐明一下这两个函数:-
tcp_v4_connect – 内核尝试建设 socket 时调用
/* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) {...}
-
-
tcp_rcv_state_process – 内核 socket 状态变动时调用
/* * This function implements the receiving procedure of RFC 793 for * all states except ESTABLISHED and TIME_WAIT. * It's called from both tcp_v4_rcv and tcp_v6_rcv and should be * address independent. */ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) {...}
- 用户态程序负责加载 (load) 和 attach 内核态 BPF 程序。而后监听 bpf_perf_event_output 事件,打印输出。
$ sudo ./tcpconnlat
PID COMM IP SADDR DADDR DPORT LAT(ms)
4218 code 4 192.168.1.14 192.168.1.17 8118 0.62
3930 Chrome_Child 4 192.168.1.14 192.168.1.17 8118 0.61
...
程序阐明
uprobe 与内核互动概述
如上图排版有问题,请点这里用 Draw.io 关上。局部带互动链接和 hover tips
图中是我跟踪的后果。用 Draw.io 关上后,鼠标放到区域上,会 hover 出 stack(调用堆栈)。
图中的阐明曾经比拟具体。其中包含重要的数据结构和步骤。
1~5. 用户态 libbpf 数据加载与内存数据结构筹备
.rodata
mmap 内存页筹备- vmlinux BTF 加载,用于
BPF CO-RE
- 👇
为什么不再写了?因为切实不必要写,图中曾经有,一个疾速找到序号在图中的地位的小 tips 是,在 draw.io 中 CTRL+f
查找序号:
剖析环境阐明
$ uname -a
Linux T30 5.15.0-67-generic #74-Ubuntu SMP Wed Feb 22 14:14:39 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux
$ cat /etc/os-release
PRETTY_NAME="Ubuntu 22.04.2 LTS"
VERSION="22.04.2 LTS (Jammy Jellyfish)"
内核态 BPF 字节码程序
<mark> 我始终致力防止在文章间接上代码。起因是,我本人的体验是,在文章中读代码太难了…… </mark> 不过有时还是要贴。指标不是让读者齐全一次看懂代码,而是对次要逻辑和命名符号有个理性的理解。我尽量精简一下吧。不要被这纸老虎吓跑。只有配合图解。
先看 BPF 内核字节码程序局部:
tcpconnlat.bpf.c
const volatile __u64 targ_min_us = 0;
const volatile pid_t targ_tgid = 0;
struct piddata {char comm[TASK_COMM_LEN];
u64 ts;
u32 tgid;
};
struct {__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 4096);
__type(key, struct sock *);
__type(value, struct piddata);
} start SEC(".maps");
struct {__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
__uint(key_size, sizeof(u32));
__uint(value_size, sizeof(u32));
} events SEC(".maps");
static int trace_connect(struct sock *sk)
{u32 tgid = bpf_get_current_pid_tgid() >> 32;
struct piddata piddata = {};
if (targ_tgid && targ_tgid != tgid)
return 0;
bpf_get_current_comm(&piddata.comm, sizeof(piddata.comm));
piddata.ts = bpf_ktime_get_ns();
piddata.tgid = tgid;
bpf_map_update_elem(&start, &sk, &piddata, 0);
return 0;
}
static int handle_tcp_rcv_state_process(void *ctx, struct sock *sk)
{
struct piddata *piddatap;
struct event event = {};
s64 delta;
u64 ts;
if (BPF_CORE_READ(sk, __sk_common.skc_state) != TCP_SYN_SENT)
return 0;
piddatap = bpf_map_lookup_elem(&start, &sk);
if (!piddatap)
return 0;
ts = bpf_ktime_get_ns();
delta = (s64)(ts - piddatap->ts);
if (delta < 0)
goto cleanup;
event.delta_us = delta / 1000U;
if (targ_min_us && event.delta_us < targ_min_us)
goto cleanup;
__builtin_memcpy(&event.comm, piddatap->comm,
sizeof(event.comm));
event.ts_us = ts / 1000;
event.tgid = piddatap->tgid;
event.lport = BPF_CORE_READ(sk, __sk_common.skc_num);
event.dport = BPF_CORE_READ(sk, __sk_common.skc_dport);
event.af = BPF_CORE_READ(sk, __sk_common.skc_family);
if (event.af == AF_INET) {event.saddr_v4 = BPF_CORE_READ(sk, __sk_common.skc_rcv_saddr);
event.daddr_v4 = BPF_CORE_READ(sk, __sk_common.skc_daddr);
} else {
BPF_CORE_READ_INTO(&event.saddr_v6, sk,
__sk_common.skc_v6_rcv_saddr.in6_u.u6_addr32);
BPF_CORE_READ_INTO(&event.daddr_v6, sk,
__sk_common.skc_v6_daddr.in6_u.u6_addr32);
}
bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
&event, sizeof(event));
cleanup:
bpf_map_delete_elem(&start, &sk);
return 0;
}
SEC("fentry/tcp_v4_connect")
int BPF_PROG(fentry_tcp_v4_connect, struct sock *sk)
{return trace_connect(sk);
}
SEC("fentry/tcp_rcv_state_process")
int BPF_PROG(fentry_tcp_rcv_state_process, struct sock *sk)
{return handle_tcp_rcv_state_process(ctx, sk);
}
用户态 bpf 程序
tcpconnlat.c
#define PERF_BUFFER_PAGES 16
#define PERF_POLL_TIMEOUT_MS 100
static volatile sig_atomic_t exiting = 0;
static struct env {
__u64 min_us;
pid_t pid;
bool timestamp;
bool lport;
bool verbose;
} env;
const char *argp_program_version = "tcpconnlat 0.1";
const char *argp_program_bug_address =
"https://github.com/iovisor/bcc/tree/master/libbpf-tools";
const char argp_program_doc[] =
"\nTrace TCP connects and show connection latency.\n"
"\n"
"USAGE: tcpconnlat [--help] [-t] [-p PID] [-L]\n"
"\n"
"EXAMPLES:\n"
"tcpconnlat # summarize on-CPU time as a histogram\n"
"tcpconnlat 1 # trace connection latency slower than 1 ms\n"
"tcpconnlat 0.1 # trace connection latency slower than 100 us\n"
"tcpconnlat -t # 1s summaries, milliseconds, and timestamps\n"
"tcpconnlat -p 185 # trace PID 185 only\n"
"tcpconnlat -L # include LPORT while printing outputs\n";
static const struct argp_option opts[] = {{ "timestamp", 't', NULL, 0, "Include timestamp on output"},
{"pid", 'p', "PID", 0, "Trace this PID only"},
{"lport", 'L', NULL, 0, "Include LPORT on output"},
{"verbose", 'v', NULL, 0, "Verbose debug output"},
{NULL, 'h', NULL, OPTION_HIDDEN, "Show the full help"},
{},};
static error_t parse_arg(int key, char *arg, struct argp_state *state)
{...}
static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
{...}
static void sig_int(int signo)
{exiting = 1;}
void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
{
const struct event *e = data;
char src[INET6_ADDRSTRLEN];
char dst[INET6_ADDRSTRLEN];
union {
struct in_addr x4;
struct in6_addr x6;
} s, d;
static __u64 start_ts;
if (env.timestamp) {if (start_ts == 0)
start_ts = e->ts_us;
printf("%-9.3f", (e->ts_us - start_ts) / 1000000.0);
}
if (e->af == AF_INET) {
s.x4.s_addr = e->saddr_v4;
d.x4.s_addr = e->daddr_v4;
} else if (e->af == AF_INET6) {memcpy(&s.x6.s6_addr, e->saddr_v6, sizeof(s.x6.s6_addr));
memcpy(&d.x6.s6_addr, e->daddr_v6, sizeof(d.x6.s6_addr));
} else {fprintf(stderr, "broken event: event->af=%d", e->af);
return;
}
if (env.lport) {
printf("%-6d %-12.12s %-2d %-16s %-6d %-16s %-5d %.2f\n", e->tgid, e->comm,
e->af == AF_INET ? 4 : 6, inet_ntop(e->af, &s, src, sizeof(src)), e->lport,
inet_ntop(e->af, &d, dst, sizeof(dst)), ntohs(e->dport),
e->delta_us / 1000.0);
} else {
printf("%-6d %-12.12s %-2d %-16s %-16s %-5d %.2f\n", e->tgid, e->comm,
e->af == AF_INET ? 4 : 6, inet_ntop(e->af, &s, src, sizeof(src)),
inet_ntop(e->af, &d, dst, sizeof(dst)), ntohs(e->dport),
e->delta_us / 1000.0);
}
}
void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
{fprintf(stderr, "lost %llu events on CPU #%d\n", lost_cnt, cpu);
}
int main(int argc, char **argv)
{
static const struct argp argp = {
.options = opts,
.parser = parse_arg,
.doc = argp_program_doc,
};
struct perf_buffer *pb = NULL;
struct tcpconnlat_bpf *obj;
int err;
err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
if (err)
return err;
libbpf_set_print(libbpf_print_fn);
obj = tcpconnlat_bpf__open();
if (!obj) {fprintf(stderr, "failed to open BPF object\n");
return 1;
}
/* initialize global data (filtering options) */
obj->rodata->targ_min_us = env.min_us;
obj->rodata->targ_tgid = env.pid;
if (fentry_can_attach("tcp_v4_connect", NULL)) {bpf_program__set_attach_target(obj->progs.fentry_tcp_v4_connect, 0, "tcp_v4_connect");
bpf_program__set_attach_target(obj->progs.fentry_tcp_v6_connect, 0, "tcp_v6_connect");
bpf_program__set_attach_target(obj->progs.fentry_tcp_rcv_state_process, 0, "tcp_rcv_state_process");
bpf_program__set_autoload(obj->progs.tcp_v4_connect, false);
bpf_program__set_autoload(obj->progs.tcp_v6_connect, false);
bpf_program__set_autoload(obj->progs.tcp_rcv_state_process, false);
} else {bpf_program__set_autoload(obj->progs.fentry_tcp_v4_connect, false);
bpf_program__set_autoload(obj->progs.fentry_tcp_v6_connect, false);
bpf_program__set_autoload(obj->progs.fentry_tcp_rcv_state_process, false);
}
err = tcpconnlat_bpf__load(obj);
if (err) {fprintf(stderr, "failed to load BPF object: %d\n", err);
goto cleanup;
}
err = tcpconnlat_bpf__attach(obj);
if (err) {goto cleanup;}
pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES,
handle_event, handle_lost_events, NULL, NULL);
if (!pb) {fprintf(stderr, "failed to open perf buffer: %d\n", errno);
goto cleanup;
}
/* print header */
if (env.timestamp)
printf("%-9s", ("TIME(s)"));
if (env.lport) {
printf("%-6s %-12s %-2s %-16s %-6s %-16s %-5s %s\n",
"PID", "COMM", "IP", "SADDR", "LPORT", "DADDR", "DPORT", "LAT(ms)");
} else {
printf("%-6s %-12s %-2s %-16s %-16s %-5s %s\n",
"PID", "COMM", "IP", "SADDR", "DADDR", "DPORT", "LAT(ms)");
}
if (signal(SIGINT, sig_int) == SIG_ERR) {fprintf(stderr, "can't set signal handler: %s\n", strerror(errno));
err = 1;
goto cleanup;
}
/* main: poll */
while (!exiting) {err = perf_buffer__poll(pb, PERF_POLL_TIMEOUT_MS);
if (err < 0 && err != -EINTR) {fprintf(stderr, "error polling perf buffer: %s\n", strerror(-err));
goto cleanup;
}
/* reset err to return 0 if exiting */
err = 0;
}
cleanup:
perf_buffer__free(pb);
tcpconnlat_bpf__destroy(obj);
return err != 0;
}
后记
技术开悟的路,或者和人的成熟过程一样,只有事实的磨难能力得道。