mirror of
https://github.com/eunomia-bpf/bpf-developer-tutorial.git
synced 2026-02-04 10:44:14 +08:00
542 lines
29 KiB
HTML
542 lines
29 KiB
HTML
<!DOCTYPE HTML>
|
||
<html lang="en" class="sidebar-visible no-js light">
|
||
<head>
|
||
<!-- Book generated using mdBook -->
|
||
<meta charset="UTF-8">
|
||
<title>eBPF 入门开发实践教程九：一个 Linux 内核 BPF 程序，通过柱状图来总结调度程序运行队列延迟，显示任务等待运行在 CPU 上的时间长度 - bpf-developer-tutorial</title>
|
||
|
||
|
||
<!-- Custom HTML head -->
|
||
|
||
<meta name="description" content="">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||
<meta name="theme-color" content="#ffffff" />
|
||
|
||
<link rel="icon" href="../favicon.svg">
|
||
<link rel="shortcut icon" href="../favicon.png">
|
||
<link rel="stylesheet" href="../css/variables.css">
|
||
<link rel="stylesheet" href="../css/general.css">
|
||
<link rel="stylesheet" href="../css/chrome.css">
|
||
<link rel="stylesheet" href="../css/print.css" media="print">
|
||
|
||
<!-- Fonts -->
|
||
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
|
||
<link rel="stylesheet" href="../fonts/fonts.css">
|
||
|
||
<!-- Highlight.js Stylesheets -->
|
||
<link rel="stylesheet" href="../highlight.css">
|
||
<link rel="stylesheet" href="../tomorrow-night.css">
|
||
<link rel="stylesheet" href="../ayu-highlight.css">
|
||
|
||
<!-- Custom theme stylesheets -->
|
||
|
||
</head>
|
||
<body>
|
||
<div id="body-container">
|
||
<!-- Provide site root to javascript -->
|
||
<script>
|
||
var path_to_root = "../";
|
||
var default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? "navy" : "light";
|
||
</script>
|
||
|
||
<!-- Work around some values being stored in localStorage wrapped in quotes -->
|
||
<script>
|
||
try {
|
||
var theme = localStorage.getItem('mdbook-theme');
|
||
var sidebar = localStorage.getItem('mdbook-sidebar');
|
||
|
||
if (theme.startsWith('"') && theme.endsWith('"')) {
|
||
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
|
||
}
|
||
|
||
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
|
||
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
|
||
}
|
||
} catch (e) { }
|
||
</script>
|
||
|
||
<!-- Set the theme before any content is loaded, prevents flash -->
|
||
<script>
|
||
var theme;
|
||
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
|
||
if (theme === null || theme === undefined) { theme = default_theme; }
|
||
var html = document.querySelector('html');
|
||
html.classList.remove('no-js')
|
||
html.classList.remove('light')
|
||
html.classList.add(theme);
|
||
html.classList.add('js');
|
||
</script>
|
||
|
||
<!-- Hide / unhide sidebar before it is displayed -->
|
||
<script>
|
||
var html = document.querySelector('html');
|
||
var sidebar = null;
|
||
if (document.body.clientWidth >= 1080) {
|
||
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
|
||
sidebar = sidebar || 'visible';
|
||
} else {
|
||
sidebar = 'hidden';
|
||
}
|
||
html.classList.remove('sidebar-visible');
|
||
html.classList.add("sidebar-" + sidebar);
|
||
</script>
|
||
|
||
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
|
||
<div class="sidebar-scrollbox">
|
||
<ol class="chapter"><li class="chapter-item expanded affix "><li class="part-title">eBPF 实践教程：基于 libbpf 和 CO-RE</li><li class="chapter-item expanded "><a href="../0-introduce/index.html"><strong aria-hidden="true">1.</strong> eBPF 入门开发实践教程一：介绍 eBPF 的基本概念、常见的开发工具</a></li><li class="chapter-item expanded "><a href="../1-helloworld/index.html"><strong aria-hidden="true">2.</strong> eBPF 入门开发实践教程二：Hello World，基本框架和开发流程</a></li><li class="chapter-item expanded "><a href="../2-kprobe-unlink/index.html"><strong aria-hidden="true">3.</strong> eBPF 入门开发实践教程二：在 eBPF 中使用 kprobe 监测捕获 unlink 系统调用</a></li><li class="chapter-item expanded "><a href="../3-fentry-unlink/index.html"><strong aria-hidden="true">4.</strong> eBPF 入门开发实践教程三：在 eBPF 中使用 fentry 监测捕获 unlink 系统调用</a></li><li class="chapter-item expanded "><a href="../4-opensnoop/index.html"><strong aria-hidden="true">5.</strong> eBPF 入门开发实践教程四：在 eBPF 中捕获进程打开文件的系统调用集合，使用全局变量过滤进程 pid</a></li><li class="chapter-item expanded "><a href="../5-uprobe-bashreadline/index.html"><strong aria-hidden="true">6.</strong> eBPF 入门开发实践教程五：在 eBPF 中使用 uprobe 捕获 bash 的 readline 函数调用</a></li><li class="chapter-item expanded "><a href="../6-sigsnoop/index.html"><strong aria-hidden="true">7.</strong> eBPF 入门开发实践教程六：捕获进程发送信号的系统调用集合，使用 hash map 保存状态</a></li><li class="chapter-item expanded "><a href="../7-execsnoop/index.html"><strong aria-hidden="true">8.</strong> eBPF 入门实践教程七：捕获进程执行/退出时间，通过 perf event array 向用户态打印输出</a></li><li class="chapter-item expanded "><a href="../8-exitsnoop/index.html"><strong aria-hidden="true">9.</strong> eBPF 入门开发实践教程八：在 eBPF 中使用 exitsnoop 监控进程退出事件，使用 ring buffer 向用户态打印输出</a></li><li class="chapter-item expanded "><a href="../9-runqlat/index.html" class="active"><strong aria-hidden="true">10.</strong> eBPF 入门开发实践教程九：一个 Linux 内核 BPF 程序，通过柱状图来总结调度程序运行队列延迟，显示任务等待运行在 CPU 上的时间长度</a></li><li class="chapter-item expanded "><a href="../10-hardirqs/index.html"><strong aria-hidden="true">11.</strong> eBPF 入门开发实践教程十：在 eBPF 中使用 hardirqs 或 softirqs 捕获中断事件</a></li><li class="chapter-item expanded "><a href="../11-bootstrap/index.html"><strong aria-hidden="true">12.</strong> eBPF 入门开发实践教程十一：在 eBPF 中使用 bootstrap 开发用户态程序并跟踪 exec() 和 exit() 系统调用</a></li><li class="chapter-item expanded "><a href="../13-tcpconnlat/index.html"><strong aria-hidden="true">13.</strong> eBPF入门实践教程：使用 libbpf-bootstrap 开发程序统计 TCP 连接延时</a></li><li class="chapter-item expanded "><a href="../13-tcpconnlat/tcpconnlat.html"><strong aria-hidden="true">14.</strong> eBPF 入门实践教程：编写 eBPF 程序 tcpconnlat 测量 tcp 连接延时</a></li><li class="chapter-item expanded "><a href="../14-tcpstates/index.html"><strong aria-hidden="true">15.</strong> eBPF入门实践教程：使用 libbpf-bootstrap 开发程序统计 TCP 连接延时</a></li><li class="chapter-item expanded "><a href="../15-tcprtt/index.html"><strong aria-hidden="true">16.</strong> eBPF 入门实践教程：编写 eBPF 程序 Tcprtt 测量 TCP 连接的往返时间</a></li><li class="chapter-item expanded "><a href="../16-memleak/index.html"><strong aria-hidden="true">17.</strong> eBPF 入门实践教程：编写 eBPF 程序 Memleak 监控内存泄漏</a></li><li class="chapter-item expanded "><a href="../17-biopattern/index.html"><strong aria-hidden="true">18.</strong> eBPF 入门实践教程：编写 eBPF 程序 Biopattern: 统计随机/顺序磁盘 I/O</a></li><li class="chapter-item expanded "><a href="../18-further-reading/index.html"><strong aria-hidden="true">19.</strong> 更多的参考资料</a></li><li class="chapter-item expanded "><a href="../19-lsm-connect/index.html"><strong aria-hidden="true">20.</strong> eBPF 入门实践教程：使用 LSM 进行安全检测防御</a></li><li class="chapter-item expanded "><a href="../20-tc/index.html"><strong aria-hidden="true">21.</strong> eBPF 入门实践教程：使用 eBPF 进行 tc 流量控制</a></li><li class="chapter-item expanded affix "><li class="part-title">bcc 开发者教程</li><li class="chapter-item expanded "><a href="../bcc-documents/kernel-versions.html"><strong aria-hidden="true">22.</strong> BPF Features by Linux Kernel Version</a></li><li class="chapter-item expanded "><a href="../bcc-documents/kernel_config.html"><strong aria-hidden="true">23.</strong> Kernel Configuration for BPF Features</a></li><li class="chapter-item expanded "><a href="../bcc-documents/reference_guide.html"><strong aria-hidden="true">24.</strong> bcc Reference Guide</a></li><li class="chapter-item expanded "><a href="../bcc-documents/special_filtering.html"><strong aria-hidden="true">25.</strong> Special Filtering</a></li><li class="chapter-item expanded "><a href="../bcc-documents/tutorial.html"><strong aria-hidden="true">26.</strong> bcc Tutorial</a></li><li class="chapter-item expanded "><a href="../bcc-documents/tutorial_bcc_python_developer.html"><strong aria-hidden="true">27.</strong> bcc Python Developer Tutorial</a></li></ol>
|
||
</div>
|
||
<div id="sidebar-resize-handle" class="sidebar-resize-handle"></div>
|
||
</nav>
|
||
|
||
<div id="page-wrapper" class="page-wrapper">
|
||
|
||
<div class="page">
|
||
<div id="menu-bar-hover-placeholder"></div>
|
||
<div id="menu-bar" class="menu-bar sticky bordered">
|
||
<div class="left-buttons">
|
||
<button id="sidebar-toggle" class="icon-button" type="button" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
|
||
<i class="fa fa-bars"></i>
|
||
</button>
|
||
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
|
||
<i class="fa fa-paint-brush"></i>
|
||
</button>
|
||
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
|
||
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
|
||
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
|
||
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
|
||
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
|
||
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
|
||
</ul>
|
||
<button id="search-toggle" class="icon-button" type="button" title="Search. (Shortkey: s)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="S" aria-controls="searchbar">
|
||
<i class="fa fa-search"></i>
|
||
</button>
|
||
</div>
|
||
|
||
<h1 class="menu-title">bpf-developer-tutorial</h1>
|
||
|
||
<div class="right-buttons">
|
||
<a href="../print.html" title="Print this book" aria-label="Print this book">
|
||
<i id="print-button" class="fa fa-print"></i>
|
||
</a>
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div id="search-wrapper" class="hidden">
|
||
<form id="searchbar-outer" class="searchbar-outer">
|
||
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
|
||
</form>
|
||
<div id="searchresults-outer" class="searchresults-outer hidden">
|
||
<div id="searchresults-header" class="searchresults-header"></div>
|
||
<ul id="searchresults">
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
|
||
<script>
|
||
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
|
||
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
|
||
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
|
||
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
|
||
});
|
||
</script>
|
||
|
||
<div id="content" class="content">
|
||
<main>
|
||
<h1 id="ebpf-入门开发实践教程九捕获进程调度延迟以直方图方式记录"><a class="header" href="#ebpf-入门开发实践教程九捕获进程调度延迟以直方图方式记录">eBPF 入门开发实践教程九：捕获进程调度延迟，以直方图方式记录</a></h1>
|
||
<p>eBPF (Extended Berkeley Packet Filter) 是 Linux 内核上的一个强大的网络和性能分析工具。它允许开发者在内核运行时动态加载、更新和运行用户定义的代码。</p>
|
||
<p>runqlat 是一个 eBPF 工具，用于分析 Linux 系统的调度性能。具体来说，runqlat 用于测量一个任务在被调度到 CPU 上运行之前在运行队列中等待的时间。这些信息对于识别性能瓶颈和提高 Linux 内核调度算法的整体效率非常有用。</p>
|
||
<h2 id="runqlat-原理"><a class="header" href="#runqlat-原理">runqlat 原理</a></h2>
|
||
<p>runqlat 的实现利用了 eBPF 程序，它通过内核跟踪点和函数探针来测量进程在运行队列中的时间。当进程被排队时，trace_enqueue 函数会在一个映射中记录时间戳。当进程被调度到 CPU 上运行时，handle_switch 函数会检索时间戳，并计算当前时间与排队时间之间的时间差。这个差值（或 delta）被用于更新进程的直方图，该直方图记录运行队列延迟的分布。该直方图可用于分析 Linux 内核的调度性能。</p>
|
||
<h2 id="runqlat-代码实现"><a class="header" href="#runqlat-代码实现">runqlat 代码实现</a></h2>
|
||
<h3 id="runqlatbpfc"><a class="header" href="#runqlatbpfc">runqlat.bpf.c</a></h3>
|
||
<p>首先我们需要编写一个源代码文件 runqlat.bpf.c:</p>
|
||
<pre><code class="language-c">// SPDX-License-Identifier: GPL-2.0
|
||
// Copyright (c) 2020 Wenbo Zhang
|
||
#include <vmlinux.h>
|
||
#include <bpf/bpf_helpers.h>
|
||
#include <bpf/bpf_core_read.h>
|
||
#include <bpf/bpf_tracing.h>
|
||
#include "runqlat.h"
|
||
#include "bits.bpf.h"
|
||
#include "maps.bpf.h"
|
||
#include "core_fixes.bpf.h"
|
||
|
||
#define MAX_ENTRIES 10240
|
||
#define TASK_RUNNING 0
|
||
|
||
const volatile bool filter_cg = false;
|
||
const volatile bool targ_per_process = false;
|
||
const volatile bool targ_per_thread = false;
|
||
const volatile bool targ_per_pidns = false;
|
||
const volatile bool targ_ms = false;
|
||
const volatile pid_t targ_tgid = 0;
|
||
|
||
struct {
|
||
__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
|
||
__type(key, u32);
|
||
__type(value, u32);
|
||
__uint(max_entries, 1);
|
||
} cgroup_map SEC(".maps");
|
||
|
||
struct {
|
||
__uint(type, BPF_MAP_TYPE_HASH);
|
||
__uint(max_entries, MAX_ENTRIES);
|
||
__type(key, u32);
|
||
__type(value, u64);
|
||
} start SEC(".maps");
|
||
|
||
static struct hist zero;
|
||
|
||
/// @sample {"interval": 1000, "type" : "log2_hist"}
|
||
struct {
|
||
__uint(type, BPF_MAP_TYPE_HASH);
|
||
__uint(max_entries, MAX_ENTRIES);
|
||
__type(key, u32);
|
||
__type(value, struct hist);
|
||
} hists SEC(".maps");
|
||
|
||
static int trace_enqueue(u32 tgid, u32 pid)
|
||
{
|
||
u64 ts;
|
||
|
||
if (!pid)
|
||
return 0;
|
||
if (targ_tgid && targ_tgid != tgid)
|
||
return 0;
|
||
|
||
ts = bpf_ktime_get_ns();
|
||
bpf_map_update_elem(&start, &pid, &ts, BPF_ANY);
|
||
return 0;
|
||
}
|
||
|
||
static unsigned int pid_namespace(struct task_struct *task)
|
||
{
|
||
struct pid *pid;
|
||
unsigned int level;
|
||
struct upid upid;
|
||
unsigned int inum;
|
||
|
||
/* get the pid namespace by following task_active_pid_ns(),
|
||
* pid->numbers[pid->level].ns
|
||
*/
|
||
pid = BPF_CORE_READ(task, thread_pid);
|
||
level = BPF_CORE_READ(pid, level);
|
||
bpf_core_read(&upid, sizeof(upid), &pid->numbers[level]);
|
||
inum = BPF_CORE_READ(upid.ns, ns.inum);
|
||
|
||
return inum;
|
||
}
|
||
|
||
static int handle_switch(bool preempt, struct task_struct *prev, struct task_struct *next)
|
||
{
|
||
struct hist *histp;
|
||
u64 *tsp, slot;
|
||
u32 pid, hkey;
|
||
s64 delta;
|
||
|
||
if (filter_cg && !bpf_current_task_under_cgroup(&cgroup_map, 0))
|
||
return 0;
|
||
|
||
if (get_task_state(prev) == TASK_RUNNING)
|
||
trace_enqueue(BPF_CORE_READ(prev, tgid), BPF_CORE_READ(prev, pid));
|
||
|
||
pid = BPF_CORE_READ(next, pid);
|
||
|
||
tsp = bpf_map_lookup_elem(&start, &pid);
|
||
if (!tsp)
|
||
return 0;
|
||
delta = bpf_ktime_get_ns() - *tsp;
|
||
if (delta < 0)
|
||
goto cleanup;
|
||
|
||
if (targ_per_process)
|
||
hkey = BPF_CORE_READ(next, tgid);
|
||
else if (targ_per_thread)
|
||
hkey = pid;
|
||
else if (targ_per_pidns)
|
||
hkey = pid_namespace(next);
|
||
else
|
||
hkey = -1;
|
||
histp = bpf_map_lookup_or_try_init(&hists, &hkey, &zero);
|
||
if (!histp)
|
||
goto cleanup;
|
||
if (!histp->comm[0])
|
||
bpf_probe_read_kernel_str(&histp->comm, sizeof(histp->comm),
|
||
next->comm);
|
||
if (targ_ms)
|
||
delta /= 1000000U;
|
||
else
|
||
delta /= 1000U;
|
||
slot = log2l(delta);
|
||
if (slot >= MAX_SLOTS)
|
||
slot = MAX_SLOTS - 1;
|
||
__sync_fetch_and_add(&histp->slots[slot], 1);
|
||
|
||
cleanup:
|
||
bpf_map_delete_elem(&start, &pid);
|
||
return 0;
|
||
}
|
||
|
||
SEC("raw_tp/sched_wakeup")
|
||
int BPF_PROG(handle_sched_wakeup, struct task_struct *p)
|
||
{
|
||
if (filter_cg && !bpf_current_task_under_cgroup(&cgroup_map, 0))
|
||
return 0;
|
||
|
||
return trace_enqueue(BPF_CORE_READ(p, tgid), BPF_CORE_READ(p, pid));
|
||
}
|
||
|
||
SEC("raw_tp/sched_wakeup_new")
|
||
int BPF_PROG(handle_sched_wakeup_new, struct task_struct *p)
|
||
{
|
||
if (filter_cg && !bpf_current_task_under_cgroup(&cgroup_map, 0))
|
||
return 0;
|
||
|
||
return trace_enqueue(BPF_CORE_READ(p, tgid), BPF_CORE_READ(p, pid));
|
||
}
|
||
|
||
SEC("raw_tp/sched_switch")
|
||
int BPF_PROG(handle_sched_switch, bool preempt, struct task_struct *prev, struct task_struct *next)
|
||
{
|
||
return handle_switch(preempt, prev, next);
|
||
}
|
||
|
||
char LICENSE[] SEC("license") = "GPL";
|
||
</code></pre>
|
||
<p>首先，定义了一些常量和全局变量：</p>
|
||
<pre><code class="language-c">#define MAX_ENTRIES 10240
|
||
#define TASK_RUNNING 0
|
||
|
||
const volatile bool filter_cg = false;
|
||
const volatile bool targ_per_process = false;
|
||
const volatile bool targ_per_thread = false;
|
||
const volatile bool targ_per_pidns = false;
|
||
const volatile bool targ_ms = false;
|
||
const volatile pid_t targ_tgid = 0;
|
||
</code></pre>
|
||
<p>这些变量包括最大映射项数量、任务状态、过滤选项和目标选项。这些选项可以通过用户空间程序设置，以定制 eBPF 程序的行为。</p>
|
||
<p>接下来，定义了一些 eBPF 映射：</p>
|
||
<pre><code class="language-c">struct {
|
||
__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
|
||
__type(key, u32);
|
||
__type(value, u32);
|
||
__uint(max_entries, 1);
|
||
} cgroup_map SEC(".maps");
|
||
|
||
struct {
|
||
__uint(type, BPF_MAP_TYPE_HASH);
|
||
__uint(max_entries, MAX_ENTRIES);
|
||
__type(key, u32);
|
||
__type(value, u64);
|
||
} start SEC(".maps");
|
||
|
||
static struct hist zero;
|
||
|
||
struct {
|
||
__uint(type, BPF_MAP_TYPE_HASH);
|
||
__uint(max_entries, MAX_ENTRIES);
|
||
__type(key, u32);
|
||
__type(value, struct hist);
|
||
} hists SEC(".maps");
|
||
</code></pre>
|
||
<p>这些映射包括：</p>
|
||
<ul>
|
||
<li>cgroup_map 用于过滤 cgroup；</li>
|
||
<li>start 用于存储进程入队时的时间戳；</li>
|
||
<li>hists 用于存储直方图数据，记录进程调度延迟。</li>
|
||
</ul>
|
||
<p>接下来是一些辅助函数：</p>
|
||
<p>trace_enqueue 函数用于在进程入队时记录其时间戳：</p>
|
||
<pre><code class="language-c">static int trace_enqueue(u32 tgid, u32 pid)
|
||
{
|
||
u64 ts;
|
||
|
||
if (!pid)
|
||
return 0;
|
||
if (targ_tgid && targ_tgid != tgid)
|
||
return 0;
|
||
|
||
ts = bpf_ktime_get_ns();
|
||
bpf_map_update_elem(&start, &pid, &ts, BPF_ANY);
|
||
return 0;
|
||
}
|
||
</code></pre>
|
||
<p>pid_namespace 函数用于获取进程所属的 PID namespace：</p>
|
||
<pre><code class="language-c">static unsigned int pid_namespace(struct task_struct *task)
|
||
{
|
||
struct pid *pid;
|
||
unsigned int level;
|
||
struct upid upid;
|
||
unsigned int inum;
|
||
|
||
/* get the pid namespace by following task_active_pid_ns(),
|
||
* pid->numbers[pid->level].ns
|
||
*/
|
||
pid = BPF_CORE_READ(task, thread_pid);
|
||
level = BPF_CORE_READ(pid, level);
|
||
bpf_core_read(&upid, sizeof(upid), &pid->numbers[level]);
|
||
inum = BPF_CORE_READ(upid.ns, ns.inum);
|
||
|
||
return inum;
|
||
}
|
||
</code></pre>
|
||
<p>handle_switch 函数是核心部分，用于处理调度切换事件，计算进程调度延迟并更新直方图数据：</p>
|
||
<pre><code class="language-c">static int handle_switch(bool preempt, struct task_struct *prev, struct task_struct *next)
|
||
{
|
||
...
|
||
}
|
||
</code></pre>
|
||
<p>首先，函数根据 filter_cg 的设置判断是否需要过滤 cgroup。然后，如果之前的进程状态为 TASK_RUNNING，则调用 trace_enqueue 函数记录进程的入队时间。接着，函数查找下一个进程的入队时间戳，如果找不到，直接返回。计算调度延迟（delta），并根据不同的选项设置（targ_per_process，targ_per_thread，targ_per_pidns），确定直方图映射的键（hkey）。然后查找或初始化直方图映射，更新直方图数据，最后删除进程的入队时间戳记录。</p>
|
||
<p>接下来是 eBPF 程序的入口点。程序使用三个入口点来捕获不同的调度事件：</p>
|
||
<ul>
|
||
<li>handle_sched_wakeup：用于处理 sched_wakeup 事件，当一个进程从睡眠状态被唤醒时触发。</li>
|
||
<li>handle_sched_wakeup_new：用于处理 sched_wakeup_new 事件，当一个新创建的进程被唤醒时触发。</li>
|
||
<li>handle_sched_switch：用于处理 sched_switch 事件，当调度器选择一个新的进程运行时触发。</li>
|
||
</ul>
|
||
<p>这些入口点分别处理不同的调度事件，但都会调用 handle_switch 函数来计算进程的调度延迟并更新直方图数据。</p>
|
||
<p>最后，程序包含一个许可证声明：</p>
|
||
<pre><code class="language-c">char LICENSE[] SEC("license") = "GPL";
|
||
</code></pre>
|
||
<p>这一声明指定了 eBPF 程序的许可证类型，这里使用的是 "GPL"。这对于许多内核功能是必需的，因为它们要求 eBPF 程序遵循 GPL 许可证。</p>
|
||
<h3 id="runqlath"><a class="header" href="#runqlath">runqlat.h</a></h3>
|
||
<p>然后我们需要定义一个头文件<code>runqlat.h</code>，用来给用户态处理从内核态上报的事件：</p>
|
||
<pre><code class="language-c">/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
|
||
#ifndef __RUNQLAT_H
|
||
#define __RUNQLAT_H
|
||
|
||
#define TASK_COMM_LEN 16
|
||
#define MAX_SLOTS 26
|
||
|
||
struct hist {
|
||
__u32 slots[MAX_SLOTS];
|
||
char comm[TASK_COMM_LEN];
|
||
};
|
||
|
||
#endif /* __RUNQLAT_H */
|
||
</code></pre>
|
||
<h2 id="编译运行"><a class="header" href="#编译运行">编译运行</a></h2>
|
||
<p>eunomia-bpf 是一个结合 Wasm 的开源 eBPF 动态加载运行时和开发工具链，它的目的是简化 eBPF 程序的开发、构建、分发、运行。可以参考 <a href="https://github.com/eunomia-bpf/eunomia-bpf">https://github.com/eunomia-bpf/eunomia-bpf</a> 下载和安装 ecc 编译工具链和 ecli 运行时。我们使用 eunomia-bpf 编译运行这个例子。</p>
|
||
<p>Compile:</p>
|
||
<pre><code class="language-shell">docker run -it -v `pwd`/:/src/ yunwei37/ebpm:latest
|
||
</code></pre>
|
||
<p>或者</p>
|
||
<pre><code class="language-console">$ ecc runqlat.bpf.c runqlat.h
|
||
Compiling bpf object...
|
||
Generating export types...
|
||
Packing ebpf object and config into package.json...
|
||
</code></pre>
|
||
<p>Run:</p>
|
||
<pre><code class="language-console">$ sudo ecli run examples/bpftools/runqlat/package.json -h
|
||
Usage: runqlat_bpf [--help] [--version] [--verbose] [--filter_cg] [--targ_per_process] [--targ_per_thread] [--targ_per_pidns] [--targ_ms] [--targ_tgid VAR]
|
||
|
||
A simple eBPF program
|
||
|
||
Optional arguments:
|
||
-h, --help shows help message and exits
|
||
-v, --version prints version information and exits
|
||
--verbose prints libbpf debug information
|
||
--filter_cg set value of bool variable filter_cg
|
||
--targ_per_process set value of bool variable targ_per_process
|
||
--targ_per_thread set value of bool variable targ_per_thread
|
||
--targ_per_pidns set value of bool variable targ_per_pidns
|
||
--targ_ms set value of bool variable targ_ms
|
||
--targ_tgid set value of pid_t variable targ_tgid
|
||
|
||
Built with eunomia-bpf framework.
|
||
See https://github.com/eunomia-bpf/eunomia-bpf for more information.
|
||
|
||
$ sudo ecli run examples/bpftools/runqlat/package.json
|
||
key = 4294967295
|
||
comm = rcu_preempt
|
||
|
||
(unit) : count distribution
|
||
0 -> 1 : 9 |**** |
|
||
2 -> 3 : 6 |** |
|
||
4 -> 7 : 12 |***** |
|
||
8 -> 15 : 28 |************* |
|
||
16 -> 31 : 40 |******************* |
|
||
32 -> 63 : 83 |****************************************|
|
||
64 -> 127 : 57 |*************************** |
|
||
128 -> 255 : 19 |********* |
|
||
256 -> 511 : 11 |***** |
|
||
512 -> 1023 : 2 | |
|
||
1024 -> 2047 : 2 | |
|
||
2048 -> 4095 : 0 | |
|
||
4096 -> 8191 : 0 | |
|
||
8192 -> 16383 : 0 | |
|
||
16384 -> 32767 : 1 | |
|
||
|
||
$ sudo ecli run examples/bpftools/runqlat/package.json --targ_per_process
|
||
key = 3189
|
||
comm = cpptools
|
||
|
||
(unit) : count distribution
|
||
0 -> 1 : 0 | |
|
||
2 -> 3 : 0 | |
|
||
4 -> 7 : 0 | |
|
||
8 -> 15 : 1 |*** |
|
||
16 -> 31 : 2 |******* |
|
||
32 -> 63 : 11 |****************************************|
|
||
64 -> 127 : 8 |***************************** |
|
||
128 -> 255 : 3 |********** |
|
||
</code></pre>
|
||
<h2 id="总结"><a class="header" href="#总结">总结</a></h2>
|
||
<p>runqlat 是一个 Linux 内核 BPF 程序，通过柱状图来总结调度程序运行队列延迟，显示任务等待运行在 CPU 上的时间长度。编译这个程序可以使用 ecc 工具，运行时可以使用 ecli 命令。</p>
|
||
<p>runqlat 是一种用于监控Linux内核中进程调度延迟的工具。它可以帮助您了解进程在内核中等待执行的时间，并根据这些信息优化进程调度，提高系统的性能。可以在 libbpf-tools 中找到最初的源代码：<a href="https://github.com/iovisor/bcc/blob/master/libbpf-tools/runqlat.bpf.c">https://github.com/iovisor/bcc/blob/master/libbpf-tools/runqlat.bpf.c</a></p>
|
||
<p>更多的例子和详细的开发指南，请参考 eunomia-bpf 的官方文档：<a href="https://github.com/eunomia-bpf/eunomia-bpf">https://github.com/eunomia-bpf/eunomia-bpf</a></p>
|
||
<p>完整的教程和源代码已经全部开源，可以在 <a href="https://github.com/eunomia-bpf/bpf-developer-tutorial">https://github.com/eunomia-bpf/bpf-developer-tutorial</a> 中查看。</p>
|
||
|
||
</main>
|
||
|
||
<nav class="nav-wrapper" aria-label="Page navigation">
|
||
<!-- Mobile navigation buttons -->
|
||
<a rel="prev" href="../8-exitsnoop/index.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
||
<i class="fa fa-angle-left"></i>
|
||
</a>
|
||
|
||
<a rel="next" href="../10-hardirqs/index.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
||
<i class="fa fa-angle-right"></i>
|
||
</a>
|
||
|
||
<div style="clear: both"></div>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
|
||
<nav class="nav-wide-wrapper" aria-label="Page navigation">
|
||
<a rel="prev" href="../8-exitsnoop/index.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
||
<i class="fa fa-angle-left"></i>
|
||
</a>
|
||
|
||
<a rel="next" href="../10-hardirqs/index.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
||
<i class="fa fa-angle-right"></i>
|
||
</a>
|
||
</nav>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<script>
|
||
window.playground_copyable = true;
|
||
</script>
|
||
|
||
|
||
<script src="../elasticlunr.min.js"></script>
|
||
<script src="../mark.min.js"></script>
|
||
<script src="../searcher.js"></script>
|
||
|
||
<script src="../clipboard.min.js"></script>
|
||
<script src="../highlight.js"></script>
|
||
<script src="../book.js"></script>
|
||
|
||
<!-- Custom JS scripts -->
|
||
|
||
|
||
</div>
|
||
</body>
|
||
</html>
|