诊断报告#

稳定性:2 - 稳定

生成 JSON 格式的诊断摘要,并写入文件。

该报告旨在用于开发、测试和生产环境,以捕获并保留用于问题排查的信息。它包括 JavaScript 和原生堆栈跟踪、堆统计信息、平台信息、资源使用情况等。启用报告选项后,除了通过 API 调用以编程方式触发外,还可以在未处理的异常、致命错误和用户信号上触发诊断报告。

下面提供了一个在未捕获异常时生成的完整示例报告,以供参考。

{
  "header": {
    "reportVersion": 5,
    "event": "exception",
    "trigger": "Exception",
    "filename": "report.20181221.005011.8974.0.001.json",
    "dumpEventTime": "2018-12-21T00:50:11Z",
    "dumpEventTimeStamp": "1545371411331",
    "processId": 8974,
    "cwd": "/home/nodeuser/project/node",
    "commandLine": [
      "/home/nodeuser/project/node/out/Release/node",
      "--report-uncaught-exception",
      "/home/nodeuser/project/node/test/report/test-exception.js",
      "child"
    ],
    "nodejsVersion": "v12.0.0-pre",
    "glibcVersionRuntime": "2.17",
    "glibcVersionCompiler": "2.17",
    "wordSize": "64 bit",
    "arch": "x64",
    "platform": "linux",
    "componentVersions": {
      "node": "12.0.0-pre",
      "v8": "7.1.302.28-node.5",
      "uv": "1.24.1",
      "zlib": "1.2.11",
      "ares": "1.15.0",
      "modules": "68",
      "nghttp2": "1.34.0",
      "napi": "3",
      "llhttp": "1.0.1",
      "openssl": "1.1.0j"
    },
    "release": {
      "name": "node"
    },
    "osName": "Linux",
    "osRelease": "3.10.0-862.el7.x86_64",
    "osVersion": "#1 SMP Wed Mar 21 18:14:51 EDT 2018",
    "osMachine": "x86_64",
    "cpus": [
      {
        "model": "Intel(R) Core(TM) i7-6820HQ CPU @ 2.70GHz",
        "speed": 2700,
        "user": 88902660,
        "nice": 0,
        "sys": 50902570,
        "idle": 241732220,
        "irq": 0
      },
      {
        "model": "Intel(R) Core(TM) i7-6820HQ CPU @ 2.70GHz",
        "speed": 2700,
        "user": 88902660,
        "nice": 0,
        "sys": 50902570,
        "idle": 241732220,
        "irq": 0
      }
    ],
    "networkInterfaces": [
      {
        "name": "en0",
        "internal": false,
        "mac": "13:10:de:ad:be:ef",
        "address": "10.0.0.37",
        "netmask": "255.255.255.0",
        "family": "IPv4"
      }
    ],
    "host": "test_machine"
  },
  "javascriptStack": {
    "message": "Error: *** test-exception.js: throwing uncaught Error",
    "stack": [
      "at myException (/home/nodeuser/project/node/test/report/test-exception.js:9:11)",
      "at Object.<anonymous> (/home/nodeuser/project/node/test/report/test-exception.js:12:3)",
      "at Module._compile (internal/modules/cjs/loader.js:718:30)",
      "at Object.Module._extensions..js (internal/modules/cjs/loader.js:729:10)",
      "at Module.load (internal/modules/cjs/loader.js:617:32)",
      "at tryModuleLoad (internal/modules/cjs/loader.js:560:12)",
      "at Function.Module._load (internal/modules/cjs/loader.js:552:3)",
      "at Function.Module.runMain (internal/modules/cjs/loader.js:771:12)",
      "at executeUserCode (internal/bootstrap/node.js:332:15)"
    ]
  },
  "nativeStack": [
    {
      "pc": "0x000055b57f07a9ef",
      "symbol": "report::GetNodeReport(v8::Isolate*, node::Environment*, char const*, char const*, v8::Local<v8::String>, std::ostream&) [./node]"
    },
    {
      "pc": "0x000055b57f07cf03",
      "symbol": "report::GetReport(v8::FunctionCallbackInfo<v8::Value> const&) [./node]"
    },
    {
      "pc": "0x000055b57f1bccfd",
      "symbol": " [./node]"
    },
    {
      "pc": "0x000055b57f1be048",
      "symbol": "v8::internal::Builtin_HandleApiCall(int, v8::internal::Object**, v8::internal::Isolate*) [./node]"
    },
    {
      "pc": "0x000055b57feeda0e",
      "symbol": " [./node]"
    }
  ],
  "javascriptHeap": {
    "totalMemory": 5660672,
    "executableMemory": 524288,
    "totalCommittedMemory": 5488640,
    "availableMemory": 4341379928,
    "totalGlobalHandlesMemory": 8192,
    "usedGlobalHandlesMemory": 3136,
    "usedMemory": 4816432,
    "memoryLimit": 4345298944,
    "mallocedMemory": 254128,
    "externalMemory": 315644,
    "peakMallocedMemory": 98752,
    "nativeContextCount": 1,
    "detachedContextCount": 0,
    "doesZapGarbage": 0,
    "heapSpaces": {
      "read_only_space": {
        "memorySize": 524288,
        "committedMemory": 39208,
        "capacity": 515584,
        "used": 30504,
        "available": 485080
      },
      "new_space": {
        "memorySize": 2097152,
        "committedMemory": 2019312,
        "capacity": 1031168,
        "used": 985496,
        "available": 45672
      },
      "old_space": {
        "memorySize": 2273280,
        "committedMemory": 1769008,
        "capacity": 1974640,
        "used": 1725488,
        "available": 249152
      },
      "code_space": {
        "memorySize": 696320,
        "committedMemory": 184896,
        "capacity": 152128,
        "used": 152128,
        "available": 0
      },
      "map_space": {
        "memorySize": 536576,
        "committedMemory": 344928,
        "capacity": 327520,
        "used": 327520,
        "available": 0
      },
      "large_object_space": {
        "memorySize": 0,
        "committedMemory": 0,
        "capacity": 1520590336,
        "used": 0,
        "available": 1520590336
      },
      "new_large_object_space": {
        "memorySize": 0,
        "committedMemory": 0,
        "capacity": 0,
        "used": 0,
        "available": 0
      }
    }
  },
  "resourceUsage": {
    "rss": "35766272",
    "free_memory": "1598337024",
    "total_memory": "17179869184",
    "available_memory": "1598337024",
    "maxRss": "36624662528",
    "constrained_memory": "36624662528",
    "userCpuSeconds": 0.040072,
    "kernelCpuSeconds": 0.016029,
    "cpuConsumptionPercent": 5.6101,
    "userCpuConsumptionPercent": 4.0072,
    "kernelCpuConsumptionPercent": 1.6029,
    "pageFaults": {
      "IORequired": 0,
      "IONotRequired": 4610
    },
    "fsActivity": {
      "reads": 0,
      "writes": 0
    }
  },
  "uvthreadResourceUsage": {
    "userCpuSeconds": 0.039843,
    "kernelCpuSeconds": 0.015937,
    "cpuConsumptionPercent": 5.578,
    "userCpuConsumptionPercent": 3.9843,
    "kernelCpuConsumptionPercent": 1.5937,
    "fsActivity": {
      "reads": 0,
      "writes": 0
    }
  },
  "libuv": [
    {
      "type": "async",
      "is_active": true,
      "is_referenced": false,
      "address": "0x0000000102910900",
      "details": ""
    },
    {
      "type": "timer",
      "is_active": false,
      "is_referenced": false,
      "address": "0x00007fff5fbfeab0",
      "repeat": 0,
      "firesInMsFromNow": 94403548320796,
      "expired": true
    },
    {
      "type": "check",
      "is_active": true,
      "is_referenced": false,
      "address": "0x00007fff5fbfeb48"
    },
    {
      "type": "idle",
      "is_active": false,
      "is_referenced": true,
      "address": "0x00007fff5fbfebc0"
    },
    {
      "type": "prepare",
      "is_active": false,
      "is_referenced": false,
      "address": "0x00007fff5fbfec38"
    },
    {
      "type": "check",
      "is_active": false,
      "is_referenced": false,
      "address": "0x00007fff5fbfecb0"
    },
    {
      "type": "async",
      "is_active": true,
      "is_referenced": false,
      "address": "0x000000010188f2e0"
    },
    {
      "type": "tty",
      "is_active": false,
      "is_referenced": true,
      "address": "0x000055b581db0e18",
      "width": 204,
      "height": 55,
      "fd": 17,
      "writeQueueSize": 0,
      "readable": true,
      "writable": true
    },
    {
      "type": "signal",
      "is_active": true,
      "is_referenced": false,
      "address": "0x000055b581d80010",
      "signum": 28,
      "signal": "SIGWINCH"
    },
    {
      "type": "tty",
      "is_active": true,
      "is_referenced": true,
      "address": "0x000055b581df59f8",
      "width": 204,
      "height": 55,
      "fd": 19,
      "writeQueueSize": 0,
      "readable": true,
      "writable": true
    },
    {
      "type": "loop",
      "is_active": true,
      "address": "0x000055fc7b2cb180",
      "loopIdleTimeSeconds": 22644.8
    },
    {
      "type": "tcp",
      "is_active": true,
      "is_referenced": true,
      "address": "0x000055e70fcb85d8",
      "localEndpoint": {
        "host": "localhost",
        "ip4": "127.0.0.1",
        "port": 48986
      },
      "remoteEndpoint": {
        "host": "localhost",
        "ip4": "127.0.0.1",
        "port": 38573
      },
      "sendBufferSize": 2626560,
      "recvBufferSize": 131072,
      "fd": 24,
      "writeQueueSize": 0,
      "readable": true,
      "writable": true
    }
  ],
  "workers": [],
  "environmentVariables": {
    "REMOTEHOST": "REMOVED",
    "MANPATH": "/opt/rh/devtoolset-3/root/usr/share/man:",
    "XDG_SESSION_ID": "66126",
    "HOSTNAME": "test_machine",
    "HOST": "test_machine",
    "TERM": "xterm-256color",
    "SHELL": "/bin/csh",
    "SSH_CLIENT": "REMOVED",
    "PERL5LIB": "/opt/rh/devtoolset-3/root//usr/lib64/perl5/vendor_perl:/opt/rh/devtoolset-3/root/usr/lib/perl5:/opt/rh/devtoolset-3/root//usr/share/perl5/vendor_perl",
    "OLDPWD": "/home/nodeuser/project/node/src",
    "JAVACONFDIRS": "/opt/rh/devtoolset-3/root/etc/java:/etc/java",
    "SSH_TTY": "/dev/pts/0",
    "PCP_DIR": "/opt/rh/devtoolset-3/root",
    "GROUP": "normaluser",
    "USER": "nodeuser",
    "LD_LIBRARY_PATH": "/opt/rh/devtoolset-3/root/usr/lib64:/opt/rh/devtoolset-3/root/usr/lib",
    "HOSTTYPE": "x86_64-linux",
    "XDG_CONFIG_DIRS": "/opt/rh/devtoolset-3/root/etc/xdg:/etc/xdg",
    "MAIL": "/var/spool/mail/nodeuser",
    "PATH": "/home/nodeuser/project/node:/opt/rh/devtoolset-3/root/usr/bin:/usr/local/bin:/usr/bin:/usr/local/sbin:/usr/sbin",
    "PWD": "/home/nodeuser/project/node",
    "LANG": "en_US.UTF-8",
    "PS1": "\\u@\\h : \\[\\e[31m\\]\\w\\[\\e[m\\] >  ",
    "SHLVL": "2",
    "HOME": "/home/nodeuser",
    "OSTYPE": "linux",
    "VENDOR": "unknown",
    "PYTHONPATH": "/opt/rh/devtoolset-3/root/usr/lib64/python2.7/site-packages:/opt/rh/devtoolset-3/root/usr/lib/python2.7/site-packages",
    "MACHTYPE": "x86_64",
    "LOGNAME": "nodeuser",
    "XDG_DATA_DIRS": "/opt/rh/devtoolset-3/root/usr/share:/usr/local/share:/usr/share",
    "LESSOPEN": "||/usr/bin/lesspipe.sh %s",
    "INFOPATH": "/opt/rh/devtoolset-3/root/usr/share/info",
    "XDG_RUNTIME_DIR": "/run/user/50141",
    "_": "./node"
  },
  "userLimits": {
    "core_file_size_blocks": {
      "soft": "",
      "hard": "unlimited"
    },
    "data_seg_size_bytes": {
      "soft": "unlimited",
      "hard": "unlimited"
    },
    "file_size_blocks": {
      "soft": "unlimited",
      "hard": "unlimited"
    },
    "max_locked_memory_bytes": {
      "soft": "unlimited",
      "hard": 65536
    },
    "max_memory_size_bytes": {
      "soft": "unlimited",
      "hard": "unlimited"
    },
    "open_files": {
      "soft": "unlimited",
      "hard": 4096
    },
    "stack_size_bytes": {
      "soft": "unlimited",
      "hard": "unlimited"
    },
    "cpu_time_seconds": {
      "soft": "unlimited",
      "hard": "unlimited"
    },
    "max_user_processes": {
      "soft": "unlimited",
      "hard": 4127290
    },
    "virtual_memory_bytes": {
      "soft": "unlimited",
      "hard": "unlimited"
    }
  },
  "sharedObjects": [
    "/lib64/libdl.so.2",
    "/lib64/librt.so.1",
    "/lib64/libstdc++.so.6",
    "/lib64/libm.so.6",
    "/lib64/libgcc_s.so.1",
    "/lib64/libpthread.so.0",
    "/lib64/libc.so.6",
    "/lib64/ld-linux-x86-64.so.2"
  ]
} 

用法#

node --report-uncaught-exception --report-on-signal \
--report-on-fatalerror app.js 
  • --report-uncaught-exception 启用在未捕获异常时生成报告。在检查 JavaScript 堆栈以及原生堆栈和其他运行时环境数据时很有用。

  • --report-on-signal 启用在正在运行的 Node.js 进程接收到指定(或预定义)信号时生成报告。(关于如何修改触发报告的信号,请参见下文。)默认信号为 SIGUSR2。当需要从另一个程序触发报告时很有用。应用程序监控器可以利用此功能定期收集报告,并将丰富的内部运行时数据绘制到其视图中。

Windows 不支持基于信号的报告生成。

在正常情况下,无需修改触发报告的信号。但是,如果 SIGUSR2 已被用于其他目的,则此标志有助于更改用于报告生成的信号,并保留 SIGUSR2 用于所述目的的原始含义。

  • --report-on-fatalerror 启用在导致应用程序终止的致命错误(Node.js 运行时内部的错误,例如内存不足)时触发报告。有助于检查各种诊断数据元素,如堆、堆栈、事件循环状态、资源消耗等,以分析致命错误的原因。

  • --report-compact 以紧凑格式(单行 JSON)写入报告,比专为人类阅读设计的默认多行格式更容易被日志处理系统使用。

  • --report-directory 生成报告的位置。

  • --report-filename 写入报告的文件名。

  • --report-signal 设置或重置用于报告生成的信号(在 Windows 上不支持)。默认信号为 SIGUSR2

  • --report-exclude-network 从诊断报告中排除 header.networkInterfaces 并禁用 libuv.*.(remote|local)Endpoint.host 中的反向 DNS 查询。默认情况下此选项未设置,网络接口会被包含在内。

  • --report-exclude-env 从诊断报告中排除 environmentVariables。默认情况下此选项未设置,环境变量会被包含在内。

也可以通过 JavaScript 应用程序的 API 调用来触发报告。

process.report.writeReport(); 

此函数接受一个可选的附加参数 filename,它是报告写入文件的名称。

process.report.writeReport('./foo.json'); 

此函数接受一个可选的附加参数 err,它是一个 Error 对象,将用作报告中打印的 JavaScript 堆栈的上下文。当使用报告处理回调或异常处理程序中的错误时,这允许报告包含原始错误的位置以及处理它的位置。

try {
  process.chdir('/non-existent-path');
} catch (err) {
  process.report.writeReport(err);
}
// Any other code 

如果同时将文件名和错误对象传递给 writeReport(),则错误对象必须是第二个参数。

try {
  process.chdir('/non-existent-path');
} catch (err) {
  process.report.writeReport(filename, err);
}
// Any other code 

诊断报告的内容可以通过 JavaScript 应用程序的 API 调用以 JavaScript 对象的形式返回。

const report = process.report.getReport();
console.log(typeof report === 'object'); // true

// Similar to process.report.writeReport() output
console.log(JSON.stringify(report, null, 2)); 

此函数接受一个可选的附加参数 err,它是一个 Error 对象,将用作报告中打印的 JavaScript 堆栈的上下文。

const report = process.report.getReport(new Error('custom error'));
console.log(typeof report === 'object'); // true 

API 版本在从应用程序内部检查运行时状态时很有用,以便进行资源消耗、负载均衡、监控等的自我调整。

报告的内容包括一个头部部分,包含事件类型、日期、时间、PID 和 Node.js 版本;包含 JavaScript 和原生堆栈跟踪的部分;包含 V8 堆信息的部分;包含 libuv 句柄信息的部分;以及显示 CPU 和内存使用情况及系统限制的操作系统平台信息部分。可以使用 Node.js REPL 触发一个示例报告。

$ node
> process.report.writeReport();
Writing Node.js report to file: report.20181126.091102.8480.0.001.json
Node.js report completed
> 

当报告被写入时,开始和结束消息会输出到 stderr,并且报告的文件名会返回给调用者。默认文件名包括日期、时间、PID 和一个序列号。如果为同一个 Node.js 进程多次生成报告,序列号有助于将报告转储与运行时状态关联起来。

报告版本#

诊断报告有一个关联的单位数版本号(report.header.reportVersion),唯一地代表报告的格式。当添加或删除新键,或值的数据类型发生变化时,版本号会增加。报告版本定义在 LTS 版本之间保持一致。

版本历史#

版本 5#

userLimits 部分中,将键 data_seg_size_kbytesmax_memory_size_kbytesvirtual_memory_kbytes 分别替换为 data_seg_size_bytesmax_memory_size_bytesvirtual_memory_bytes,因为这些值是以字节为单位给出的。

{
  "userLimits": {
    // Skip some keys ...
    "data_seg_size_bytes": { // replacing data_seg_size_kbytes
      "soft": "unlimited",
      "hard": "unlimited"
    },
    // ...
    "max_memory_size_bytes": { // replacing max_memory_size_kbytes
      "soft": "unlimited",
      "hard": "unlimited"
    },
    // ...
    "virtual_memory_bytes": { // replacing virtual_memory_kbytes
      "soft": "unlimited",
      "hard": "unlimited"
    }
  }
} 
版本 4#

tcpudp libuv 句柄端点添加了新字段 ipv4ipv6。示例:

{
  "libuv": [
    {
      "type": "tcp",
      "is_active": true,
      "is_referenced": true,
      "address": "0x000055e70fcb85d8",
      "localEndpoint": {
        "host": "localhost",
        "ip4": "127.0.0.1", // new key
        "port": 48986
      },
      "remoteEndpoint": {
        "host": "localhost",
        "ip4": "127.0.0.1", // new key
        "port": 38573
      },
      "sendBufferSize": 2626560,
      "recvBufferSize": 131072,
      "fd": 24,
      "writeQueueSize": 0,
      "readable": true,
      "writable": true
    },
    {
      "type": "tcp",
      "is_active": true,
      "is_referenced": true,
      "address": "0x000055e70fcd68c8",
      "localEndpoint": {
        "host": "ip6-localhost",
        "ip6": "::1", // new key
        "port": 52266
      },
      "remoteEndpoint": {
        "host": "ip6-localhost",
        "ip6": "::1", // new key
        "port": 38573
      },
      "sendBufferSize": 2626560,
      "recvBufferSize": 131072,
      "fd": 25,
      "writeQueueSize": 0,
      "readable": false,
      "writable": false
    }
  ]
} 
版本 3#

以下内存使用键已添加到 resourceUsage 部分。

{
  "resourceUsage": {
    "rss": "35766272",
    "free_memory": "1598337024",
    "total_memory": "17179869184",
    "available_memory": "1598337024",
    "constrained_memory": "36624662528"
  }
} 
版本 2#

添加了 Worker 支持。有关更多详细信息,请参阅与工作线程的交互部分。

版本 1#

这是诊断报告的第一个版本。

配置#

报告生成的额外运行时配置可通过 process.report 的以下属性获得:

reportOnFatalError 当为 true 时,在致命错误时触发诊断报告。默认为 false

reportOnSignal 当为 true 时,在接收到信号时触发诊断报告。这在 Windows 上不受支持。默认为 false

reportOnUncaughtException 当为 true 时,在未捕获的异常时触发诊断报告。默认为 false

signal 指定将用于拦截外部触发器以生成报告的 POSIX 信号标识符。默认为 'SIGUSR2'

filename 指定文件系统中输出文件的名称。stdoutstderr 具有特殊含义。使用它们将导致报告被写入到相应的标准流中。在使用标准流的情况下,directory 中的值将被忽略。不支持 URL。默认为一个包含时间戳、PID 和序列号的复合文件名。

directory 指定报告将被写入的文件系统目录。不支持 URL。默认为 Node.js 进程的当前工作目录。

excludeNetwork 从诊断报告中排除 header.networkInterfaces

// Trigger report only on uncaught exceptions.
process.report.reportOnFatalError = false;
process.report.reportOnSignal = false;
process.report.reportOnUncaughtException = true;

// Trigger report for both internal errors as well as external signal.
process.report.reportOnFatalError = true;
process.report.reportOnSignal = true;
process.report.reportOnUncaughtException = false;

// Change the default signal to 'SIGQUIT' and enable it.
process.report.reportOnFatalError = false;
process.report.reportOnUncaughtException = false;
process.report.reportOnSignal = true;
process.report.signal = 'SIGQUIT';

// Disable network interfaces reporting
process.report.excludeNetwork = true; 

模块初始化时的配置也可以通过环境变量进行:

NODE_OPTIONS="--report-uncaught-exception \
  --report-on-fatalerror --report-on-signal \
  --report-signal=SIGUSR2  --report-filename=./report.json \
  --report-directory=/home/nodeuser" 

具体的 API 文档可以在 process API 文档部分找到。

与工作线程的交互#

Worker 线程可以像主线程一样创建报告。

报告将作为 workers 部分的一部分,包含有关当前线程的任何子工作线程的信息,每个工作线程都会以标准报告格式生成一份报告。

正在生成报告的线程将等待工作线程的报告完成。然而,这方面的延迟通常很低,因为正在运行的 JavaScript 和事件循环都会被中断以生成报告。