jjzjj

Java G1GC 突然系统使用率飙升 100%

coder 2024-04-05 原文

我们使用的是 java 1.8.144_b_01。我们遇到 G1GC 系统使用率突然飙升的问题，例如:从 1 到 113、140，这比用户空间的 CPU 使用率非常高。

那时对象复制时间变得非常高~是正常值的 10 倍，我经常看到以下日志:

2018-03-09T14:55:30.111+0530: 45966.639: [GC pause (G1 Evacuation Pause) (young) (to-space exhausted), 2.1706858 secs]

在此之后负载平均值。开始飙升 > 100，当我在顶部看到时，我看到所有 CPU 都被系统空间占用，并且大多数情况下它在那里显示 100%。

所有这一切都是突然发生的 ~ 每天在 AWS 上的某个固定时间。有时应用程序运行 10 天没有问题，有时每天大约在同一时间我们会看到问题。每天的使用模式都完全相同。

接下来我该做什么？

   [Eden: 2656.0M(13.5G)->0.0B(13.7G) Survivors: 440.0M->592.0M Heap: 14.2G(23.2G)->2547.0M(23.8G)]
 [Times: user=0.00 sys=0.00, real=1.76 secs] 
2018-03-09T14:55:26.647+0530: 45963.175: [GC pause (GCLocker Initiated GC) (young) (initial-mark), 0.1116088 secs]
   [Parallel Time: 97.9 ms, GC Workers: 16]
      [GC Worker Start (ms): Min: 45963178.4, Avg: 45963178.6, Max: 45963178.8, Diff: 0.4]
      [Ext Root Scanning (ms): Min: 5.7, Avg: 6.6, Max: 12.7, Diff: 7.0, Sum: 104.9]
      [Update RS (ms): Min: 40.7, Avg: 47.1, Max: 47.7, Diff: 7.0, Sum: 753.2]
         [Processed Buffers: Min: 181, Avg: 226.9, Max: 310, Diff: 129, Sum: 3631]
      [Scan RS (ms): Min: 3.8, Avg: 4.1, Max: 4.2, Diff: 0.3, Sum: 64.9]
      [Code Root Scanning (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
      [Object Copy (ms): Min: 38.2, Avg: 38.8, Max: 39.3, Diff: 1.1, Sum: 620.9]
      [Termination (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
         [Termination Attempts: Min: 1, Avg: 1.0, Max: 1, Diff: 0, Sum: 16]
      [GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.2, Diff: 0.2, Sum: 1.3]
      [GC Worker Total (ms): Min: 96.3, Avg: 96.6, Max: 96.8, Diff: 0.4, Sum: 1545.4]
      [GC Worker End (ms): Min: 45963275.1, Avg: 45963275.2, Max: 45963275.3, Diff: 0.2]
   [Code Root Fixup: 0.4 ms]
   [Code Root Purge: 0.0 ms]
   [Clear CT: 0.6 ms]
   [Other: 12.7 ms]
      [Choose CSet: 0.0 ms]
      [Ref Proc: 5.6 ms]
      [Ref Enq: 0.0 ms]
      [Redirty Cards: 0.5 ms]
      [Humongous Register: 0.1 ms]
      [Humongous Reclaim: 1.3 ms]
      [Free CSet: 0.6 ms]
   [Eden: 592.0M(13.7G)->0.0B(13.8G) Survivors: 592.0M->504.0M Heap: 4605.8M(23.8G)->2469.3M(23.8G)]
 [Times: user=0.00 sys=0.00, real=0.11 secs] 
2018-03-09T14:55:26.760+0530: 45963.287: [GC concurrent-root-region-scan-start]
2018-03-09T14:55:26.798+0530: 45963.325: [GC concurrent-root-region-scan-end, 0.0379580 secs]
2018-03-09T14:55:26.798+0530: 45963.325: [GC concurrent-mark-start]
2018-03-09T14:55:27.851+0530: 45964.379: [GC concurrent-mark-end, 1.0532587 secs]
2018-03-09T14:55:27.877+0530: 45964.405: [GC remark 2018-03-09T14:55:27.878+0530: 45964.405: [Finalize Marking, 0.0035673 secs] 2018-03-09T14:55:27.881+0530: 45964.409: [GC ref-proc, 0.0021035 secs] 2018-03-09T14:55:27.883+0530: 45964.411: [Unloading, 0.0291335 secs], 0.0380596 secs]
 [Times: user=0.00 sys=0.00, real=0.03 secs] 
2018-03-09T14:55:27.942+0530: 45964.470: [GC cleanup 6702M->6702M(23G), 0.0086775 secs]
 [Times: user=0.00 sys=0.00, real=0.01 secs] 
2018-03-09T14:55:30.111+0530: 45966.639: [GC pause (G1 Evacuation Pause) (young) (to-space exhausted), 2.1706858 secs]
   [Parallel Time: 1692.2 ms, GC Workers: 16]
      [GC Worker Start (ms): Min: 45966642.3, Avg: 45966642.5, Max: 45966642.7, Diff: 0.4]
      [Ext Root Scanning (ms): Min: 1.3, Avg: 3.9, Max: 12.1, Diff: 10.7, Sum: 62.8]
      [Update RS (ms): Min: 30.6, Avg: 37.9, Max: 38.5, Diff: 7.9, Sum: 605.8]
         [Processed Buffers: Min: 166, Avg: 246.8, Max: 343, Diff: 177, Sum: 3949]
      [Scan RS (ms): Min: 4.0, Avg: 4.1, Max: 4.2, Diff: 0.2, Sum: 65.6]
      [Code Root Scanning (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
      [Object Copy (ms): Min: 1640.6, Avg: 1645.6, Max: 1647.7, Diff: 7.1, Sum: 26329.1]
      [Termination (ms): Min: 0.0, Avg: 0.2, Max: 0.3, Diff: 0.3, Sum: 2.4]
         [Termination Attempts: Min: 1, Avg: 4.2, Max: 6, Diff: 5, Sum: 67]
      [GC Worker Other (ms): Min: 0.0, Avg: 0.0, Max: 0.1, Diff: 0.1, Sum: 0.7]
      [GC Worker Total (ms): Min: 1691.5, Avg: 1691.7, Max: 1691.8, Diff: 0.4, Sum: 27066.6]
      [GC Worker End (ms): Min: 45968334.1, Avg: 45968334.2, Max: 45968334.2, Diff: 0.1]
   [Code Root Fixup: 0.3 ms]
   [Code Root Purge: 0.0 ms]
   [Clear CT: 0.7 ms]
   [Other: 477.5 ms]
      [Evacuation Failure: 302.2 ms]
      [Choose CSet: 0.0 ms]
      [Ref Proc: 159.1 ms]
      [Ref Enq: 0.1 ms]
      [Redirty Cards: 1.1 ms]
      [Humongous Register: 0.6 ms]
      [Humongous Reclaim: 9.6 ms]
      [Free CSet: 0.3 ms]
   [Eden: 1768.0M(13.8G)->0.0B(13.5G) Survivors: 504.0M->176.0M Heap: 14.1G(23.8G)->4432.1M(24.0G)]
 [Times: user=0.00 sys=0.00, real=2.17 secs] 
2018-03-09T14:55:32.555+0530: 45969.083: [GC pause (G1 Humongous Allocation) (young) (initial-mark), 0.1336821 secs]
   [Parallel Time: 105.7 ms, GC Workers: 16]
      [GC Worker Start (ms): Min: 45969086.4, Avg: 45969086.6, Max: 45969086.7, Diff: 0.3]
      [Ext Root Scanning (ms): Min: 5.8, Avg: 6.6, Max: 13.2, Diff: 7.4, Sum: 105.1]
      [Update RS (ms): Min: 72.0, Avg: 78.6, Max: 79.4, Diff: 7.4, Sum: 1258.2]
         [Processed Buffers: Min: 243, Avg: 337.2, Max: 502, Diff: 259, Sum: 5396]
      [Scan RS (ms): Min: 0.4, Avg: 0.7, Max: 0.8, Diff: 0.5, Sum: 11.8]
      [Code Root Scanning (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.0]
      [Object Copy (ms): Min: 18.0, Avg: 18.4, Max: 18.6, Diff: 0.6, Sum: 294.7]
      [Termination (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
         [Termination Attempts: Min: 1, Avg: 1.1, Max: 2, Diff: 1, Sum: 18]
      [GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 1.0]
      [GC Worker Total (ms): Min: 104.3, Avg: 104.4, Max: 104.6, Diff: 0.3, Sum: 1670.9]
      [GC Worker End (ms): Min: 45969191.0, Avg: 45969191.0, Max: 45969191.1, Diff: 0.1]
   [Code Root Fixup: 0.6 ms]
   [Code Root Purge: 0.0 ms]
   [Clear CT: 0.6 ms]
   [Other: 26.8 ms]
      [Choose CSet: 0.0 ms]
      [Ref Proc: 19.6 ms]
      [Ref Enq: 0.1 ms]
      [Redirty Cards: 0.8 ms]
      [Humongous Register: 0.0 ms]
      [Humongous Reclaim: 0.4 ms]
      [Free CSet: 0.2 ms]
   [Eden: 392.0M(13.5G)->0.0B(13.3G) Survivors: 176.0M->224.0M Heap: 5148.1M(24.0G)->4486.3M(24.0G)]
 [Times: user=0.00 sys=0.00, real=0.14 secs] 
2018-03-09T14:55:32.689+0530: 45969.217: [GC concurrent-root-region-scan-start]
2018-03-09T14:55:32.751+0530: 45969.279: [GC concurrent-root-region-scan-end, 0.0620086 secs]
2018-03-09T14:55:32.751+0530: 45969.279: [GC concurrent-mark-start]
2018-03-09T14:55:34.004+0530: 45970.531: [GC concurrent-mark-end, 1.2523056 secs]
2018-03-09T14:55:34.031+0530: 45970.559: [GC remark 2018-03-09T14:55:34.031+0530: 45970.559: [Finalize Marking, 0.0036417 secs] 2018-03-09T14:55:34.035+0530: 45970.563: [GC ref-proc, 0.0171440 secs] 2018-03-09T14:55:34.052+0530: 45970.580: [Unloading, 0.0319188 secs], 0.0563588 secs]
 [Times: user=0.40 sys=0.00, real=0.06 secs] 
2018-03-09T14:55:34.115+0530: 45970.642: [GC cleanup 8540M->8540M(24G), 0.0092065 secs]
 [Times: user=0.12 sys=0.00, real=0.01 secs] 
2018-03-09T14:55:35.889+0530: 45972.417: [GC pause (G1 Humongous Allocation) (young) (to-space exhausted), 1.5352217 secs]
   [Parallel Time: 1216.7 ms, GC Workers: 16]
      [GC Worker Start (ms): Min: 45972420.7, Avg: 45972420.9, Max: 45972421.1, Diff: 0.4]
      [Ext Root Scanning (ms): Min: 1.7, Avg: 3.2, Max: 10.8, Diff: 9.0, Sum: 51.4]
      [Update RS (ms): Min: 44.0, Avg: 45.0, Max: 45.5, Diff: 1.4, Sum: 719.4]
         [Processed Buffers: Min: 209, Avg: 295.3, Max: 401, Diff: 192, Sum: 4725]
      [Scan RS (ms): Min: 7.5, Avg: 7.9, Max: 8.0, Diff: 0.5, Sum: 125.9]
      [Code Root Scanning (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
      [Object Copy (ms): Min: 1153.4, Avg: 1160.0, Max: 1161.4, Diff: 8.0, Sum: 18559.9]
      [Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.3, Diff: 0.3, Sum: 2.1]
         [Termination Attempts: Min: 1, Avg: 1.0, Max: 1, Diff: 0, Sum: 16]
      [GC Worker Other (ms): Min: 0.0, Avg: 0.0, Max: 0.1, Diff: 0.1, Sum: 0.8]
      [GC Worker Total (ms): Min: 1216.0, Avg: 1216.2, Max: 1216.4, Diff: 0.4, Sum: 19459.4]
      [GC Worker End (ms): Min: 45973637.0, Avg: 45973637.1, Max: 45973637.1, Diff: 0.1]
   [Code Root Fixup: 0.3 ms]
   [Code Root Purge: 0.0 ms]
   [Clear CT: 0.9 ms]
   [Other: 317.3 ms]
      [Evacuation Failure: 302.0 ms]
      [Choose CSet: 0.0 ms]
      [Ref Proc: 0.5 ms]
      [Ref Enq: 0.0 ms]
      [Redirty Cards: 1.3 ms]
      [Humongous Register: 0.5 ms]
      [Humongous Reclaim: 7.7 ms]
      [Free CSet: 0.4 ms]
   [Eden: 2504.0M(13.3G)->0.0B(1224.0M) Survivors: 224.0M->0.0B Heap: 15.5G(24.0G)->6956.9M(24.0G)]
 [Times: user=5.67 sys=0.11, real=1.53 secs] 
2018-03-09T14:55:38.964+0530: 45975.492: [GC pause (G1 Evacuation Pause) (mixed), 0.1187935 secs]
   [Parallel Time: 95.2 ms, GC Workers: 16]
      [GC Worker Start (ms): Min: 45975495.3, Avg: 45975495.5, Max: 45975495.8, Diff: 0.5]
      [Ext Root Scanning (ms): Min: 4.3, Avg: 5.7, Max: 13.8, Diff: 9.5, Sum: 91.2]
      [Update RS (ms): Min: 64.9, Avg: 73.0, Max: 74.3, Diff: 9.4, Sum: 1167.3]
         [Processed Buffers: Min: 268, Avg: 343.9, Max: 491, Diff: 223, Sum: 5503]
      [Scan RS (ms): Min: 1.7, Avg: 2.0, Max: 2.1, Diff: 0.4, Sum: 32.4]
      [Code Root Scanning (ms): Min: 0.0, Avg: 0.0, Max: 0.0, Diff: 0.0, Sum: 0.1]
:

虚拟机参数是:

-XX:+PrintGCDateStamps
-XX:+UseG1GC
-XX:MaxJavaStackTraceDepth=1000000
-XX:MaxGCPauseMillis=500
-Xmx24576m
-Xloggc:/tmp/gc/gc-%t.log
-XX:+PrintGCTimeStamps
-XX:G1ReservePercent=20
-XX:+PrintGCDetails
-XX:MaxPermSize=768m
-XX:+HeapDumpOnOutOfMemoryError
-XX:InitiatingHeapOccupancyPercent=20
-Xms10480m

最佳答案

有很多事情同时发生。由于 InitiatingHeapOccupancyPercent=20，它似乎连续开始并发标记周期。

GC pause (G1 Humongous Allocation) 的多个条目表明您正在连续分配非常大的对象并且没有足够的连续可用空间来容纳它们，大概是由于之前分配的对象没有已被收集或due to heap fragmentation ，同样是由巨大的分配引起的。

(to-space exhausted)

此时这只是锦上添花，收集器找不到足够的空间来移动对象，不得不过早地占用区域。

您应该在分配分析器下运行您的应用程序并优化您的代码以减少巨大的、短暂的对象的爆发。

关于Java G1GC 突然系统使用率飙升 100%，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/49207352/

JavaG1GCDiffms0.0garbage-collectionload

有关Java G1GC 突然系统使用率飙升 100%的更多相关文章

  1. ruby - 如何使用 Nokogiri 的 xpath 和 at_xpath 方法 - 2

    我正在学习如何使用Nokogiri，根据这段代码我遇到了一些问题:require'rubygems'require'mechanize'post_agent=WWW::Mechanize.newpost_page=post_agent.get('http://www.vbulletin.org/forum/showthread.php?t=230708')puts"\nabsolutepathwithtbodygivesnil"putspost_page.parser.xpath('/html/body/div/div/div/div/div/table/tbody/tr/td/div

  2. ruby - 使用 RubyZip 生成 ZIP 文件时设置压缩级别 - 2

    我有一个Ruby程序，它使用rubyzip压缩XML文件的目录树。gem。我的问题是文件开始变得很重，我想提高压缩级别，因为压缩时间不是问题。我在rubyzipdocumentation中找不到一种为创建的ZIP文件指定压缩级别的方法。有人知道如何更改此设置吗？是否有另一个允许指定压缩级别的Ruby库？ 最佳答案 这是我通过查看ruby​​zip内部创建的代码。level=Zlib::BEST_COMPRESSIONZip::ZipOutputStream.open(zip_file)do|zip|Dir.glob("**/*")d

  3. ruby - 为什么我可以在 Ruby 中使用 Object#send 访问私有(private)/ protected 方法？ - 2

    类classAprivatedeffooputs:fooendpublicdefbarputs:barendprivatedefzimputs:zimendprotecteddefdibputs:dibendendA的实例a=A.new测试a.foorescueputs:faila.barrescueputs:faila.zimrescueputs:faila.dibrescueputs:faila.gazrescueputs:fail测试输出failbarfailfailfail.发送测试[:foo,:bar,:zim,:dib,:gaz].each{|m|a.send(m)resc

  4. ruby-on-rails - 使用 Ruby on Rails 进行自动化测试 - 最佳实践 - 2

    很好奇，就使用ruby​​onrails自动化单元测试而言，你们正在做什么？您是否创建了一个脚本来在cron中运行rake作业并将结果邮寄给您？git中的预提交Hook？只是手动调用？我完全理解测试，但想知道在错误发生之前捕获错误的最佳实践是什么。让我们理所当然地认为测试本身是完美无缺的，并且可以正常工作。下一步是什么以确保他们在正确的时间将可能有害的结果传达给您？ 最佳答案 不确定您到底想听什么，但是有几个级别的自动代码库控制:在处理某项功能时，您可以使用类似autotest的内容获得关于哪些有效，哪些无效的即时反馈。要确保您的提

  5. ruby - 在 Ruby 中使用匿名模块 - 2

    假设我做了一个模块如下:m=Module.newdoclassCendend三个问题:除了对m的引用之外，还有什么方法可以访问C和m中的其他内容？我可以在创建匿名模块后为其命名吗(就像我输入“module...”一样)？如何在使用完匿名模块后将其删除，使其定义的常量不再存在？ 最佳答案 三个答案:是的，使用ObjectSpace.此代码使c引用你的类(class)C不引用m:c=nilObjectSpace.each_object{|obj|c=objif(Class===objandobj.name=~/::C$/)}当然这取决于

  6. ruby - 使用 ruby​​ 和 savon 的 SOAP 服务 - 2

    我正在尝试使用ruby​​和Savon来使用网络服务。测试服务为http://www.webservicex.net/WS/WSDetails.aspx?WSID=9&CATID=2require'rubygems'require'savon'client=Savon::Client.new"http://www.webservicex.net/stockquote.asmx?WSDL"client.get_quotedo|soap|soap.body={:symbol=>"AAPL"}end返回SOAP异常。检查soap信封，在我看来soap请求没有正确的命名空间。任何人都可以建议我

  7. python - 如何使用 Ruby 或 Python 创建一系列高音调和低音调的蜂鸣声？ - 2

    关闭。这个问题是opinion-based.它目前不接受答案。想要改进这个问题？更新问题，以便editingthispost可以用事实和引用来回答它.关闭4年前。Improvethisquestion我想在固定时间创建一系列低音和高音调的哔哔声。例如:在150毫秒时发出高音调的蜂鸣声在151毫秒时发出低音调的蜂鸣声200毫秒时发出低音调的蜂鸣声250毫秒的高音调蜂鸣声有没有办法在Ruby或Python中做到这一点？我真的不在乎输出编码是什么(.wav、.mp3、.ogg等等)，但我确实想创建一个输出文件。

  8. ruby-on-rails - 'compass watch' 是如何工作的/它是如何与 rails 一起使用的 - 2

    我在我的项目目录中完成了compasscreate.和compassinitrails。几个问题:我已将我的.sass文件放在public/stylesheets中。这是放置它们的正确位置吗？当我运行compasswatch时，它不会自动编译这些.sass文件。我必须手动指定文件:compasswatchpublic/stylesheets/myfile.sass等。如何让它自动运行？文件ie.css、print.css和screen.css已放在stylesheets/compiled。如何在编译后不让它们重新出现的情况下删除它们？我自己编译的.sass文件编译成compiled/t

  9. ruby - 使用 ruby​​ 将 HTML 转换为纯文本并维护结构/格式 - 2

    我想将html转换为纯文本。不过，我不想只删除标签，我想智能地保留尽可能多的格式。为插入换行符标签，检测段落并格式化它们等。输入非常简单，通常是格式良好的html(不是整个文档，只是一堆内容，通常没有anchor或图像)。我可以将几个正则表达式放在一起，让我达到80%，但我认为可能有一些现有的解决方案更智能。 最佳答案 首先，不要尝试为此使用正则表达式。很有可能你会想出一个脆弱/脆弱的解决方案，它会随着HTML的变化而崩溃，或者很难管理和维护。您可以使用Nokogiri快速解析HTML并提取文本:require'nokogiri'h

  10. ruby - 在 64 位 Snow Leopard 上使用 rvm、postgres 9.0、ruby 1.9.2-p136 安装 pg gem 时出现问题 - 2

    我想为Heroku构建一个Rails3应用程序。他们使用Postgres作为他们的数据库，所以我通过MacPorts安装了postgres9.0。现在我需要一个postgresgem并且共识是出于性能原因你想要pggem。但是我对我得到的错误感到非常困惑当我尝试在rvm下通过geminstall安装pg时。我已经非常明确地指定了所有postgres目录的位置可以找到但仍然无法完成安装:$envARCHFLAGS='-archx86_64'geminstallpg--\--with-pg-config=/opt/local/var/db/postgresql90/defaultdb/po

随机推荐