使用HtmlUnit的Java中的内存不足错误

Question

我使用htmlUnit和java构建了一个网络机器人，该机器人执行了很多工作，但是运行大约10分钟后，我总是收到以下错误消息。

该程序处理了一些文本文件，但以下错误似乎与HtmlUnit解析javascript有关。

Exception in thread "main" java.lang.OutOfMemoryError: GC overhead limit exceeded
at net.sourceforge.htmlunit.corejs.javascript.Parser.forLoop(Parser.java:1297)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statementHelper(Parser.java:982)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statement(Parser.java:926)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statements(Parser.java:886)
at net.sourceforge.htmlunit.corejs.javascript.Parser.block(Parser.java:1699)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statementHelper(Parser.java:1031)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statement(Parser.java:926)
at net.sourceforge.htmlunit.corejs.javascript.Parser.ifStatement(Parser.java:1102)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statementHelper(Parser.java:970)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statement(Parser.java:926)
at net.sourceforge.htmlunit.corejs.javascript.Parser.parseFunctionBody(Parser.java:662)
at net.sourceforge.htmlunit.corejs.javascript.Parser.function(Parser.java:827)
at net.sourceforge.htmlunit.corejs.javascript.Parser.primaryExpr(Parser.java:2746)
at net.sourceforge.htmlunit.corejs.javascript.Parser.memberExpr(Parser.java:2388)
at net.sourceforge.htmlunit.corejs.javascript.Parser.unaryExpr(Parser.java:2292)
at net.sourceforge.htmlunit.corejs.javascript.Parser.mulExpr(Parser.java:2219)
at net.sourceforge.htmlunit.corejs.javascript.Parser.addExpr(Parser.java:2205)
at net.sourceforge.htmlunit.corejs.javascript.Parser.shiftExpr(Parser.java:2188)
at net.sourceforge.htmlunit.corejs.javascript.Parser.relExpr(Parser.java:2165)
at net.sourceforge.htmlunit.corejs.javascript.Parser.eqExpr(Parser.java:2139)
at net.sourceforge.htmlunit.corejs.javascript.Parser.bitAndExpr(Parser.java:2130)
at net.sourceforge.htmlunit.corejs.javascript.Parser.bitXorExpr(Parser.java:2121)
at net.sourceforge.htmlunit.corejs.javascript.Parser.bitOrExpr(Parser.java:2112)
at net.sourceforge.htmlunit.corejs.javascript.Parser.andExpr(Parser.java:2103)
at net.sourceforge.htmlunit.corejs.javascript.Parser.orExpr(Parser.java:2094)
at net.sourceforge.htmlunit.corejs.javascript.Parser.condExpr(Parser.java:2060)
at net.sourceforge.htmlunit.corejs.javascript.Parser.assignExpr(Parser.java:2033)
at net.sourceforge.htmlunit.corejs.javascript.Parser.assignExpr(Parser.java:2044)
at net.sourceforge.htmlunit.corejs.javascript.Parser.expr(Parser.java:2023)
at net.sourceforge.htmlunit.corejs.javascript.Parser.nameOrLabel(Parser.java:1774)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statementHelper(Parser.java:1053)
at net.sourceforge.htmlunit.corejs.javascript.Parser.statement(Parser.java:926)

每当我用HtmlUnit加载javascript页面时，都会出现大量错误，例如：

net.sourceforge.htmlunit.corejs.javascript.EcmaError: TypeError: Expected argument of type object, but instead had type object (http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js#4)
at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.constructError(ScriptRuntime.java:3935)
at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.constructError(ScriptRuntime.java:3919)
at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.typeError(ScriptRuntime.java:3944)
at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.typeError1(ScriptRuntime.java:3954)
at net.sourceforge.htmlunit.corejs.javascript.ScriptableObject.ensureScriptableObject(ScriptableObject.java:2193)
at net.sourceforge.htmlunit.corejs.javascript.NativeObject.execIdCall(NativeObject.java:303)
at net.sourceforge.htmlunit.corejs.javascript.IdFunctionObject.call(IdFunctionObject.java:93)
at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1536)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:4)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:5)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:4)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:3)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:3)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:4)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:4)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script.n(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at script(http://ca.classistatic.com/service-static/frontend-service/common.b28d6b2c3f10a7b5388a.js:1)
at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:798)
at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.call(InterpretedFunction.java:105)
at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.doTopCall(ContextFactory.java:411)
at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.doTopCall(HtmlUnitContextFactory.java:309)
at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.doTopCall(ScriptRuntime.java:3286)
at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.exec(InterpretedFunction.java:115)
at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:827)
at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:939)
at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:628)
at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:513)
at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:836)
at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.execute(JavaScriptEngine.java:812)
at com.gargoylesoftware.htmlunit.html.HtmlPage.loadExternalJavaScriptFile(HtmlPage.java:997)
at com.gargoylesoftware.htmlunit.html.HtmlScript.executeScriptIfNeeded(HtmlScript.java:399)
at com.gargoylesoftware.htmlunit.html.HtmlScript$3.execute(HtmlScript.java:277)
at com.gargoylesoftware.htmlunit.html.HtmlScript.onAllChildrenAddedToPage(HtmlScript.java:293)
at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:799)
at org.apache.xerces.parsers.AbstractSAXParser.endElement(Unknown Source)
at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.endElement(HTMLParser.java:756)
at org.cyberneko.html.HTMLTagBalancer.callEndElement(HTMLTagBalancer.java:1170)
at org.cyberneko.html.HTMLTagBalancer.endElement(HTMLTagBalancer.java:1072)
at org.cyberneko.html.filters.DefaultFilter.endElement(DefaultFilter.java:206)
at org.cyberneko.html.filters.NamespaceBinder.endElement(NamespaceBinder.java:330)
at org.cyberneko.html.HTMLScanner$ContentScanner.scanEndElement(HTMLScanner.java:3126)
at org.cyberneko.html.HTMLScanner$ContentScanner.scan(HTMLScanner.java:2093)
at org.cyberneko.html.HTMLScanner.scanDocument(HTMLScanner.java:920)
at org.cyberneko.html.HTMLConfiguration.parse(HTMLConfiguration.java:499)
at org.cyberneko.html.HTMLConfiguration.parse(HTMLConfiguration.java:452)
at org.apache.xerces.parsers.XMLParser.parse(Unknown Source)
at com.gargoylesoftware.htmlunit.html.HTMLParser$HtmlUnitDOMBuilder.parse(HTMLParser.java:1039)
at com.gargoylesoftware.htmlunit.html.HTMLParser.parse(HTMLParser.java:252)
at com.gargoylesoftware.htmlunit.html.HTMLParser.parseHtml(HTMLParser.java:198)
at com.gargoylesoftware.htmlunit.DefaultPageCreator.createHtmlPage(DefaultPageCreator.java:271)
at com.gargoylesoftware.htmlunit.DefaultPageCreator.createPage(DefaultPageCreator.java:159)
at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:478)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:352)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:417)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:402)
at WebBotServicesAdID.replyToAd(WebBotServicesAdID.java:269)
at WebBotServicesAdID.main(WebBotServicesAdID.java:771)
======= EXCEPTION END ========

但是，这些错误似乎是不可避免的，并且不会导致程序停止。 页面仍然被加载，我仍然可以做我需要做的事情，因此我一直忽略它们。

这是OutOfMemoryError导致我忽略了这些错误的结果吗？

Answer 1

GC错误：

GC代表垃圾收集器，该错误表示GC正在努力工作，几乎什么也没做。 例如， 这里和这里已经讨论了这种错误。 您可以尝试增加堆（“ -Xmx1024m”，“-Xmx512m”等）或禁用错误验证（“ -XX：-UseGCOverheadLimit”）。 我认为您不应该使用这些选项中的任何一个。

如果您正在运行linux，则可以尝试使用jmap检查堆中的实时数据，然后相应地优化代码。

JS错误：

根据此答案，这些错误似乎是由脚本错误引起的。 尝试使用给定的建议禁用它们。

如果抛出了这些错误并且未正确处理，则某些对象可能会留在堆中，从而导致GC问题。 或者，您可能有一些代码（例如一个循环）实例化了多个对象。