0

我正在尝试使用 Jena 的读取方法来读取大型数据集(超过 1 GB),但我收到内存不足错误。我尝试将 tomcat heapsize(-Xmx 参数)增加到 2048,这也是 eclipse.ini 文件中的相同参数。但是,我无法获得有效的解决方案,我愿意接受有关如何处理大型数据集的任何建议,因为我会将数据集解析为哈希图并在网页上显示内容。

控制台错误如下:

Exception in thread "http-bio-8080-AsyncTimeout" java.lang.OutOfMemoryError: GC overhead limit exceeded
    at java.util.concurrent.ConcurrentLinkedQueue.iterator(ConcurrentLinkedQueue.java:667)
    at org.apache.tomcat.util.net.JIoEndpoint$AsyncTimeout.run(JIoEndpoint.java:157)
    at java.lang.Thread.run(Thread.java:745)
Exception in thread "http-bio-8080-exec-6" java.lang.OutOfMemoryError: GC overhead limit exceeded
    at java.util.concurrent.CopyOnWriteArrayList.iterator(CopyOnWriteArrayList.java:959)
    at com.hp.hpl.jena.graph.impl.SimpleEventManager.notifyAddTriple(SimpleEventManager.java:91)
    at com.hp.hpl.jena.graph.impl.GraphBase.notifyAdd(GraphBase.java:124)
    at com.hp.hpl.jena.graph.impl.GraphBase.add(GraphBase.java:203)
    at org.apache.jena.riot.system.StreamRDFLib$ParserOutputGraph.triple(StreamRDFLib.java:165)
    at org.apache.jena.riot.lang.LangNTriples.runParser(LangNTriples.java:56)
    at org.apache.jena.riot.lang.LangBase.parse(LangBase.java:42)
    at org.apache.jena.riot.RDFParserRegistry$ReaderRIOTLang.read(RDFParserRegistry.java:182)
    at org.apache.jena.riot.RDFDataMgr.process(RDFDataMgr.java:906)
    at org.apache.jena.riot.RDFDataMgr.read(RDFDataMgr.java:257)
    at org.apache.jena.riot.RDFDataMgr.read(RDFDataMgr.java:243)
    at org.apache.jena.riot.adapters.RDFReaderRIOT_Web.read(RDFReaderRIOT_Web.java:96)
    at com.hp.hpl.jena.rdf.model.impl.ModelCom.read(ModelCom.java:235)
    at com.packages.rdf.FileAnalyse.GetFileComponents(FileAnalyse.java:77)
    at com.packages.servlets.CreatePatternServlet.GetStatements(CreatePatternServlet.java:96)
    at com.packages.servlets.CreatePatternServlet.doPost(CreatePatternServlet.java:68)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:646)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:727)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:303)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
    at org.apache.tomcat.websocket.server.WsFilter.doFilter(WsFilter.java:52)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
    at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:220)
    at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:122)
    at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:501)
    at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:171)
    at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:103)
    at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:950)
    at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:116)
    at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:408)
    at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:1070)

Exception in thread "ContainerBackgroundProcessor[StandardEngine[Catalina]]" java.lang.OutOfMemoryError: GC overhead limit exceeded
    at org.apache.naming.resources.FileDirContext.file(FileDirContext.java:765)
    at org.apache.naming.resources.FileDirContext.doGetAttributes(FileDirContext.java:398)
    at org.apache.naming.resources.BaseDirContext.getAttributes(BaseDirContext.java:1137)
    at org.apache.naming.resources.BaseDirContext.getAttributes(BaseDirContext.java:1090)
    at org.apache.naming.resources.ProxyDirContext.getAttributes(ProxyDirContext.java:882)
    at org.apache.catalina.loader.WebappClassLoader.modified(WebappClassLoader.java:1026)
    at org.apache.catalina.loader.WebappLoader.modified(WebappLoader.java:500)
    at org.apache.catalina.loader.WebappLoader.backgroundProcess(WebappLoader.java:420)
    at org.apache.catalina.core.ContainerBase.backgroundProcess(ContainerBase.java:1345)
    at org.apache.catalina.core.ContainerBase$ContainerBackgroundProcessor.processChildren(ContainerBase.java:1546)
    at org.apache.catalina.core.ContainerBase$ContainerBackgroundProcessor.processChildren(ContainerBase.java:1556)
    at org.apache.catalina.core.ContainerBase$ContainerBackgroundProcessor.processChildren(ContainerBase.java:1556)
    at org.apache.catalina.core.ContainerBase$ContainerBackgroundProcessor.run(ContainerBase.java:1524)
    at java.lang.Thread.run(Thread.java:745)
Exception in thread "http-bio-8080-exec-6" java.lang.OutOfMemoryError: GC overhead limit exceeded
    at org.apache.jena.riot.tokens.TokenizerText.parseToken(TokenizerText.java:170)
    at org.apache.jena.riot.tokens.TokenizerText.hasNext(TokenizerText.java:86)
    at org.apache.jena.atlas.iterator.PeekIterator.fill(PeekIterator.java:50)
    at org.apache.jena.atlas.iterator.PeekIterator.next(PeekIterator.java:92)
    at org.apache.jena.riot.lang.LangEngine.nextToken(LangEngine.java:99)
    at org.apache.jena.riot.lang.LangNTriples.parseOne(LangNTriples.java:71)
    at org.apache.jena.riot.lang.LangNTriples.runParser(LangNTriples.java:54)
    at org.apache.jena.riot.lang.LangBase.parse(LangBase.java:42)
    at org.apache.jena.riot.RDFParserRegistry$ReaderRIOTLang.read(RDFParserRegistry.java:182)
    at org.apache.jena.riot.RDFDataMgr.process(RDFDataMgr.java:906)
    at org.apache.jena.riot.RDFDataMgr.read(RDFDataMgr.java:257)
    at org.apache.jena.riot.RDFDataMgr.read(RDFDataMgr.java:243)
    at org.apache.jena.riot.adapters.RDFReaderRIOT_Web.read(RDFReaderRIOT_Web.java:96)
    at com.hp.hpl.jena.rdf.model.impl.ModelCom.read(ModelCom.java:235)
    at com.packages.rdf.FileAnalyse.GetFileComponents(FileAnalyse.java:77)
    at com.packages.servlets.CreatePatternServlet.GetStatements(CreatePatternServlet.java:96)
    at com.packages.servlets.CreatePatternServlet.doPost(CreatePatternServlet.java:68)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:646)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:727)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:303)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
    at org.apache.tomcat.websocket.server.WsFilter.doFilter(WsFilter.java:52)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
    at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:220)
    at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:122)
    at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:501)
    at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:171)
    at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:103)
    at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:950)
    at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:116)
    at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:408)
4

1 回答 1

1

看到这个: GC 开销限制超出


我认为您绝对应该自定义 GC。阅读有关 gc 实现的 oracle 文章,也许你会在那里取得一些进展。

于 2015-03-18T22:54:37.310 回答