[ https://issues.apache.org/jira/browse/PDFBOX-4876?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17133785#comment-17133785 ]
Dushyanth Balasubramanian commented on PDFBOX-4876: --------------------------------------------------- Thanks, [~tilman] That is good to know. Also, how can we use subsampling? Any example code? We will also try the latest Java version if that helps. > OOM issue in using PDFBOX > ------------------------- > > Key: PDFBOX-4876 > URL: https://issues.apache.org/jira/browse/PDFBOX-4876 > Project: PDFBox > Issue Type: Bug > Affects Versions: 2.0.19 > Reporter: Dushyanth Balasubramanian > Priority: Major > > I see a lot of OOM for many documents which are either big in size or have > many objects per page or complex images. We started the project with JVM size > of 4GB and now we have increased it to 24GB JVM memory. The OOM issues have > reduced but we still see some OOM issues. We have followed all the > recommendations given here: > [https://pdfbox.apache.org/2.0/faq.html] > > Here is the stack trace. Any recommendations for preventing OOM? Thanks. > **************************************************************************************************************************************************************************************************** > Stack 1 > ------- > at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) > [?:1.8.0_172] > at > com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:125) > [guava-27.0.1-jre.jar:?] > at > com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:57) > [guava-27.0.1-jre.jar:?] > at > com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:78) > [guava-27.0.1-jre.jar:?] > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) > [?:1.8.0_172] > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) > [?:1.8.0_172] > at java.lang.Thread.run(Thread.java:748) [?:1.8.0_172] > Caused by: java.lang.OutOfMemoryError > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > ~[?:1.8.0_172] > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) > ~[?:1.8.0_172] > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > ~[?:1.8.0_172] > at java.lang.reflect.Constructor.newInstance(Constructor.java:423) > ~[?:1.8.0_172] > at > java.util.concurrent.ForkJoinTask.getThrowableException(ForkJoinTask.java:598) > ~[?:1.8.0_172] > at java.util.concurrent.ForkJoinTask.get(ForkJoinTask.java:1066) > ~[?:1.8.0_172] > ... 23 more > Caused by: java.lang.OutOfMemoryError: Java heap space > at java.util.Arrays.copyOf(Arrays.java:3236) ~[?:1.8.0_172] > at java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:118) > ~[?:1.8.0_172] > at > java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93) > ~[?:1.8.0_172] > at java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:153) > ~[?:1.8.0_172] > at > org.apache.pdfbox.pdfwriter.COSStandardOutputStream.write(COSStandardOutputStream.java:129) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.io.IOUtils.copy(IOUtils.java:70) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdfwriter.COSWriter.visitFromStream(COSWriter.java:1220) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.cos.COSStream.accept(COSStream.java:475) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.cos.COSObject.accept(COSObject.java:158) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdfwriter.COSWriter.doWriteObject(COSWriter.java:526) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdfwriter.COSWriter.doWriteObjects(COSWriter.java:464) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdfwriter.COSWriter.doWriteBody(COSWriter.java:448) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdfwriter.COSWriter.visitFromDocument(COSWriter.java:1113) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.cos.COSDocument.accept(COSDocument.java:452) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdfwriter.COSWriter.write(COSWriter.java:1386) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdfwriter.COSWriter.write(COSWriter.java:1273) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.pdmodel.PDDocument.save(PDDocument.java:1357) > ~[pdfbox-2.0.19.jar:2.0.19] > **************************************************************************************************************************************************************************************************** > Stack 2 > ------- > Caused by: java.lang.OutOfMemoryError > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > ~[?:1.8.0_172] > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) > ~[?:1.8.0_172] > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > ~[?:1.8.0_172] > at java.lang.reflect.Constructor.newInstance(Constructor.java:423) > ~[?:1.8.0_172] > at > java.util.concurrent.ForkJoinTask.getThrowableException(ForkJoinTask.java:598) > ~[?:1.8.0_172] > at java.util.concurrent.ForkJoinTask.get(ForkJoinTask.java:1066) > ~[?:1.8.0_172] > ... 23 more > Caused by: java.lang.OutOfMemoryError: Java heap space > at java.awt.image.DataBufferByte.<init>(DataBufferByte.java:92) > ~[?:1.8.0_172] > at > java.awt.image.ComponentSampleModel.createDataBuffer(ComponentSampleModel.java:445) > ~[?:1.8.0_172] > at sun.awt.image.ByteInterleavedRaster.<init>(ByteInterleavedRaster.java:90) > ~[?:1.8.0_172] > at > sun.awt.image.ByteInterleavedRaster.createCompatibleWritableRaster(ByteInterleavedRaster.java:1281) > ~[?:1.8.0_172] > at > sun.awt.image.ByteInterleavedRaster.createCompatibleWritableRaster(ByteInterleavedRaster.java:1292) > ~[?:1.8.0_172] > at org.apache.pdfbox.filter.DCTFilter.fromBGRtoRGB(DCTFilter.java:312) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.filter.DCTFilter.decode(DCTFilter.java:148) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.cos.COSInputStream.create(COSInputStream.java:84) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.cos.COSStream.createInputStream(COSStream.java:246) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.common.PDStream.createInputStream(PDStream.java:241) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.createInputStream(PDImageXObject.java:776) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.from8bit(SampledImageReader.java:373) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.getRGBImage(SampledImageReader.java:226) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:479) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:460) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.rendering.PageDrawer.drawImage(PageDrawer.java:1130) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.contentstream.operator.graphics.DrawObject.process(DrawObject.java:67) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:875) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:509) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:483) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:156) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.rendering.PageDrawer.drawPage(PageDrawer.java:270) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:321) > ~[pdfbox-2.0.19.jar:2.0.19] > at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:243) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.rendering.PDFRenderer.renderImageWithDPI(PDFRenderer.java:229) > ~[pdfbox-2.0.19.jar:2.0.19] > **************************************************************************************************************************************************************************************************** > Stack 3 > ------- > Caused by: java.lang.OutOfMemoryError > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > ~[?:1.8.0_172] > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) > ~[?:1.8.0_172] > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > ~[?:1.8.0_172] > at java.lang.reflect.Constructor.newInstance(Constructor.java:423) > ~[?:1.8.0_172] > at > java.util.concurrent.ForkJoinTask.getThrowableException(ForkJoinTask.java:598) > ~[?:1.8.0_172] > at java.util.concurrent.ForkJoinTask.get(ForkJoinTask.java:1066) > ~[?:1.8.0_172] > ... 23 more > Caused by: java.lang.OutOfMemoryError: Java heap space > at java.awt.image.DataBufferInt.<init>(DataBufferInt.java:75) ~[?:1.8.0_172] > at java.awt.image.Raster.createPackedRaster(Raster.java:467) ~[?:1.8.0_172] > at > java.awt.image.DirectColorModel.createCompatibleWritableRaster(DirectColorModel.java:1032) > ~[?:1.8.0_172] > at java.awt.image.BufferedImage.<init>(BufferedImage.java:333) ~[?:1.8.0_172] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.applyMask(PDImageXObject.java:587) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:486) > ~[pdfbox-2.0.19.jar:2.0.19] > at > org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:460) > ~[pdfbox-2.0.19.jar:2.0.19] -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: dev-unsubscr...@pdfbox.apache.org For additional commands, e-mail: dev-h...@pdfbox.apache.org