Hi, PTU team,
When I finally finished my very long run of PTU data(multiple events), I can not open the sampling view window. The error is like:
Failed to get data error
Premature end of file.
Could you help me out? Is there anyway that I can at least view something? Thanks a lot.
Regards.
Hello,
Check the experiment directory - is there any <>.tb5 file?
juf
Hi, Juf,
There are 4 *.tb5 files existing. Two of them are fairly large(>1g). Would it be the reason that the failure occur?
The Java failure log:
com.intel.ptu.viewers.basic.LoadException: Premature end of file.
at com.intel.ptu.viewers.basic.SSViewProvider.getData(SSViewProvider.java:206)
at com.intel.ptu.viewers.basic.SSViewProvider.getData(SSViewProvider.java:117)
at com.intel.ptu.viewers.basic.DataLoadJob.runInWorkspace(DataLoadJob.java:54)
at org.eclipse.core.internal.resources.InternalWorkspaceJob.run(InternalWorkspaceJob.java:38)
at org.eclipse.core.internal.jobs.Worker.run(Worker.java:58)
Caused by: com.intel.ptu.viewers.basic.LoadException: Premature end of file.
at com.intel.ptu.viewers.basic.internal.ProcessRunner.run(ProcessRunner.java:132)
Caused by: org.eclipse.emf.ecore.resource.Resource$IOWrappedException: Premature end of file.
at org.eclipse.emf.ecore.xmi.impl.XMLLoadImpl.load(XMLLoadImpl.java:199)
at org.eclipse.emf.ecore.xmi.impl.XMLResourceImpl.doLoad(XMLResourceImpl.java:179)
at org.eclipse.emf.ecore.resource.impl.ResourceImpl.load(ResourceImpl.java:1089)
at com.intel.ptu.viewers.basic.internal.ProcessRunner.run(ProcessRunner.java:110)
Caused by: org.xml.sax.SAXParseException: Premature end of file.
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(ErrorHandlerWrapper.java:236)
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(ErrorHandlerWrapper.java:215)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:386)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:316)
at com.sun.org.apache.xerces.internal.impl.XMLVersionDetector.determineDocVersion(XMLVersionDetector.java:230)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:798)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:764)
at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:148)
at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1242)
at javax.xml.parsers.SAXParser.parse(SAXParser.java:375)
at org.eclipse.emf.ecore.xmi.impl.XMLLoadImpl.load(XMLLoadImpl.java:179)
... 3 more
com.intel.ptu.viewers.basic.LoadException: Premature end of file.
at com.intel.ptu.viewers.basic.SSViewProvider.getData(SSViewProvider.java:206)
at com.intel.ptu.viewers.basic.SSViewProvider.getData(SSViewProvider.java:117)
at com.intel.ptu.viewers.basic.DataLoadJob.runInWorkspace(DataLoadJob.java:54)
at org.eclipse.core.internal.resources.InternalWorkspaceJob.run(InternalWorkspaceJob.java:38)
at org.eclipse.core.internal.jobs.Worker.run(Worker.java:58)
Caused by: com.intel.ptu.viewers.basic.LoadException: Premature end of file.
at com.intel.ptu.viewers.basic.internal.ProcessRunner.run(ProcessRunner.java:132)
Caused by: org.eclipse.emf.ecore.resource.Resource$IOWrappedException: Premature end of file.
at org.eclipse.emf.ecore.xmi.impl.XMLLoadImpl.load(XMLLoadImpl.java:199)
at org.eclipse.emf.ecore.xmi.impl.XMLResourceImpl.doLoad(XMLResourceImpl.java:179)
at org.eclipse.emf.ecore.resource.impl.ResourceImpl.load(ResourceImpl.java:1089)
at com.intel.ptu.viewers.basic.internal.ProcessRunner.run(ProcessRunner.java:110)
Caused by: org.xml.sax.SAXParseException: Premature end of file.
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.createSAXParseException(ErrorHandlerWrapper.java:236)
at com.sun.org.apache.xerces.internal.util.ErrorHandlerWrapper.fatalError(ErrorHandlerWrapper.java:215)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:386)
at com.sun.org.apache.xerces.internal.impl.XMLErrorReporter.reportError(XMLErrorReporter.java:316)
at com.sun.org.apache.xerces.internal.impl.XMLVersionDetector.determineDocVersion(XMLVersionDetector.java:230)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:798)
at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:764)
at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:148)
at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1242)
at javax.xml.parsers.SAXParser.parse(SAXParser.java:375)
at org.eclipse.emf.ecore.xmi.impl.XMLLoadImpl.load(XMLLoadImpl.java:179)
... 3 more
Thanks.
Yes. there is some limit of how large raw data files could be. it is exactly around 1Gb
So the failure could be related to this.
As i undertand you experiment runs for a long time. How long?
You can re-run same experiment putting there (in project settings) event-based sampling "Sampling After" multiplier - e.g. 10
So less samples will be written to tb5 files and so they will be smaller within limits but still reliable .
file:///C:/projects/_DT/march23/vprof.cpp
Thanks Julia for giving the exact reason. My experiment will run for about 3 days.
I'm wondering whether there is a way that I could use the data collected so far? I have 5 .tb files. Are they all useful or I could use some of them?
Typical expriment duration is seconds (e.g. 20 sec) or minutes - say 3-5 min - this is exactly where multiplier would be needed
PTU experiment is basically a benchmark / typical workload / kernel of the big program.
For such long experiments as 3 days - you need something as continuous profiling that PTU doesn't supply.
i don't think that you can use the data collected so far.
3 days are the total run time for several different runs. For single run, it's about 5 hours, seems still longer than you said.
Anyway, I have some profiling with vtune before that could handle such situation. Can you confirm that PTU can only handle program running seconds to several minutes? This is not as expected.
>> Can you confirm that PTU can only handle program running seconds to
several minutes?
i was not clear.
The crtical parameter is the number of samples. Not the time duration itslef.
If you sample with big SAV or sample on very rare event - you can collect for hours.
And then VTune and PTU open the results w/o any problem.
(PTU and VTune based on same exactly sampling mechanizm.)
Another question - what information you get from these results.
What is the problem you are trying to solve?
I was checking the different events triggered during my experiment for profiling. I did such things before in Vtune. But my latest run didn't success in Vtune. (No symbol for long simulation somehow). And PTU helps in this condition. I was thinking there must be some difference between Vtune and PTU. But since you said so, I think it could be caused by different machine/OS/installation.
Anyhow, I was trying again by enlarging the sampling intervals. I will ask for help again if it fails.