llnl / ravel Goto Github PK

Hey Livermorians,

where can I find infos about the tool without installing and running it?
A paper or a website, perhaps.
I couldn't find anything searching the web myself.

best regards,
Ronny

Is there a reason that ranks are not ordered sequentially in the trace view? See attached image.

Thanks!
jgw

While attempting to open a trace I get:

Processing /p/work1/wohlbier/devel/aster/TAU/aster/centennial21-aster-trace/0/traces.otf2
Reading definitions
Reading events
Segmentation fault (core dumped)

The trace files are 2.2GB.

wohlbier@centennial21 aster]$ du -sh TAU/aster/centennial21-aster-trace/0/traces
2.2G TAU/aster/centennial21-aster-trace/0/traces
[wohlbier@centennial21 aster]$ ls TAU/aster/centennial21-aster-trace/0/traces
0.def 1792.def 2688.def 3712.def 4608.def 5504.def 640.def 7424.def
0.evt 1792.evt 2688.evt 3712.evt 4608.evt 5504.evt 640.evt 7424.evt
1024.def 1920.def 2816.def 3840.def 4736.def 5632.def 6528.def 7552.def
1024.evt 1920.evt 2816.evt 3840.evt 4736.evt 5632.evt 6528.evt 7552.evt
1152.def 2048.def 2944.def 384.def 4864.def 5760.def 6656.def 7680.def
1152.evt 2048.evt 2944.evt 384.evt 4864.evt 5760.evt 6656.evt 7680.evt
1280.def 2176.def 3072.def 3968.def 4992.def 5888.def 6784.def 768.def
1280.evt 2176.evt 3072.evt 3968.evt 4992.evt 5888.evt 6784.evt 768.evt
128.def 2304.def 3200.def 4096.def 5120.def 6016.def 6912.def 7808.def
128.evt 2304.evt 3200.evt 4096.evt 5120.evt 6016.evt 6912.evt 7808.evt
1408.def 2432.def 3328.def 4224.def 512.def 6144.def 7040.def 7936.def
1408.evt 2432.evt 3328.evt 4224.evt 512.evt 6144.evt 7040.evt 7936.evt
1536.def 2560.def 3456.def 4352.def 5248.def 6272.def 7168.def 8064.def
1536.evt 2560.evt 3456.evt 4352.evt 5248.evt 6272.evt 7168.evt 8064.evt
1664.def 256.def 3584.def 4480.def 5376.def 6400.def 7296.def 896.def
1664.evt 256.evt 3584.evt 4480.evt 5376.evt 6400.evt 7296.evt 896.evt

"" For details, see https://scalability-llnl.github.io/ravel ""

This link is probably present in all license headers in all source files

best regards,
Ronny

I am able to visualise otf2 traces without any issues.

I was also playing with otf traces provided on [vampir.eu website]:(https://www.vampir.eu/downloads/tracefiles)

small trace file => https://www.vampir.eu/public/files/tracefiles/Small.zip

When I try to open trace file, it segfault at below location:

Processing /Users/kumbhar/Downloads/Small/wrf.otf
Reading definitions
Reading events
Finish reading
0 unmatched sends and 0 unmatched recvs.
OTF Reading: 0.667056 seconds
Event/Message Matching: 0.935606 seconds
Merging for messages...
Partition Merge: 0.187787 seconds
Message Merge: 0.304303 seconds
Merging cycles...
Setting partition dag...
Tarjan...
Merging from the cycles...
Partition Merge: 0.150744 seconds
Cycle Merge: 0.224786 seconds
Setting DAG leaps...
Assigning local steps
Local Stepping: 0.032864 seconds
Setting global steps
Global Stepping: 0.0151446 seconds
Total Algorithm Time: 0.587945 seconds
Calculating step-wise metrics
Process 17290 stopped
* thread #16: tid = 0x285770c, 0x00000001000b52d0 Ravel`Metrics::setMetric(this=<unavailable>, name=<unavailable>, event_value=0, aggregate_value=0) + 64 at metrics.cpp:29, name = 'QThread', stop reason = EXC_BAD_ACCESS (code=1, address=0x0)
    frame #0: 0x00000001000b52d0 Ravel`Metrics::setMetric(this=<unavailable>, name=<unavailable>, event_value=0, aggregate_value=0) + 64 at metrics.cpp:29
   26  	                          double aggregate_value)
   27  	{
   28  	    MetricPair * mp = metrics->value(name);
-> 29  	    mp->event = event_value;
   30  	    mp->aggregate = aggregate_value;
   31  	}
   32

p.s. I am not using/generation otf1 traces but thought I should just report the issue.

I have installed Ravel on a clean Ubuntu.
When I try to run it I get an error:

# /ravel/bin/Ravel
QWidget::setLayout: Attempting to set QLayout "" on QWidget "traditionalLabelWidget", which already has a layout
QXcbXSettings::QXcbXSettings(QXcbScreen*) Failed to get selection owner for XSETTINGS_S atom
QXcbConnection: XCB error: 152 (Unknown), sequence: 158, resource id: 0, major code: 142 (Unknown), minor code: 20

I am writing this for three things:

1. If sendrecv to self is present in the code, the program fails to load the otf2, with messages like "Error, skipping message (by recv) at on ".
2. "metric overview" cannot be shown by itself. Always the last other view is present as blacked area even when it is not selected. To reproduce, after loading a trace, select "Physical Time" and "Metric Overview" both, then deselct "Physical Time", its portion still remains as blacked out area.
3. Once zoomed in, zooming in in another place seems to be problematic. clicking and dragging by the mouse seems to be moving the trace drawing only till certain portion.
   I am using the master branch.

Hi,

I compiled the library successfully but after installation when I try to run it, I get the following error

ravel/bin/Ravel: error while loading shared libraries: libmuster.so: cannot open shared object file: No such file or directory

I have installed it in /usr/local/lib and libmuster.so is in /usr/local/lib/muster/lib/libmuster.so.

I used the following command for installing

cmake -DCMAKE_INSTALL_PREFIX=/usr/local/lib/ravel/ -DCMAKE_PREFIX_PATH=/usr/local/lib/muster;/usr/local/lib/otf2 ..

in the build directory.

I am visualising sample otf2 trace and I see lots of messages:
{code}
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
QColor::setRgb: RGB parameters out of range
....
{code}

Is there any obvious reason for these warning messages? (see attached screenshot)

Also, is there any way to colorise the user functions? for example, in the attached screenshot, all user instrumented functions appears in black colour.

I'm looking at some otf2 files in Ravel and trying to understand them. In the attached 2 figures Ravel shows lateness on rank 0, but I don't see how it's correct. From the physical timeline it looks like rank 0 is early, not late.

The code issues non-blocking recv's before blocking sends, if that matters.