[Beowulf] Bioinformatics Benchmark System v3 rc1 ready

Jan-Frode Myklebust janfrode at parallab.uib.no
Mon Jul 12 06:31:45 PDT 2004


On Mon, Jul 12, 2004 at 08:55:44AM -0400, Joe Landman wrote:
> 
> On the Perl modules, could you let me know which ones were not in the
> RHEL 3 AS on PPC?  I included a method to handle missing modules, though
> I don't know what this particular version of RHEL requires.  

When doing 'make' under perl_modules I get:

cd   Getopt-Long-2.34_01 ; perl Makefile.PL ; make ; make test ; make install
 
WARNING: This is Getopt::Long version 2.34_01.
The underscore in the version number indicates that this is
an intermediate, preview or beta release.
Please keep checking CPAN for the official release.
 
 
Warning: I could not locate your pod2man program. Please make sure,
         your pod2man program is in your PATH before you execute 'make'
 
Writing Makefile for Getopt::Long
make[1]: Entering directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
Makefile:87: *** missing separator.  Stop.
make[1]: Leaving directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
make[1]: Entering directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
Makefile:87: *** missing separator.  Stop.
make[1]: Leaving directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
make[1]: Entering directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
Makefile:87: *** missing separator.  Stop.
make[1]: Leaving directory `/scratch/janfrode/bbsv3rc1/perl_modules/Getopt-Long-2.34_01'
make: *** [Getopt-Long] Error 2

% which pod2man
/usr/bin/pod2man
% rpm -qf /usr/bin/pod2man
perl-5.8.0-88.4



When trying to run 'bbsrun' I get:

% ./bbsrun
Can't locate Object/MultiType.pm in @INC (@INC contains: /usr/lib/perl5/5.8.0/ppc-linux-thread-multi /usr/lib/perl5/5.8.0 /usr/lib/perl5/site_perl/5.8.0/ppc-linux-thread-multi /usr/lib/perl5/site_perl/5.8.0 /usr/lib/perl5/site_perl /usr/lib/perl5/vendor_perl/5.8.0/ppc-linux-thread-multi /usr/lib/perl5/vendor_perl/5.8.0 /usr/lib/perl5/vendor_perl /usr/lib/perl5/5.8.0/ppc-linux-thread-multi /usr/lib/perl5/5.8.0 .) at /usr/lib/perl5/site_perl/5.8.0/XML/Smart.pm line 18.
BEGIN failed--compilation aborted at /usr/lib/perl5/site_perl/5.8.0/XML/Smart.pm line 18.
Compilation failed in require at ./bbsrun line 76.
BEGIN failed--compilation aborted at ./bbsrun line 76.


> As for the fancy XML input and output, one of the intended uses of this
> tool is for automatic generation of benchmark tests and results for
> complex distributed systems in conjunction with other tools under
> development, which might not always have a bourne shell available. 
> Additionally, the input system is meant to be as flexible and simple as
> possible, so we try to avoid being "fancy" :)

Then maybe you should consider splitting it into separate programs? Like
bonnie++ which does simple comma-separated output (csv), which can be fed
to other tools for fancy-formating.

The fact that it failed to run for me here is a bit of a turn off, and
it's not very tempting to try to fix it on every platform I want to use in
my current benchmarking (Currently AIX, RedHat 7.1, RHEL 3 on x86, RHEL 3
on ppc970 and Rocks).  Then it's much easier to pick the simple command
lines from baseline/*xml and execute them by hand.  

BTW: thanks a lot for providing these benchmark configurations. They're
very usefull to us! 


> The bbsv1 benchmarks?  These are the original from the previous
> version.  The baselines are (eventually) supposed to cover the small
> through huge cases.  

Yes, I've only run blast from the previous version. And it seemed to be
very much affected by the 1 GB memory on our nodes. 

> What I didn't mention in the docs was database formatting.  You can use
> formatdb -v N  and set N large enough such that the indices do not
> overflow buffer cache.  One of the uses of this tool is to figure out
> where this size might be, by examining the time of BLAST execution
> versus database volume size.  I will try to work up an example of this
> in the next few days and get this onto the page.

OK, great!


  -jf



More information about the Beowulf mailing list