fun with pools: how to create a compilation script that spreads itself on multiple cpu's
- From: "Dimitar Vasilev" <dimitar.vassilev@xxxxxxxxx>
- Date: Tue, 21 Aug 2007 13:34:01 +0300
Hi all!
I've got an Oracle forms compilation on an e4500 with Solaris 10 u3, 14cpus
8mb cache each that I'd like to
spread on multiple processors, because the compilation binds to 1 CPU and
400mhz is on always enough.
I've read http://docs.sun.com/app/docs/doc/817-1592 and
http://docs.sun.com/app/docs/doc/817-1975/6mhlv6vus?a=view
My questions are:
1. Could someone pass a straw on how to paralellize compilation on multiple
processors?
Forms are compiled with something like this:
cat $ORACLE_HOME/bin/f90genm.sh
export blurb
-------
$ORACLE_HOME/bin/f90genm $*
2. Is it safe to enable both static and dynamic pools or I should choose
what to run.E.g
svcs -a | grep pool
online Aug_18 svc:/system/pools:default
online 11:31:29 svc:/system/pools/dynamic:default
or I should disable either dynamic or default?
I'm thinking of the following as a possible solution:
1.Divide the number of forms on 14,
2.arrange the threads,
3. pass each form per CPU
4. wait to complete with sleep.
5.pass the next.
Thanks a lot for the ideas.
Will sum up.
--
PP8P<P8QQ
Q PP0QP8P;P5P2
Dimitar Vassilev
GnuPG key ID: 0x4B8DB525
Keyserver: pgp.mit.edu
Key fingerprint: D88A 3B92 DED5 917E 341E D62F 8C51 5FC4 4B8D B525
_______________________________________________
sunmanagers mailing list
sunmanagers@xxxxxxxxxxxxxxx
http://www.sunmanagers.org/mailman/listinfo/sunmanagers
- Prev by Date: Sun Cluster Problem
- Next by Date: SUMMARY: Sun Cluster Problem
- Previous by thread: Sun Cluster Problem
- Next by thread: SUMMARY: Sun Cluster Problem
- Index(es):
Relevant Pages
- Re: What is a type?
... >> compilation time. ... The type int is perfectly supported by
... You probably won't find the term "int" in a CPU reference manual. ... I meant
that a function pointer could be implemented as an index into ... (comp.lang.c) - Re: dual processor machine
... I don't think CPU matters ... > Compilation will be I/O limitted?
... lots of small source files is certainly more I/O bound than compiling a ...
few large source files. ... (comp.os.linux.hardware) - Re: [PATCH [RT] 08/14] add a loop counter based timeout mechanism
... into Kconfig. ... Compilation is usually the wrong place to configure
... It looks suspiciously round and worse the actual spin time depends a lot on the ...
differently from a 2Ghz CPU) Did you experiment with other spin times? ... (Linux-Kernel) - Re: GCC on multiprocessor platform?
... >somewhere in gentoo faq) but now I set up more and CPU usage grows up:) ...
compilation processes per CPU (we only tested powers of two, ... total amount of memory,
and the ratio of memory bandwidth to CPU speed. ... probably be somewhat different from the answer
for a high-end RISC machine ... (comp.unix.bsd.openbsd.misc)