Commit 368c9594 authored by Philip Carns's avatar Philip Carns

proof reading


git-svn-id: https://svn.mcs.anl.gov/repos/darshan/trunk@533 3b7491f3-a168-0410-bf4b-c445ed680a29
parent 815fe29c
......@@ -51,19 +51,19 @@ scheduler does not advertise the job ID) then you can specify `NONE` here.
Darshan will fall back to using the pid of the rank 0 process if the
specified environment variable is not set.
* `CC=`: specifies the MPI C compiler to use for compilation
* `--with-log-path-by-env`: specified an environment variable to use to
* `--with-log-path-by-env`: specifies an environment variable to use to
determine the log path at run time.
* `--with-log-hints=`: specifies hints to use when writing the Darshan log
file. See `./configure --help` for details.
* `--with-zlib=`: specifies an alternate location for the zlib development
header and library
header and library.
=== Cross compilation
On some systems (notably the IBM BlueGene series) the login nodes do not
On some systems (notably the IBM Blue Gene series), the login nodes do not
have the same architecture or runtime environment as the compute nodes. In
this case, you must configure darshan-runtime to be built using a cross
compiler. The following arguments show an example for the BG/P system:
compiler. The following configure arguments show an example for the BG/P system:
----
--host=powerpc-bgp-linux CC=/bgsys/drivers/ppcfloor/comm/default/bin/mpicc
......@@ -71,20 +71,20 @@ compiler. The following arguments show an example for the BG/P system:
== Environment preparation
Once darshan-runtime has been installed, you must still prepare a location
to store Darshan log files and configure an instrumentation method.
Once darshan-runtime has been installed, you must prepare a location
in which to store the Darshan log files and configure an instrumentation method.
=== Log directory
This step can be safely skipped if you configured darshan-runtime using the
`--with-log-path-by-env` option. A more typical configuration, however, is
to provide a static directory hierarchy in which to gather Darshan log
`--with-log-path-by-env` option. A more typical configuration uses a static
directory hierarchy for Darshan log
files.
The `darshan-mk-log-dirs.pl` utility will configure the path specified at
configure time to include
subdirectories organized by year, month, and day in which log files will be
placed. The last subdirectories will have sticky permissions to enable
placed. The deepest subdirectories will have sticky permissions to enable
multiple users to write to the same directory. If the log directory is
shared system-wide across many users then the following script should be run
as root.
......@@ -132,8 +132,8 @@ list for help.
== Instrumenting dynamically-linked applications
For dynamically-linked executables, darshan relies on the `LD_PRELOAD`
environment variable to insert instrumentation at run time. The application
can be compiled using the normal, unmodified MPI compiler.
environment variable to insert instrumentation at run time. The executables
should be compiled using the normal, unmodified MPI compiler.
To use this mechanism, set the `LD_PRELOAD` environment variable to the full
path to the Darshan shared library, as in this example:
......@@ -152,7 +152,7 @@ local site documentation for details.
Please follow the general steps outlined in the previous section. For
Fortran applications compiled with MPICH you may have to take the additional
step fo adding
step of adding
`libfmpich.so` to your `LD_PRELOAD` environment variable. For example:
----
......@@ -161,9 +161,8 @@ export LD_PRELOAD=libfmpich.so:/home/carns/darshan-install/lib/libdarshan.so
== Darshan installation recipes
The following recipes provide examples for some prominant HPC systems.
These are intended to be used as a starting point for installation on such
systems, although you will most likely have to adjust paths and options to
The following recipes provide examples for prominant HPC systems.
These are intended to be used as a starting point. You will most likely have to adjust paths and options to
reflect the specifics of your system.
=== IBM Blue Gene/P
......@@ -215,24 +214,26 @@ module swap PrgEnv-pgi PrgEnv-gnu
--with-log-path=/lustre/beagle/carns/darshan-logs \
--prefix=/home/carns/working/darshan/releases/install-darshan-2.2.0-pre1 \
--with-jobid-env=PBS_JOBID CC=cc
module swap PrgEnv-gnu PrgEnv-pgi
----
.Rationale
[NOTE]
====
Before compiling Darshan you must modify your environment to use the GNU
compilers rather than the default PGI or Cray compilers. Please see your
compilers rather than the default PGI or Cray compilers. You can swap this
configuration back once Darshan has been compiled. Please see your
site documentation for details.
The job ID is set to `PBS_JOBID` for use with a Torque or PBS based scheduler.
The `CC` variable is configured to point the standard MPI compiler.
====
The darshan-runtime package does not provide any scripts or wrappers to use
The darshan-runtime package does not provide scripts or wrappers to use
for instrumenting static executables in the Cray environment. It may be
possible to do this manually. However, you _can_ instrument dynamic
possible to do this manually. Another option is to instrument dynamic
executables using `LD_PRELOAD`. To do this, compile your application with
the `-dynamic` compiler option and follow the instructions for dynamic
the `-dynamic` compiler option and follow the instructions for instrumenting dynamic
executables listed earlier in this document. This method has been tested
with PGI and GNU compilers and is likely to work with other compiler
combinations as well.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment