darshan-runtime.txt 15.1 KB
Newer Older
1 2 3 4 5
Darshan-runtime installation and usage
======================================

== Introduction

6 7 8
This document describes darshan-runtime, which is the instrumentation
portion of the Darshan characterization tool.  It should be installed on the
system where you intend to collect I/O characterization information.
Philip Carns's avatar
Philip Carns committed
9

10 11 12
Darshan instruments applications via either compile time wrappers for static
executables or dynamic library preloading for dynamic executables.  An
application that has been instrumented with Darshan will produce a single
Kevin Harms's avatar
Kevin Harms committed
13
log file each time it is executed.  This log summarizes the I/O access patterns
14 15 16 17 18 19 20 21 22 23
used by the application.

The darshan-runtime instrumentation only instruments MPI applications (the
application must at least call `MPI_Init()` and `MPI_Finalize()`).  However,
it captures both MPI-IO and POSIX file access.  It also captures limited
information about HDF5 and PnetCDF access.

This document provides generic installation instructions, but "recipes" for
several common HPC systems are provided at the end of the document as well.

24 25 26
More information about Darshan can be found at the 
http://www.mcs.anl.gov/darshan[Darshan web site].

27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
== Requirements

* MPI C compiler
* zlib development headers and library

== Compilation and installation

.Configure and build example
----
tar -xvzf darshan-<version-number>.tar.gz
cd darshan-<version-number>/darshan-runtime
./configure --with-mem-align=8 --with-log-path=/darshan-logs --with-jobid-env=PBS_JOBID CC=mpicc
make
make install
----

.Explanation of configure arguments:
* `--with-mem-align` (mandatory): This value is system-dependent and will be
used by Darshan to determine if the buffer for a read or write operation is
aligned in memory.
* `--with-log-path` (this, or `--with-log-path-by-env`, is mandatory): This
specifies the parent directory for the directory tree where darshan logs
will be placed
* `--with-jobid-env` (mandatory): this specifies the environment variable that
Darshan should check to determine the jobid of a job.  Common values are
`PBS_JOBID` or `COBALT_JOBID`.  If you are not using a scheduler (or your
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
Philip Carns's avatar
Philip Carns committed
57
* `--with-log-path-by-env`: specifies an environment variable to use to
58 59 60 61
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
Philip Carns's avatar
Philip Carns committed
62
header and library.
63 64 65

=== Cross compilation

Philip Carns's avatar
Philip Carns committed
66
On some systems (notably the IBM Blue Gene series), the login nodes do not
67 68
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
Philip Carns's avatar
Philip Carns committed
69
compiler.  The following configure arguments show an example for the BG/P system:
70 71 72 73 74 75 76

----
--host=powerpc-bgp-linux CC=/bgsys/drivers/ppcfloor/comm/default/bin/mpicc 
----

== Environment preparation

Philip Carns's avatar
Philip Carns committed
77 78
Once darshan-runtime has been installed, you must prepare a location
in which to store the Darshan log files and configure an instrumentation method.
79 80 81

=== Log directory

82
This step can be safely skipped if you configured darshan-runtime using the
Philip Carns's avatar
Philip Carns committed
83 84
`--with-log-path-by-env` option.  A more typical configuration uses a static
directory hierarchy for Darshan log
85 86 87 88 89
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
Philip Carns's avatar
Philip Carns committed
90
placed. The deepest subdirectories will have sticky permissions to enable
91 92 93 94 95 96 97
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.
 
----
darshan-mk-log-dirs.pl
----
98

99
=== Instrumentation method
100

101 102 103 104 105 106 107 108 109
The instrumentation method to use depends on whether the executables
produced by your MPI compiler are statically or dynamically linked.  If you
are unsure, you can check by running `ldd <executable_name>` on an example
executable.  Dynamically-linked executables will produce a list of shared
libraries when this command is executed.

Most MPI compilers allow you to toggle dynamic or static linking via options
such as `-dynamic` or `-static`.  Please check your MPI compiler man page
for details if you intend to force one mode or the other.
110 111 112

== Instrumenting statically-linked applications

113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133
Statically linked executables must be instrumented at compile time.  The
simplest way to do this is to generate an MPI compiler script (e.g. `mpicc`)
that includes the link options and libraries needed by Darshan.  Once this
is done, Darshan instrumentation is transparent; you simply compile
applications using the darshan-enabled MPI compiler scripts.

For MPICH-based MPI libraries, such as MPICH1, MPICH2, or MVAPICH, these
wrapper scripts can be generated automatically.  The following example
illustrates how to produce wrappers for C, C++, and Fortran compilers:

----
darshan-gen-cc.pl `which mpicc` --output mpicc.darshan
darshan-gen-cxx.pl `which mpicxx` --output mpicxx.darshan
darshan-gen-fortran.pl `which mpif77` --output mpif77.darshan
darshan-gen-fortran.pl `which mpif90` --output mpif90.darshan
-----

For other MPI Libraries you must manually modify the MPI compiler scripts to
add the necessary link options and libraries.  Please see the
`darshan-gen-*` scripts for examples or contact the Darshan users mailing
list for help.
134 135 136

== Instrumenting dynamically-linked applications

137
For dynamically-linked executables, darshan relies on the `LD_PRELOAD`
Philip Carns's avatar
Philip Carns committed
138 139
environment variable to insert instrumentation at run time.  The executables
should be compiled using the normal, unmodified MPI compiler.
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157

To use this mechanism, set the `LD_PRELOAD` environment variable to the full
path to the Darshan shared library, as in this example:

----
export LD_PRELOAD=/home/carns/darshan-install/lib/libdarshan.so
----

You can then run your application as usual.  Some environments may require a
special `mpirun` or `mpiexec` command line argument to propagate the
environment variable to all processes.  Other environments may require a
scheduler submission option to control this behavior.  Please check your
local site documentation for details.

=== Instrumenting dynamically-linked Fortran applications

Please follow the general steps outlined in the previous section.  For
Fortran applications compiled with MPICH you may have to take the additional
Philip Carns's avatar
Philip Carns committed
158
step of adding
159 160 161 162 163
`libfmpich.so` to your `LD_PRELOAD` environment variable. For example:

----
export LD_PRELOAD=libfmpich.so:/home/carns/darshan-install/lib/libdarshan.so
----
164 165 166

== Darshan installation recipes

Philip Carns's avatar
Philip Carns committed
167
The following recipes provide examples for prominent HPC systems.
Philip Carns's avatar
Philip Carns committed
168
These are intended to be used as a starting point.  You will most likely have to adjust paths and options to
169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
reflect the specifics of your system.

=== IBM Blue Gene/P

The IBM Blue Gene/P series produces static executables by default, uses a
different architecture for login and compute nodes, and uses an MPI
environment based on MPICH.

The following example shows how to configure Darshan on a BG/P system:

----
./configure --with-mem-align=16 \
 --with-log-path=/home/carns/working/darshan/releases/logs \
 --prefix=/home/carns/working/darshan/install --with-jobid-env=COBALT_JOBID \
 --with-zlib=/soft/apps/zlib-1.2.3/ \
 --host=powerpc-bgp-linux CC=/bgsys/drivers/ppcfloor/comm/default/bin/mpicc 
----

.Rationale
[NOTE]
====
The memory alignment is set to 16 not because that is the proper alignment
for the BG/P CPU architecture, but because that is the optimal alignment for
the network transport used between compute nodes and I/O nodes in the
system.  The jobid environment variable is set to `COBALT_JOBID` in this
case for use with the Cobalt scheduler, but other BG/P systems may use
different schedulers.  The `--with-zlib` argument is used to point to a
version of zlib that has been compiled for use on the compute nodes rather
than the login node.  The `--host` argument is used to force cross-compilation
of Darshan.  The `CC` variable is set to point to a stock MPI compiler.
====

Once Darshan has been installed, use the `darshan-gen-*.pl` scripts as
described earlier in this document to produce darshan-enabled MPI compilers.
This method has been widely used and tested with both the GNU and IBM XL
compilers.

206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
=== Cray XE6 (or similar)

The Cray programming environment produces static executables by default.
Darshan should therefore be configured to insert instrumentation at link
time by way of compiler script wrappers.  Darshan 2.2.3 supports GNU,
PGI, Cray, Pathscale, and Intel compilers.  The following documentation
describes how to modify the Cray compiler wrappers to add Darshan
capability, as well as how to install a Darshan software module that
allows users to enable or disable Darshan instrumentation.

==== Building and installing Darshan

Please set your environment to use the GNU programming environment before
configuring or compiling Darshan.  Although Darshan can be built with a
variety of compilers, the GNU compilers are recommended because it will
produce a Darshan library that is interoperable with a variety of linkers.
On most Cray systems you can enable the GNU programming environment with
a command similar to "module swap PrgEnv-pgi PrgEnv-gnu".  Please see
your site documentation for information about how to switch programming
environments.

The following example shows how to configure and build Darshan on a Cray
system using either the GNU programming environment.  Please adjust the 
--with-log-path and --prefix arguments to point to the desired log file path 
and installation path, respectively.
231 232

----
233
module swap PrgEnv-pgi PrgEnv-gnu
234
./configure --with-mem-align=8 \
235 236
 --with-log-path=/shared-file-system/darshan-logs \
 --prefix=/soft/darshan-2.2.3 \
Philip Carns's avatar
Philip Carns committed
237
 --with-jobid-env=PBS_JOBID --disable-cuserid --enable-st-dev-workaround CC=cc
238 239
make install
module swap PrgEnv-gnu PrgEnv-pgi
240 241 242 243 244 245 246
----

.Rationale
[NOTE]
====
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.
Philip Carns's avatar
Philip Carns committed
247 248 249 250 251 252 253 254

The --disable-cuserid argument is used to prevent Darshan from attempting to
use the cuserid() function to retrieve the user name associated with a job.
Darshan automatically falls back to other methods if this function fails,
but on some Cray environments (notably the Beagle XE6 system as of March 2012)
the cuserid() call triggers a segmentation fault.  With this option set,
Darshan will typically use the LOGNAME environment variable to determine a
userid.
Philip Carns's avatar
Philip Carns committed
255 256 257 258

The --enable-st-dev-workaround argument is used to tell Darshan to
determine the device type of each file by checking the parent directory
rather than the file itself.  This is a workaround for a file stat
259
inconsistency observed on some systems.
260 261
====

262 263 264
As in any Darshan installation, the darshan-mk-log-dirs.pl script can then be 
used to create the appropriate directory hierarchy for storing Darshan log 
files in the --with-log-path directory.
Philip Carns's avatar
Philip Carns committed
265

266
==== Compiler wrappers (system-wide installation)
Philip Carns's avatar
Philip Carns committed
267

268 269 270 271 272
.Warning
[NOTE]
====
The instructions in this section will modify the default compiler scripts
that underly the system-wide CC, ftn, and cc scripts.  Please proceed
Philip Carns's avatar
Philip Carns committed
273 274
with caution.  We recommend performing the following steps
on a copy of the scripts and then moving them to the correct location afterwards.
275
====
Philip Carns's avatar
Philip Carns committed
276

277 278 279 280 281 282 283 284
The Darshan distribution includes a patch to the Cray programming environment 
that adds Darshan capability to the compiler scripts.  It does not modify the
behavior of the scripts in any way unless the CRAY_DARSHAN_DIR environment 
variable is set by the Darshan software module.  This approach is similar to
that used by the HDF5, NetCDF, and PETSc packages on Cray XE6 systems.  Darshan
requires compiler script modifications in order to apply instrumentation
libraries and link options in the correct order relative to other libraries used
at link time.
Philip Carns's avatar
Philip Carns committed
285

286 287
Perform the following steps to patch the system compiler scripts.  The patch 
provided in the Darshan source tree was generated against the xt-asyncpe-5.10
Philip Carns's avatar
Philip Carns committed
288
environment, but it should also work on similar versions as well. 
Philip Carns's avatar
Philip Carns committed
289

290 291 292 293 294 295
----
cd $ASYNCPE_DIR/bin
patch -p0 --dry-run < /home/carns/darshan-2.2.3/darshan-runtime/share/cray/cray-xt-asyncpe-5.10-darshan.patch
# CONFIRM THE RESULTS OF THE DRY RUN SHOWN ABOVE
patch -p0 < /home/carns/darshan-2.2.3/darshan-runtime/share/cray/cray-xt-asyncpe-5.10-darshan.patch
----
Philip Carns's avatar
Philip Carns committed
296

297 298 299
The next step is to install the Darshan software module.  Note that the module
file will be found in the Darshan installation dir, as it is generated 
automatically based on configuration parameters:
Philip Carns's avatar
Philip Carns committed
300

301 302 303 304 305 306 307 308
----
cp -r /soft/darshan-2.2.3/share/cray/modulefiles/darshan /opt/modulefiles/
----

Users (or administrators) can now enable or disable darshan instrumentation by 
loading or unloading the "darshan" module.

==== Compiler wrappers (user installation)
Philip Carns's avatar
Philip Carns committed
309

310 311 312 313
In order to install Darshan for a single user in a Cray environment, the steps
are similar to those described above, except that the compiler script
modifications are applied to a local copy of the compiler scripts and the 
Darshan module is added locally rather than globally:
Philip Carns's avatar
Philip Carns committed
314

315 316 317 318 319 320 321 322 323 324
----
mkdir xt-asyncpe-darshan
cp -r $ASYNCPE_DIR/* xt-asyncpe-darshan
cd xt-axyncpe-darshan/bin
patch -p0 --dry-run < /home/carns/darshan-2.2.3/darshan-runtime/share/cray/cray-xt-asyncpe-5.10-darshan.patch
# CONFIRM THE RESULTS OF THE DRY RUN SHOWN ABOVE
patch -p0 < /home/carns/darshan-2.2.3/darshan-runtime/share/cray/cray-xt-asyncpe-5.10-darshan.patch

module use /soft/darshan-2.2.3/share/cray/modulefiles/
----
Philip Carns's avatar
Philip Carns committed
325

326 327 328
In addition to loading the "darshan" software module, in order to use the 
modified compiler script you must also set the following environment
variables:
Philip Carns's avatar
Philip Carns committed
329

330 331 332 333
----
setenv ASYNCPE_DIR /home/carns/xt-asyncpe-darshan
setenv PATH "/home/carns/xt-asyncpe-darshan/bin:$PATH"
----
334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365

=== Linux clusters using Intel MPI 

Most Intel MPI installations produce dynamic executables by default.  To
configure Darshan in this environment you can use the following example:

----
./configure --with-mem-align=8 --with-log-path=/darshan-logs --with-jobid-env=PBS_JOBID CC=mpicc
----

.Rationale
[NOTE]
====
There is nothing unusual in this configuration except that you should use
the underlying GNU compilers rather than the Intel ICC compilers to compile
Darshan itself.
====

You can use the `LD_PRELOAD` method described earlier in this document to
instrument executables compiled with the Intel MPI compiler scripts.  This
method has been briefly tested using both GNU and Intel compilers.

.Caveat
[NOTE]
====
Darshan is only known to work with C and C++ executables generated by the
Intel MPI suite.  Darshan will not produce instrumentation for Fortran
executables.  For more details please check this Intel forum discussion:

http://software.intel.com/en-us/forums/showthread.php?t=103447&o=a&s=lr
====

366
=== Linux clusters using MPICH or OpenMPI
367 368 369 370 371 372

Follow the generic instructions provided at the top of this document.  The
only modification is to make sure that the `CC` used for compilation is
based on a GNU compiler.  Once Darshan has been installed, it should be
capable of instrumenting executables built with GNU, Intel, and PGI
compilers.
Philip Carns's avatar
Philip Carns committed
373