darshan-job-summary.pl 13.2 KB
Newer Older
1
#!/usr/bin/perl -w
2 3 4 5 6
#
#  (C) 2009 by Argonne National Laboratory.
#      See COPYRIGHT in top-level directory.
#

7 8
use FindBin;
use lib "$FindBin::Bin/../lib/";
9 10
use TeX::Encode;
use Encode;
11 12
use File::Temp qw/ tempdir /;
use Cwd;
13 14
use Getopt::Long;
use English;
15 16 17 18 19

my $gnuplot = "";

my $tmp_dir = tempdir( CLEANUP => 1 );
my $orig_dir = getcwd;
20 21
my $output_file = "summary.pdf";
my $input_file = "";
22

23 24 25
process_args();

open(TRACE, $input_file) || die("can't open $input_file for processing: $!\n");
26 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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119

$max_access = -1;
$max_access_hash = 0;

while ($line = <TRACE>) {
    chop($line);
    
    if ($line =~ /^\s*$/) {
        # ignore blank lines
    }
    elsif ($line =~ /^#/) {
	if ($line =~ /^# exe: /) {
	    ($junk, $cmdline) = split(':', $line, 2);
            # add escape characters if needed for special characters in
            # command line
            $cmdline = encode('latex', $cmdline);
	}
	if ($line =~ /^# nprocs: /) {
	    ($junk, $nprocs) = split(':', $line, 2);
	    $procreads[$nprocs] = 0;
	}
	if ($line =~ /^# run time: /) {
	    ($junk, $runtime) = split(':', $line, 2);
	}
	if ($line =~ /^# start_time: /) {
	    ($junk, $starttime) = split(':', $line, 2);
	}
	if ($line =~ /^# uid: /) {
	    ($junk, $uid) = split(':', $line, 2);
	}
    }
    else {
	@fields = split(/[\t ]+/, $line);
	$summary{$fields[2]} += $fields[3];

	# record per-process POSIX read count
	if ($fields[2] eq "CP_POSIX_READS") {
	    if ($fields[0] == -1) {
		$procreads[$nprocs] += $fields[3];
	    }
	    else {
		$procreads[$fields[0]] += $fields[3];
	    }
	}

	# record per-proces POSIX write count
	if ($fields[2] eq "CP_POSIX_WRITES") {
	    if ($fields[0] == -1) {
		$procwrites[$nprocs] += $fields[3];
	    }
	    else {
		$procwrites[$fields[0]] += $fields[3];
	    }
	}

        # record access and stride counters
        if ($fields[2] =~ /(^CP_STRIDE.*)/) {
            $tmpfield = $1;

            if(defined $common{$fields[1]}{$tmpfield}) {
                $common{$fields[1]}{$tmpfield} += $fields[3];
            }
            else {
                $common{$fields[1]}{$tmpfield} = $fields[3];
            }
            $common{$fields[1]}{'name'} = $fields[4];
        }
        if ($fields[2] =~ /(^CP_ACCESS.*)/) {
            $tmpfield = $1;
            if(defined $common{$fields[1]}{$tmpfield}) {
                $common{$fields[1]}{$tmpfield} += $fields[3];
            }
            else {
                $common{$fields[1]}{$tmpfield} = $fields[3];
            }
            if(defined $common{$fields[1]}{'totalaccess'}) {
                $common{$fields[1]}{'totalaccess'} += $fields[3];
            }
            else {
                $common{$fields[1]}{'totalaccess'} = $fields[3];
            }

            if($common{$fields[1]}{'totalaccess'} > $max_access) {
                $max_access = $common{$fields[1]}{'totalaccess'};
                $max_access_hash = $fields[1];
            }
        }
    }
}

# print "max_access: $max_access.\n";
# print "max_access_hash: $max_access_hash.\n";

# counts of operations
120
open(COUNTS, ">$tmp_dir/counts.dat") || die("error opening output file: $!\n");
121 122 123 124 125 126 127 128 129 130 131 132 133 134
print COUNTS "# P=POSIX, MI=MPI-IO indep., MC=MPI-IO coll., R=read, W=write\n";
print COUNTS "# PR, MIR, MCR, PW, MIW, MCW, Popen, Pseek, Pstat\n";
print COUNTS "Read, ", $summary{CP_POSIX_READS}, ", ",
    $summary{CP_INDEP_READS}, ", ", $summary{CP_COLL_READS}, "\n",
    "Write, ", $summary{CP_POSIX_WRITES}, ", ", 
    $summary{CP_INDEP_WRITES}, ", ", $summary{CP_COLL_WRITES}, "\n",
    "Open, ", $summary{CP_POSIX_OPENS}, ", ", $summary{CP_INDEP_OPENS},", ",
    $summary{CP_COLL_OPENS}, "\n",
    "Stat, ", $summary{CP_POSIX_STATS}, ", 0, 0\n",
    "Seek, ", $summary{CP_POSIX_SEEKS}, ", 0, 0\n",
    "Mmap, ", $summary{CP_POSIX_MMAPS}, ", 0, 0\n";
close COUNTS;

# histograms of reads and writes
135
open (HIST, ">$tmp_dir/hist.dat") || die("error opening output file: $!\n");
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
print HIST "# size_range read write\n";
print HIST "0-100, ", $summary{CP_SIZE_READ_0_100}, ", ",
                 $summary{CP_SIZE_WRITE_0_100}, "\n";
print HIST "101-1K, ", $summary{CP_SIZE_READ_100_1K}, ", ",
                 $summary{CP_SIZE_WRITE_100_1K}, "\n";
print HIST "1K-10K, ", $summary{CP_SIZE_READ_1K_10K}, ", ",
                 $summary{CP_SIZE_WRITE_1K_10K}, "\n";
print HIST "10K-100K, ", $summary{CP_SIZE_READ_10K_100K}, ", ",
                 $summary{CP_SIZE_WRITE_10K_100K}, "\n";
print HIST "100K-1M, ", $summary{CP_SIZE_READ_100K_1M}, ", ",
                 $summary{CP_SIZE_WRITE_100K_1M}, "\n";
print HIST "1M-4M, ", $summary{CP_SIZE_READ_1M_4M}, ", ",
                 $summary{CP_SIZE_WRITE_1M_4M}, "\n";
print HIST "4M-10M, ", $summary{CP_SIZE_READ_4M_10M}, ", ",
                 $summary{CP_SIZE_WRITE_4M_10M}, "\n";
print HIST "10M-100M, ", $summary{CP_SIZE_READ_10M_100M}, ", ",
                 $summary{CP_SIZE_WRITE_10M_100M}, "\n";
print HIST "100M-1G, ", $summary{CP_SIZE_READ_100M_1G}, ", ",
                 $summary{CP_SIZE_WRITE_100M_1G}, "\n";
print HIST "1G+, ", $summary{CP_SIZE_READ_1G_PLUS}, ", ",
                 $summary{CP_SIZE_WRITE_1G_PLUS}, "\n";
close HIST;

# sequential and consecutive accesses
160
open (PATTERN, ">$tmp_dir/pattern.dat") || die("error opening output file: $!\n");
161 162 163 164 165 166 167 168
print PATTERN "# op total sequential consecutive\n";
print PATTERN "Read, ", $summary{CP_POSIX_READS}, ", ",
    $summary{CP_SEQ_READS}, ", ", $summary{CP_CONSEC_READS}, "\n";
print PATTERN "Write, ", $summary{CP_POSIX_WRITES}, ", ",
    $summary{CP_SEQ_WRITES}, ", ", $summary{CP_CONSEC_WRITES}, "\n";
close PATTERN;

# aligned I/O
169
open (ALIGN, ">$tmp_dir/align.dat") || die("error opening output file: $!\n");
170 171 172 173 174 175
print ALIGN "# total unaligned_mem unaligned_file align_mem align_file\n";
print ALIGN $summary{CP_POSIX_READS} + $summary{CP_POSIX_WRITES}, ", ",
    $summary{CP_MEM_NOT_ALIGNED}, ", ", $summary{CP_FILE_NOT_ALIGNED}, "\n";
close ALIGN;

# MPI types
176
open (TYPES, ">$tmp_dir/types.dat") || die("error opening output file: $!\n");
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
print TYPES "# type use_count\n";
print TYPES "Named, ", $summary{CP_COMBINER_NAMED}, "\n";
print TYPES "Dup, ", $summary{CP_COMBINER_DUP}, "\n";
print TYPES "Contig, ", $summary{CP_COMBINER_CONTIGUOUS}, "\n";
print TYPES "Vector, ", $summary{CP_COMBINER_VECTOR}, "\n";
print TYPES "HvecInt, ", $summary{CP_COMBINER_HVECTOR_INTEGER}, "\n";
print TYPES "Hvector, ", $summary{CP_COMBINER_HVECTOR}, "\n";
print TYPES "Indexed, ", $summary{CP_COMBINER_INDEXED}, "\n";
print TYPES "HindInt, ", $summary{CP_COMBINER_HINDEXED_INTEGER}, "\n";
print TYPES "Hindexed, ", $summary{CP_COMBINER_HINDEXED}, "\n";
print TYPES "IndBlk, ", $summary{CP_COMBINER_INDEXED_BLOCK}, "\n";
print TYPES "StructInt, ", $summary{CP_COMBINER_STRUCT_INTEGER}, "\n";
print TYPES "Struct, ", $summary{CP_COMBINER_STRUCT}, "\n";
print TYPES "Subarray, ", $summary{CP_COMBINER_SUBARRAY}, "\n";
print TYPES "Darray, ", $summary{CP_COMBINER_DARRAY}, "\n";
print TYPES "F90Real, ", $summary{CP_COMBINER_F90_REAL}, "\n";
print TYPES "F90Complex, ", $summary{CP_COMBINER_F90_COMPLEX}, "\n";
print TYPES "F90Int, ", $summary{CP_COMBINER_F90_INTEGER}, "\n";
print TYPES "Resized, ", $summary{CP_COMBINER_RESIZED}, "\n";
close TYPES;

# generate histogram of process I/O counts
#
# NOTE: NEED TO FILL IN ACTUAL WRITE DATA!!!
#
$minprocread = (defined $procreads[0]) ? $procreads[0] : 0;
$maxprocread = (defined $procreads[0]) ? $procreads[0] : 0;
for ($i=1; $i < $nprocs; $i++) {
    $rdi = (defined $procreads[$i]) ? $procreads[$i] : 0;
    $minprocread = ($rdi > $minprocread) ? $minprocread : $rdi;
    $maxprocread = ($rdi < $maxprocread) ? $maxprocread : $rdi;
}
$minprocread += $procreads[$nprocs];
$maxprocread += $procreads[$nprocs];
# print "$minprocread $maxprocread\n";

@bucket = ( 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 );

for ($i=0; $i < $nprocs; $i++) {
    $mysize = ((defined $procreads[$i]) ? $procreads[$i] : 0) +
	$procreads[$nprocs];
    $mysize -= $minprocread;
    $mybucket = ($mysize > 0) ?
	(($mysize * 10) / ($maxprocread - $minprocread)) : 0;
    $bucket[$mybucket]++;
}

224
open(IODIST, ">$tmp_dir/iodist.dat") || die("error opening output file: $!\n");
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245
print IODIST "# bucket n_procs_rd n_procs_wr\n";
print IODIST "# NOTE: WRITES ARE A COPY OF READS FOR NOW!!!\n";

$bucketsize = $maxprocread - $minprocread / 10;
# TODO: do writes also, is dropping a 0 in for now
for ($i=0; $i < 10; $i++) {
    print IODIST $bucketsize * $i + $minprocread, "-",
    $bucketsize * ($i+1) + $minprocread, ", ", $bucket[$i], ", 0\n";
}
close IODIST;

# generate title for summary
($executable, $junk) = split(' ', $cmdline, 2);
@parts = split('/', $executable);
$cmd = $parts[$#parts];

@timearray = localtime($starttime);
$year = $timearray[5] + 1900;
$mon = $timearray[4] + 1;
$mday = $timearray[3];

246
open(TITLE, ">$tmp_dir/title.tex") || die("error opening output file:$!\n");
247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263
print TITLE "
\\rhead{\\thepage\\ of \\pageref{LastPage}}
\\chead[
\\large $cmd ($mon/$mday/$year)
]
{
\\large $cmd ($mon/$mday/$year)
}
\\cfoot[
\\scriptsize{$cmdline}
]
{
\\scriptsize{$cmdline}
}
";
close TITLE;

264
open(TABLES, ">$tmp_dir/job-table.tex") || die("error opening output file:$!\n");
265 266 267 268 269 270 271 272 273
print TABLES "
\\begin{tabular}{|p{.63\\columnwidth}|p{.63\\columnwidth}|p{.63\\columnwidth}|}
\\hline
uid: $uid \& nprocs: $nprocs \& runtime: $runtime seconds\\\\
\\hline
\\end{tabular}
";
close TABLES;

274
open(TABLES, ">$tmp_dir/access-table.tex") || die("error opening output file:$!\n");
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
print TABLES "
\\begin{tabular}{|r|r|}
\\multicolumn{2}{c}{Top 4 Access Sizes} \\\\
\\hline
access size \& count \\\\
\\hline
  $common{$max_access_hash}{CP_ACCESS1_ACCESS} \& $common{$max_access_hash}{CP_ACCESS1_COUNT} \\\\
  $common{$max_access_hash}{CP_ACCESS2_ACCESS} \& $common{$max_access_hash}{CP_ACCESS2_COUNT} \\\\
  $common{$max_access_hash}{CP_ACCESS3_ACCESS} \& $common{$max_access_hash}{CP_ACCESS3_COUNT} \\\\
  $common{$max_access_hash}{CP_ACCESS4_ACCESS} \& $common{$max_access_hash}{CP_ACCESS4_COUNT} \\\\
\\hline
\\end{tabular}
";
close TABLES;

290
open(TABLES, ">$tmp_dir/stride-table.tex") || die("error opening output file:$!\n");
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306
print TABLES "
\\begin{tabular}{|r|r|}
\\multicolumn{2}{c}{file: $common{$max_access_hash}{'name'}} \\\\
\\hline
stride size \& count \\\\
\\hline
  $common{$max_access_hash}{CP_STRIDE1_STRIDE} \& $common{$max_access_hash}{CP_STRIDE1_COUNT} \\\\
  $common{$max_access_hash}{CP_STRIDE2_STRIDE} \& $common{$max_access_hash}{CP_STRIDE2_COUNT} \\\\
  $common{$max_access_hash}{CP_STRIDE3_STRIDE} \& $common{$max_access_hash}{CP_STRIDE3_COUNT} \\\\
  $common{$max_access_hash}{CP_STRIDE4_STRIDE} \& $common{$max_access_hash}{CP_STRIDE4_COUNT} \\\\
\\hline
\\end{tabular}
";
close TABLES;


307
open(TIME, ">$tmp_dir/time-summary.dat") || die("error opening output file:$!\n");
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
print TIME "# <type>, <app time>, <read>, <write>, <meta>\n";
print TIME "POSIX, ", ((($runtime * $nprocs - $summary{CP_F_POSIX_READ_TIME} -
    $summary{CP_F_POSIX_WRITE_TIME} -
    $summary{CP_F_POSIX_META_TIME})/($runtime * $nprocs)) * 100);
print TIME ", ", (($summary{CP_F_POSIX_READ_TIME}/($runtime * $nprocs))*100);
print TIME ", ", (($summary{CP_F_POSIX_WRITE_TIME}/($runtime * $nprocs))*100);
print TIME ", ", (($summary{CP_F_POSIX_META_TIME}/($runtime * $nprocs))*100), "\n";
print TIME "MPI-IO, ", ((($runtime * $nprocs - $summary{CP_F_MPI_READ_TIME} -
    $summary{CP_F_MPI_WRITE_TIME} -
    $summary{CP_F_MPI_META_TIME})/($runtime * $nprocs)) * 100);
print TIME ", ", (($summary{CP_F_MPI_READ_TIME}/($runtime * $nprocs))*100);
print TIME ", ", (($summary{CP_F_MPI_WRITE_TIME}/($runtime * $nprocs))*100);
print TIME ", ", (($summary{CP_F_MPI_META_TIME}/($runtime * $nprocs))*100), "\n";
close TIME;

323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
# copy template files to tmp tmp_dir
system "cp $FindBin::Bin/../share/* $tmp_dir/";

if(-x "$FindBin::Bin/gnuplot")
{
    $gnuplot = "$FindBin::Bin/gnuplot";
}
else
{
    $gnuplot = "gnuplot";
}

# move to tmp_dir
chdir $tmp_dir;

338
# execute gnuplot scripts
339
system "$gnuplot counts-eps.gplt";
340
system "epstopdf counts.eps";
341
system "$gnuplot hist-eps.gplt";
342
system "epstopdf hist.eps";
343
system "$gnuplot pattern-eps.gplt";
344
system "epstopdf pattern.eps";
345
system "$gnuplot time-summary-eps.gplt";
346
system "epstopdf time-summary.eps";
347

348 349 350 351
#system "gnuplot align-pdf.gplt";
#system "gnuplot iodist-pdf.gplt";
#system "gnuplot types-pdf.gplt";

352 353 354 355
# generate summary PDF
system "pdflatex -halt-on-error summary.tex > latex.output";
system "pdflatex -halt-on-error summary.tex > latex.output2";

356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408
# get back out of tmp dir and grab results
chdir $orig_dir;
system "mv $tmp_dir/summary.pdf $output_file";

sub process_args
{
    use vars qw( $opt_help $opt_output );

    Getopt::Long::Configure("no_ignore_case", "bundling");
    GetOptions( "help",
        "output=s");

    if($opt_help)
    {
        print_help();
        exit(0);
    }

    if($opt_output)
    {
        $output_file = $opt_output;
    }

    # there should only be one remaining argument: the input file 
    if($#ARGV != 0)
    {
        print "Error: invalid arguments.\n";
        print_help();
        exit(1);
    }
    $input_file = $ARGV[0];

    return;
}

sub print_help
{
    print <<EOF;

Usage: $PROGRAM_NAME <options> input_file

    --help          Prints this help message
    --output        Specifies a file to write pdf output to
                    (defaults to ./summary.pdf)
Purpose:

    This script reads a Darshan output file in text format (as 
    produced by the darshan-parser utility) and generates a pdf file 
    summarizing job behavior.

EOF
    return;
}