darshan-job-summary.pl.in 45.3 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
# Set via configure
8
my $PREFIX="@prefix@";
9

10
use lib "@prefix@/lib";
11 12
use TeX::Encode;
use Encode;
13
use File::Temp qw/ tempdir /;
14
use File::Basename;
15
use Cwd;
16 17
use Getopt::Long;
use English;
18
use Number::Bytes::Human qw(format_bytes);
19
use POSIX qw(strftime);
20

21 22 23 24 25 26 27 28
#
# system commands used
#
my $darshan_parser = "$PREFIX/bin/darshan-parser";
my $pdflatex       = "pdflatex";
my $epstopdf       = "epstopdf";
my $cp             = "cp";
my $mv             = "mv";
29 30 31 32 33 34 35 36 37 38
my $gnuplot;
# Prefer gnuplot installed with darshan, if present.
if(-x "$PREFIX/bin/gnuplot")
{
    $gnuplot       = "$PREFIX/bin/gnuplot";
}
else
{
    $gnuplot       = "gnuplot";
}
39

40
my $orig_dir = getcwd;
41
my $output_file = "summary.pdf";
42
my $verbose_flag = 0;
43
my $input_file = "";
44 45
my %access_hash = ();
my @access_size = ();
46
my %hash_files = ();
47
my $size_est_flag = 0;
48

49
# data structures for calculating performance
50 51
my %hash_unique_file_time = ();
my $shared_file_time = 0;
52
my $total_job_bytes = 0;
53

54 55
process_args();

56 57
check_prereqs();

58 59 60 61 62 63
my $tmp_dir = tempdir( CLEANUP => !$verbose_flag );
if ($verbose_flag)
{
    print "verbose: $tmp_dir\n";
}

64 65 66

open(TRACE, "$darshan_parser $input_file |") || die("Can't execute \"$darshan_parser $input_file\": $!\n");

67 68
open(FA_READ, ">$tmp_dir/file-access-read.dat") || die("error opening output file: $!\n");
open(FA_WRITE, ">$tmp_dir/file-access-write.dat") || die("error opening output file: $!\n");
69 70
open(FA_READ_SH, ">$tmp_dir/file-access-read-sh.dat") || die("error opening output file: $!\n");
open(FA_WRITE_SH, ">$tmp_dir/file-access-write-sh.dat") || die("error opening output file: $!\n");
71 72 73

my $last_read_start = 0;
my $last_write_start = 0;
74

75 76 77 78 79 80 81 82 83 84 85 86
my $cumul_read_indep = 0;
my $cumul_read_bytes_indep = 0;

my $cumul_write_indep = 0;
my $cumul_write_bytes_indep = 0;

my $cumul_read_shared = 0;
my $cumul_read_bytes_shared = 0;

my $cumul_write_shared = 0;
my $cumul_write_bytes_shared = 0;

87 88 89
my $cumul_meta_shared = 0;
my $cumul_meta_indep = 0;

90 91 92 93 94
my $first_data_line = 1;
my $current_rank = 0;
my $current_hash = 0;
my %file_record_hash = ();

95 96
my %fs_data = ();

97
while ($line = <TRACE>) {
98
    chomp($line);
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122
    
    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(':', $line, 2);
	}
123 124 125
        if ($line =~ /^# jobid: /) {
	    ($junk, $jobid) = split(':', $line, 2);
        }
126 127 128 129 130
        if ($line =~ /^# darshan log version: /) {
            ($junk, $version) = split(':', $line, 2);
            $version =~ s/^\s+//;
            ($major, $minor) = split(/\./, $version, 2);
        }
131 132
    }
    else {
133
        # parse line
134
	@fields = split(/[\t ]+/, $line);
135

136 137 138
        # encode the file system name to protect against special characters
        $fields[5] = encode('latex', $fields[5]);
        
139 140 141 142 143 144 145 146 147
        # is this our first piece of data?
        if($first_data_line)
        {
            $current_rank = $fields[0];
            $current_hash = $fields[1];
            $first_data_line = 0;
        }

        # is this a new file record?
148
        if($fields[0] != $current_rank || $fields[1] != $current_hash)
149 150
        {
            # process previous record
151
            process_file_record($current_rank, $current_hash, \%file_record_hash);
152 153 154 155 156

            # reset variables for next record 
            $current_rank = $fields[0];
            $current_hash = $fields[1];
            %file_record_hash = ();
157
            $file_record_hash{CP_NAME_SUFFIX} = $fields[4];
158 159 160 161
        }

        $file_record_hash{$fields[2]} = $fields[3];

162 163 164
	$summary{$fields[2]} += $fields[3];

	# record per-process POSIX read count
165
	if ($fields[2] eq "CP_POSIX_READS" || $fields[2] eq "CP_POSIX_FREADS") {
166 167 168 169 170 171 172 173 174
	    if ($fields[0] == -1) {
		$procreads[$nprocs] += $fields[3];
	    }
	    else {
		$procreads[$fields[0]] += $fields[3];
	    }
	}

	# record per-proces POSIX write count
175
	if ($fields[2] eq "CP_POSIX_WRITES" || $fields[2] eq "CP_POSIX_FWRITES") {
176 177 178 179 180 181 182 183
	    if ($fields[0] == -1) {
		$procwrites[$nprocs] += $fields[3];
	    }
	    else {
		$procwrites[$fields[0]] += $fields[3];
	    }
	}

184
        # seperate accumulators for independent and shared reads and writes
185
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] == -1){
186 187
            $cumul_read_shared += $fields[3];
        }
188
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] != -1){
189 190
            $cumul_read_indep += $fields[3];
        }
191
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] == -1){
192 193
            $cumul_write_shared += $fields[3];
        }
194
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] != -1){
195 196 197
            $cumul_write_indep += $fields[3];
        }

198 199 200 201 202 203 204
        if ($fields[2] eq "CP_F_POSIX_META_TIME" && $fields[0] == -1){
            $cumul_meta_shared += $fields[3];
        }
        if ($fields[2] eq "CP_F_POSIX_META_TIME" && $fields[0] != -1){
            $cumul_meta_indep += $fields[3];
        }

205 206
        if ((($fields[2] eq "CP_BYTES_READ") or
             ($fields[2] eq "CP_BYTES_WRITTEN")) and
207 208 209 210
            not defined($fs_data{$fields[5]}))
        {
            $fs_data{$fields[5]} = [0,0];
        }
211

212
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] == -1){
213
            $cumul_read_bytes_shared += $fields[3];
214
            $fs_data{$fields[5]}->[0] += $fields[3];
215
        }
216
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] != -1){
217
            $cumul_read_bytes_indep += $fields[3];
218
            $fs_data{$fields[5]}->[0] += $fields[3];
219
        }
220
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] == -1){
221
            $cumul_write_bytes_shared += $fields[3];
222
            $fs_data{$fields[5]}->[1] += $fields[3];
223
        }
224
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] != -1){
225
            $cumul_write_bytes_indep += $fields[3];
226
            $fs_data{$fields[5]}->[1] += $fields[3];
227 228
        }

229 230 231 232 233 234 235 236 237 238 239 240 241 242
        # record start and end of reads and writes

        if ($fields[2] eq "CP_F_READ_START_TIMESTAMP") {
            # store until we find the end
            # adjust for systems that give absolute time stamps
            $last_read_start = $fields[3];
        }
        if ($fields[2] eq "CP_F_READ_END_TIMESTAMP" && $fields[3] != 0) {
            # assume we got the read start already 
            my $xdelta = $fields[3] - $last_read_start;
            # adjust for systems that have absolute time stamps 
            if($last_read_start > $starttime) {
                $last_read_start -= $starttime;
            }
243 244 245 246
            if($fields[3] > $runtime)
            {
                print "Warning: detected read access at time $fields[3] but runtime is only $runtime seconds.\n";
            }
247 248 249 250 251 252
            if($fields[0] == -1){
                print FA_READ_SH "$last_read_start\t0\t$xdelta\t0\n";
            }
            else{
                print FA_READ "$last_read_start\t$fields[0]\t$xdelta\t0\n";
            }
253 254 255 256 257 258 259 260 261 262 263 264
        }
        if ($fields[2] eq "CP_F_WRITE_START_TIMESTAMP") {
            # store until we find the end
            $last_write_start = $fields[3];
        }
        if ($fields[2] eq "CP_F_WRITE_END_TIMESTAMP" && $fields[3] != 0) {
            # assume we got the write start already 
            my $xdelta = $fields[3] - $last_write_start;
            # adjust for systems that have absolute time stamps 
            if($last_write_start > $starttime) {
                $last_write_start -= $starttime;
            }
265 266 267 268
            if($fields[3] > $runtime)
            {
                print "Warning: detected write access at time $fields[3] but runtime is only $runtime seconds.\n";
            }
269 270 271 272 273 274
            if($fields[0] == -1){
                print FA_WRITE_SH "$last_write_start\t0\t$xdelta\t0\n";
            }
            else{
                print FA_WRITE "$last_write_start\t$fields[0]\t$xdelta\t0\n";
            }
275 276
        }

277 278
        if ($fields[2] =~ /^CP_ACCESS(.)_ACCESS/) {
            $access_size[$1] = $fields[3];
279
        }
280 281 282 283
        if ($fields[2] =~ /^CP_ACCESS(.)_COUNT/) {
            my $tmp_access_size = $access_size[$1];
            if(defined $access_hash{$tmp_access_size}){
                $access_hash{$tmp_access_size} += $fields[3];
284
            }
285 286
            else{
                $access_hash{$tmp_access_size} = $fields[3];
287 288 289 290 291
            }
        }
    }
}

292 293
close(TRACE) || die "darshan-parser failure: $! $?";

294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310
#
# Exit out if there are no actual file accesses
#
if ($first_data_line)
{
    $strtm = strftime("%a %b %e %H:%M:%S %Y", localtime($starttime));

    print "This darshan log has no file records. No summary was produced.\n";
    print "    jobid:$jobid\n";
    print "      uid:$uid\n";
    print "starttime: $strtm ($starttime )\n";
    print "  runtime:$runtime (seconds)\n";
    print "   nprocs:$nprocs\n";
    print "  version: $version\n";
    exit(1);
}

311
# process last file record
312
$file_record_hash{CP_NAME_SUFFIX} = $fields[4];
313
process_file_record($current_rank, $current_hash, \%file_record_hash);
314

315 316 317 318
# Fudge one point at the end to make xrange match in read and write plots.
# For some reason I can't get the xrange command to work.  -Phil
print FA_READ "$runtime\t-1\t0\t0\n";
print FA_WRITE "$runtime\t-1\t0\t0\n";
319 320
print FA_READ_SH "$runtime\t0\t0\t0\n";
print FA_WRITE_SH "$runtime\t0\t0\t0\n";
321 322
close(FA_READ);
close(FA_WRITE);
323 324
close(FA_READ_SH);
close(FA_WRITE_SH);
325

326
# counts of operations
327
open(COUNTS, ">$tmp_dir/counts.dat") || die("error opening output file: $!\n");
328 329
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";
330
my $total_posix_opens = $summary{CP_POSIX_OPENS} + $summary{CP_POSIX_FOPENS};
331
my $total_syncs = $summary{CP_POSIX_FSYNCS} + $summary{CP_POSIX_FDSYNCS};
332
print COUNTS "Read, ", $summary{CP_POSIX_READS} + $summary{CP_POSIX_FREADS}, ", ",
333
    $summary{CP_INDEP_READS}, ", ", $summary{CP_COLL_READS}, "\n",
334
    "Write, ", $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FWRITES}, ", ", 
335
    $summary{CP_INDEP_WRITES}, ", ", $summary{CP_COLL_WRITES}, "\n",
336
    "Open, ", $total_posix_opens, ", ", $summary{CP_INDEP_OPENS},", ",
337 338 339
    $summary{CP_COLL_OPENS}, "\n",
    "Stat, ", $summary{CP_POSIX_STATS}, ", 0, 0\n",
    "Seek, ", $summary{CP_POSIX_SEEKS}, ", 0, 0\n",
340 341
    "Mmap, ", $summary{CP_POSIX_MMAPS}, ", 0, 0\n",
    "Fsync, ", $total_syncs, ", 0, 0\n";
342 343 344
close COUNTS;

# histograms of reads and writes
345
open (HIST, ">$tmp_dir/hist.dat") || die("error opening output file: $!\n");
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
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
370
open (PATTERN, ">$tmp_dir/pattern.dat") || die("error opening output file: $!\n");
371
print PATTERN "# op total sequential consecutive\n";
372
print PATTERN "Read, ", $summary{CP_POSIX_READS} + $summary{CP_POSIX_FREADS}, ", ",
373
    $summary{CP_SEQ_READS}, ", ", $summary{CP_CONSEC_READS}, "\n";
374
print PATTERN "Write, ", $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FWRITES}, ", ",
375 376 377 378
    $summary{CP_SEQ_WRITES}, ", ", $summary{CP_CONSEC_WRITES}, "\n";
close PATTERN;

# aligned I/O
379
open (ALIGN, ">$tmp_dir/align.dat") || die("error opening output file: $!\n");
380
print ALIGN "# total unaligned_mem unaligned_file align_mem align_file\n";
381 382
print ALIGN $summary{CP_POSIX_READS} + $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FREADS} + $summary{CP_POSIX_FWRITES}
, ", ",
383 384 385 386
    $summary{CP_MEM_NOT_ALIGNED}, ", ", $summary{CP_FILE_NOT_ALIGNED}, "\n";
close ALIGN;

# MPI types
387
open (TYPES, ">$tmp_dir/types.dat") || die("error opening output file: $!\n");
388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434
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]++;
}

435
open(IODIST, ">$tmp_dir/iodist.dat") || die("error opening output file: $!\n");
436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
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];

457
open(TITLE, ">$tmp_dir/title.tex") || die("error opening output file:$!\n");
458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474
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;

475
open(TABLES, ">$tmp_dir/job-table.tex") || die("error opening output file:$!\n");
476
print TABLES "
477
\\begin{tabular}{|p{.47\\columnwidth}|p{.35\\columnwidth}|p{.47\\columnwidth}|p{.6\\columnwidth}|}
478
\\hline
479
jobid: $jobid \& uid: $uid \& nprocs: $nprocs \& runtime: $runtime seconds\\\\
480 481 482 483 484
\\hline
\\end{tabular}
";
close TABLES;

485
open(TABLES, ">$tmp_dir/access-table.tex") || die("error opening output file:$!\n");
486
print TABLES "
Philip Carns's avatar
Philip Carns committed
487
\\begin{tabular}{r|r}
488
\\multicolumn{2}{c}{ } \\\\
489
\\multicolumn{2}{c}{Most Common Access Sizes} \\\\
490 491 492
\\hline
access size \& count \\\\
\\hline
Philip Carns's avatar
Philip Carns committed
493
\\hline
494 495
";

496 497
# sort access sizes (descending)
my $i = 0;
498 499
foreach $value (sort {$access_hash{$b} <=> $access_hash{$a} } keys %access_hash) {
    if($i == 4) {
500 501 502 503 504 505 506 507 508
        last;
    }
    if($access_hash{$value} == 0) {
        last;
    }
    print TABLES "$value \& $access_hash{$value} \\\\\n";
    $i++;
}

509 510 511 512 513 514
print TABLES "
\\hline
\\end{tabular}
";
close TABLES;

515 516 517
open(TABLES, ">$tmp_dir/file-count-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{r|r|r|r}
518
\\multicolumn{4}{c}{ } \\\\
519
\\multicolumn{4}{c}{File Count Summary} \\\\
520 521 522 523 524 525 526 527
";
if($size_est_flag == 1)
{
print TABLES "
\\multicolumn{4}{c}{(estimated by I/O access offsets)} \\\\
";
}
print TABLES "
528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
\\hline
type \& number of files \& avg. size \& max size \\\\
\\hline
\\hline
";
my $counter;
my $sum;
my $max;
my $key;
my $avg;

$counter = 0;
$sum = 0;
$max = 0;
foreach $key (keys %hash_files) {
    $counter++;
    if($hash_files{$key}{'min_open_size'} >
        $hash_files{$key}{'max_size'})
    {
        $sum += $hash_files{$key}{'min_open_size'};
        if($hash_files{$key}{'min_open_size'} > $max)
        {
            $max = $hash_files{$key}{'min_open_size'};
        }
    }
    else
    {
        $sum += $hash_files{$key}{'max_size'};
        if($hash_files{$key}{'max_size'} > $max)
        {
            $max = $hash_files{$key}{'max_size'};
        }
    }
}
562 563
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
564 565
$avg = format_bytes($avg);
$max = format_bytes($max);
566 567
print TABLES "total opened \& $counter \& $avg \& $max \\\\\n";

568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697
$counter = 0;
$sum = 0;
$max = 0;
foreach $key (keys %hash_files) {
    if($hash_files{$key}{'was_read'} && !($hash_files{$key}{'was_written'}))
    {
        $counter++;
        if($hash_files{$key}{'min_open_size'} >
            $hash_files{$key}{'max_size'})
        {
            $sum += $hash_files{$key}{'min_open_size'};
            if($hash_files{$key}{'min_open_size'} > $max)
            {
                $max = $hash_files{$key}{'min_open_size'};
            }
        }
        else
        {
            $sum += $hash_files{$key}{'max_size'};
            if($hash_files{$key}{'max_size'} > $max)
            {
                $max = $hash_files{$key}{'max_size'};
            }
        }
    }
}
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
$avg = format_bytes($avg);
$max = format_bytes($max);
print TABLES "read-only files \& $counter \& $avg \& $max \\\\\n";

$counter = 0;
$sum = 0;
$max = 0;
foreach $key (keys %hash_files) {
    if(!($hash_files{$key}{'was_read'}) && $hash_files{$key}{'was_written'})
    {
        $counter++;
        if($hash_files{$key}{'min_open_size'} >
            $hash_files{$key}{'max_size'})
        {
            $sum += $hash_files{$key}{'min_open_size'};
            if($hash_files{$key}{'min_open_size'} > $max)
            {
                $max = $hash_files{$key}{'min_open_size'};
            }
        }
        else
        {
            $sum += $hash_files{$key}{'max_size'};
            if($hash_files{$key}{'max_size'} > $max)
            {
                $max = $hash_files{$key}{'max_size'};
            }
        }
    }
}
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
$avg = format_bytes($avg);
$max = format_bytes($max);
print TABLES "write-only files \& $counter \& $avg \& $max \\\\\n";

$counter = 0;
$sum = 0;
$max = 0;
foreach $key (keys %hash_files) {
    if($hash_files{$key}{'was_read'} && $hash_files{$key}{'was_written'})
    {
        $counter++;
        if($hash_files{$key}{'min_open_size'} >
            $hash_files{$key}{'max_size'})
        {
            $sum += $hash_files{$key}{'min_open_size'};
            if($hash_files{$key}{'min_open_size'} > $max)
            {
                $max = $hash_files{$key}{'min_open_size'};
            }
        }
        else
        {
            $sum += $hash_files{$key}{'max_size'};
            if($hash_files{$key}{'max_size'} > $max)
            {
                $max = $hash_files{$key}{'max_size'};
            }
        }
    }
}
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
$avg = format_bytes($avg);
$max = format_bytes($max);
print TABLES "read/write files \& $counter \& $avg \& $max \\\\\n";

$counter = 0;
$sum = 0;
$max = 0;
foreach $key (keys %hash_files) {
    if($hash_files{$key}{'was_written'} &&
        $hash_files{$key}{'min_open_size'} == 0 &&
        $hash_files{$key}{'max_size'} > 0)
    {
        $counter++;
        if($hash_files{$key}{'min_open_size'} >
            $hash_files{$key}{'max_size'})
        {
            $sum += $hash_files{$key}{'min_open_size'};
            if($hash_files{$key}{'min_open_size'} > $max)
            {
                $max = $hash_files{$key}{'min_open_size'};
            }
        }
        else
        {
            $sum += $hash_files{$key}{'max_size'};
            if($hash_files{$key}{'max_size'} > $max)
            {
                $max = $hash_files{$key}{'max_size'};
            }
        }
    }
}
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
$avg = format_bytes($avg);
$max = format_bytes($max);
print TABLES "created files \& $counter \& $avg \& $max \\\\\n";

698 699 700 701 702 703 704
print TABLES "
\\hline
\\end{tabular}
";
close(TABLES);


705 706 707 708
#
# Generate Per Filesystem Data
#
open(TABLES, ">$tmp_dir/fs-data-table.tex") || die("error opening output files:$!\n");
709
if (($major > 1) or ($minor > 23))
710
{
711 712 713 714 715 716 717 718 719 720 721 722
    print TABLES "
    \\begin{tabular}{c|r|r|r|r}
    \\multicolumn{5}{c}{ } \\\\
    \\multicolumn{5}{c}{Data Transfer Per Filesystem} \\\\
    \\hline
    \\multirow{2}{*}{File System} \& \\multicolumn{2}{c}{Write} \\vline \& \\multicolumn{2}{c}{Read} \\\\
    \\cline{2-5}
    \& MiB \& Ratio \& MiB \& Ratio \\\\\
    \\hline
    \\hline
    ";
    foreach $key (keys %fs_data)
723
    {
724 725 726
        my $wr_total_mb = ($fs_data{$key}->[1] / (1024*1024));
        my $rd_total_mb = ($fs_data{$key}->[0] / (1024*1024));
        my $wr_total_rt;
727

728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
        if ($cumul_write_bytes_shared+$cumul_write_bytes_shared)
        {
            $wr_total_rt = ($fs_data{$key}->[1] / ($cumul_write_bytes_shared + $cumul_write_bytes_indep));
        }
        else
        {
            $wr_total_rt = 0;
        }

        my $rd_total_rt;
        if ($cumul_read_bytes_shared+$cumul_read_bytes_indep)
        {
            $rd_total_rt = ($fs_data{$key}->[0] / ($cumul_read_bytes_shared + $cumul_read_bytes_indep));
        }
        else
        {
            $rd_total_rt = 0;
        }
746

747 748
        printf TABLES "%s \& %.5f \& %.5f \& %.5f \& %.5f \\\\\n",
            $key, $wr_total_mb, $wr_total_rt, $rd_total_mb, $rd_total_rt;
749 750 751 752 753
}
print TABLES "
\\hline
\\end{tabular}
";
754 755 756 757 758 759 760 761
}
else
{
    print TABLES "
\\rule{0in}{1in}
\\parbox{5in}{Log versions prior to 1.24 do not support per-filesystem data.}
";
}
762 763 764
close(TABLES);


765
open(TIME, ">$tmp_dir/time-summary.dat") || die("error opening output file:$!\n");
766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
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;

781
# copy template files to tmp tmp_dir
782 783
system "$cp $PREFIX/share/*.gplt $tmp_dir/";
system "$cp $PREFIX/share/*.tex $tmp_dir/";
784

785 786 787 788 789 790 791
# generate template for file access plot (we have to set range)
my $ymax = $nprocs + 1;
open(FILEACC, ">$tmp_dir/file-access-read-eps.gplt") || die("error opening output file:$!\n");
print FILEACC "#!/usr/bin/gnuplot -persist

set terminal postscript eps color solid font \"Helvetica\" 18 size 10in,2.5in
set output \"file-access-read.eps\"
792 793
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
794 795 796
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
797
set yrange [-1:$ymax]
798
set title \"Timespan from first to last read access on independent files\"
799
set xrange [\"0\":\"$runtime\"]
800
#set ytics -1,1
801
set lmargin 4
802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820

# color blindness work around
set style line 2 lc 3
set style line 3 lc 4
set style line 4 lc 5
set style line 5 lc 2
set style increment user

# lw 3 to make lines thicker...
# note that writes are slightly offset for better visibility
plot \"file-access-read.dat\" using 1:2:3:4 with vectors nohead filled notitle
";
close FILEACC;

open(FILEACC, ">$tmp_dir/file-access-write-eps.gplt") || die("error opening output file:$!\n");
print FILEACC "#!/usr/bin/gnuplot -persist

set terminal postscript eps color solid font \"Helvetica\" 18 size 10in,2.5in
set output \"file-access-write.eps\"
821 822
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
823 824 825
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
826
set title \"Timespan from first to last write access on independent files\"
827
set yrange [-1:$ymax]
828
set xrange [\"0\":\"$runtime\"]
829
#set ytics -1,1
830
set lmargin 4
831 832 833 834 835 836 837 838 839 840 841 842 843

# color blindness work around
set style line 2 lc 3
set style line 3 lc 4
set style line 4 lc 5
set style line 5 lc 2
set style increment user

# lw 3 to make lines thicker...
plot \"file-access-write.dat\" using 1:2:3:4 with vectors nohead filled lt 2 notitle
";
close FILEACC;

844 845 846 847 848 849 850 851 852 853
open(FILEACC, ">$tmp_dir/file-access-shared-eps.gplt") || die("error opening output file:$!\n");
print FILEACC "#!/usr/bin/gnuplot -persist

set terminal postscript eps color solid font \"Helvetica\" 18 size 10in,2.5in
set output \"file-access-shared.eps\"
set xlabel \"hours:minutes:seconds\"
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
unset ytics
854
set ylabel \"All processes\"
855
set xrange [\"0\":\"$runtime\"]
856
set yrange [-1:1]
857
set title \"Timespan from first to last access on files shared by all processes\"
858
set lmargin 4
859 860 861 862 863 864 865 866 867 868 869 870 871

# color blindness work around
set style line 2 lc 3
set style line 3 lc 4
set style line 4 lc 5
set style line 5 lc 2
set style increment user

plot \"file-access-read-sh.dat\" using 1:2:3:4 with vectors nohead filled lw 10 title \"read\", \\
\"file-access-write-sh.dat\" using 1:((\$2)-.2):3:4 with vectors nohead filled lw 10 title \"write\"
";
close FILEACC;

872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887
$cumul_read_indep /= $nprocs;
$cumul_read_bytes_indep /= $nprocs;
$cumul_read_bytes_indep /= 1048576.0;

$cumul_write_indep /= $nprocs;
$cumul_write_bytes_indep /= $nprocs;
$cumul_write_bytes_indep /= 1048576.0;

$cumul_read_shared /= $nprocs;
$cumul_read_bytes_shared /= $nprocs;
$cumul_read_bytes_shared /= 1048576.0;

$cumul_write_shared /= $nprocs;
$cumul_write_bytes_shared /= $nprocs;
$cumul_write_bytes_shared /= 1048576.0;

888 889 890
$cumul_meta_shared /= $nprocs;
$cumul_meta_indep /= $nprocs;

891
open(FILEACC, ">$tmp_dir/file-access-table.tex") || die("error opening output file:$!\n");
892
print FILEACC "
Philip Carns's avatar
Philip Carns committed
893 894 895 896
\\begin{tabular}{l|p{1.7in}r}
\\multicolumn{3}{c}{Average I/O per process} \\\\
\\hline
 \& Cumulative time spent in I/O functions (seconds) \& Amount of I/O (MB) \\\\
897 898
\\hline
\\hline
899 900
";

Philip Carns's avatar
Philip Carns committed
901 902 903 904 905
# printf to get consistent precision in output
printf(FILEACC "Independent reads \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{%f} \\\\", 
    $cumul_read_indep, $cumul_read_bytes_indep);
printf(FILEACC "Independent writes \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{%f} \\\\", 
    $cumul_write_indep, $cumul_write_bytes_indep);
906 907
printf(FILEACC "Independent metadata \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{N/A} \\\\", 
    $cumul_meta_indep);
Philip Carns's avatar
Philip Carns committed
908 909 910 911
printf(FILEACC "Shared reads \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{%f} \\\\", 
    $cumul_read_shared, $cumul_read_bytes_shared);
printf(FILEACC "Shared writes \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{%f} \\\\", 
    $cumul_write_shared, $cumul_write_bytes_shared);
912 913
printf(FILEACC "Shared metadata \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{N/A} \\\\", 
    $cumul_meta_shared);
914 915

print FILEACC "
916 917 918
\\hline
\\end{tabular}
";
919 920
close(FILEACC);

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
#
# Variance Data
#
open(VARP, ">$tmp_dir/variance-table.tex") || die("error opening output file:$!\n");
print VARP "
\\begin{tabular}{c|r|r|r|r|r|r|r|r|r}
\\multicolumn{10}{c}{} \\\\
\\multicolumn{10}{c}{Variance in Shared Files} \\\\
\\hline
File \& Processes \& \\multicolumn{3}{c}{Fastest} \\vline \&
\\multicolumn{3}{c}{Slowest} \\vline \& \\multicolumn{2}{c}{\$\\sigma\$} \\\\
\\cline{3-10}
Suffix \&  \& Rank \& Time \& Bytes \& Rank \& Time \& Bytes \& Time \& Bytes \\\\
\\hline
\\hline
";

938 939 940 941 942
my $curcount = 1;
foreach $key (sort { $hash_files{$b}{'slowest_time'} <=> $hash_files{$a}{'slowest_time'} } keys %hash_files) {

    if ($curcount > 20) { last; }

943 944 945 946 947 948
    if ($hash_files{$key}{'procs'} > 1)
    {
        my $vt = sprintf("%.3g", sqrt($hash_files{$key}{'variance_time'}));
        my $vb = sprintf("%.3g", sqrt($hash_files{$key}{'variance_bytes'}));
        my $fast_bytes = format_bytes($hash_files{$key}{'fastest_bytes'});
        my $slow_bytes = format_bytes($hash_files{$key}{'slowest_bytes'});
949
        my $name = encode('latex', $hash_files{$key}{'name'});
950 951

        print VARP "
952
               $name \&
953 954 955 956 957 958 959 960 961 962
               $hash_files{$key}{'procs'} \&
               $hash_files{$key}{'fastest_rank'} \&
               $hash_files{$key}{'fastest_time'} \&
               $fast_bytes \&
               $hash_files{$key}{'slowest_rank'} \&
               $hash_files{$key}{'slowest_time'} \& 
               $slow_bytes \&
               $vt \&
               $vb \\\\
         ";
963
        $curcount++;
964 965 966 967 968 969 970 971 972
    }
}

print VARP "
\\hline
\\end{tabular}
";
close(VARP);

973 974 975 976 977 978 979 980 981 982
# calculate performance
##########################################################################

# what was the slowest time by any proc for unique file access?
my $slowest_uniq_time = 0;
if(keys %hash_unique_file_time > 0)
{
    $slowest_uniq_time < $_ and $slowest_uniq_time = $_ for values %hash_unique_file_time;
}
print("Slowest unique file time: $slowest_uniq_time\n");
983
print("Slowest shared file time: $shared_file_time\n");
984 985 986
print("Total bytes read and written by app (may be incorrect): $total_job_bytes\n");
my $tmp_total_time = $slowest_uniq_time+$shared_file_time;
print("Total absolute I/O time: $tmp_total_time\n");
987

988 989 990
# move to tmp_dir
chdir $tmp_dir;

991
# execute gnuplot scripts
992
system "$gnuplot counts-eps.gplt";
993
system "$epstopdf counts.eps";
994
system "$gnuplot hist-eps.gplt";
995
system "$epstopdf hist.eps";
996
system "$gnuplot pattern-eps.gplt";
997
system "$epstopdf pattern.eps";
998
system "$gnuplot time-summary-eps.gplt";
999
system "$epstopdf time-summary.eps";
1000
system "$gnuplot file-access-read-eps.gplt";
1001
system "$epstopdf file-access-read.eps";
1002
system "$gnuplot file-access-write-eps.gplt";
1003
system "$epstopdf file-access-write.eps";
1004
system "$gnuplot file-access-shared-eps.gplt";
1005
system "$epstopdf file-access-shared.eps";
1006

1007 1008 1009 1010
#system "gnuplot align-pdf.gplt";
#system "gnuplot iodist-pdf.gplt";
#system "gnuplot types-pdf.gplt";

1011
# generate summary PDF
1012 1013 1014
# NOTE: an autoconf test determines if -halt-on-error is available and sets
# __CP_PDFLATEX_HALT_ON_ERROR accordingly
$system_rc = system "$pdflatex @__CP_PDFLATEX_HALT_ON_ERROR@ summary.tex > latex.output";
1015 1016 1017 1018 1019 1020 1021
if($system_rc)
{
    print("LaTeX generation (phase1) failed [$system_rc], aborting summary creation.\n");
    print("error log:\n");
    system("tail latex.output");
    exit(1);
}
1022
$system_rc = system "$pdflatex @__CP_PDFLATEX_HALT_ON_ERROR@ summary.tex > latex.output2";
1023 1024 1025 1026 1027 1028 1029
if($system_rc)
{
    print("LaTeX generation (phase2) failed [$system_rc], aborting summary creation.\n");
    print("error log:\n");
    system("tail latex.output2");
    exit(1);
}
1030

1031 1032
# get back out of tmp dir and grab results
chdir $orig_dir;
1033
system "$mv $tmp_dir/summary.pdf $output_file";
1034

1035

1036 1037
sub process_file_record
{
1038 1039 1040 1041 1042 1043
    my $rank = $_[0];
    my $hash = $_[1];
    my(%file_record) = %{$_[2]};

    if($file_record{'CP_INDEP_OPENS'} == 0 &&
        $file_record{'CP_COLL_OPENS'} == 0 &&
1044
        $file_record{'CP_POSIX_OPENS'} == 0 &&
1045
        $file_record{'CP_POSIX_FOPENS'} == 0)
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
    {
        # file wasn't really opened, just stat probably
        return;
    }

    # record smallest open time size reported by any rank
    if(!defined($hash_files{$hash}{'min_open_size'}) ||
        $hash_files{$hash}{'min_open_size'} > 
        $file_record{'CP_SIZE_AT_OPEN'})
    {
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068
        # size at open will be set to -1 if the darshan library was not
        # configured to stat files at open time
        if($file_record{'CP_SIZE_AT_OPEN'} < 0)
        {
            $hash_files{$hash}{'min_open_size'} = 0;
            # set flag indicating that file sizes are estimated 
            $size_est_flag = 1;
        }
        else
        {
            $hash_files{$hash}{'min_open_size'} = 
                $file_record{'CP_SIZE_AT_OPEN'};
        }
1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
    }

    # record largest size that the file reached at any rank
    if(!defined($hash_files{$hash}{'max_size'}) ||
        $hash_files{$hash}{'max_size'} <  
        ($file_record{'CP_MAX_BYTE_READ'} + 1))
    {
        $hash_files{$hash}{'max_size'} = 
            $file_record{'CP_MAX_BYTE_READ'} + 1;
    }
    if(!defined($hash_files{$hash}{'max_size'}) ||
        $hash_files{$hash}{'max_size'} <  
        ($file_record{'CP_MAX_BYTE_WRITTEN'} + 1))
    {
        $hash_files{$hash}{'max_size'} = 
            $file_record{'CP_MAX_BYTE_WRITTEN'} + 1;
    }

    # make sure there is an initial value for read and write flags
    if(!defined($hash_files{$hash}{'was_read'}))
    {
        $hash_files{$hash}{'was_read'} = 0;
    }
    if(!defined($hash_files{$hash}{'was_written'}))
    {
        $hash_files{$hash}{'was_written'} = 0;
    }

    if($file_record{'CP_INDEP_OPENS'} > 0 ||
        $file_record{'CP_COLL_OPENS'} > 0)
    {
        # mpi file
        if($file_record{'CP_INDEP_READS'} > 0 ||
            $file_record{'CP_COLL_READS'} > 0 ||
            $file_record{'CP_SPLIT_READS'} > 0 ||
            $file_record{'CP_NB_READS'} > 0)
        {
            # data was read from the file
            $hash_files{$hash}{'was_read'} = 1;
        }
        if($file_record{'CP_INDEP_WRITES'} > 0 ||
            $file_record{'CP_COLL_WRITES'} > 0 ||
            $file_record{'CP_SPLIT_WRITES'} > 0 ||
            $file_record{'CP_NB_WRITES'} > 0)
        {
            # data was written to the file
            $hash_files{$hash}{'was_written'} = 1;
        }
    }
    else
    {
        # posix file
        if($file_record{'CP_POSIX_READS'} > 0 ||
            $file_record{'CP_POSIX_FREADS'} > 0)
        {
            # data was read from the file
            $hash_files{$hash}{'was_read'} = 1;
        }
        if($file_record{'CP_POSIX_WRITES'} > 0 ||
            $file_record{'CP_POSIX_FWRITES'} > 0)
        {
            # data was written to the file 
            $hash_files{$hash}{'was_written'} = 1;
        }
    }

1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205
    $hash_files{$hash}{'name'} = $file_record{CP_NAME_SUFFIX};

    if ($rank == -1)
    {
        $hash_files{$hash}{'procs'}          = $nprocs;
        $hash_files{$hash}{'slowest_rank'}   = $file_record{'CP_SLOWEST_RANK'};
        $hash_files{$hash}{'slowest_time'}   = $file_record{'CP_F_SLOWEST_RANK_TIME'};
        $hash_files{$hash}{'slowest_bytes'}  = $file_record{'CP_SLOWEST_RANK_BYTES'};
        $hash_files{$hash}{'fastest_rank'}   = $file_record{'CP_FASTEST_RANK'};
        $hash_files{$hash}{'fastest_time'}   = $file_record{'CP_F_FASTEST_RANK_TIME'};
        $hash_files{$hash}{'fastest_bytes'}  = $file_record{'CP_FASTEST_RANK_BYTES'};
        $hash_files{$hash}{'variance_time'}  = $file_record{'CP_F_VARIANCE_RANK_TIME'};
        $hash_files{$hash}{'variance_bytes'} = $file_record{'CP_F_VARIANCE_RANK_BYTES'};
    }
    else
    {
        my $total_time = $file_record{'CP_F_POSIX_META_TIME'} +
                         $file_record{'CP_F_POSIX_READ_TIME'} +
                         $file_record{'CP_F_POSIX_WRITE_TIME'};

        my $total_bytes = $file_record{'CP_BYTES_READ'} +
                          $file_record{'CP_BYTES_WRITTEN'};

        if(!defined($hash_files{$hash}{'slowest_time'}) ||
           $hash_files{$hash}{'slowest_time'} < $total_time)
        {
            $hash_files{$hash}{'slowest_time'}  = $total_time;
            $hash_files{$hash}{'slowest_rank'}  = $rank;
            $hash_files{$hash}{'slowest_bytes'} = $total_bytes;
        }

        if(!defined($hash_files{$hash}{'fastest_time'}) ||
           $hash_files{$hash}{'fastest_time'} > $total_time)
        {
            $hash_files{$hash}{'fastest_time'}  = $total_time;
            $hash_files{$hash}{'fastest_rank'}  = $rank;
            $hash_files{$hash}{'fastest_bytes'} = $total_bytes;
        }

        if(!defined($hash_files{$hash}{'variance_time_S'}))
        {
            $hash_files{$hash}{'variance_time_S'} = 0;
            $hash_files{$hash}{'variance_time_T'} = $total_time;
            $hash_files{$hash}{'variance_time_n'} = 1;
            $hash_files{$hash}{'variance_bytes_S'} = 0;
            $hash_files{$hash}{'variance_bytes_T'} = $total_bytes;
            $hash_files{$hash}{'variance_bytes_n'} = 1;
            $hash_files{$hash}{'procs'} = 1;
            $hash_files{$hash}{'variance_time'} = 0;
            $hash_files{$hash}{'variance_bytes'} = 0;
        }
        else
        {
            my $n = $hash_files{$hash}{'variance_time_n'};
            my $m = 1;
            my $T = $hash_files{$hash}{'variance_time_T'};
            $hash_files{$hash}{'variance_time_S'} += ($m/($n*($n+$m)))*(($n/$m)*$total_time - $T)*(($n/$m)*$total_time - $T);
            $hash_files{$hash}{'variance_time_T'} += $total_time;
            $hash_files{$hash}{'variance_time_n'} += 1;

            $hash_files{$hash}{'variance_time'}    = $hash_files{$hash}{'variance_time_S'} / $hash_files{$hash}{'variance_time_n'};

            $n = $hash_files{$hash}{'variance_bytes_n'};
            $m = 1;
            $T = $hash_files{$hash}{'variance_bytes_T'};
            $hash_files{$hash}{'variance_bytes_S'} += ($m/($n*($n+$m)))*(($n/$m)*$total_bytes - $T)*(($n/$m)*$total_bytes - $T);
            $hash_files{$hash}{'variance_bytes_T'} += $total_bytes;
            $hash_files{$hash}{'variance_bytes_n'} += 1;

            $hash_files{$hash}{'variance_bytes'}    = $hash_files{$hash}{'variance_bytes_S'} / $hash_files{$hash}{'variance_bytes_n'};

1206
            $hash_files{$hash}{'procs'} = $hash_files{$hash}{'variance_time_n'};
1207 1208 1209
        }
    }

1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
    # if this is a non-shared file, then add the time spent here to the
    # total for that particular rank
    if ($rank != -1)
    {
        # is it mpi-io or posix?
        if($file_record{CP_INDEP_OPENS} > 0 ||
            $file_record{CP_COLL_OPENS} > 0)
        {
            # add up mpi times
            if(defined($hash_unique_file_time{$rank}))
            {
                $hash_unique_file_time{$rank} +=
                    $file_record{CP_F_MPI_META_TIME} + 
                    $file_record{CP_F_MPI_READ_TIME} + 
                    $file_record{CP_F_MPI_WRITE_TIME};
            }
            else
            {
                $hash_unique_file_time{$rank} =
                    $file_record{CP_F_MPI_META_TIME} + 
                    $file_record{CP_F_MPI_READ_TIME} + 
                    $file_record{CP_F_MPI_WRITE_TIME};
            }
        }
        else
        {
            # add up posix times
            if(defined($hash_unique_file_time{$rank}))
            {
                $hash_unique_file_time{$rank} +=
                    $file_record{CP_F_POSIX_META_TIME} + 
                    $file_record{CP_F_POSIX_READ_TIME} + 
                    $file_record{CP_F_POSIX_WRITE_TIME};
            }
            else
            {
                $hash_unique_file_time{$rank} =
                    $file_record{CP_F_POSIX_META_TIME} + 
                    $file_record{CP_F_POSIX_READ_TIME} + 
                    $file_record{CP_F_POSIX_WRITE_TIME};
            }
        }
    }
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268
    else
    {

        # cumulative time spent on shared files by slowest proc
        if($major > 1)
        {
            # new file format
            $shared_file_time += $file_record{'CP_F_SLOWEST_RANK_TIME'};
        }
        else
        {
            # old file format.  Guess time spent as duration between first open
            # and last io
            if($file_record{'CP_F_READ_END_TIMESTAMP'} >
                $file_record{'CP_F_WRITE_END_TIMESTAMP'})
            {
1269 1270 1271 1272 1273 1274
                # be careful of files that were opened but not read or
                # written
                if($file_record{'CP_F_READ_END_TIMESTAMP'} > $file_record{'CP_F_OPEN_TIMESTAMP'}) {
                    $shared_file_time += $file_record{'CP_F_READ_END_TIMESTAMP'} -
                        $file_record{'CP_F_OPEN_TIMESTAMP'};
                }
1275 1276 1277
            }
            else
            {
1278 1279 1280 1281
                if($file_record{'CP_F_WRITE_END_TIMESTAMP'} > $file_record{'CP_F_OPEN_TIMESTAMP'}) {
                    $shared_file_time += $file_record{'CP_F_WRITE_END_TIMESTAMP'} -
                        $file_record{'CP_F_OPEN_TIMESTAMP'};
                }
1282 1283 1284
            }
        }
    }
1285

1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306
    my $mpi_did_read = 
        $file_record{'CP_INDEP_READS'} + 
        $file_record{'CP_COLL_READS'} + 
        $file_record{'CP_NB_READS'} + 
        $file_record{'CP_SPLIT_READS'};

    # add up how many bytes were transferred
    if(($file_record{CP_INDEP_OPENS} > 0 ||
        $file_record{CP_COLL_OPENS} > 0) && (!($mpi_did_read)))
    {
        # mpi file that was only written; disregard any read accesses that
        # may have been performed for sieving at the posix level
        $total_job_bytes += $file_record{'CP_BYTES_WRITTEN'}; 
    }
    else
    {
        # normal case
        $total_job_bytes += $file_record{'CP_BYTES_WRITTEN'} +
            $file_record{'CP_BYTES_READ'};
    }

1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
    # TODO 
    # (detect mpi or posix and):
    # - sum meta time per rank for uniq files
    # - sum io time per rank for uniq files
    # - sum time from first open to last io for shared files
    # - sum meta time/nprocs for shared files
    # - sum io time/nprocs for shared files
    
    # TODO: ideas
    # graph time spent performing I/O per rank
    # for rank that spent the most time performing I/O:
    # - meta on ro files, meta on wo files, read time, write time
    # table with nfiles accessed, ro, wo, rw, created
1320 1321
}

1322 1323
sub process_args
{
1324
    use vars qw( $opt_help $opt_output $opt_verbose );
1325 1326 1327

    Getopt::Long::Configure("no_ignore_case", "bundling");
    GetOptions( "help",
1328 1329
        "output=s",
        "verbose");
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341

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

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

1342 1343 1344 1345 1346
    if($opt_verbose)
    {
        $verbose_flag = $opt_verbose;
    }

1347 1348 1349 1350 1351 1352 1353
    # there should only be one remaining argument: the input file 
    if($#ARGV != 0)
    {
        print "Error: invalid arguments.\n";
        print_help();
        exit(1);
    }
1354

1355 1356
    $input_file = $ARGV[0];

1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372
    # give default output file a similar name to the input file.
    #   log.darshan.gz => log.pdf
    #   log_name => log_name.pdf
    if (not $opt_output)
    {
        $output_file = basename($input_file);
        if ($output_file =~ /\.darshan\.gz$/)
        {
            $output_file =~ s/\.darshan\.gz$/\.pdf/;
        }
        else
        {
            $output_file .= ".pdf";
        }
    }

1373 1374 1375
    return;
}

1376 1377 1378 1379 1380 1381
#
# Check for all support programs needed to generate the summary.
#
sub check_prereqs
{
    my $rc;
1382
    my $output;
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
    my @bins = ($darshan_parser, $pdflatex, $epstopdf,
                $gnuplot, $cp, $mv);
    foreach my $bin (@bins)
    {
        $rc = checkbin($bin);
        if ($rc)
        {
            print("error: $bin not found in PATH\n");
            exit(1);
        }
    }

1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409
    # check  gnuplot version
    $output = `$gnuplot --version`;
    if($? != 0)
    {
        print("error: failed to execute $gnuplot.\n");
        exit(1);
    }
    
    $output =~ /gnuplot (\d+)\.(\d+)/;
    if($1 < 4 || $2 < 2)
    {
        print("error: detected $gnuplot version $1.$2, but darshan-job-summary requires at least 4.2.\n");
        exit(1);
    }

1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447
    return;
}

#
# Execute which to see if the binary can be found in
# the users path.
#
sub checkbin($)
{
    my $binname = shift;
    my $rc;

    # save stdout/err
    open(SAVEOUT, ">&STDOUT");
    open(SAVEERR, ">&STDERR");

    # redirect stdout/error
    open(STDERR, '>/dev/null');
    open(STDOUT, '>/dev/null');
    $rc = system("which $binname");
    if ($rc)
    {
        $rc = 1;
    }
    close(STDOUT);
    close(STDERR);

    # suppress perl warning
    select(SAVEERR);
    select(SAVEOUT);

    # restore stdout/err
    open(STDOUT, ">&SAVEOUT");
    open(STDERR, ">&SAVEERR");

    return $rc;
}

1448 1449 1450 1451 1452 1453 1454 1455 1456
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)
1457 1458
    --verbose       Prints and retains tmpdir used for LaTeX output

1459 1460
Purpose:

1461 1462
    This script reads a Darshan output file generated by a job and
    generates a pdf file summarizing job behavior.
1463 1464 1465 1466

EOF
    return;
}