darshan-job-summary.pl 41.5 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
use Number::Bytes::Human qw(format_bytes);
16
use POSIX qw(strftime);
17 18 19

my $gnuplot = "";

20

21
my $orig_dir = getcwd;
22
my $output_file = "summary.pdf";
23
my $verbose_flag = 0;
24
my $input_file = "";
25 26
my %access_hash = ();
my @access_size = ();
27
my %hash_files = ();
28

29
# data structures for calculating performance
30 31
my %hash_unique_file_time = ();
my $shared_file_time = 0;
32
my $total_job_bytes = 0;
33

34 35
process_args();

36 37 38 39 40 41
my $tmp_dir = tempdir( CLEANUP => !$verbose_flag );
if ($verbose_flag)
{
    print "verbose: $tmp_dir\n";
}

42 43 44 45 46 47 48 49 50 51 52 53 54
# find a darshan-parser executable somewhere
my $darshan_parser = "";
if(-x "$FindBin::Bin/../bin/darshan-parser")
{
    $darshan_parser = "$FindBin::Bin/../bin/darshan-parser";
}
else
{
    $darshan_parser = "darshan-parser";
}

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

55 56
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: $!\n");
57 58
open(FA_READ_SH, ">$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");
59 60 61

my $last_read_start = 0;
my $last_write_start = 0;
62

63 64 65 66 67 68 69 70 71 72 73 74
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;

75 76 77
my $cumul_meta_shared = 0;
my $cumul_meta_indep = 0;

78 79 80 81 82
my $first_data_line = 1;
my $current_rank = 0;
my $current_hash = 0;
my %file_record_hash = ();

83 84
my %fs_data = ();

85
while ($line = <TRACE>) {
86
    chomp($line);
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
    
    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(':', $line, 2);
	}
111 112 113
        if ($line =~ /^# jobid: /) {
	    ($junk, $jobid) = split(':', $line, 2);
        }
114 115 116 117 118
        if ($line =~ /^# darshan log version: /) {
            ($junk, $version) = split(':', $line, 2);
            $version =~ s/^\s+//;
            ($major, $minor) = split(/\./, $version, 2);
        }
119 120
    }
    else {
121
        # parse line
122
	@fields = split(/[\t ]+/, $line);
123 124 125 126 127 128 129 130 131 132

        # 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?
133
        if($fields[0] != $current_rank || $fields[1] != $current_hash)
134
        {
135 136
            $file_record_hash{CP_NAME_SUFFIX} = $fields[4];

137
            # process previous record
138
            process_file_record($current_rank, $current_hash, \%file_record_hash);
139 140 141 142 143 144 145 146 147

            # reset variables for next record 
            $current_rank = $fields[0];
            $current_hash = $fields[1];
            %file_record_hash = ();
        }

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

148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
	$summary{$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];
	    }
	}

170
        # seperate accumulators for independent and shared reads and writes
Philip Carns's avatar
Philip Carns committed
171
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] == -1){
172 173
            $cumul_read_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
174
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] != -1){
175 176
            $cumul_read_indep += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
177
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] == -1){
178 179
            $cumul_write_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
180
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] != -1){
181 182 183
            $cumul_write_indep += $fields[3];
        }

184 185 186 187 188 189 190
        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];
        }

191 192
        if ((($fields[2] eq "CP_BYTES_READ") or
             ($fields[2] eq "CP_BYTES_WRITTEN")) and
193 194 195 196
            not defined($fs_data{$fields[5]}))
        {
            $fs_data{$fields[5]} = [0,0];
        }
197

Philip Carns's avatar
Philip Carns committed
198
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] == -1){
199
            $cumul_read_bytes_shared += $fields[3];
200
            $fs_data{$fields[5]}->[0] += $fields[3];
201
        }
Philip Carns's avatar
Philip Carns committed
202
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] != -1){
203
            $cumul_read_bytes_indep += $fields[3];
204
            $fs_data{$fields[5]}->[0] += $fields[3];
205
        }
Philip Carns's avatar
Philip Carns committed
206
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] == -1){
207
            $cumul_write_bytes_shared += $fields[3];
208
            $fs_data{$fields[5]}->[1] += $fields[3];
209
        }
Philip Carns's avatar
Philip Carns committed
210
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] != -1){
211
            $cumul_write_bytes_indep += $fields[3];
212
            $fs_data{$fields[5]}->[1] += $fields[3];
213 214
        }

215 216 217 218 219 220 221 222 223 224 225 226 227 228
        # 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 -= $starttime;
            }
229 230 231 232 233 234
            if($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$xdelta\t0\n";
            }
235 236 237 238 239 240 241 242 243 244 245 246
        }
        if ($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 -= $starttime;
            }
247 248 249 250 251 252
            if($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";
            }
253 254
        }

255 256
        if ($fields[2] =~ /^CP_ACCESS(.)_ACCESS/) {
            $access_size[$1] = $fields[3];
257
        }
258 259 260 261
        if ($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];
262
            }
263 264
            else{
                $access_hash{$tmp_access_size} = $fields[3];
265 266 267 268 269
            }
        }
    }
}

270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
#
# 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";
    close(TRACE);
    exit(1);
}

288
# process last file record
289
$file_record_hash{CP_NAME_SUFFIX} = $fields[4];
290
process_file_record($current_rank, $current_hash, \%file_record_hash);
291
close(TRACE) || die "darshan-parser failure: $! $?";
292

293 294 295 296
# 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";
297 298
print FA_READ_SH "$runtime\t0\t0\t0\n";
print FA_WRITE_SH "$runtime\t0\t0\t0\n";
299 300
close(FA_READ);
close(FA_WRITE);
301 302
close(FA_READ_SH);
close(FA_WRITE_SH);
303

304
# counts of operations
305
open(COUNTS, ">$tmp_dir/counts.dat") || die("error opening output file: $!\n");
306 307
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";
308
my $total_posix_opens = $summary{CP_POSIX_OPENS} + $summary{CP_POSIX_FOPENS};
309
my $total_syncs = $summary{CP_POSIX_FSYNCS} + $summary{CP_POSIX_FDSYNCS};
310 311 312 313
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",
314
    "Open, ", $total_posix_opens, ", ", $summary{CP_INDEP_OPENS},", ",
315 316 317
    $summary{CP_COLL_OPENS}, "\n",
    "Stat, ", $summary{CP_POSIX_STATS}, ", 0, 0\n",
    "Seek, ", $summary{CP_POSIX_SEEKS}, ", 0, 0\n",
318 319
    "Mmap, ", $summary{CP_POSIX_MMAPS}, ", 0, 0\n",
    "Fsync, ", $total_syncs, ", 0, 0\n";
320 321 322
close COUNTS;

# histograms of reads and writes
323
open (HIST, ">$tmp_dir/hist.dat") || die("error opening output file: $!\n");
324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347
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
348
open (PATTERN, ">$tmp_dir/pattern.dat") || die("error opening output file: $!\n");
349 350 351 352 353 354 355 356
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
357
open (ALIGN, ">$tmp_dir/align.dat") || die("error opening output file: $!\n");
358 359 360 361 362 363
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
364
open (TYPES, ">$tmp_dir/types.dat") || die("error opening output file: $!\n");
365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411
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]++;
}

412
open(IODIST, ">$tmp_dir/iodist.dat") || die("error opening output file: $!\n");
413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
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];

434
open(TITLE, ">$tmp_dir/title.tex") || die("error opening output file:$!\n");
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451
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;

452
open(TABLES, ">$tmp_dir/job-table.tex") || die("error opening output file:$!\n");
453
print TABLES "
454
\\begin{tabular}{|p{.47\\columnwidth}|p{.35\\columnwidth}|p{.47\\columnwidth}|p{.6\\columnwidth}|}
455
\\hline
456
jobid: $jobid \& uid: $uid \& nprocs: $nprocs \& runtime: $runtime seconds\\\\
457 458 459 460 461
\\hline
\\end{tabular}
";
close TABLES;

462
open(TABLES, ">$tmp_dir/access-table.tex") || die("error opening output file:$!\n");
463
print TABLES "
Philip Carns's avatar
Philip Carns committed
464
\\begin{tabular}{r|r}
465
\\multicolumn{2}{c}{ } \\\\
466
\\multicolumn{2}{c}{Most Common Access Sizes} \\\\
467 468 469
\\hline
access size \& count \\\\
\\hline
Philip Carns's avatar
Philip Carns committed
470
\\hline
471 472
";

473 474
# sort access sizes (descending)
my $i = 0;
475 476
foreach $value (sort {$access_hash{$b} <=> $access_hash{$a} } keys %access_hash) {
    if($i == 4) {
477 478 479 480 481 482 483 484 485
        last;
    }
    if($access_hash{$value} == 0) {
        last;
    }
    print TABLES "$value \& $access_hash{$value} \\\\\n";
    $i++;
}

486 487 488 489 490 491
print TABLES "
\\hline
\\end{tabular}
";
close TABLES;

Philip Carns's avatar
Philip Carns committed
492 493 494
open(TABLES, ">$tmp_dir/file-count-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{r|r|r|r}
495
\\multicolumn{4}{c}{ } \\\\
Philip Carns's avatar
Philip Carns committed
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
\\multicolumn{4}{c}{File Count Summary} \\\\
\\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'};
        }
    }
}
531 532
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
533 534
$avg = format_bytes($avg);
$max = format_bytes($max);
Philip Carns's avatar
Philip Carns committed
535 536
print TABLES "total opened \& $counter \& $avg \& $max \\\\\n";

537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
$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";

Philip Carns's avatar
Philip Carns committed
667 668 669 670 671 672 673
print TABLES "
\\hline
\\end{tabular}
";
close(TABLES);


674 675 676 677
#
# Generate Per Filesystem Data
#
open(TABLES, ">$tmp_dir/fs-data-table.tex") || die("error opening output files:$!\n");
678
if (($major > 1) or ($minor > 23))
679
{
680 681 682 683 684 685 686 687 688 689 690 691
    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)
692
    {
693 694 695
        my $wr_total_mb = ($fs_data{$key}->[1] / (1024*1024));
        my $rd_total_mb = ($fs_data{$key}->[0] / (1024*1024));
        my $wr_total_rt;
696

697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714
        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;
        }
715

716 717
        printf TABLES "%s \& %.5f \& %.5f \& %.5f \& %.5f \\\\\n",
            $key, $wr_total_mb, $wr_total_rt, $rd_total_mb, $rd_total_rt;
718 719 720 721 722
}
print TABLES "
\\hline
\\end{tabular}
";
723 724 725 726 727 728 729 730
}
else
{
    print TABLES "
\\rule{0in}{1in}
\\parbox{5in}{Log versions prior to 1.24 do not support per-filesystem data.}
";
}
731 732 733
close(TABLES);


734
open(TIME, ">$tmp_dir/time-summary.dat") || die("error opening output file:$!\n");
735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
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;

750
# copy template files to tmp tmp_dir
Philip Carns's avatar
Philip Carns committed
751 752
system "cp $FindBin::Bin/../share/*.gplt $tmp_dir/";
system "cp $FindBin::Bin/../share/*.tex $tmp_dir/";
753

754 755 756 757 758 759 760
# 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\"
761 762
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
763 764 765
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
766
set yrange [-1:$ymax]
Philip Carns's avatar
Philip Carns committed
767
set title \"Timespan from first to last read access on independent files\"
768 769 770
# the xrange doesn't work for some reason
#set xrange [0:$runtime]
#set ytics -1,1
771
set lmargin 4
772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790

# 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\"
791 792
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
793 794 795
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
Philip Carns's avatar
Philip Carns committed
796
set title \"Timespan from first to last write access on independent files\"
797
set yrange [-1:$ymax]
798 799 800
# the xrange doesn't work for some reason
# set xrange [0:$runtime]
#set ytics -1,1
801
set lmargin 4
802 803 804 805 806 807 808 809 810 811 812 813 814

# 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;

815 816 817 818 819 820 821 822 823 824
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
825
set ylabel \"All processes\"
826 827 828
# the xrange doesn't work for some reason
# set xrange [0:$runtime]
set yrange [-1:1]
Philip Carns's avatar
Philip Carns committed
829
set title \"Timespan from first to last access on files shared by all processes\"
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

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;

844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
$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;

860 861 862
$cumul_meta_shared /= $nprocs;
$cumul_meta_indep /= $nprocs;

863
open(FILEACC, ">$tmp_dir/file-access-table.tex") || die("error opening output file:$!\n");
864
print FILEACC "
Philip Carns's avatar
Philip Carns committed
865 866 867 868
\\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) \\\\
869 870
\\hline
\\hline
Philip Carns's avatar
Philip Carns committed
871 872
";

Philip Carns's avatar
Philip Carns committed
873 874 875 876 877
# 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);
878 879
printf(FILEACC "Independent metadata \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{N/A} \\\\", 
    $cumul_meta_indep);
Philip Carns's avatar
Philip Carns committed
880 881 882 883
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);
884 885
printf(FILEACC "Shared metadata \& \\multicolumn{1}{r}{%f} \& \\multicolumn{1}{r}{N/A} \\\\", 
    $cumul_meta_shared);
Philip Carns's avatar
Philip Carns committed
886 887

print FILEACC "
888 889 890
\\hline
\\end{tabular}
";
891 892
close(FILEACC);

893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
#
# 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
";

910 911 912 913 914
my $curcount = 1;
foreach $key (sort { $hash_files{$b}{'slowest_time'} <=> $hash_files{$a}{'slowest_time'} } keys %hash_files) {

    if ($curcount > 20) { last; }

915 916 917 918 919 920
    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'});
921
        my $name = encode('latex', $hash_files{$key}{'name'});
922 923

        print VARP "
924
               $name \&
925 926 927 928 929 930 931 932 933 934
               $hash_files{$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 \\\\
         ";
935
        $curcount++;
936 937 938 939 940 941 942 943 944
    }
}

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

945 946 947 948 949 950 951 952 953 954
# 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");
955
print("Slowest shared file time: $shared_file_time\n");
956 957 958
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");
959

960 961 962 963 964 965 966 967 968 969 970 971
if(-x "$FindBin::Bin/gnuplot")
{
    $gnuplot = "$FindBin::Bin/gnuplot";
}
else
{
    $gnuplot = "gnuplot";
}

# move to tmp_dir
chdir $tmp_dir;

972
# execute gnuplot scripts
973
system "$gnuplot counts-eps.gplt";
974
system "epstopdf counts.eps";
975
system "$gnuplot hist-eps.gplt";
976
system "epstopdf hist.eps";
977
system "$gnuplot pattern-eps.gplt";
978
system "epstopdf pattern.eps";
979
system "$gnuplot time-summary-eps.gplt";
980
system "epstopdf time-summary.eps";
981 982 983 984
system "$gnuplot file-access-read-eps.gplt";
system "epstopdf file-access-read.eps";
system "$gnuplot file-access-write-eps.gplt";
system "epstopdf file-access-write.eps";
985 986
system "$gnuplot file-access-shared-eps.gplt";
system "epstopdf file-access-shared.eps";
987

988 989 990 991
#system "gnuplot align-pdf.gplt";
#system "gnuplot iodist-pdf.gplt";
#system "gnuplot types-pdf.gplt";

992 993 994 995
# generate summary PDF
system "pdflatex -halt-on-error summary.tex > latex.output";
system "pdflatex -halt-on-error summary.tex > latex.output2";

996 997 998 999
# get back out of tmp dir and grab results
chdir $orig_dir;
system "mv $tmp_dir/summary.pdf $output_file";

1000

1001 1002
sub process_file_record
{
1003 1004 1005 1006 1007 1008
    my $rank = $_[0];
    my $hash = $_[1];
    my(%file_record) = %{$_[2]};

    if($file_record{'CP_INDEP_OPENS'} == 0 &&
        $file_record{'CP_COLL_OPENS'} == 0 &&
1009
        $file_record{'CP_POSIX_OPENS'} == 0 &&
1010
        $file_record{'CP_POSIX_FOPENS'} == 0)
1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088
    {
        # 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'})
    {
        $hash_files{$hash}{'min_open_size'} = 
            $file_record{'CP_SIZE_AT_OPEN'};
    }

    # 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;
        }
    }

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 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
    $hash_files{$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'};

            $hash_files{$hash}{'procs'} = $n;
        }
    }

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 1206
    # 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};
            }
        }
    }
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
    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'})
            {
                $shared_file_time += $file_record{'CP_F_READ_END_TIMESTAMP'} -
                    $file_record{'CP_F_OPEN_TIMESTAMP'};
            }
            else
            {
                $shared_file_time += $file_record{'CP_F_WRITE_END_TIMESTAMP'} -
                    $file_record{'CP_F_OPEN_TIMESTAMP'};
            }
        }
    }
1233

1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254
    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'};
    }

1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267
    # 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
1268 1269
}

1270 1271
sub process_args
{
1272
    use vars qw( $opt_help $opt_output $opt_verbose );
1273 1274 1275

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