darshan-job-summary.pl 25 KB
Newer Older
1
#!/usr/bin/perl -w
2 3 4 5 6
#
#  (C) 2009 by Argonne National Laboratory.
#      See COPYRIGHT in top-level directory.
#

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

my $gnuplot = "";

my $tmp_dir = tempdir( CLEANUP => 1 );
19 20 21
#my $tmp_dir = tempdir( CLEANUP => 0 );
#print "tmp dir: $tmp_dir\n";

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

29 30 31
process_args();

open(TRACE, $input_file) || die("can't open $input_file for processing: $!\n");
32 33
open(FA_READ, ">$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: $!\n");
34 35
open(FA_READ_SH, ">$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");
36 37 38

my $last_read_start = 0;
my $last_write_start = 0;
39

40 41 42 43 44 45 46 47 48 49 50 51
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;

52 53 54 55 56
my $first_data_line = 1;
my $current_rank = 0;
my $current_hash = 0;
my %file_record_hash = ();

57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
while ($line = <TRACE>) {
    chop($line);
    
    if ($line =~ /^\s*$/) {
        # ignore blank lines
    }
    elsif ($line =~ /^#/) {
	if ($line =~ /^# exe: /) {
	    ($junk, $cmdline) = split(':', $line, 2);
            # add escape characters if needed for special characters in
            # command line
            $cmdline = encode('latex', $cmdline);
	}
	if ($line =~ /^# nprocs: /) {
	    ($junk, $nprocs) = split(':', $line, 2);
	    $procreads[$nprocs] = 0;
	}
	if ($line =~ /^# run time: /) {
	    ($junk, $runtime) = split(':', $line, 2);
	}
	if ($line =~ /^# start_time: /) {
	    ($junk, $starttime) = split(':', $line, 2);
	}
	if ($line =~ /^# uid: /) {
	    ($junk, $uid) = split(':', $line, 2);
	}
    }
    else {
85
        # parse line
86
	@fields = split(/[\t ]+/, $line);
87 88 89 90 91 92 93 94 95 96 97 98 99

        # 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?
        if($fields[0] != $current_rank && $fields[1] != $current_hash)
        {
            # process previous record
100
            process_file_record($current_rank, $current_hash, \%file_record_hash);
101 102 103 104 105 106 107 108 109

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

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

110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
	$summary{$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];
	    }
	}

132
        # seperate accumulators for independent and shared reads and writes
Philip Carns's avatar
Philip Carns committed
133
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] == -1){
134 135
            $cumul_read_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
136
        if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] != -1){
137 138
            $cumul_read_indep += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
139
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] == -1){
140 141
            $cumul_write_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
142
        if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] != -1){
143 144 145
            $cumul_write_indep += $fields[3];
        }

Philip Carns's avatar
Philip Carns committed
146
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] == -1){
147 148
            $cumul_read_bytes_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
149
        if ($fields[2] eq "CP_BYTES_READ" && $fields[0] != -1){
150 151
            $cumul_read_bytes_indep += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
152
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] == -1){
153 154
            $cumul_write_bytes_shared += $fields[3];
        }
Philip Carns's avatar
Philip Carns committed
155
        if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] != -1){
156 157 158
            $cumul_write_bytes_indep += $fields[3];
        }

159 160 161 162 163 164 165 166 167 168 169 170 171 172
        # 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 -= $starttime;
            }
173 174 175 176 177 178
            if($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$xdelta\t0\n";
            }
179 180 181 182 183 184 185 186 187 188 189 190
        }
        if ($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 -= $starttime;
            }
191 192 193 194 195 196
            if($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";
            }
197 198
        }

199 200
        if ($fields[2] =~ /^CP_ACCESS(.)_ACCESS/) {
            $access_size[$1] = $fields[3];
201
        }
202 203 204 205
        if ($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];
206
            }
207 208
            else{
                $access_hash{$tmp_access_size} = $fields[3];
209 210 211 212 213
            }
        }
    }
}

214
# process last file record
215
process_file_record($current_rank, $current_hash, \%file_record_hash);
216 217
close(TRACE);

218 219 220 221
# 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";
222 223
print FA_READ_SH "$runtime\t0\t0\t0\n";
print FA_WRITE_SH "$runtime\t0\t0\t0\n";
224 225
close(FA_READ);
close(FA_WRITE);
226 227
close(FA_READ_SH);
close(FA_WRITE_SH);
228

229
# counts of operations
230
open(COUNTS, ">$tmp_dir/counts.dat") || die("error opening output file: $!\n");
231 232
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";
233
my $total_syncs = $summary{CP_POSIX_FSYNCS} + $summary{CP_POSIX_FDSYNCS};
234 235 236 237 238 239 240 241
print COUNTS "Read, ", $summary{CP_POSIX_READS}, ", ",
    $summary{CP_INDEP_READS}, ", ", $summary{CP_COLL_READS}, "\n",
    "Write, ", $summary{CP_POSIX_WRITES}, ", ", 
    $summary{CP_INDEP_WRITES}, ", ", $summary{CP_COLL_WRITES}, "\n",
    "Open, ", $summary{CP_POSIX_OPENS}, ", ", $summary{CP_INDEP_OPENS},", ",
    $summary{CP_COLL_OPENS}, "\n",
    "Stat, ", $summary{CP_POSIX_STATS}, ", 0, 0\n",
    "Seek, ", $summary{CP_POSIX_SEEKS}, ", 0, 0\n",
242 243
    "Mmap, ", $summary{CP_POSIX_MMAPS}, ", 0, 0\n",
    "Fsync, ", $total_syncs, ", 0, 0\n";
244 245 246
close COUNTS;

# histograms of reads and writes
247
open (HIST, ">$tmp_dir/hist.dat") || die("error opening output file: $!\n");
248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271
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
272
open (PATTERN, ">$tmp_dir/pattern.dat") || die("error opening output file: $!\n");
273 274 275 276 277 278 279 280
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
281
open (ALIGN, ">$tmp_dir/align.dat") || die("error opening output file: $!\n");
282 283 284 285 286 287
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
288
open (TYPES, ">$tmp_dir/types.dat") || die("error opening output file: $!\n");
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
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]++;
}

336
open(IODIST, ">$tmp_dir/iodist.dat") || die("error opening output file: $!\n");
337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357
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];

358
open(TITLE, ">$tmp_dir/title.tex") || die("error opening output file:$!\n");
359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375
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;

376
open(TABLES, ">$tmp_dir/job-table.tex") || die("error opening output file:$!\n");
377 378 379 380 381 382 383 384 385
print TABLES "
\\begin{tabular}{|p{.63\\columnwidth}|p{.63\\columnwidth}|p{.63\\columnwidth}|}
\\hline
uid: $uid \& nprocs: $nprocs \& runtime: $runtime seconds\\\\
\\hline
\\end{tabular}
";
close TABLES;

386
open(TABLES, ">$tmp_dir/access-table.tex") || die("error opening output file:$!\n");
387
print TABLES "
Philip Carns's avatar
Philip Carns committed
388
\\begin{tabular}{r|r}
389
\\multicolumn{2}{c}{Most Common Access Sizes} \\\\
390 391 392
\\hline
access size \& count \\\\
\\hline
Philip Carns's avatar
Philip Carns committed
393
\\hline
394 395
";

396 397
# sort access sizes (descending)
my $i = 0;
398 399
foreach $value (sort {$access_hash{$b} <=> $access_hash{$a} } keys %access_hash) {
    if($i == 4) {
400 401 402 403 404 405 406 407 408
        last;
    }
    if($access_hash{$value} == 0) {
        last;
    }
    print TABLES "$value \& $access_hash{$value} \\\\\n";
    $i++;
}

409 410 411 412 413 414
print TABLES "
\\hline
\\end{tabular}
";
close TABLES;

Philip Carns's avatar
Philip Carns committed
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
open(TABLES, ">$tmp_dir/file-count-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{r|r|r|r}
\\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'};
        }
    }
}
$avg = $sum / $counter;
print TABLES "total opened \& $counter \& $avg \& $max \\\\\n";

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


463
open(TIME, ">$tmp_dir/time-summary.dat") || die("error opening output file:$!\n");
464 465 466 467 468 469 470 471 472 473 474 475 476 477 478
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;

479
# copy template files to tmp tmp_dir
Philip Carns's avatar
Philip Carns committed
480 481
system "cp $FindBin::Bin/../share/*.gplt $tmp_dir/";
system "cp $FindBin::Bin/../share/*.tex $tmp_dir/";
482

483 484 485 486 487 488 489
# 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\"
490 491
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
492 493 494
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
495
set yrange [-1:$ymax]
Philip Carns's avatar
Philip Carns committed
496
set title \"Timespan from first to last read access on independent files\"
497 498 499
# the xrange doesn't work for some reason
#set xrange [0:$runtime]
#set ytics -1,1
500
set lmargin 4
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519

# 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\"
520 521
set ylabel \"MPI rank\"
set xlabel \"hours:minutes:seconds\"
522 523 524
set xdata time
set timefmt \"%s\"
set format x \"%H:%M:%S\"
Philip Carns's avatar
Philip Carns committed
525
set title \"Timespan from first to last write access on independent files\"
526
set yrange [-1:$ymax]
527 528 529
# the xrange doesn't work for some reason
# set xrange [0:$runtime]
#set ytics -1,1
530
set lmargin 4
531 532 533 534 535 536 537 538 539 540 541 542 543

# 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;

544 545 546 547 548 549 550 551 552 553
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
554
set ylabel \"All processes\"
555 556 557
# the xrange doesn't work for some reason
# set xrange [0:$runtime]
set yrange [-1:1]
Philip Carns's avatar
Philip Carns committed
558
set title \"Timespan from first to last access on files shared by all processes\"
559
set lmargin 4
560 561 562 563 564 565 566 567 568 569 570 571 572

# 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;

573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589
$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;

open(FILEACC, ">$tmp_dir/file-access-table.tex") || die("error opening output file:$!\n");
590
print FILEACC "
Philip Carns's avatar
Philip Carns committed
591 592 593 594
\\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) \\\\
595 596
\\hline
\\hline
Philip Carns's avatar
Philip Carns committed
597 598
";

Philip Carns's avatar
Philip Carns committed
599 600 601 602 603 604 605 606 607
# 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);
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);
Philip Carns's avatar
Philip Carns committed
608 609

print FILEACC "
610 611 612
\\hline
\\end{tabular}
";
613 614
close(FILEACC);

615 616 617 618 619 620 621 622 623 624 625 626
if(-x "$FindBin::Bin/gnuplot")
{
    $gnuplot = "$FindBin::Bin/gnuplot";
}
else
{
    $gnuplot = "gnuplot";
}

# move to tmp_dir
chdir $tmp_dir;

627
# execute gnuplot scripts
628
system "$gnuplot counts-eps.gplt";
629
system "epstopdf counts.eps";
630
system "$gnuplot hist-eps.gplt";
631
system "epstopdf hist.eps";
632
system "$gnuplot pattern-eps.gplt";
633
system "epstopdf pattern.eps";
634
system "$gnuplot time-summary-eps.gplt";
635
system "epstopdf time-summary.eps";
636 637 638 639
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";
640 641
system "$gnuplot file-access-shared-eps.gplt";
system "epstopdf file-access-shared.eps";
642

643 644 645 646
#system "gnuplot align-pdf.gplt";
#system "gnuplot iodist-pdf.gplt";
#system "gnuplot types-pdf.gplt";

647 648 649 650
# generate summary PDF
system "pdflatex -halt-on-error summary.tex > latex.output";
system "pdflatex -halt-on-error summary.tex > latex.output2";

651 652 653 654
# get back out of tmp dir and grab results
chdir $orig_dir;
system "mv $tmp_dir/summary.pdf $output_file";

655 656
sub process_file_record
{
657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
    my $rank = $_[0];
    my $hash = $_[1];
    my(%file_record) = %{$_[2]};

    if($file_record{'CP_INDEP_OPENS'} == 0 &&
        $file_record{'CP_COLL_OPENS'} == 0 &&
        $file_record{'CP_POSIX_OPENS'} == 0)
    {
        # 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;
        }
    }

    # 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
755 756
}

757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805
sub process_args
{
    use vars qw( $opt_help $opt_output );

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

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

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

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

    return;
}

sub print_help
{
    print <<EOF;

Usage: $PROGRAM_NAME <options> input_file

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

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

EOF
    return;
}