Skip to content

GitLab

Commit fab0224e authored by Shane Snyder's avatar Shane Snyder
Browse files

stubbed out version of job summary script

parent e5172a88
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 1347 deletions
darshan-util/darshan-job-summary/bin/darshan-job-summary.pl.in
View file @ fab0224e
#!/usr/bin/perl -w
#
# (C) 2009 by Argonne National Laboratory.
# (C) 2015 by Argonne National Laboratory.
# See COPYRIGHT in top-level directory.
#
......@@ -18,1315 +18,6 @@ use English;
use Number::Bytes::Human qw(format_bytes);
use POSIX qw(strftime);
#
# system commands used
#
my $darshan_parser = "$PREFIX/bin/darshan-parser";
my $pdflatex = "pdflatex";
my $epstopdf = "epstopdf";
my $cp = "cp";
my $mv = "mv";
my $gnuplot;
# Prefer gnuplot installed with darshan, if present.
if(-x "$PREFIX/bin/gnuplot")
{
$gnuplot = "$PREFIX/bin/gnuplot";
}
else
{
$gnuplot = "gnuplot";
}
my $orig_dir = getcwd;
my $output_file = "summary.pdf";
my $verbose_flag = 0;
my $input_file = "";
my %access_hash = ();
my @access_size = ();
my %hash_files = ();
my $size_est_flag = 0;
my $read_interval_overflow_flag = 0;
my $write_interval_overflow_flag = 0;
# data structures for calculating performance
my %hash_unique_file_time = ();
my $shared_file_time = 0;
my $total_job_bytes = 0;
process_args();
check_prereqs();
my $tmp_dir = tempdir( CLEANUP => !$verbose_flag );
if ($verbose_flag)
{
print "verbose: $tmp_dir\n";
}
open(TRACE, "$darshan_parser $input_file |") || die("Can't execute \"$darshan_parser $input_file\": $!\n");
open(FA_READ, ">$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: $!\n");
open(FA_READ_SH, ">$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");
my $last_read_start = 0;
my $last_write_start = 0;
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;
my $cumul_meta_shared = 0;
my $cumul_meta_indep = 0;
my $first_data_line = 1;
my $current_rank = 0;
my $current_hash = 0;
my %file_record_hash = ();
my %fs_data = ();
while ($line = <TRACE>) {
chomp($line);
if ($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(':', $line, 2);
}
if ($line =~ /^# jobid: /) {
($junk, $jobid) = split(':', $line, 2);
}
if ($line =~ /^# darshan log version: /) {
($junk, $version) = split(':', $line, 2);
$version =~ s/^\s+//;
($major, $minor) = split(/\./, $version, 2);
}
}
else {
# parse line
@fields = split(/[\t ]+/, $line);
# encode the file system name to protect against special characters
$fields[5] = encode('latex', $fields[5]);
# is this our first piece of data?
if($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] != $current_hash)
{
# process previous record
process_file_record($current_rank, $current_hash, \%file_record_hash);
# reset variables for next record
$current_rank = $fields[0];
$current_hash = $fields[1];
%file_record_hash = ();
$file_record_hash{CP_NAME_SUFFIX} = $fields[4];
}
$file_record_hash{$fields[2]} = $fields[3];
$summary{$fields[2]} += $fields[3];
# record per-process POSIX read count
if ($fields[2] eq "CP_POSIX_READS" || $fields[2] eq "CP_POSIX_FREADS") {
if ($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" || $fields[2] eq "CP_POSIX_FWRITES") {
if ($fields[0] == -1) {
$procwrites[$nprocs] += $fields[3];
}
else {
$procwrites[$fields[0]] += $fields[3];
}
}
# seperate accumulators for independent and shared reads and writes
if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] == -1){
$cumul_read_shared += $fields[3];
}
if ($fields[2] eq "CP_F_POSIX_READ_TIME" && $fields[0] != -1){
$cumul_read_indep += $fields[3];
}
if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] == -1){
$cumul_write_shared += $fields[3];
}
if ($fields[2] eq "CP_F_POSIX_WRITE_TIME" && $fields[0] != -1){
$cumul_write_indep += $fields[3];
}
if ($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 += $fields[3];
}
if ((($fields[2] eq "CP_BYTES_READ") or
($fields[2] eq "CP_BYTES_WRITTEN")) and
not defined($fs_data{$fields[5]}))
{
$fs_data{$fields[5]} = [0,0];
}
if ($fields[2] eq "CP_BYTES_READ" && $fields[0] == -1){
$cumul_read_bytes_shared += $fields[3];
$fs_data{$fields[5]}->[0] += $fields[3];
}
if ($fields[2] eq "CP_BYTES_READ" && $fields[0] != -1){
$cumul_read_bytes_indep += $fields[3];
$fs_data{$fields[5]}->[0] += $fields[3];
}
if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] == -1){
$cumul_write_bytes_shared += $fields[3];
$fs_data{$fields[5]}->[1] += $fields[3];
}
if ($fields[2] eq "CP_BYTES_WRITTEN" && $fields[0] != -1){
$cumul_write_bytes_indep += $fields[3];
$fs_data{$fields[5]}->[1] += $fields[3];
}
# record start and end of reads and writes
if ($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 -= $starttime;
}
if($fields[3] > $runtime && !$read_interval_overflow_flag)
{
$read_interval_overflow_flag = 1;
print "Warning: detected read access at time $fields[3] but runtime is only $runtime seconds.\n";
}
if($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$xdelta\t0\n";
}
}
if ($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 -= $starttime;
}
if($fields[3] > $runtime && !$write_interval_overflow_flag)
{
$write_interval_overflow_flag = 1;
print "Warning: detected write access at time $fields[3] but runtime is only $runtime seconds.\n";
}
if($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$xdelta\t0\n";
}
}
if ($fields[2] =~ /^CP_ACCESS(.)_ACCESS/) {
$access_size[$1] = $fields[3];
}
if ($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];
}
else{
$access_hash{$tmp_access_size} = $fields[3];
}
}
}
}
close(TRACE) || die "darshan-parser failure: $! $?";
#
# Exit out if there are no actual file accesses
#
if ($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);
}
# process last file record
$file_record_hash{CP_NAME_SUFFIX} = $fields[4];
process_file_record($current_rank, $current_hash, \%file_record_hash);
# Fudge one point at the end to make xrange match in read and write plots.
# For some reason I can't get the xrange command to work. -Phil
print FA_READ "$runtime\t-1\t0\t0\n";
print FA_WRITE "$runtime\t-1\t0\t0\n";
print FA_READ_SH "$runtime\t0\t0\t0\n";
print FA_WRITE_SH "$runtime\t0\t0\t0\n";
close(FA_READ);
close(FA_WRITE);
close(FA_READ_SH);
close(FA_WRITE_SH);
# counts of operations
open(COUNTS, ">$tmp_dir/counts.dat") || die("error opening output file: $!\n");
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";
my $total_posix_opens = $summary{CP_POSIX_OPENS} + $summary{CP_POSIX_FOPENS};
my $total_syncs = $summary{CP_POSIX_FSYNCS} + $summary{CP_POSIX_FDSYNCS};
print COUNTS "Read, ", $summary{CP_POSIX_READS} + $summary{CP_POSIX_FREADS}, ", ",
$summary{CP_INDEP_READS}, ", ", $summary{CP_COLL_READS}, "\n",
"Write, ", $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FWRITES}, ", ",
$summary{CP_INDEP_WRITES}, ", ", $summary{CP_COLL_WRITES}, "\n",
"Open, ", $total_posix_opens, ", ", $summary{CP_INDEP_OPENS},", ",
$summary{CP_COLL_OPENS}, "\n",
"Stat, ", $summary{CP_POSIX_STATS}, ", 0, 0\n",
"Seek, ", $summary{CP_POSIX_SEEKS}, ", 0, 0\n",
"Mmap, ", $summary{CP_POSIX_MMAPS}, ", 0, 0\n",
"Fsync, ", $total_syncs, ", 0, 0\n";
close COUNTS;
# histograms of reads and writes
open (HIST, ">$tmp_dir/hist.dat") || die("error opening output file: $!\n");
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}, ", ",
$summary{CP_SIZE_WRITE_1G_PLUS}, "\n";
close HIST;
# sequential and consecutive accesses
open (PATTERN, ">$tmp_dir/pattern.dat") || die("error opening output file: $!\n");
print PATTERN "# op total sequential consecutive\n";
print PATTERN "Read, ", $summary{CP_POSIX_READS} + $summary{CP_POSIX_FREADS}, ", ",
$summary{CP_SEQ_READS}, ", ", $summary{CP_CONSEC_READS}, "\n";
print PATTERN "Write, ", $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FWRITES}, ", ",
$summary{CP_SEQ_WRITES}, ", ", $summary{CP_CONSEC_WRITES}, "\n";
close PATTERN;
# aligned I/O
open (ALIGN, ">$tmp_dir/align.dat") || die("error opening output file: $!\n");
print ALIGN "# total unaligned_mem unaligned_file align_mem align_file\n";
print ALIGN $summary{CP_POSIX_READS} + $summary{CP_POSIX_WRITES} + $summary{CP_POSIX_FREADS} + $summary{CP_POSIX_FWRITES}
, ", ",
$summary{CP_MEM_NOT_ALIGNED}, ", ", $summary{CP_FILE_NOT_ALIGNED}, "\n";
close ALIGN;
# MPI types
open (TYPES, ">$tmp_dir/types.dat") || die("error opening output file: $!\n");
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]++;
}
open(IODIST, ">$tmp_dir/iodist.dat") || die("error opening output file: $!\n");
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 = $timearray[3];
open(TITLE, ">$tmp_dir/title.tex") || die("error opening output file:$!\n");
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;
open(TABLES, ">$tmp_dir/job-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{|p{.47\\columnwidth}|p{.35\\columnwidth}|p{.47\\columnwidth}|p{.6\\columnwidth}|}
\\hline
jobid: $jobid \& uid: $uid \& nprocs: $nprocs \& runtime: $runtime seconds\\\\
\\hline
\\end{tabular}
";
close TABLES;
open(TABLES, ">$tmp_dir/access-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{r|r}
\\multicolumn{2}{c}{ } \\\\
\\multicolumn{2}{c}{Most Common Access Sizes} \\\\
\\hline
access size \& count \\\\
\\hline
\\hline
";
# sort access sizes (descending)
my $i = 0;
foreach $value (sort {$access_hash{$b} <=> $access_hash{$a} } keys %access_hash) {
if($i == 4) {
last;
}
if($access_hash{$value} == 0) {
last;
}
print TABLES "$value \& $access_hash{$value} \\\\\n";
$i++;
}
print TABLES "
\\hline
\\end{tabular}
";
close TABLES;
open(TABLES, ">$tmp_dir/file-count-table.tex") || die("error opening output file:$!\n");
print TABLES "
\\begin{tabular}{r|r|r|r}
\\multicolumn{4}{c}{ } \\\\
\\multicolumn{4}{c}{File Count Summary} \\\\
";
if($size_est_flag == 1)
{
print TABLES "
\\multicolumn{4}{c}{(estimated by I/O access offsets)} \\\\
";
}
print TABLES "
\\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'};
}
}
}
if($counter > 0) { $avg = $sum / $counter; }
else { $avg = 0; }
$avg = format_bytes($avg);
$max = format_bytes($max);
print TABLES "total opened \& $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'};
}