$interrupt = 1;
}
-# With multiprocess we need to wait all childs
+# With multiprocess we need to wait for all children
sub wait_child
{
my $sig = shift;
}
&usage() if ($help);
-# Rewrite some command line argument as lists
+# Rewrite some command line arguments as lists
&compute_arg_list();
-# Log file to be parsed are passed as command line argument
+# Log files to be parsed are passed as command line arguments
if ($#ARGV >= 0) {
foreach my $file (@ARGV) {
if ($file ne '-') {
die "FATAL: output file $outfile is a directory, should be a file\nor maybe you want to use -O | --outdir option instead.\n";
}
} elsif (!-d "$outdir") {
- # An output directory have been passed as command line parameter
+ # An output directory has been passed as command line parameter
die "FATAL: $outdir is not a directory or doesn't exist.\n";
}
$outfile = basename($outfile);
my $global_totalsize = 0;
my @given_log_files = ( @log_files );
-# Verify that the file have not changed for incremental move
+# Verify that the file has not changed for incremental move
if ( ($saved_last_line{current_pos} > 0) && ($#given_log_files == 0)) {
$saved_last_line{current_pos} = 0 if (&check_file_changed($given_log_files[0], $saved_last_line{datetime}));
$saved_last_line{current_pos}++ if ($saved_last_line{current_pos} > 0);
}
-# log files must be erase when loading stats from binary format
+# log files must be erased when loading stats from binary format
if ($format eq 'binary') {
$queue_size = 1;
$job_per_file = 1;
}
# Do not use split method with compressed files
if ( ($queue_size > 1) && ($logfile !~ /\.(gz|bz2|zip)/i) ) {
- # Create multiple process to parse one log file by chunks of data
+ # Create multiple processes to parse one log file by chunks of data
my @chunks = &split_logfile($logfile);
for (my $i = 0; $i < $#chunks; $i++) {
while ($child_count >= $parallel_process) {
my $minproc = 1;
$minproc = 0 if (!$progress);
- # Wait for all child dies less the logger
+ # Wait for all child processes to die except for the logger
while (scalar keys %RUNNING_PIDS > $minproc) {
my $kid = waitpid(-1, WNOHANG);
if ($kid > 0) {
# Clear previous statistics
&init_stats_vars();
- # Load all data gathered by all the differents processes
+ # Load all data gathered by all the different processes
foreach my $f (@tempfiles) {
next if (!-e "$f->[1]" || -z "$f->[1]");
my $fht = new IO::File;
# First clear previous stored statistics
&init_stats_vars();
- # Load all data gathered by all the differents processes
+ # Load all data gathered by all the different processes
unless(opendir(DIR, "$outdir/$bpath")) {
die "Error: can't opendir $outdir/$bpath: $!";
}
</style>
};
- # get years directories
+ # get year directories
unless(opendir(DIR, "$outdir")) {
die "Error: can't opendir $outdir: $!";
}
-d | --dbname database : only report on entries for the given database.
-e | --end datetime : end date/time for the data to be parsed in log.
-f | --format logtype : possible values: syslog,stderr,csv. Default: stderr.
- -G | --nograph : disable graphs on HTML output. Enable by default.
+ -G | --nograph : disable graphs on HTML output. Enabled by default.
-h | --help : show this message and exit.
-i | --ident name : programname used as syslog ident. Default: postgres
-I | --incremental : use incremental mode, reports will be generated by
on the output format: out.html, out.txt or out.tsung.
To dump output to stdout use - as filename.
-O | --outdir path : directory where out file must be saved.
- -p | --prefix string : give here the value of your custom log_line_prefix
+ -p | --prefix string : the value of your custom log_line_prefix as
defined in your postgresql.conf. Only use it if you
aren't using one of the standard prefixes specified
in the pgBadger documentation, such as if your prefix
-P | --no-prettify : disable SQL queries prettify formatter.
-q | --quiet : don't print anything to stdout, not even a progress bar.
-s | --sample number : number of query samples to store/display. Default: 3
- -S | --select-only : use it if you want to report select queries only.
+ -S | --select-only : only report SELECT queries.
-t | --top number : number of queries to store/display. Default: 20
-T | --title string : change title of the HTML page report.
-u | --dbuser username : only report on entries for the given user.
-w | --watch-mode : only report errors just like logwatch could do.
-x | --extension : output format. Values: text, html or tsung. Default: html
-z | --zcat exec_path : set the full path to the zcat program. Use it if
- zcat or bzcat or unzip is not on your path.
+ zcat or bzcat or unzip is not in your path.
--pie-limit num : pie data lower than num% will show a sum instead.
--exclude-query regex : any query matching the given regex will be excluded
- from the report. For example: "^(VACUUM|COMMIT)"
+ from the report. For example: "^(VACUUM|COMMIT)"
You can use this option multiple times.
--exclude-file filename: path of the file which contains all the regex to use
to exclude queries from the report. One regex per line.
pgbadger -b "2012-06-25 10:56:11" -e "2012-06-25 10:59:11" \
/var/log/postgresql.log
cat /var/log/postgres.log | pgbadger -
- # log prefix with stderr log output
+ # Log prefix with stderr log output
perl pgbadger --prefix '%t [%p]: [%l-1] user=%u,db=%d,client=%h' \
/pglog/postgresql-2012-08-21*
perl pgbadger --prefix '%m %u@%d %p %r %a : ' /pglog/postgresql.log
# Log line prefix with syslog log output
perl pgbadger --prefix 'user=%u,db=%d,client=%h,appname=%a' \
/pglog/postgresql-2012-08-21*
- # Use my 8 CPUs to parse my 10GB file faster, really faster
+ # Use my 8 CPUs to parse my 10GB file faster, much faster
perl pgbadger -j 8 /pglog/postgresql-9.1-main.log
pgbadger --exclude-time "2013-09-.* (23|13):.*" postgresql.log
-This will help to not have all COPY order on top of slowest queries. You can
-also use --exclude-appname "pg_dump" to solve this problem in a more simple way.
+This will help avoid having COPY statements, as generated by pg_dump, on top of
+the list of slowest queries. You can also use --exclude-appname "pg_dump" to
+solve this problem in a simpler way.
};
$0 = 'pgbadger logger';
- # Terminate the process when we doesn't read the complete file but must exit
+ # Terminate the process when we haven't read the complete file but must exit
local $SIG{USR1} = sub {
print STDERR "\n";
exit 0;
# skip non postgresql lines
next if ($prefix_vars{'t_ident'} ne $ident);
- # Stores temporary files and locks information
+ # Store temporary files and locks information
&store_temporary_and_lock_infos($cur_pid);
# Standard syslog format does not have year information, months are
- # three letters and day are not always with 2 digit.
+ # three letters and days are not always with 2 digits.
if ($prefix_vars{'t_month'} !~ /\d/) {
$prefix_vars{'t_year'} = $gyear;
$prefix_vars{'t_day'} = sprintf("%02d", $prefix_vars{'t_day'});
$cur_info{$cur_pid}{query} .= "\n" . $t_query;
}
- # Collect orphans lines of multiline queries
+ # Collect orphaned lines of multiline queries
} elsif ($cur_pid && ($line !~ $orphan_syslog_line)) {
if (exists $cur_temp_info{$cur_pid}{query}) {
$prefix_vars{$prefix_params[$i]} = $matches[$i];
}
- # Stores temporary files and locks information
+ # Stores temporary files and lock information
&store_temporary_and_lock_infos($cur_pid);
if (!$prefix_vars{'t_timestamp'} && $prefix_vars{'t_mtimestamp'}) {
$cur_info{$cur_pid}{query} .= "\n" . $line;
}
- # Collect orphans lines of multiline queries
+ # Collect orphaned lines of multiline queries
} elsif ($cur_pid && ($cur_info{$cur_pid}{query})) {
$cur_info{$cur_pid}{detail} .= "\n" . $line;
# Get stats from all pending temporary storage
foreach my $pid (sort {$cur_info{$a}{date} <=> $cur_info{$b}{date}} keys %cur_info) {
- # Stores last queries information
+ # Stores last query information
&store_queries($pid);
}
- # Stores last temporary files and locks information
+ # Stores last temporary files and lock information
foreach my $pid (keys %cur_temp_info) {
&store_temporary_and_lock_infos($pid);
}
- # Stores last temporary files and locks information
+ # Stores last temporary files and lock information
foreach my $pid (keys %cur_lock_info) {
&store_temporary_and_lock_infos($pid);
}
$prefix_vars{$prefix_params[$i]} = $matches[$i];
}
# Standard syslog format does not have year information, months are
- # three letters and day are not always with 2 digit.
+ # three letters and days are not always with 2 digits.
if ($prefix_vars{'t_month'} !~ /\d/) {
$prefix_vars{'t_year'} = $gyear;
$prefix_vars{'t_day'} = sprintf("%02d", $prefix_vars{'t_day'});
}
-# Method used to check if we have already reach the last parsing position in incremental mode
+# Method used to check if we have already reached the last parsing position in incremental mode
# This position should have been saved in the incremental file and read in the $last_parsed at
# start up.
sub check_incremental_position
# Stores last queries information
&store_queries($pid);
}
- # Stores last temporary files and locks information
+ # Stores last temporary files and lock information
foreach my $pid (keys %cur_temp_info) {
&store_temporary_and_lock_infos($pid);
}
- # Stores last temporary files and locks information
+ # Stores last temporary files and lock information
foreach my $pid (keys %cur_lock_info) {
&store_temporary_and_lock_infos($pid);
}
if (exists $q_dataavg{count}) {
# Average queries per minute
$graph_data{query} .= "[$t, " . int(($q_dataavg{count}{"$rd"} || 0) / (60 * $avg_minutes)) . "],";
- # Maxi queries per minute
+ # Max queries per minute
$graph_data{'query-max'} .= "[$t, " . ($q_dataavg{max}{"$rd"} || 0) . "],";
- # Mini queries per minute
+ # Min queries per minute
$graph_data{'query-min'} .= "[$t, " . ($q_dataavg{min}{"$rd"} || 0) . "],";
# Average duration per minute
$graph_data{query4} .= "[$t, " . sprintf("%.3f", ($q_dataavg{duration}{"$rd"} || 0) / ($q_dataavg{count}{"$rd"} || 1)) . "],";
if (scalar keys %c_dataavg) {
# Average connections per minute
$graph_data{conn_avg} .= "[$t, " . int(($c_dataavg{average}{"$rd"} || 0) / (60 * $avg_minutes)) . "],";
- # Maxi connections per minute
+ # Max connections per minute
$graph_data{conn_max} .= "[$t, " . ($c_dataavg{max}{"$rd"} || 0) . "],";
- # Mini connections per minute
+ # Min connections per minute
$graph_data{conn_min} .= "[$t, " . ($c_dataavg{min}{"$rd"} || 0) . "],";
}
if (scalar keys %s_dataavg) {
# Average connections per minute
$graph_data{sess_avg} .= "[$t, " . int(($s_dataavg{average}{"$rd"} || 0) / (60 * $avg_minutes)) . "],";
- # Maxi connections per minute
+ # Max connections per minute
$graph_data{sess_max} .= "[$t, " . ($s_dataavg{max}{"$rd"} || 0) . "],";
- # Mini connections per minute
+ # Min connections per minute
$graph_data{sess_min} .= "[$t, " . ($s_dataavg{min}{"$rd"} || 0) . "],";
}
if (!$disable_query && (scalar keys %a_dataavg > 0)) {
# Average queries per minute
$graph_data{"$action"} .= "[$t, " . int(($a_dataavg{$action}{count}{"$rd"} || 0) / (60 * $avg_minutes)) . "],";
if ($action eq 'SELECT') {
- # Maxi queries per minute
+ # Max queries per minute
$graph_data{"$action-max"} .= "[$t, " . ($a_dataavg{$action}{max}{"$rd"} || 0) . "],";
- # Mini queries per minute
+ # Min queries per minute
$graph_data{"$action-min"} .= "[$t, " . ($a_dataavg{$action}{min}{"$rd"} || 0) . "],";
# Average query duration
$graph_data{"$action-2"} .= "[$t, " . sprintf("%.3f", ($a_dataavg{$action}{duration}{"$rd"} || 0) / ($a_dataavg{$action}{count}{"$rd"} || 1)) . "]," if ($action eq 'SELECT');
next if ($t < $t_min);
last if ($t > $t_max);
- # Average of written checkpoints buffers and wal files
+ # Average of written checkpoint buffers and wal files
if (exists $chk_dataavg{wbuffer}) {
$graph_data{wbuffer} .= "[$t, " . ($chk_dataavg{wbuffer}{"$rd"} || 0) . "],";
$graph_data{file_added} .= "[$t, " . ($chk_dataavg{file_added}{"$rd"} || 0) . "],";
$graph_data{$_} =~ s/,$//;
}
}
- # Checkpoints buffers and files
+ # Checkpoint buffers and files
$drawn_graphs{checkpointwritebuffers_graph} =
&flotr2_graph($graphid++, 'checkpointwritebuffers_graph', $graph_data{wbuffer}, '', '',
'Checkpoint write buffers (' . $avg_minutes . ' minutes period)',
{
my ($t_pid) = @_;
- # Look at particular cas of vacuum/analyze that have the database
+ # Look at particular cases of vacuum/analyze that have the database
# name inside the log message so that they could be associated
if ($prefix_vars{'t_query'} =~ / of table "([^\.]+)\.[^\.]+\.[^\.]+":/) {
$prefix_vars{'t_dbname'} = $1;
}
- # Check user and/or database if require
+ # Check user and/or database if required
if ($#dbname >= 0) {
# Log line does not match the required dbname
# Stores the error's detail if previous line was an error
if ($cur_info{$t_pid}{loglevel} =~ $main_error_regex) {
- # and current one is a detailed information
+ # and current one is detailed information
if ($prefix_vars{'t_loglevel'} =~ /(DETAIL|STATEMENT|CONTEXT|HINT)/) {
$cur_info{$t_pid}{"\L$1\E"} .= $prefix_vars{'t_query'};
return;
$lock_info{$1}{chronos}{$date_part}{$prefix_vars{'t_hour'}}{count}++;
$lock_info{$1}{chronos}{$date_part}{$prefix_vars{'t_hour'}}{duration}++;
# Store current lock information that will be used later
- # when we will parse the query responsible of the locks
+ # when we will parse the query responsible for the locks
$cur_lock_info{$t_pid}{wait} = $3;
if ($format eq 'csv') {
$cur_lock_info{$t_pid}{query} = $prefix_vars{'t_statement'};
$per_minute_info{$date_part}{$prefix_vars{'t_hour'}}{$prefix_vars{'t_min'}}{tempfile}{size} += $1;
$tempfile_info{maxsize} = $1 if ($tempfile_info{maxsize} < $1);
# Store current temporary file information that will be used later
- # when we will parse the query responsible of the tempfile
+ # when we will parse the query responsible for the tempfile
$cur_temp_info{$t_pid}{size} = $1;
$overall_stat{'peak'}{$cur_last_log_timestamp}{tempfile_size} += $1;
$overall_stat{'peak'}{$cur_last_log_timestamp}{tempfile_count}++;
return;
}
- # Store time in millisecond
+ # Store time in milliseconds
$time =~ /(\d+):(\d+):(\d+\.\d+)/;
$time = ($3 * 1000) + ($2 * 60 * 1000) + ($1 * 60 * 60 * 1000);
$session_info{count}++;
}
####
- # Registrer previous query storage into global statistics before starting to store current query
+ # Register previous query storage into global statistics before starting to store current query
####
if (exists $cur_info{$t_pid}{query}) {
# when switching to a new log message
$per_minute_info{$date_part}{$prefix_vars{'t_hour'}}{$prefix_vars{'t_min'}}{$t_action}++;
# Skipping parse and bind logs
return if ($t_action !~ /query|statement|execute/);
- # Log line that would not be parse
+ # Log line that could not be parsed
} elsif ($prefix_vars{'t_loglevel'} eq 'LOG') {
if ($prefix_vars{'t_query'} !~
/incomplete startup packet|connection|receive|unexpected EOF|still waiting for [^\s]+Lock|checkpoint starting:|could not send data to client|parameter .*configuration file|autovacuum launcher|automatic (analyze|vacuum)|detected deadlock while waiting for/
$cur_info{$t_pid}{query} =~ s/\/\*(.*?)\*\///gs;
}
- # Stores temporary files and locks information
+ # Stores temporary files and lock information
&store_temporary_and_lock_infos($t_pid);
return if (!exists $cur_info{$t_pid});
$normalyzed_info{$normalized}{chronos}{"$cur_day_str"}{"$cur_hour_str"}{count}++;
if ($cur_info{$t_pid}{duration}) {
- # Updtate top slowest queries statistics
+ # Update top slowest queries statistics
&set_top_slowest($cur_info{$t_pid}{query}, $cur_info{$t_pid}{duration}, $cur_last_log_timestamp, $cur_info{$t_pid}{dbname}, $cur_info{$t_pid}{dbuser}, $cur_info{$t_pid}{dbclient},$cur_info{$t_pid}{dbappname});
# Store normalized query total duration
# %U The week number of the current year as a decimal number, range 00 to 53, starting with the first
# Sunday as the first day of week 01.
-# %V The ISO 8601 week number (see NOTES) of the current year as a decimal number, range 01 to 53,
+# %V The ISO 8601 week number (see NOTES) of the current year as a decimal number, range 01 to 53,
# where week 1 is the first week that has at least 4 days in the new year.
# %W The week number of the current year as a decimal number, range 00 to 53, starting with the first
# Monday as the first day of week 01.
- # Check if the date is valide first
+ # Check if the date is valid first
my $datefmt = POSIX::strftime("%F", 1, 1, 1, $day, $month - 1, $year - 1900);
if ($datefmt ne "$year-$month-$day") {
return -1;
my $y = $1;
my $m = $2;
foreach my $day ("01" .. "31") {
- # Check if the date is valide first
+ # Check if the date is valid first
my $datefmt = POSIX::strftime("%F", 1, 1, 1, $day, $m - 1, $y - 1900);
if ($datefmt ne "$y-$m-$day") {
next;
foreach my $m ("01" .. "12") {
foreach my $day ("01" .. "31") {
- # Check if the date is valide first
+ # Check if the date is valid first
my $datefmt = POSIX::strftime("%F", 1, 1, 1, $day, $m - 1, $y - 1900);
if ($datefmt ne "$y-$m-$day") {
next;
projects / pgbadger / commitdiff