752 lines · 27.8 KB · Perl
RawDownload
#!/usr/bin/env perl# This is a POC for reading the text representation of trace output related to# page reclaim. It makes an attempt to extract some high-level information on# what is going on. The accuracy of the parser may vary## Example usage: trace-vmscan-postprocess.pl < /sys/kernel/tracing/trace_pipe# other options#   --read-procstat	If the trace lacks process info, get it from /proc#   --ignore-pid	Aggregate processes of the same name together## Copyright (c) IBM Corporation 2009# Author: Mel Gorman <mel@csn.ul.ie>use strict;use Getopt::Long; # Tracepoint eventsuse constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN	=> 1;use constant MM_VMSCAN_DIRECT_RECLAIM_END	=> 2;use constant MM_VMSCAN_KSWAPD_WAKE		=> 3;use constant MM_VMSCAN_KSWAPD_SLEEP		=> 4;use constant MM_VMSCAN_LRU_SHRINK_ACTIVE	=> 5;use constant MM_VMSCAN_LRU_SHRINK_INACTIVE	=> 6;use constant MM_VMSCAN_LRU_ISOLATE		=> 7;use constant MM_VMSCAN_WRITEPAGE_FILE_SYNC	=> 8;use constant MM_VMSCAN_WRITEPAGE_ANON_SYNC	=> 9;use constant MM_VMSCAN_WRITEPAGE_FILE_ASYNC	=> 10;use constant MM_VMSCAN_WRITEPAGE_ANON_ASYNC	=> 11;use constant MM_VMSCAN_WRITEPAGE_ASYNC		=> 12;use constant EVENT_UNKNOWN			=> 13; # Per-order eventsuse constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER => 11;use constant MM_VMSCAN_WAKEUP_KSWAPD_PERORDER 	=> 12;use constant MM_VMSCAN_KSWAPD_WAKE_PERORDER	=> 13;use constant HIGH_KSWAPD_REWAKEUP_PERORDER	=> 14; # Constants used to track stateuse constant STATE_DIRECT_BEGIN 		=> 15;use constant STATE_DIRECT_ORDER 		=> 16;use constant STATE_KSWAPD_BEGIN			=> 17;use constant STATE_KSWAPD_ORDER			=> 18; # High-level events extrapolated from tracepointsuse constant HIGH_DIRECT_RECLAIM_LATENCY	=> 19;use constant HIGH_KSWAPD_LATENCY		=> 20;use constant HIGH_KSWAPD_REWAKEUP		=> 21;use constant HIGH_NR_SCANNED			=> 22;use constant HIGH_NR_TAKEN			=> 23;use constant HIGH_NR_RECLAIMED			=> 24;use constant HIGH_NR_FILE_SCANNED		=> 25;use constant HIGH_NR_ANON_SCANNED		=> 26;use constant HIGH_NR_FILE_RECLAIMED		=> 27;use constant HIGH_NR_ANON_RECLAIMED		=> 28; my %perprocesspid;my %perprocess;my %last_procmap;my $opt_ignorepid;my $opt_read_procstat; my $total_wakeup_kswapd;my ($total_direct_reclaim, $total_direct_nr_scanned);my ($total_direct_nr_file_scanned, $total_direct_nr_anon_scanned);my ($total_direct_latency, $total_kswapd_latency);my ($total_direct_nr_reclaimed);my ($total_direct_nr_file_reclaimed, $total_direct_nr_anon_reclaimed);my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async);my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async);my ($total_kswapd_nr_scanned, $total_kswapd_wake);my ($total_kswapd_nr_file_scanned, $total_kswapd_nr_anon_scanned);my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async);my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async);my ($total_kswapd_nr_reclaimed);my ($total_kswapd_nr_file_reclaimed, $total_kswapd_nr_anon_reclaimed); # Catch sigint and exit on requestmy $sigint_report = 0;my $sigint_exit = 0;my $sigint_pending = 0;my $sigint_received = 0;sub sigint_handler {	my $current_time = time;	if ($current_time - 2 > $sigint_received) {		print "SIGINT received, report pending. Hit ctrl-c again to exit\n";		$sigint_report = 1;	} else {		if (!$sigint_exit) {			print "Second SIGINT received quickly, exiting\n";		}		$sigint_exit++;	} 	if ($sigint_exit > 3) {		print "Many SIGINTs received, exiting now without report\n";		exit;	} 	$sigint_received = $current_time;	$sigint_pending = 1;}$SIG{INT} = "sigint_handler"; # Parse command line optionsGetOptions(	'ignore-pid'	 =>	\$opt_ignorepid,	'read-procstat'	 =>	\$opt_read_procstat,); # Defaults for dynamically discovered regex'smy $regex_direct_begin_default = 'order=([0-9]*) gfp_flags=([A-Z_|]*)';my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)';my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';my $regex_kswapd_sleep_default = 'nid=([0-9]*)';my $regex_wakeup_kswapd_default = 'nid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)';my $regex_lru_isolate_default = 'classzone=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)';my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate_anon=([0-9]*) nr_activate_file=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_taken=([0-9]*) nr_active=([0-9]*) nr_deactivated=([0-9]*) nr_referenced=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)' ;my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)'; # Dyanically discovered regexmy $regex_direct_begin;my $regex_direct_end;my $regex_kswapd_wake;my $regex_kswapd_sleep;my $regex_wakeup_kswapd;my $regex_lru_isolate;my $regex_lru_shrink_inactive;my $regex_lru_shrink_active;my $regex_writepage; # Static regex used. Specified like this for readability and for use with /o#                      (process_pid)     (cpus      )   ( time  )   (tpoint    ) (details)my $regex_traceevent = '\s*([a-zA-Z0-9-]*)\s*(\[[0-9]*\])(\s*[dX.][Nnp.][Hhs.][0-9a-fA-F.]*|)\s*([0-9.]*):\s*([a-zA-Z_]*):\s*(.*)';my $regex_statname = '[-0-9]*\s\((.*)\).*';my $regex_statppid = '[-0-9]*\s\(.*\)\s[A-Za-z]\s([0-9]*).*'; sub generate_traceevent_regex {	my $event = shift;	my $default = shift;	my $regex; 	# Read the event format or use the default	if (!open (FORMAT, "/sys/kernel/tracing/events/$event/format")) {		print("WARNING: Event $event format string not found\n");		return $default;	} else {		my $line;		while (!eof(FORMAT)) {			$line = <FORMAT>;			$line =~ s/, REC->.*//;			if ($line =~ /^print fmt:\s"(.*)".*/) {				$regex = $1;				$regex =~ s/%s/\([0-9a-zA-Z|_]*\)/g;				$regex =~ s/%p/\([0-9a-f]*\)/g;				$regex =~ s/%d/\([-0-9]*\)/g;				$regex =~ s/%ld/\([-0-9]*\)/g;				$regex =~ s/%lu/\([0-9]*\)/g;			}		}	} 	# Can't handle the print_flags stuff but in the context of this	# script, it really doesn't matter	$regex =~ s/\(REC.*\) \? __print_flags.*//; 	# Verify fields are in the right order	my $tuple;	foreach $tuple (split /\s/, $regex) {		my ($key, $value) = split(/=/, $tuple);		my $expected = shift;		if ($key ne $expected) {			print("WARNING: Format not as expected for event $event '$key' != '$expected'\n");			$regex =~ s/$key=\((.*)\)/$key=$1/;		}	} 	if (defined shift) {		die("Fewer fields than expected in format");	} 	return $regex;} $regex_direct_begin = generate_traceevent_regex(			"vmscan/mm_vmscan_direct_reclaim_begin",			$regex_direct_begin_default,			"order", "gfp_flags");$regex_direct_end = generate_traceevent_regex(			"vmscan/mm_vmscan_direct_reclaim_end",			$regex_direct_end_default,			"nr_reclaimed");$regex_kswapd_wake = generate_traceevent_regex(			"vmscan/mm_vmscan_kswapd_wake",			$regex_kswapd_wake_default,			"nid", "order");$regex_kswapd_sleep = generate_traceevent_regex(			"vmscan/mm_vmscan_kswapd_sleep",			$regex_kswapd_sleep_default,			"nid");$regex_wakeup_kswapd = generate_traceevent_regex(			"vmscan/mm_vmscan_wakeup_kswapd",			$regex_wakeup_kswapd_default,			"nid", "order", "gfp_flags");$regex_lru_isolate = generate_traceevent_regex(			"vmscan/mm_vmscan_lru_isolate",			$regex_lru_isolate_default,			"classzone", "order",			"nr_requested", "nr_scanned", "nr_skipped", "nr_taken",			"lru");$regex_lru_shrink_inactive = generate_traceevent_regex(			"vmscan/mm_vmscan_lru_shrink_inactive",			$regex_lru_shrink_inactive_default,			"nid", "nr_scanned", "nr_reclaimed", "nr_dirty", "nr_writeback",			"nr_congested", "nr_immediate", "nr_activate_anon",			"nr_activate_file", "nr_ref_keep",			"nr_unmap_fail", "priority", "flags");$regex_lru_shrink_active = generate_traceevent_regex(			"vmscan/mm_vmscan_lru_shrink_active",			$regex_lru_shrink_active_default,			"nid", "nr_taken", "nr_active", "nr_deactivated", "nr_referenced",			"priority", "flags");$regex_writepage = generate_traceevent_regex(			"vmscan/mm_vmscan_write_folio",			$regex_writepage_default,			"page", "pfn", "flags"); sub read_statline($) {	my $pid = $_[0];	my $statline; 	if (open(STAT, "/proc/$pid/stat")) {		$statline = <STAT>;		close(STAT);	} 	if ($statline eq '') {		$statline = "-1 (UNKNOWN_PROCESS_NAME) R 0";	} 	return $statline;} sub guess_process_pid($$) {	my $pid = $_[0];	my $statline = $_[1]; 	if ($pid == 0) {		return "swapper-0";	} 	if ($statline !~ /$regex_statname/o) {		die("Failed to math stat line for process name :: $statline");	}	return "$1-$pid";} # Convert sec.usec timestamp formatsub timestamp_to_ms($) {	my $timestamp = $_[0]; 	my ($sec, $usec) = split (/\./, $timestamp);	return ($sec * 1000) + ($usec / 1000);} sub process_events {	my $traceevent;	my $process_pid;	my $cpus;	my $timestamp;	my $tracepoint;	my $details;	my $statline; 	# Read each line of the event logEVENT_PROCESS:	while ($traceevent = <STDIN>) {		if ($traceevent =~ /$regex_traceevent/o) {			$process_pid = $1;			$timestamp = $4;			$tracepoint = $5; 			$process_pid =~ /(.*)-([0-9]*)$/;			my $process = $1;			my $pid = $2; 			if ($process eq "") {				$process = $last_procmap{$pid};				$process_pid = "$process-$pid";			}			$last_procmap{$pid} = $process; 			if ($opt_read_procstat) {				$statline = read_statline($pid);				if ($opt_read_procstat && $process eq '') {					$process_pid = guess_process_pid($pid, $statline);				}			}		} else {			next;		} 		# Perl Switch() sucks majorly		if ($tracepoint eq "mm_vmscan_direct_reclaim_begin") {			$timestamp = timestamp_to_ms($timestamp);			$perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}++;			$perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN} = $timestamp; 			$details = $6;			if ($details !~ /$regex_direct_begin/o) {				print "WARNING: Failed to parse mm_vmscan_direct_reclaim_begin as expected\n";				print "         $details\n";				print "         $regex_direct_begin\n";				next;			}			my $order = $1;			$perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order]++;			$perprocesspid{$process_pid}->{STATE_DIRECT_ORDER} = $order;		} elsif ($tracepoint eq "mm_vmscan_direct_reclaim_end") {			# Count the event itself			my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END};			$perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END}++; 			# Record how long direct reclaim took this time			if (defined $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN}) {				$timestamp = timestamp_to_ms($timestamp);				my $order = $perprocesspid{$process_pid}->{STATE_DIRECT_ORDER};				my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN});				$perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] = "$order-$latency";			}		} elsif ($tracepoint eq "mm_vmscan_kswapd_wake") {			$details = $6;			if ($details !~ /$regex_kswapd_wake/o) {				print "WARNING: Failed to parse mm_vmscan_kswapd_wake as expected\n";				print "         $details\n";				print "         $regex_kswapd_wake\n";				next;			} 			my $order = $2;			$perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER} = $order;			if (!$perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN}) {				$timestamp = timestamp_to_ms($timestamp);				$perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}++;				$perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = $timestamp;				$perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order]++;			} else {				$perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP}++;				$perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP_PERORDER}[$order]++;			}		} elsif ($tracepoint eq "mm_vmscan_kswapd_sleep") { 			# Count the event itself			my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP};			$perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP}++; 			# Record how long kswapd was awake			$timestamp = timestamp_to_ms($timestamp);			my $order = $perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER};			my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN});			$perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index] = "$order-$latency";			$perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = 0;		} elsif ($tracepoint eq "mm_vmscan_wakeup_kswapd") {			$perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}++; 			$details = $6;			if ($details !~ /$regex_wakeup_kswapd/o) {				print "WARNING: Failed to parse mm_vmscan_wakeup_kswapd as expected\n";				print "         $details\n";				print "         $regex_wakeup_kswapd\n";				next;			}			my $order = $2;			$perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]++;		} elsif ($tracepoint eq "mm_vmscan_lru_isolate") {			$details = $6;			if ($details !~ /$regex_lru_isolate/o) {				print "WARNING: Failed to parse mm_vmscan_lru_isolate as expected\n";				print "         $details\n";				print "         $regex_lru_isolate/o\n";				next;			}			my $nr_scanned = $4;			my $lru = $7; 			# To closer match vmstat scanning statistics, only count			# inactive lru as scanning			if ($lru =~ /inactive_/) {				$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;				if ($lru =~ /_file/) {					$perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED} += $nr_scanned;				} else {					$perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED} += $nr_scanned;				}			}		} elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {			$details = $6;			if ($details !~ /$regex_lru_shrink_inactive/o) {				print "WARNING: Failed to parse mm_vmscan_lru_shrink_inactive as expected\n";				print "         $details\n";				print "         $regex_lru_shrink_inactive/o\n";				next;			} 			my $nr_reclaimed = $3;			my $flags = $13;			my $file = 0;			if ($flags =~ /RECLAIM_WB_FILE/) {				$file = 1;			}			$perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED} += $nr_reclaimed;			if ($file) {				$perprocesspid{$process_pid}->{HIGH_NR_FILE_RECLAIMED} += $nr_reclaimed;			} else {				$perprocesspid{$process_pid}->{HIGH_NR_ANON_RECLAIMED} += $nr_reclaimed;			}		} elsif ($tracepoint eq "mm_vmscan_writepage") {			$details = $6;			if ($details !~ /$regex_writepage/o) {				print "WARNING: Failed to parse mm_vmscan_writepage as expected\n";				print "         $details\n";				print "         $regex_writepage\n";				next;			} 			my $flags = $3;			my $file = 0;			my $sync_io = 0;			if ($flags =~ /RECLAIM_WB_FILE/) {				$file = 1;			}			if ($flags =~ /RECLAIM_WB_SYNC/) {				$sync_io = 1;			}			if ($sync_io) {				if ($file) {					$perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}++;				} else {					$perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}++;				}			} else {				if ($file) {					$perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}++;				} else {					$perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}++;				}			}		} else {			$perprocesspid{$process_pid}->{EVENT_UNKNOWN}++;		} 		if ($sigint_pending) {			last EVENT_PROCESS;		}	}} sub dump_stats {	my $hashref = shift;	my %stats = %$hashref; 	# Dump per-process stats	my $process_pid;	my $max_strlen = 0; 	# Get the maximum process name	foreach $process_pid (keys %perprocesspid) {		my $len = length($process_pid);		if ($len > $max_strlen) {			$max_strlen = $len;		}	}	$max_strlen += 2; 	# Work out latencies	printf("\n") if !$opt_ignorepid;	printf("Reclaim latencies expressed as order-latency_in_ms\n") if !$opt_ignorepid;	foreach $process_pid (keys %stats) { 		if (!$stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[0] &&				!$stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[0]) {			next;		} 		printf "%-" . $max_strlen . "s ", $process_pid if !$opt_ignorepid;		my $index = 0;		while (defined $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] ||			defined $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) { 			if ($stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) {				printf("%s ", $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) if !$opt_ignorepid;				my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]);				$total_direct_latency += $latency;			} else {				printf("%s ", $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) if !$opt_ignorepid;				my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]);				$total_kswapd_latency += $latency;			}			$index++;		}		print "\n" if !$opt_ignorepid;

Lines 1–500 of 752.