[i-g-t,v4,7/7] trace.pl: Fix request split mode

Commit Message

Tvrtko Ursulin May 9, 2018, 3:32 p.m. UTC

From: Tvrtko Ursulin <[e-mail]>

Request split mode had several bugs, both in the original version and also
after the recent refactorings.

One big one was that it wasn't considering different submit ports as a
reason to split execution, and also that it was too time based instead of
looking at relevant timelines.

In this refactoring we address the former by using the engine timelines
introduced in the previous patch. Secondary port submissions are moved
to follow the preceding submission as a first step in the correction
process.

In the second step, we add context timelines and use then in a similar
fashion to separate start and end time of coalesced requests. For each
coalesced request we know its boundaries by looking at the engine
timeline (via global seqnos), and we know the previous request it should
only start after, by looking at the context timeline.

v2:
 * Remove some dead code.
 * Fix !port0 shifting logic.

v3:
 * Refactor for less list walking as with incomplete handling.

v4:
 * Database of context timelines should not contain duplicates!
   (Converted from array into a hash.)

Signed-off-by: Tvrtko Ursulin <[e-mail]>
Cc: John Harrison <[e-mail]>
---
 scripts/trace.pl | 126 ++++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 98 insertions(+), 28 deletions(-)

Patch

diff --git a/scripts/trace.pl b/scripts/trace.pl
index 935f57117a37..936e4fe6b885 100755
--- a/scripts/trace.pl
+++ b/scripts/trace.pl
@@ -27,7 +27,7 @@  use warnings;
 use 5.010;
 
 my $gid = 0;
-my (%db, %queue, %submit, %notify, %rings, %ctxdb, %ringmap, %reqwait);
+my (%db, %queue, %submit, %notify, %rings, %ctxdb, %ringmap, %reqwait, %ctxtimelines);
 my @freqs;
 
 my $max_items = 3000;
@@ -435,6 +435,7 @@  while (<>) {
 		$req{'ring'} = $ring;
 		$req{'seqno'} = $seqno;
 		$req{'ctx'} = $ctx;
+		$ctxtimelines{$ctx . '/' . $ring} = 1;
 		$req{'name'} = $ctx . '/' . $seqno;
 		$req{'global'} = $tp{'global'};
 		$req{'port'} = $tp{'port'};
@@ -589,41 +590,110 @@  sub sortStart {
 	return $val;
 }
 
-my @sorted_keys = sort sortStart keys %db;
-my $re_sort = 0;
+my $re_sort = 1;
+my @sorted_keys;
 
-die "Database changed size?!" unless scalar(@sorted_keys) == $key_count;
+sub maybe_sort_keys
+{
+	if ($re_sort) {
+		@sorted_keys = sort sortStart keys %db;
+		$re_sort = 0;
+		die "Database changed size?!" unless scalar(@sorted_keys) ==
+						     $key_count;
+	}
+}
 
-foreach my $key (@sorted_keys) {
-	my $ring = $db{$key}->{'ring'};
-	my $end = $db{$key}->{'end'};
+maybe_sort_keys();
+
+my %ctx_timelines;
+
+sub sortContext {
+	my $as = $db{$a}->{'seqno'};
+	my $bs = $db{$b}->{'seqno'};
+	my $val;
+
+	$val = $as <=> $bs;
+
+	die if $val == 0;
+
+	return $val;
+}
+
+sub get_ctx_timeline {
+	my ($ctx, $ring, $key) = @_;
+	my @timeline;
+
+	return $ctx_timelines{$key} if exists $ctx_timelines{$key};
+
+	@timeline = grep { $db{$_}->{'ring'} == $ring and
+			   $db{$_}->{'ctx'} == $ctx } @sorted_keys;
+	# FIXME seqno restart
+	@timeline = sort sortContext @timeline;
+
+	$ctx_timelines{$key} = \@timeline;
+
+	return \@timeline;
+}
+
+# Split out merged batches if requested.
+if ($correct_durations) {
+	# Shift !port0 requests start time to after the previous context on the
+	# same timeline has finished.
+	foreach my $gid (sort keys %rings) {
+		my $ring = $ringmap{$rings{$gid}};
+		my $timeline = get_engine_timeline($ring);
+		my $complete;
+
+		foreach my $pos (0..$#{$timeline}) {
+			my $key = @{$timeline}[$pos];
+			my $prev = $complete;
+			my $pkey;
+
+			$complete = $key unless exists $db{$key}->{'no-end'};
+			$pkey = $complete;
+
+			next if $db{$key}->{'port'} == 0;
+
+			$pkey = $prev if $complete eq $key;
+
+			die unless defined $pkey;
+
+			$db{$key}->{'start'} = $db{$pkey}->{'end'};
+			$db{$key}->{'start'} = $db{$pkey}->{'notify'} if $db{$key}->{'start'} > $db{$key}->{'end'};
+
+			die if $db{$key}->{'start'} > $db{$key}->{'end'};
+
+			$re_sort = 1;
+		}
+	}
+
+	maybe_sort_keys();
+
+	# Batch with no-end (no request_out) means it was submitted as part of
+	# colaesced context. This means it's start time should be set to end
+	# time of a following request on this timeline.
+	foreach my $tkey (sort keys %ctxtimelines) {
+		my ($ctx, $ring) = split '/', $tkey;
+		my $timeline = get_ctx_timeline($ctx, $ring, $tkey);
+		my $last_complete = -1;
+		my $complete;
+
+		foreach my $pos (0..$#{$timeline}) {
+			my $key = @{$timeline}[$pos];
+			my $next_key;
+
+			next unless exists $db{$key}->{'no-end'};
+			last if $pos == $#{$timeline};
 
-	# correct duration of merged batches
-	if ($correct_durations and exists $db{$key}->{'no-end'}) {
-		my $ctx = $db{$key}->{'ctx'};
-		my $seqno = $db{$key}->{'seqno'};
-		my $start = $db{$key}->{'start'};
-		my $next_key;
-		my $i = 1;
-
-		do {
-			$next_key = db_key($ring, $ctx, $seqno + $i);
-			$i++;
-		} until (exists $db{$next_key} or $i > $key_count);  # ugly stop hack
-
-		# 20us tolerance
-		if (exists $db{$next_key} and $db{$next_key}->{'start'} < $start + 20) {
-			my $notify = $db{$key}->{'notify'};
+			# Shift following request to start after the current one
+			$next_key = ${$timeline}[$pos + 1];
+			$db{$next_key}->{'start'} = $db{$key}->{'notify'};
 			$re_sort = 1;
-			$db{$next_key}->{'start'} = $notify;
-			$db{$next_key}->{'start'} = $db{$next_key}->{'end'} if $db{$next_key}->{'start'} > $db{$next_key}->{'end'};
-			die if $db{$next_key}->{'start'} > $db{$next_key}->{'end'};
 		}
-		die if $start > $end;
 	}
 }
 
-@sorted_keys = sort sortStart keys %db if $re_sort;
+maybe_sort_keys();
 
 # GPU time accounting
 my (%running, %runnable, %queued, %batch_avg, %batch_total_avg, %batch_count);