All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tvrtko Ursulin <tursulin@ursulin.net>
To: igt-dev@lists.freedesktop.org
Cc: Intel-gfx@lists.freedesktop.org,
	Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Subject: [igt-dev] [PATCH i-g-t 11/11] trace.pl: Fix request split mode
Date: Tue,  6 Mar 2018 12:43:15 +0000	[thread overview]
Message-ID: <20180306124315.30208-12-tvrtko.ursulin@linux.intel.com> (raw)
In-Reply-To: <20180306124315.30208-1-tvrtko.ursulin@linux.intel.com>

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

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.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: John Harrison <John.C.Harrison@intel.com>
---
 scripts/trace.pl | 121 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 95 insertions(+), 26 deletions(-)

diff --git a/scripts/trace.pl b/scripts/trace.pl
index 4d1da98daa0d..de02bb1018f2 100755
--- a/scripts/trace.pl
+++ b/scripts/trace.pl
@@ -601,41 +601,110 @@ 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;
 
-	# correct duration of merged batches
-	if ($correct_durations and exists $db{$key}->{'no-end'}) {
+	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) {
+	my @port1;
+	my @no_end;
+
+	# Shift !port0 requests start time to after the previous context on the
+	# same timeline has finished.
+	@port1 = grep { $db{$_}->{'port'} != 0 } @sorted_keys;
+	foreach my $key (@port1) {
+		my $timeline = get_engine_timeline($db{$key}->{'ring'});
+		my $i = List::Util::first { ${$timeline}[$_] eq $key } 0..$#{$timeline};
+		my $prev_key;
+		my $start;
+
+		while ($i > 0) {
+			my $prev;
+
+			$i = $i - 1;
+			$prev = ${$timeline}[$i];
+
+			next if exists $db{$prev}->{'no-end'};
+
+			$prev_key = $prev;
+			last;
+		}
+
+		$start = $db{$prev_key}->{'end'};
+		$db{$key}->{'start'} = $start;
+		die if $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 the end
+	# time of a precedeing request on this timeline.
+	@no_end = grep { exists $db{$_}->{'no-end'} } @sorted_keys;
+	foreach my $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'};
+		my $ring = $db{$key}->{'ring'};
+		my $tkey = $ctx . '/' . $ring;
+		my $timeline = get_ctx_timeline($ctx, $ring, $tkey);
+		my $i;
+
+		$i = List::Util::first { ${$timeline}[$_] eq $key } 0..$#{$timeline};
+
+		# Shift following request to start after the current one.
+		if ($i < $#{$timeline}) {
+			my $next_key = ${$timeline}[$i + 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);
-- 
2.14.1

_______________________________________________
igt-dev mailing list
igt-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/igt-dev

WARNING: multiple messages have this Message-ID (diff)
From: Tvrtko Ursulin <tursulin@ursulin.net>
To: igt-dev@lists.freedesktop.org
Cc: Intel-gfx@lists.freedesktop.org
Subject: [PATCH i-g-t 11/11] trace.pl: Fix request split mode
Date: Tue,  6 Mar 2018 12:43:15 +0000	[thread overview]
Message-ID: <20180306124315.30208-12-tvrtko.ursulin@linux.intel.com> (raw)
In-Reply-To: <20180306124315.30208-1-tvrtko.ursulin@linux.intel.com>

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

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.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: John Harrison <John.C.Harrison@intel.com>
---
 scripts/trace.pl | 121 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 95 insertions(+), 26 deletions(-)

diff --git a/scripts/trace.pl b/scripts/trace.pl
index 4d1da98daa0d..de02bb1018f2 100755
--- a/scripts/trace.pl
+++ b/scripts/trace.pl
@@ -601,41 +601,110 @@ 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;
 
-	# correct duration of merged batches
-	if ($correct_durations and exists $db{$key}->{'no-end'}) {
+	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) {
+	my @port1;
+	my @no_end;
+
+	# Shift !port0 requests start time to after the previous context on the
+	# same timeline has finished.
+	@port1 = grep { $db{$_}->{'port'} != 0 } @sorted_keys;
+	foreach my $key (@port1) {
+		my $timeline = get_engine_timeline($db{$key}->{'ring'});
+		my $i = List::Util::first { ${$timeline}[$_] eq $key } 0..$#{$timeline};
+		my $prev_key;
+		my $start;
+
+		while ($i > 0) {
+			my $prev;
+
+			$i = $i - 1;
+			$prev = ${$timeline}[$i];
+
+			next if exists $db{$prev}->{'no-end'};
+
+			$prev_key = $prev;
+			last;
+		}
+
+		$start = $db{$prev_key}->{'end'};
+		$db{$key}->{'start'} = $start;
+		die if $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 the end
+	# time of a precedeing request on this timeline.
+	@no_end = grep { exists $db{$_}->{'no-end'} } @sorted_keys;
+	foreach my $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'};
+		my $ring = $db{$key}->{'ring'};
+		my $tkey = $ctx . '/' . $ring;
+		my $timeline = get_ctx_timeline($ctx, $ring, $tkey);
+		my $i;
+
+		$i = List::Util::first { ${$timeline}[$_] eq $key } 0..$#{$timeline};
+
+		# Shift following request to start after the current one.
+		if ($i < $#{$timeline}) {
+			my $next_key = ${$timeline}[$i + 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);
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2018-03-06 12:43 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-06 12:43 [Intel-gfx] [PATCH i-g-t v2 00/11] trace.pl fixes Tvrtko Ursulin
2018-03-06 12:43 ` Tvrtko Ursulin
2018-03-06 12:43 ` [Intel-gfx] [PATCH i-g-t 01/11] trace.pl: Catch-up with tracepoint renames Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 02/11] scripts/trace.pl: More hash key optimisations Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 03/11] scripts/trace.pl: Sort order Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 04/11] scripts/trace.pl: Calculate stats only after all munging Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 05/11] scripts/trace.pl: Simplify 'end' & 'notify' generation Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 06/11] trace.pl: Move sortQueue near its user Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-04-18 16:56   ` [Intel-gfx] [igt-dev] " Lionel Landwerlin
2018-04-18 16:56     ` Lionel Landwerlin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 07/11] trace.pl: Move min/max timestamp lookup to last loop Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-04-18 16:56   ` [igt-dev] " Lionel Landwerlin
2018-04-18 16:56     ` Lionel Landwerlin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 08/11] trace.pl: Fix engine busy accounting in split mode Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` [igt-dev] [PATCH i-g-t 09/11] trace.pl: Add support for colouring context execution Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-04-18 17:02   ` [igt-dev] [Intel-gfx] " Lionel Landwerlin
2018-04-18 17:02     ` Lionel Landwerlin
2018-03-06 12:43 ` [Intel-gfx] [PATCH i-g-t 10/11] trace.pl: Fix incomplete request handling Tvrtko Ursulin
2018-03-06 12:43   ` Tvrtko Ursulin
2018-03-06 12:43 ` Tvrtko Ursulin [this message]
2018-03-06 12:43   ` [PATCH i-g-t 11/11] trace.pl: Fix request split mode Tvrtko Ursulin
2018-03-06 14:18 ` [igt-dev] ✓ Fi.CI.BAT: success for trace.pl fixes (rev2) Patchwork
2018-03-06 19:29 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork
2018-04-18 14:52 ` [igt-dev] [PATCH i-g-t v2 00/11] trace.pl fixes Tvrtko Ursulin
2018-04-18 14:52   ` Tvrtko Ursulin
  -- strict thread matches above, loose matches on Subject: below --
2018-07-09 13:19 [Intel-gfx] [PATCH i-g-t 00/11] trace.pl fixes and improvements Tvrtko Ursulin
2018-07-09 13:20 ` [igt-dev] [PATCH i-g-t 11/11] trace.pl: Fix request split mode Tvrtko Ursulin
2018-01-30 10:11 [igt-dev] [PATCH i-g-t 00/11] trace.pl fixes Tvrtko Ursulin
2018-01-30 10:11 ` [igt-dev] [PATCH i-g-t 11/11] trace.pl: Fix request split mode Tvrtko Ursulin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180306124315.30208-12-tvrtko.ursulin@linux.intel.com \
    --to=tursulin@ursulin.net \
    --cc=Intel-gfx@lists.freedesktop.org \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=tvrtko.ursulin@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.