summaryrefslogtreecommitdiff
path: root/yjit.rb
diff options
context:
space:
mode:
authorEileen M. Uchitelle <eileencodes@users.noreply.github.com>2022-07-12 16:40:49 -0400
committerGitHub <noreply@github.com>2022-07-12 16:40:49 -0400
commit59c6b7b7abefdf8bc93d7117a3893d581f3a6c90 (patch)
tree9cb8840687d2f9f8b0fee59495cfe81a09daa078 /yjit.rb
parent8c1808151f4c1b44e8b0fe935c571f05b2641b8b (diff)
downloadruby-59c6b7b7abefdf8bc93d7117a3893d581f3a6c90.tar.gz
Speed up --yjit-trace-exits code (#6106)
In a small script the speed of this feature isn't really noticeable but on Rails it's very noticeable how slow this can be. This PR aims to speed up two parts of the functionality. 1) The Rust exit recording code Instead of adding all samples as we see them to the yjit_raw_samples and yjit_line_samples, we can increment the counter on the ones we've seen before. This will be faster on traces where we are hitting the same stack often. In a crude measurement of booting just the active record base test (`test/cases/base_test.rb`) we found that this improved the speed by 1 second. This also results in a smaller marshal dump file which sped up the test boot time by 4 seconds with trace exits on. 2) The Ruby parsing code Previously we were allocating new arrays using `shift` and `each_with_index`. This change avoids allocating new arrays by using an index. This change saves us the most amount of time, gaining 11 seconds. Before this change the test boot time took 62 seconds, after it took 47 seconds. This is still too long but it's a step closer to faster functionality. Next we're going to tackle allowing you to collect trace exits for a specific instruction. There is also some potential slowness in the GC code that I'd like to take a second look at. Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org> Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
Diffstat (limited to 'yjit.rb')
-rw-r--r--yjit.rb45
1 files changed, 26 insertions, 19 deletions
diff --git a/yjit.rb b/yjit.rb
index 15c84d0c61..226f2a8134 100644
--- a/yjit.rb
+++ b/yjit.rb
@@ -41,16 +41,11 @@ module RubyVM::YJIT
frames = results[:frames].dup
samples_count = 0
- frames.each do |frame_id, frame|
- frame[:samples] = 0
- frame[:edges] = {}
- end
-
# Loop through the instructions and set the frame hash with the data.
# We use nonexistent.def for the file name, otherwise insns.def will be displayed
# and that information isn't useful in this context.
RubyVM::INSTRUCTION_NAMES.each_with_index do |name, frame_id|
- frame_hash = { samples: 0, total_samples: 0, edges: {}, name: name, file: "nonexistent.def", line: nil }
+ frame_hash = { samples: 0, total_samples: 0, edges: {}, name: name, file: "nonexistent.def", line: nil, lines: {} }
results[:frames][frame_id] = frame_hash
frames[frame_id] = frame_hash
end
@@ -58,12 +53,22 @@ module RubyVM::YJIT
# Loop through the raw_samples and build the hashes for StackProf.
# The loop is based off an example in the StackProf documentation and therefore
# this functionality can only work with that library.
- while raw_samples.length > 0
- stack_trace = raw_samples.shift(raw_samples.shift + 1)
- lines = line_samples.shift(line_samples.shift + 1)
+ #
+ # Raw Samples:
+ # [ length, frame1, frame2, frameN, ..., instruction, count
+ #
+ # Line Samples
+ # [ length, line_1, line_2, line_n, ..., dummy value, count
+ i = 0
+ while i < raw_samples.length
+ stack_length = raw_samples[i] + 1
+ i += 1 # consume the stack length
+
prev_frame_id = nil
+ stack_length.times do |idx|
+ idx += i
+ frame_id = raw_samples[idx]
- stack_trace.each_with_index do |frame_id, idx|
if prev_frame_id
prev_frame = frames[prev_frame_id]
prev_frame[:edges][frame_id] ||= 0
@@ -71,26 +76,28 @@ module RubyVM::YJIT
end
frame_info = frames[frame_id]
- frame_info[:total_samples] ||= 0
frame_info[:total_samples] += 1
- frame_info[:lines] ||= {}
- frame_info[:lines][lines[idx]] ||= [0, 0]
- frame_info[:lines][lines[idx]][0] += 1
+ frame_info[:lines][line_samples[idx]] ||= [0, 0]
+ frame_info[:lines][line_samples[idx]][0] += 1
prev_frame_id = frame_id
end
- top_frame_id = stack_trace.last
+ i += stack_length # consume the stack
+
+ top_frame_id = prev_frame_id
top_frame_line = 1
- frames[top_frame_id][:samples] += 1
+ sample_count = raw_samples[i]
+
+ frames[top_frame_id][:samples] += sample_count
frames[top_frame_id][:lines] ||= {}
frames[top_frame_id][:lines][top_frame_line] ||= [0, 0]
- frames[top_frame_id][:lines][top_frame_line][1] += 1
+ frames[top_frame_id][:lines][top_frame_line][1] += sample_count
- samples_count += raw_samples.shift
- line_samples.shift
+ samples_count += sample_count
+ i += 1
end
results[:samples] = samples_count