{{ message }}
Fixed timer cast-to-int crash causing incorrect benchmark.#1953
Merged
Conversation
Member
benjchristensen
added a commit
that referenced
this pull request
Dec 12, 2014
Fixed timer cast-to-int crash causing incorrect benchmark.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The perf benchmark uses a 1 millisecond timer to interfere with the serializing process. However, the original benchmark used
cast(Integer.class)which just simply throws an error on a long value thus terminating the whole serialization process almost immediately. What gets measured is how fast can the whole process restarted to fail again.With the fix, I get the following numbers:
Clearly, the serializedTwoStreamsSlightlyContended() shows that under a second, you can serialize two 1 millisecond sources.
For comparison with my latest endeavors, the custom WriterReaderPhaser + AtomicResizableArray + Fast-path queue drain with front check produces the following values:
(Mode: thrpt, Samples: 5)
A specialized two-way only striped custom WriterReaderPhaser produces these:
I'm not quite sure why
serializedTwoStreamsOneFastOneSlowis so low in my versions. My guess is that since they are lock-free, the timer's thread ends up shoveling the events more frequently than in the synchronized case (because it can sleep).