fix: Path is not app limited if more data is available to transmit, with limits #1367
Conversation
This file contains 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
…mited # Conflicts: # quic/s2n-quic-core/src/recovery/congestion_controller.rs
…mited # Conflicts: # quic/s2n-quic-transport/src/recovery/manager.rs # quic/s2n-quic-transport/src/recovery/manager/tests.rs # quic/s2n-quic-transport/src/space/application.rs # quic/s2n-quic-transport/src/space/handshake.rs # quic/s2n-quic-transport/src/space/initial.rs
camshaft
reviewed
Jun 20, 2022
| self.delivered_bytes > app_limited_bytes | ||
| }) | ||
| { | ||
| // Clear app-limited field if bubble is ACKed and gone |
There was a problem hiding this comment.
It comes from the related delivery rate estimation draft RFC:
An application-limited phase starts when the sending application
requests to send new data, or the connection's retransmission
mechanisms decide to retransmit data, and the connection meets all of
the following conditions ...
If these conditions are all met then the sender has run out of data
to feed the network. This would effectively create a "bubble" of
idle time in the data pipeline.
This comment specifically is from the pseudocode: https://datatracker.ietf.org/doc/html/draft-cheng-iccrg-delivery-rate-estimation#section-3.3
camshaft
previously approved these changes
Jun 20, 2022
…mited # Conflicts: # quic/s2n-quic-transport/src/space/application.rs
camshaft
approved these changes
Jun 23, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Description of changes:
This change re-introduces the changes from #1326, with additional limits on the maximum size the congestion window can grow to.
From the original description:
The original change would allow the congestion window to grow significantly, even if sending was blocked by flow control. This happened because if the pacer interrupts sending at a moment when sending is momentarily not blocked by flow control (after more flow control credit is received, for example), we will not be considered app-limited, and any acknowledgements received will increase the window.
This change introduces a
bytes_in_flight_hivalue to the Cubic congestion controller that tracks the highest value ofbytes_in_flightseen since the last congestion event. The congestion window is not allowed to grow beyondbytes_in_flight_himultiplied by a multiplier (2.0 while in Slow Start and 1.5 in Congestion Avoidance).Testing:
Unit tests, tested on two EC2 hosts:
Before:
After:
Is this a refactor change? If so, how have you proved that the intended behavior hasn't changed? -->
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.