Bugfix for the retrans-issue that stopped RDMA-writes at 8k: We now h… #86
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
…ave a ddr-write-access counter in rdma_mux_retrans that allows to split the incoming data stream in multiple MTU-sized bursts for writing to the retrans-memory in HBM.
bo3z
requested changes
Nov 15, 2024
bo3z
approved these changes
Nov 18, 2024
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Outdated suggestions cannot be applied.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.
The previous bug stopped RDMA-transmissions at 8k message size. The issue was in the retransmission-capability: On the command-interface, multiple commands for writing MTU-sized data chunks to the retrans memory are submitted, while the datastream has one single data chunk that has a size of multiple MTUs. Therefore, the data mover IP-core doesn't accept the incoming data and builds up backpressure.
This bugfix introduces a counter (cnt_ddr_wr) for successful write-beats to the retrans-memory and uses it to split up the data stream in multiple MTU-sized chunks by asserting a .tlast signal. The design change has been tested quite extensively, also with a packet dropper module and seems to work reasonably well.