[draft] lib.blit: Introduce API for optimized "blitter" for Virtio-net DMA #711
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
This is a simple placeholder implementation for an optimized bit-blitting API.
Update the vhost-user code to perform Snabb<->VM memory copies via the lib.blit module. This allows experimental optimizations with local changes to the blit module. This essentially separates "virtio vring processing" and "virtio memory copies" into being two separate problems that can be profiled and optimized separately. This is work-in-progress: Care must be taken not to let the guest see that packets are available until the blit.barrier() operation has been executed and I think this will require moving the ring index updates.
|
Closed: action has moved to #719. |
takikawa
pushed a commit
to takikawa/snabb
that referenced
this pull request
Jan 16, 2017
lwaftr query selftest
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Outdated suggestions cannot be applied.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.
Just wanted to share this fun hack for a software blitter that I am working on in connection with #710.
The idea is to isolate the virtio-net memory copy operations from the rest of the vring processing so that they can be optimized separately. See the individual commit comments for more details.
I have started to experiment with writing an optimized batch-mode version of the blitter in assembler. The initial results are encouraging but it is early days yet and I don't know which aspects of the design are important. See gist for rough notes and code.
I started looking at this in the context of debugging #665.
If there is a suitable online betting site then I am willing to wager that a suitable blit subroutine will speed up the copy operations for Virtio-net by 2x - 4x 😄 because the performance we see with
memcpyseems nowhere near the capabilities of the processor.