next: Changes queued for the v2015.08 release #981
Merged
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
# Conflicts: # src/program/snabbnfv/selftest.sh
Everyone has their own shell scripts to bind/unbind PCI cards. This patch adds a tool to consolidate the key options into Snabb.
…code...
- removed “alias” and “path” from core.shm
- added “register” and “{create,open,delete}_frame” to core.shm
- made core.counter API match create/open/delete interface
- registered core.counter and core.histogram with core.shm
- moved inline documentation of core.{shm,counter,histogram} to README.md
- update modules to use shm frame abstraction where sensible
Skip selftest if SNABB_PCI_INTEL1G0 is empty.
(cherry picked from commit 9746f24)
Setting the environment variable SNABB_SHM_KEEP to a non-empty string means that the shm directory will be kept after the process terminates. This can be useful for post-moretem inspection e.g. of counters, histograms, timeline logs.
Fixed merge conflicts from new debug vars
|
@eugeneia This release is good to go from my perspective. I updated the releases benchmark to include The full test matrix is harder to interpret... work in progress... I have some fixes to push that should have a big impact there (either for 2016.09 or 2016.08.1) by resolving most of the error cases. |
eugeneia
added a commit
that referenced
this pull request
Aug 3, 2016
dpino
pushed a commit
to dpino/snabb
that referenced
this pull request
Oct 2, 2017
Hopefully fixes snabbco#981.
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Outdated suggestions cannot be applied.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.
Here is some good stuff for v2016.08.
@eugeneia The one blocker I see is to resolve the counter-related performance regression that we introduced in v2016.07. Could be done either with optimization or with the minimum sufficient disabling of functionality. (Having the minimal difference that removes the problem would also make it easier for people to help with optimization because then there is a very clear A/B comparison to make.)
@eugeneia Sorry but I removed your branch from the Hydra jobset
snabb-new-tests/releases-lugano-small-20x. I want to keep this as a stable configuration that tests releases only. I think that for development you can define a new jobset that tests e.g.v2016.06(good) andv2016.07(bad) andmax-dev-branch(work in progress) and it should show you what you need to see.Then once you push to
max-nextthe changes will be benchmarked on thelukego/next-tributaryjobset. (This may even reuse the results of your run if nix detects from the sha256 hashes that the code on max-next has already been tested separately.)