Merged
Conversation
AsyncCompressor is a stucture which implement the nonblock compress method, callers could compress this and then get the resulted data later. Of course, callers could directly wait for the compressor completed. Compression algorithm usually uses lots of helper data to speed compress, so here AsyncCompressor uses dedicated threads to help cache-affinity. Second, We want to make compression parallel with normal io logic. For example, any component receive data may not need to care the actual data and need to do some things with metadata. We could let metadata process parallel with data compression. Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
|
Awesome! Was Snappy your first choice, or I did I help motivate that? :) |
Member
|
This looks very reasonable to me! I'm not sure I see the value in the affinity (pinning compression/decompression to a core) since the data its operating on located who knows where in the system, and we're never going to be compressing and decompressing the same buffers in the same process (right?). |
Member
Author
|
Hmm, I think it's fine that we dont bind thread to cores |
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Member
Author
liewegas
added a commit
that referenced
this pull request
Jul 28, 2015
Wip compressor Reviewed-by: Sage Weil <sage@redhat.com>
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Compressor: Add compressor infrastructure for ceph
AsyncCompressor is a stucture which implement the nonblock compress method, callers could compress this and then get the resulted data later. Of course, callers could directly wait for the compressor completed.
Compression algorithm usually uses lots of helper data to speed compress, so here AsyncCompressor uses dedicated threads to help cache-affinity. Second, We want to make compression parallel with normal io logic. For example, any component receive data may not need to care the actual data and need to do some things with metadata. We could let metadata process parallel with data compression.