Mv write sizing #132
Merged
Mv write sizing #132
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
added 2 commits
May 3, 2014 14:27
…ted option from github user licenser. Fix all unit tests.
|
|
||
| if (NULL!=options) | ||
| { | ||
| // large buffers, try for a little bit bigger than half hoping |
There was a problem hiding this comment.
This code is the same as in db/builder.cc. Can it be abstracted to it's own function?
There was a problem hiding this comment.
AARGH! I missed this location. I thought there were 3 places that needed to call the function. You have found the 4th. Bad Matthew. Bad Bad Matthew. Yes I will substitute the call. Thank you for spotting this.
I did a copy/paste of the same code to multiple locations for proof of concept. Missed this one on the clean-up.
|
Besides my comment above, code looks good. Tests pass. |
…ave a good code reviewer. Thank you ajs.
|
👍 |
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Outdated suggestions cannot be applied.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.
All types of memory mapped files previously shared the same mapping size of 20Mbytes. This is wasteful for many files, especially the smaller files created by Riak's AAE feature. The waste is in two forms. First the full 20Mbytes is always reserved by leveldb's flexcache. This could lead to 2.5Gbytes of available memory being set aside unnecessarily for a node with 64 databases/vnodes/partitions. The second waste is in physical writes to disk. The entire 20Mbyte mapping is written to disk, then the file is resized smaller. Again, this is a heavy burden for small files.