-
Notifications
You must be signed in to change notification settings - Fork 411
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[DNM] Use Bitmap Filter to do MVCC in Normal Scan #6322
Conversation
[REVIEW NOTIFICATION] This pull request has been approved by:
To complete the pull request process, please ask the reviewers in the list to review by filling The full list of commands accepted by this bot can be found here. Reviewer can indicate their review by submitting an approval review. |
d48b688
to
9d177c1
Compare
1d94f16
to
1df5dc5
Compare
/rebuild |
bef1b32
to
2bb52a9
Compare
auto bitmap_filter = buildBitmapFilter( | ||
dm_context, | ||
segment_snap, | ||
data_ranges, | ||
filter, | ||
max_version, | ||
expected_block_size); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need to build bitmap filter each query? Maybe just one bitmap for one segment snapshot?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
accidentally approved……
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- If the snapshots of two queries are identical, they can share merge sort, but the changes may be large, I think it can be a further improvment.
- Since the timestamps of each query are different, it is difficult to merge the results of MVCC filtering.
- Another simple approach is to cache the bitmap so that the segment that is not written does not need to recompute the bitmap. It will be adopted in this PR soon.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Although the segment is not written, the filter and rowkey range may change, and it is still troublesome to use the cached bitmap.
/status LGT1 cancel |
@Lloyd-Pottiger: The label(s) In response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the ti-community-infra/tichi repository. |
/remove-approve |
08e51d6
to
821db1d
Compare
821db1d
to
900712f
Compare
fd6d136
to
2870428
Compare
2870428
to
d9f64e7
Compare
@JinheLin: PR needs rebase. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. |
What problem does this PR solve?
Issue Number: close #6296
Problem Summary:
What is changed and how it works?
Check List
Tests
Side effects
Documentation
Release note