-
Notifications
You must be signed in to change notification settings - Fork 226
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
Merge integration to master version 0.9.7 #790
Merged
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
…-query (#741) QuerySession object can now be used to store per-query lock state, trace information etc.
Preparing to guard block memory reclaims with shard level locks. This PR just introduces shared/read locks. Subsequent PRs will introduce write locks.
Since raw data retention is finite (say 3 days), long lookback queries ( > 3d) cannot be handled by raw cluster. They end up being delegated to downsample cluster. However, there is a delay in population of downsample data. Most recent data would not be available immediately. Hence window aggregations for latest time instants may not be complete. This PR omits instants with incomplete window aggregations from query results. We will consider performant window aggregations across raw/downsample clusters for the future. The thinking here is that WoW and MoM comparisons can wait for 6-12 hours. Instant queries can apply offset of 6 or 12 hours depending on delay.
We now estimate data size based on schema, sample size, time range and block queries that go beyond limit. The user guidance if this occurs is to reduce time range, or number of time series queried.
…ies (#765) Allows us to simulate the case where data is spread over many shards, and explore query issues with that setup
Merge develop to integration 0.9.7
… downsampled data (#770) Other fixes: * Also fixing DownsampleMainSpec to use synthetic timestamps to bypass Query Planner restriction on data TTL * Fixed timeout check to reply with QueryError instead of failing actor
For full-odp, PK bytes is looked up using Lucene. However, BytesRef length was not being taken into consideration when formulating Part Key on-heap byte array. This fix does a copy of the array taking length into consideration.
Merge develop to integration 0.9.7 Take 3
fix(memory,core) Add a Latch class and use it instead of StampedLock.
It is possible to miss metrics from FiloDB since any shutdown may miss metrics from the last time interval. This commit adds shutdown hook to drain kamon metrics to reporters. Added to both server and spark jobs.
…ers when an exclusive request timed out.
fix(memory): Latch wasn't wasn't always waking up blocked shared wait…
…784) * Cardinality buster could not bust cardinality for a tag filter along with time range filter. This PR adds that capability. * Also add kamon init back for spark executors
…ers when an exclusive request timed out.
Cherry pick latch commits back to the develop branch
…eturn execPlan head in materialize when only one execPlan is present (#778)
* Removed additional monix task due to querySession.close and folded it into QueryActor inline. * Kamon instrumentation of query scheduler for metrics
Merge develop to integration 0.9.7 Take 3
tjackpaul
approved these changes
Jun 15, 2020
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.
thank you @broneill 👍
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.
No description provided.