Comments (2)
Interestingly, all of the terminated calls appear to be stuck on the isDirectory
logic. This may necessitate reworking this logic so we either don't need to check if it's a directory first, or making the directory check faster.
from astra.
This appears to be an issue with the current blobfs design, as it heavily relies on the assumption that the object store functions with directory-style functionality. This is a problem because S3 does have a traditional understanding of "folders" so attempting to operate on "directory" or "folder" level operations gets extremely slow with the larger amount of files stored (due to many ListDirectory calls).
Amazon does recommend using a secondary index if you are attempting to perform operations like this.
Our recommended path is probably to replace the existing blobfs design to one that doesn't rely on directory discovery, storing the specific file assets. This will require moving the SnapshotMetadata to store the exact list of files as well.
from astra.
Related Issues (20)
- [BUG] ZipkinService: when duration field is an int, creating a zipkin response fails because of the cast to Long
- Add continous benchmarking to Github actions
- Avoid restart indexer due to broker partition leadership change HOT 2
- Indexer couldn't find all previous metadata snapshots
- ZK session expiry shuts down Astra. Don't make ZK updates in the shutdown path HOT 1
- Recovery tasks can create excessively large chunks, resulting in out of disk HOT 2
- Add cache autoscaler configuration options
- Restarting cache nodes can exhaust disk space HOT 1
- Cache node should gracefully handle over-provisioned LRU cache configs HOT 1
- Add shard request caching HOT 1
- Add redaction to protobuf definitions to prevent PII logging HOT 2
- Add disaster recovery option for Zookeeper cluster loss HOT 1
- Split admin ports from application ports HOT 1
- [BUG] UnsupportedClassVersionError using docker run
- [FEATURE] Support Opensearch API HOT 1
- Indexers should rollover after a maximum fixed time HOT 1
- Indexers should be tolerant of a Kafka broker offset rollback
- `min_doc_count` isn't respected outside of histogram aggregations HOT 2
- Update @allcontributors references HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from astra.