apache
[BanyanDB] Unified memory data structure and memory tracking
Search before asking
- [X] I had searched in the issues and found no similar feature requirement.
Description
Memory Data Structure
Memory management is an important part of databases, and a unified memory structure can better achieve memory management and read/write. At the same time, memory alignment and padding can be used to optimize performance.
Memory tracking
It is necessary to monitor the allocation and recycling of memory, and reasonable strategies can be made based on the usage of memory, such as canceling certain queries to avoid OOM situations, which greatly helps with the stability of the database.
Use case
No response
Related issues
No response
Are you willing to submit a pull request to implement this on your own?
- [ ] Yes I am willing to submit a pull request on my own!
Code of Conduct
- [X] I agree to follow this project's Code of Conduct
@hanahmily Please be clear about the milestone.
The only known key feature for 0.5 is new file structure to replace the kv system.
hi. Is there a specific project design document to understand this part of the work ？
hi. Is there a specific project design document to understand this part of the work ？
The project is in the dev stage, iterate fast by the initial team. The best way is getting started from reading the current project docs and codes first, and understand how it works with SkyWalking OPA/backend server.
General docs are available here, https://skywalking.apache.org/docs/skywalking-banyandb/next/readme/. But it doesn't include TODO and WIP things.
hi. Is there a specific project design document to understand this part of the work ？
The project is in the dev stage, iterate fast by the initial team. The best way is getting started from reading the current project docs and codes first, and understand how it works with SkyWalking OPA/backend server.
Thank you for your reply. I'll take a look at the code, see if I can help