spcl / spcl/serverless-benchmarks
Shared objects in cloud storage
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 199
- Forks
- 105
- PR merge metrics
- No merged PRs in 30d
Description
Currently, we deploy all benchmark inputs once. While it makes perfect sense for some data (like ML model), for other inputs, it might make sense to duplicate other inputs. For example, if we plan 100 concurrent invocations, we can replicate the input image 100 times.
Similarly, we should cache and replicate inputs in NoSQL storage. Right now, we generate new input with different unique ID for every invocation. This needs to be cached and replicated, reusing across invocations.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing how benchmark inputs are deployed to cloud storage and how NoSQL inputs are generated for each invocation. The work is done when reusable inputs can be cached and replicated across concurrent invocations instead of being newly generated with unique IDs each time.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cloud, databases, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100