Skip to content
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

feat: .getMany: improve performance for many small blocks #163

Open
pgte opened this issue Jan 27, 2018 · 3 comments
Open

feat: .getMany: improve performance for many small blocks #163

pgte opened this issue Jan 27, 2018 · 3 comments
Assignees
Labels
kind/enhancement A net-new feature or improvement to an existing feature P1 High: Likely tackled by core team if no one steps up status/ready Ready to be worked

Comments

@pgte
Copy link
Contributor

pgte commented Jan 27, 2018

Currently, in peer-crdt, the latency of replication of logs is bound to the latency of getMany(cids) when the blocks are not present.

Also, I think we should create benchmarks to have a baseline we can try to improve on.

@pgte pgte self-assigned this Jan 27, 2018
@pgte pgte added kind/enhancement A net-new feature or improvement to an existing feature P1 High: Likely tackled by core team if no one steps up labels Jan 27, 2018
@daviddias daviddias added the status/ready Ready to be worked label Feb 19, 2018
@daviddias
Copy link
Member

@pgte what's the next step now that #164 is done?

@pgte
Copy link
Contributor Author

pgte commented Feb 19, 2018

Currently, the greatest blocker is the overhead of useless connections.
There's nothing obvious that can be done at this level for individual bitswap exchanges.
After connection management gets solved, my informed guess for the next candidate is overhead on resolving through DHT.

@daviddias daviddias changed the title getMany: improve performance for many small blocks feat: .getMany: improve performance for many small blocks May 30, 2018
@daviddias
Copy link
Member

daviddias commented May 30, 2018

The .getMany call is also needed for ipfs/js-ipfs#856. The next step is really augmenting the tests -- https://github.com/ipfs/js-ipfs-bitswap/blob/master/test/bitswap.js#L102-L150 -- and testing perf.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/enhancement A net-new feature or improvement to an existing feature P1 High: Likely tackled by core team if no one steps up status/ready Ready to be worked
Projects
None yet
Development

No branches or pull requests

2 participants