Slowness from prepareWantHaves

[whyrusleeping]

I'm seeing 'BroadcastWantHaves' from the peer manager showing up in profiles, spending time iterating maps inside of prepareBroadcastWantHaves. We can probably optimize this a bit

[welcome]

Thank you for submitting your first issue to this repository! A maintainer will be here shortly to triage and review.
In the meantime, please double-check that you have provided all the necessary information to make this process easy! Any information that can help save additional round trips is useful! We currently aim to give initial feedback within two business days. If this does not happen, feel free to leave a comment.
Please keep an eye on how this issue will be labeled, as labels give an overview of priorities, assignments and additional actions requested by the maintainers:

• "Priority" labels will show how urgent this is for the team.
• "Status" labels will show if this is ready to be worked on, blocked, or in progress.
• "Need" labels will indicate if additional input or analysis is required.

Finally, remember to use https://discuss.ipfs.io if you just need general support.

[whyrusleeping]

This is inside of filecoin, where pretty much every peer has every single object. So i imagine hundreds of peers are going to have the objects in question.

Additionally, it looks like we're making this whole map just to iterate over it in the caller. Maybe we can avoid these allocations somehow?

[dirkmc]

We were seeing some issues with that code path on the IPFS gateways. Do you have a pprof dump?

[dirkmc]

@whyrusleeping points out that we may be able to avoid a bunch of allocations by modifying prepareBroadcastWantHaves() to take a callback instead of returning a map

[Stebalien]

Make sure you're using sessions.

[dirkmc]

haha gave him that tip already :)