Github user vanzin commented on the pull request:
https://github.com/apache/spark/pull/4155#issuecomment-71262056
> We do actually need the processing to be single threaded, as trying to
coordinate synchronization on the centralized arbitration logic is a bit of a
nightmare.
I'm not so convinced; you'd only have a conflict if two tasks are
concurrently asking to update the state of the same split ID. Otherwise, state
updates can happen in parallel.
e.g. if you know all the split IDs up front, you can initialize the data
structure to hold all the state; when a commit request arrives, you only lock
that particular state object. So requests that arrive for other split IDs can
be processed in parallel.
(If you don't know all the split IDs up front, you can use something simple
like `ConcurrentHashMap` or `ConcurrentSkipListMap` depending on what
performance characteristics you want.)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
