Skip to content
This repository was archived by the owner on Dec 13, 2023. It is now read-only.

Conversation

@jsteemann
Copy link
Contributor

@jsteemann jsteemann added this to the 3.10 milestone May 31, 2022
@jsteemann jsteemann requested a review from a team May 31, 2022 10:35
Copy link
Contributor

@markuspf markuspf left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM (mod typos) as general documentation;

At some point we might need to write sizing-guidelines or put more detail in places.

For example it is clear to me that the max/min parallelism settings limit each individual pregel job; this does not limit how many cores might be used by the pregel subsystem as a whole.

Also memory mapped files do not cause any overhead as long as data still fits in ram, because nothing is actually written to disk, but as soon as data does go to disk this has performance implications. (the extent of which we cannot give right now because we don't know)

@joerg84 joerg84 requested a review from ansoboleva May 31, 2022 18:20
Copy link
Collaborator

@ansoboleva ansoboleva left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

reviewed

@ansoboleva ansoboleva merged commit 76d000d into main Jun 1, 2022
@ansoboleva ansoboleva deleted the feature/add-pregel-configurability branch June 1, 2022 18:26
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

4 participants