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

runtime: split data/bss into 4K chunks for scanning #8888

Open
dvyukov opened this Issue Oct 7, 2014 · 0 comments

Comments

Projects
None yet
2 participants
@dvyukov
Member

dvyukov commented Oct 7, 2014

If we split data/bss into 4K chunks, then it will improve parallelization of scanning
and make it more incremental (something we need for concurrent GC with GOMAXPROCS=1).
I've done it once, but it was reverted during precision changes.
When we have 1-bit/word pointer info, it will be trivial to restore:
1. Calculate number of 4K chunks.
2. Adjust scanning parfor boundary accordingly.
3. If a thread's parfor iteration index is data/bss scanning, it finds the relevant
piece of data/bass and relevant piece of data/bss pointer info and scans only that piece.

@rsc rsc added this to the Unplanned milestone Apr 10, 2015

@rsc rsc removed release-none labels Apr 10, 2015

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment