MGLRU & Maple Tree Miss Out On Linux 6.0 But Will Aim For Linux 6.1
We have been looking quite forward to MGLRU being mainlined since it's already widely-used by Google with Chrome OS and Android with showing very promising performance results. MGLRU overhauls the handling for Linux's page reclamation code and makes it much faster. The benchmark results are looking great and there was hope it would be merged for Linux 6.0, but alas now it's clear it will not make this two week merge window.
Merging MGLRU is held up by the Maple Tree data structure being ready for merging. Maple Tree can also help with Linux performance and has been worked on for a while now by Oracle.
Veteran Linux developer Andrew Morton sent in the memory management related changes on Wednesday for the Linux 6.0 merge window. In that pull request he commented:
"Liam's maple tree rework didn't make it. This has resulted in a few other minor patch series being held over for next time.
Multi-gen LRU still isn't merged as we were waiting for mapletree to stabilize. The current plan is to merge MGLRU into -mm soon and to later reintroduce mapletree, with a view to hopefully getting both into 5.21-rc1."
Linux 6.1 will be the next version of the kernel with Linus having decided to rename what would be Linux 5.20 to 6.0.
As for what did make it in the "MM" changes for Linux 6.0, there is continued work by Amazon on the DAMON data access monitoring, a vmalloc speed-up, continued memory folios conversion work, Huge TLB optimizations, coherent device memory mapping enhancements, and other improvements.