RFC pseudo-interleaving NUMA placement
Get series with b4
b4 am [email protected]Versions newest first
- v1 RFC Latest4 patches 0 repliesNew
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/4 | remove p->numa_migrate_deferredinclude/ kernel/ kernel/ +1 more | +0 | 0 replies | |
| 2/4 | track from which nodes NUMA faults are triggeredinclude/ kernel/ | +31 | 0 replies | |
| 3/4 | build per numa_group active node mask from faults_from statisticskernel/ | +33 | 0 replies | |
| 4/4 | use active_nodes nodemask to decide on numa migrationsinclude/ kernel/ mm/ | +48 | 0 replies |
Reviews trailers per patch
None of the 4 patches has a Reviewed-by or Acked-by.
| Patch | Rik van Riel |
|---|---|
| 1/4 | |
| 2/4 | |
| 3/4 | |
| 4/4 | Not-yet-signed-off-by |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [RFC PATCH 0/4] pseudo-interleaving NUMA placement
This patch set attempts to implement a pseudo-interleaving policy for workloads that do not fit in one NUMA node.
For each NUMA group, we track the NUMA nodes on which the workload is actively running, and try to concentrate the memory on those NUMA nodes.
Unfortunately, the scheduler appears to move tasks around quite a bit, leading to nodes being dropped from the "active nodes" mask, and re-added a little later, causing excessive memory migration.
I am not sure how to solve that. Hopefully somebody will have an idea :)
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>