XFS: Track reclaimable inodes in inode cache V2.
Get series with b4
b4 am [email protected]Versions newest first
- v1 Latest5 patches 0 repliesNew
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/5 | XFS: move inode reclaim functions to xfs_sync.cfs/ fs/ fs/ +1 more | +94 | 0 replies | |
| 2/5 | XFS: rename inode reclaim functionsfs/ fs/ fs/ +1 more | +9 | 0 replies | |
| 3/5 | XFS: mark inodes for reclaim via a tag in the inode radix treefs/ fs/ fs/ +2 more | +54 | 0 replies | |
| 4/5 | XFS: use the inode radix tree for reclaiming inodesfs/ | +71 | 0 replies | |
| 5/5 | XFS: kill deleted inodes listfs/ fs/ fs/ +5 more | +8 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [PATCH 0/5] XFS: Track reclaimable inodes in inode cache V2.
Move the tracking of reclaimable inodes into the inode radix trees. This currently does not replace the reclaim flags in the inode, rather it allows traversal of all reclaimable inodes by walking the per-AG inode radix trees without needing a separate list. This enables us to remove a struct list_head from the struct xfs_inode and the xfs_mount, as well as a filesystem global lock which also has the benefit of removing a point of serialisation during inode reclaim.
Like the matching sync code, this also allows reclaim of inodes in ascending inode numbers which substantially improves I/O patterns during reclaim driven inode flushing.
Version 2:
o reorder series to put all re-arrangement at the start
o rediff as prior patch set was updated