xfs: cache open zone in inode->i_private
PATCH v2 1/1 xfs: cache open zone in inode->i_private
The MRU cache for open zones is unfortunately still not ideal, as it can time out pretty easily when doing heavy I/O to hard disks using up most or all open zones. One option would be to just increase the timeout, but while looking into that I realized we're just better off caching it indefinitely as there is no real downside to that once we don't hold a reference to the cache open zone.
So switch the open zone to RCU freeing, and then stash the last used open zone into inode->i_private. This helps to significantly reduce fragmentation by keeping I/O localized to zones for workloads that write using many open files to HDD.
---
Changes since v1:
- keep the is_gc assert and update the comment for it
fs/xfs/xfs_mount.h | 1 - fs/xfs/xfs_super.c | 6 ++ fs/xfs/xfs_zone_alloc.c | 123 +++++++++++++--------------------------- fs/xfs/xfs_zone_priv.h | 2 + 4 files changed, 46 insertions(+), 86 deletions(-)
fs/xfs/xfs_mount.h +0 -1
@@ -236,7 +236,6 @@ typedef struct xfs_mount {bool m_update_sb;/* sb needs update in mount */ unsigned int m_max_open_zones;unsigned int m_zonegc_low_space; -struct xfs_mru_cache *m_zone_cache;/* Inode to open zone cache */ /* max_atomic_write mount option value */ unsigned long long m_awu_max_bytes;
fs/xfs/xfs_super.c +6 -0
@@ -786,6 +786,12 @@ xfs_fs_evict_inode(truncate_inode_pages_final (&inode->i_data);clear_inode (inode); + +if (IS_ENABLED (CONFIG_XFS_RT ) && +S_ISREG (inode->i_mode) && inode->i_private) { +xfs_open_zone_put (inode->i_private); + inode->i_private =NULL ; + } } static void
fs/xfs/xfs_zone_alloc.c +38 -85
190 lines not on this page · raw message
fs/xfs/xfs_zone_priv.h +2 -0
@@ -44,6 +44,8 @@ struct xfs_open_zone {* the life time of an open zone. */ struct xfs_rtgroup *oz_rtg; + +struct rcu_head oz_rcu; };/*
Signature · 1 line
2.47.3
Disregard this version, it was missing the fold of the comment update. I though I had stopped git-send-email before it went out, but that seems to have failed.