mirrors/scoutfs
1
0
Fork 0
mirror of https://github.com/versity/scoutfs.git synced 2026-01-07 04:26:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Align first free ino to lock group

Browse Source 
Currently the first inode number that can be allocated directly follows
the root inode.  This means the first batch of allocated inodes are in
the same lock group as the root inode.

The root inode is a bit special.  It is always hot as absolute path
lookups and inode-to-path resolution always read directory entries from
the root.

Let's try aligning the first free inode number to the next inode lock
group boundary.  This will stop work in those inodes from necessarily
conflicting with work in the root inode.

Signed-off-by: Zach Brown <zab@versity.com>
This commit is contained in:
Zach Brown
2021-05-05 14:43:46 -07:00
parent b0a08eb922
commit 36fcc4665d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
utils/src/mkfs.c
View File

@@ -238,7 +238,7 @@ static int do_mkfs(struct mkfs_args *args)
memset(super, 0, SCOUTFS_BLOCK_SM_SIZE);
super->version = cpu_to_le64(SCOUTFS_INTEROP_VERSION);
uuid_generate(super->uuid);
super->next_ino = cpu_to_le64(SCOUTFS_ROOT_INO + 1);
super->next_ino = cpu_to_le64(round_up(SCOUTFS_ROOT_INO + 1, SCOUTFS_LOCK_INODE_GROUP_NR));
super->seq = cpu_to_le64(1);
super->total_meta_blocks = cpu_to_le64(last_meta + 1);
super->total_data_blocks = cpu_to_le64(last_data + 1);