summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_acl.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2019-08-29 19:04:10 +0300
committerDarrick J. Wong <darrick.wong@oracle.com>2019-08-31 08:43:57 +0300
commitddbca70cc45c0ac97ff6d9529e45f10b8ae73ad4 (patch)
tree3bcb0529a2dedaf5a548cfdcf56ab69a3acd3728 /fs/xfs/xfs_acl.c
parent9df243a1a9e607e7cf5d20ee46edd5ec84b7e400 (diff)
downloadlinux-ddbca70cc45c0ac97ff6d9529e45f10b8ae73ad4.tar.xz
xfs: allocate xattr buffer on demand
When doing file lookups and checking for permissions, we end up in xfs_get_acl() to see if there are any ACLs on the inode. This requires and xattr lookup, and to do that we have to supply a buffer large enough to hold an maximum sized xattr. On workloads were we are accessing a wide range of cache cold files under memory pressure (e.g. NFS fileservers) we end up spending a lot of time allocating the buffer. The buffer is 64k in length, so is a contiguous multi-page allocation, and if that then fails we fall back to vmalloc(). Hence the allocation here is /expensive/ when we are looking up hundreds of thousands of files a second. Initial numbers from a bpf trace show average time in xfs_get_acl() is ~32us, with ~19us of that in the memory allocation. Note these are average times, so there are going to be affected by the worst case allocations more than the common fast case... To avoid this, we could just do a "null" lookup to see if the ACL xattr exists and then only do the allocation if it exists. This, however, optimises the path for the "no ACL present" case at the expense of the "acl present" case. i.e. we can halve the time in xfs_get_acl() for the no acl case (i.e down to ~10-15us), but that then increases the ACL case by 30% (i.e. up to 40-45us). To solve this and speed up both cases, drive the xattr buffer allocation into the attribute code once we know what the actual xattr length is. For the no-xattr case, we avoid the allocation completely, speeding up that case. For the common ACL case, we'll end up with a fast heap allocation (because it'll be smaller than a page), and only for the rarer "we have a remote xattr" will we have a multi-page allocation occur. Hence the common ACL case will be much faster, too. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Diffstat (limited to 'fs/xfs/xfs_acl.c')
-rw-r--r--fs/xfs/xfs_acl.c12
1 files changed, 4 insertions, 8 deletions
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 86c0697870a5..96d7071cfa46 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -112,7 +112,7 @@ xfs_get_acl(struct inode *inode, int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct posix_acl *acl = NULL;
- struct xfs_acl *xfs_acl;
+ struct xfs_acl *xfs_acl = NULL;
unsigned char *ea_name;
int error;
int len;
@@ -135,12 +135,8 @@ xfs_get_acl(struct inode *inode, int type)
* go out to the disk.
*/
len = XFS_ACL_MAX_SIZE(ip->i_mount);
- xfs_acl = kmem_zalloc_large(len, 0);
- if (!xfs_acl)
- return ERR_PTR(-ENOMEM);
-
- error = xfs_attr_get(ip, ea_name, (unsigned char *)xfs_acl,
- &len, ATTR_ROOT);
+ error = xfs_attr_get(ip, ea_name, (unsigned char **)&xfs_acl, &len,
+ ATTR_ALLOC | ATTR_ROOT);
if (error) {
/*
* If the attribute doesn't exist make sure we have a negative
@@ -151,8 +147,8 @@ xfs_get_acl(struct inode *inode, int type)
} else {
acl = xfs_acl_from_disk(xfs_acl, len,
XFS_ACL_MAX_ENTRIES(ip->i_mount));
+ kmem_free(xfs_acl);
}
- kmem_free(xfs_acl);
return acl;
}