From: Chengguang Xu <cgxu519@icloud.com>
Date: Tue, 27 Feb 2018 13:49:44 +0800
Subject: ceph: mark the cap cache as unreclaimable
Git-commit: bc4b5ad3a6a1cfe11494380affc4bfc4521af499
Patch-mainline: v4.17-rc1
References: bsc#1089115
Releasing cap is affected by many factors (e.g., avail_count/reserve_count/min_count)
and min_count could be specified high volume in client mount option. Hence it's better
to mark cap cache as unreclaimable in case of non-trivial discrepancies between memory
shown as reclaimable and what is actually reclaimed.
Signed-off-by: Chengguang Xu <cgxu519@icloud.com>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Acked-by: Luis Henriques <lhenriques@suse.com>
---
fs/ceph/super.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -699,8 +699,7 @@ static int __init init_caches(void)
if (!ceph_inode_cachep)
return -ENOMEM;
- ceph_cap_cachep = KMEM_CACHE(ceph_cap,
- SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+ ceph_cap_cachep = KMEM_CACHE(ceph_cap, SLAB_MEM_SPREAD);
if (!ceph_cap_cachep)
goto bad_cap;
ceph_cap_flush_cachep = KMEM_CACHE(ceph_cap_flush,