On Wed, 17 Oct 2018 21:10:22 -0700 Mike Kravetz mike.kravetz@oracle.com wrote:
Some test systems were experiencing negative huge page reserve counts and incorrect file block counts. This was traced to /proc/sys/vm/drop_caches removing clean pages from hugetlbfs file pagecaches. When non-hugetlbfs explicit code removes the pages, the appropriate accounting is not performed.
This can be recreated as follows: fallocate -l 2M /dev/hugepages/foo echo 1 > /proc/sys/vm/drop_caches fallocate -l 2M /dev/hugepages/foo grep -i huge /proc/meminfo AnonHugePages: 0 kB ShmemHugePages: 0 kB HugePages_Total: 2048 HugePages_Free: 2047 HugePages_Rsvd: 18446744073709551615 HugePages_Surp: 0 Hugepagesize: 2048 kB Hugetlb: 4194304 kB ls -lsh /dev/hugepages/foo 4.0M -rw-r--r--. 1 root root 2.0M Oct 17 20:05 /dev/hugepages/foo
To address this issue, dirty pages as they are added to pagecache. This can easily be reproduced with fallocate as shown above. Read faulted pages will eventually end up being marked dirty. But there is a window where they are clean and could be impacted by code such as drop_caches. So, just dirty them all as they are added to the pagecache.
In addition, it makes little sense to even try to drop hugetlbfs pagecache pages, so disable calls to these filesystems in drop_caches code.
...
--- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -9,6 +9,7 @@ #include <linux/writeback.h> #include <linux/sysctl.h> #include <linux/gfp.h> +#include <linux/magic.h> #include "internal.h" /* A global variable is a bit ugly, but it keeps the code simple */ @@ -18,6 +19,12 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) { struct inode *inode, *toput_inode = NULL;
- /*
* It makes no sense to try and drop hugetlbfs page cache pages.*/- if (sb->s_magic == HUGETLBFS_MAGIC)
return;
Hardcoding hugetlbfs seems wrong here. There are other filesystems where it makes no sense to try to drop pagecache. ramfs and, errrr...
I'm struggling to remember which is the correct thing to test here. BDI_CAP_NO_WRITEBACK should get us there, but doesn't seem quite appropriate.