inotify: Increase default inotify.max_user_watches limit to 1048576

The default value of inotify.max_user_watches sysctl parameter was set
to 8192 since the introduction of the inotify feature in 2005 by
commit 0eeca28300df ("[PATCH] inotify"). Today this value is just too
small for many modern usage. As a result, users have to explicitly set
it to a larger value to make it work.

After some searching around the web, these are the
inotify.max_user_watches values used by some projects:
 - vscode:  524288
 - dropbox support: 100000
 - users on stackexchange: 12228
 - lsyncd user: 2000000
 - code42 support: 1048576
 - monodevelop: 16384
 - tectonic: 524288
 - openshift origin: 65536

Each watch point adds an inotify_inode_mark structure to an inode to
be watched. It also pins the watched inode.

Modeled after the epoll.max_user_watches behavior to adjust the default
value according to the amount of addressable memory available, make
inotify.max_user_watches behave in a similar way to make it use no more
than 1% of addressable memory within the range [8192, 1048576].

We estimate the amount of memory used by inotify mark to size of
inotify_inode_mark plus two times the size of struct inode (we double
the inode size to cover the additional filesystem private inode part).
That means that a 64-bit system with 128GB or more memory will likely
have the maximum value of 1048576 for inotify.max_user_watches. This
default should be big enough for most use cases.

Link: https://lore.kernel.org/r/20201109035931.4740-1-longman@redhat.com
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 186722b..24d1702 100644 (file)
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -37,6 +37,15 @@
 
 #include <asm/ioctls.h>
 
+/*
+ * An inotify watch requires allocating an inotify_inode_mark structure as
+ * well as pinning the watched inode. Doubling the size of a VFS inode
+ * should be more than enough to cover the additional filesystem inode
+ * size increase.
+ */
+#define INOTIFY_WATCH_COST     (sizeof(struct inotify_inode_mark) + \
+                                2 * sizeof(struct inode))
+
 /* configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_queued_events __read_mostly;
 
@@ -801,6 +810,18 @@ out:
  */
 static int __init inotify_user_setup(void)
 {
+       unsigned long watches_max;
+       struct sysinfo si;
+
+       si_meminfo(&si);
+       /*
+        * Allow up to 1% of addressable memory to be allocated for inotify
+        * watches (per user) limited to the range [8192, 1048576].
+        */
+       watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+                       INOTIFY_WATCH_COST;
+       watches_max = clamp(watches_max, 8192UL, 1048576UL);
+
        BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
        BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
        BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
@@ -827,7 +848,7 @@ static int __init inotify_user_setup(void)
 
        inotify_max_queued_events = 16384;
        init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
-       init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192;
+       init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max;
 
        return 0;
 }