diff mbox series

[v3] inotify: Increase default inotify.max_user_watches limit to 1048576

Message ID 20201029194256.7954-1-longman@redhat.com
State New
Headers show
Series [v3] inotify: Increase default inotify.max_user_watches limit to 1048576 | expand

Commit Message

Waiman Long Oct. 29, 2020, 7:42 p.m. UTC
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].

For 64-bit archs, inotify_inode_mark plus 2 vfs inode have a size that
is a bit over 1 kbytes (1284 bytes with my x86-64 config).  That means
a 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.

[v3: increase inotify watch cost as suggested by Amir and Honza]

Signed-off-by: Waiman Long <longman@redhat.com>
---
 fs/notify/inotify/inotify_user.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

Comments

Jan Kara Oct. 30, 2020, 10:57 a.m. UTC | #1
On Thu 29-10-20 15:42:56, Waiman Long wrote:
> 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].
> 
> For 64-bit archs, inotify_inode_mark plus 2 vfs inode have a size that
> is a bit over 1 kbytes (1284 bytes with my x86-64 config).  That means
> a 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.
> 
> [v3: increase inotify watch cost as suggested by Amir and Honza]
> 
> Signed-off-by: Waiman Long <longman@redhat.com>

Overall this looks fine. Some remaining nits below.

> diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
> index 186722ba3894..f8065eda3a02 100644
> --- 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 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
>   */
>  static int __init inotify_user_setup(void)
>  {
> +	unsigned int watches_max;
> +	struct sysinfo si;
> +
> +	si_meminfo(&si);
> +	/*
> +	 * Allow up to 1% of addressible memory to be allocated for inotify
			     ^^^^ addressable

> +	 * watches (per user) limited to the range [8192, 1048576].
> +	 */
> +	watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
> +			INOTIFY_WATCH_COST;
			^^^ So for machines with > 1TB of memory
watches_max would overflow. So you probably need to use ulong for that.


> +	watches_max = min(1048576U, max(watches_max, 8192U));
			^^^ use clamp() here?

								Honza
Waiman Long Nov. 9, 2020, 2:17 a.m. UTC | #2
On 10/30/20 6:57 AM, Jan Kara wrote:
> On Thu 29-10-20 15:42:56, Waiman Long wrote:
>> 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].
>>
>> For 64-bit archs, inotify_inode_mark plus 2 vfs inode have a size that
>> is a bit over 1 kbytes (1284 bytes with my x86-64 config).  That means
>> a 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.
>>
>> [v3: increase inotify watch cost as suggested by Amir and Honza]
>>
>> Signed-off-by: Waiman Long <longman@redhat.com>
> Overall this looks fine. Some remaining nits below.
>
>> diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
>> index 186722ba3894..f8065eda3a02 100644
>> --- 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 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
>>    */
>>   static int __init inotify_user_setup(void)
>>   {
>> +	unsigned int watches_max;
>> +	struct sysinfo si;
>> +
>> +	si_meminfo(&si);
>> +	/*
>> +	 * Allow up to 1% of addressible memory to be allocated for inotify
> 			     ^^^^ addressable
>
>> +	 * watches (per user) limited to the range [8192, 1048576].
>> +	 */
>> +	watches_max = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
>> +			INOTIFY_WATCH_COST;
> 			^^^ So for machines with > 1TB of memory
> watches_max would overflow. So you probably need to use ulong for that.
>
>
>> +	watches_max = min(1048576U, max(watches_max, 8192U));
> 			^^^ use clamp() here?

Yes, it will be easier to read to use clamp() here. Will send out v4 
withat those changes.

Thanks,
Longman
diff mbox series

Patch

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 186722ba3894..f8065eda3a02 100644
--- 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 @@  SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
  */
 static int __init inotify_user_setup(void)
 {
+	unsigned int watches_max;
+	struct sysinfo si;
+
+	si_meminfo(&si);
+	/*
+	 * Allow up to 1% of addressible 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 = min(1048576U, max(watches_max, 8192U));
+
 	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;
 }