xfs: expose sysfs knob to control inode inactivation delay

Allow administrators to control the length that we defer inode
inactivation.  By default we'll set the delay to 2 seconds, as an
arbitrary choice between allowing for some batching of a deltree
operation, and not letting too many inodes pile up in memory.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

6 files changed, 23 insertions, 1 deletions

diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index f9b109bfc6a6..9dd62b155fda 100644
--- a/Documentation/admin-guide/xfs.rst
+++ b/Documentation/admin-guide/xfs.rst
@@ -277,6 +277,13 @@ The following sysctls are available for the XFS filesystem:
 	references and returns timed-out AGs back to the free stream
 	pool.
 
+  fs.xfs.inode_gc_delay
+	(Units: centiseconds   Min: 0  Default: 1  Max: 360000)
+	The amount of time to delay cleanup work that happens after a file is
+	closed by all programs.  This involves clearing speculative
+	preallocations from linked files and freeing unlinked files.  A higher
+	value here increases batching at a risk of background work storms.
+
   fs.xfs.speculative_prealloc_lifetime
 	(Units: seconds   Min: 1  Default: 300  Max: 86400)
 	The interval at which the background scanning for inodes
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 8c082acb42fe..c5e8bbbcc863 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -28,6 +28,9 @@ xfs_param_t xfs_params = {
 	.rotorstep	= {	1,		1,		255	},
 	.inherit_nodfrg	= {	0,		1,		1	},
 	.fstrm_timer	= {	1,		30*100,		3600*100},
+	.inodegc_timer	= {	0,		1,		3600*100},
+
+	/* Values below here are measured in seconds */
 	.blockgc_timer	= {	1,		300,		3600*24},
 };
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a5e19db182e2..2dd02b8254fb 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -309,7 +309,8 @@ xfs_inodegc_queue(
 
 	rcu_read_lock();
 	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_INODEGC_TAG))
-		queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work, 0);
+		queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work,
+				msecs_to_jiffies(xfs_inodegc_centisecs * 10));
 	rcu_read_unlock();
 }
 
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index af6be9b9ccdf..b4c5a2c71f43 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -99,6 +99,7 @@ typedef __u32			xfs_nlink_t;
 #define xfs_inherit_nodefrag	xfs_params.inherit_nodfrg.val
 #define xfs_fstrm_centisecs	xfs_params.fstrm_timer.val
 #define xfs_blockgc_secs	xfs_params.blockgc_timer.val
+#define xfs_inodegc_centisecs	xfs_params.inodegc_timer.val
 
 #define current_cpu()		(raw_smp_processor_id())
 #define current_set_flags_nested(sp, f)		\
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 546a6cd96729..878f31d3a587 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -177,6 +177,15 @@ static struct ctl_table xfs_table[] = {
 		.extra2		= &xfs_params.fstrm_timer.max,
 	},
 	{
+		.procname	= "inode_gc_delay",
+		.data		= &xfs_params.inodegc_timer.val,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &xfs_params.inodegc_timer.min,
+		.extra2		= &xfs_params.inodegc_timer.max
+	},
+	{
 		.procname	= "speculative_prealloc_lifetime",
 		.data		= &xfs_params.blockgc_timer.val,
 		.maxlen		= sizeof(int),
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index c8ad129b42e7..ba019942655c 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -36,6 +36,7 @@ typedef struct xfs_param {
 	xfs_sysctl_val_t inherit_nodfrg;/* Inherit the "nodefrag" inode flag. */
 	xfs_sysctl_val_t fstrm_timer;	/* Filestream dir-AG assoc'n timeout. */
 	xfs_sysctl_val_t blockgc_timer;	/* Interval between blockgc scans */
+	xfs_sysctl_val_t inodegc_timer;	/* Inode inactivation scan interval */
 } xfs_param_t;
 
 /*