From: Darrick J. Wong <djwong@xxxxxxxxxx>
Allow administrators to control the length that we defer inode
inactivation. By default we'll set the delay to 100ms, 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@xxxxxxxxxx>
---
Documentation/admin-guide/xfs.rst | 7 +++++++
fs/xfs/xfs_globals.c | 5 +++++
fs/xfs/xfs_icache.c | 5 +++--
fs/xfs/xfs_linux.h | 1 +
fs/xfs/xfs_sysctl.c | 9 +++++++++
fs/xfs/xfs_sysctl.h | 1 +
6 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index f9b109bfc6a6..f095cfe7137f 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_ms
+ (Units: milliseconds Min: 0 Default: 100 Max: 3600000)
+ 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 f62fa652c2fd..64674f424ff8 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -28,6 +28,11 @@ xfs_param_t xfs_params = {
.rotorstep = { 1, 1, 255 },
.inherit_nodfrg = { 0, 1, 1 },
.fstrm_timer = { 1, 30*100, 3600*100},
+
+ /* Values below here are measured in milliseconds */
+ .inodegc_ms = { 0, 100, 3600*1000},
+
+ /* 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 17c4cd91ea15..ddf43a60a55c 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -245,8 +245,9 @@ xfs_inodegc_queue(
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_INODEGC_TAG)) {
- trace_xfs_inodegc_queue(mp, 0, _RET_IP_);
- queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work, 0);
+ trace_xfs_inodegc_queue(mp, xfs_inodegc_ms, _RET_IP_);
+ queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work,
+ msecs_to_jiffies(xfs_inodegc_ms));
}
rcu_read_unlock();
}
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 7688663b9773..e762762256e4 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_ms xfs_params.inodegc_ms.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..6495887f4f00 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -176,6 +176,15 @@ static struct ctl_table xfs_table[] = {
.extra1 = &xfs_params.fstrm_timer.min,
.extra2 = &xfs_params.fstrm_timer.max,
},
+ {
+ .procname = "inode_gc_delay_ms",
+ .data = &xfs_params.inodegc_ms.val,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &xfs_params.inodegc_ms.min,
+ .extra2 = &xfs_params.inodegc_ms.max
+ },
{
.procname = "speculative_prealloc_lifetime",
.data = &xfs_params.blockgc_timer.val,
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index 7692e76ead33..9a867b379a1f 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_ms; /* Inode inactivation scan interval */
} xfs_param_t;
/*
