63492b8ddd
This is a backport of a collection of 12 upstream patches.
The main one being the switch to use a rwsem instead.
The next important one being the switch of the rwsem to be a
per filesystem lock instead of global.
See the individual patches for details. They did not require
much work or wiggling to get them applied.
They all come from Linus' tree and are easily located. As such
I have not modified their individual headers with upstream
commit ids.
Verification:
- two scripts, the concept behind them supplied by Vefa Bicakci.
The first one causes a lot of concurrent contention in sysfs.
The second script highlights how well systemd is also contending.
Run Script1 followed by Script2
Without this change, Script2 has timeouts and fails.
Script1:
for i in `seq 20`; do
(while :; do find /sys/fs/cgroup/ -type f -readable -print0 \
2>/dev/null | xargs -0 -n 20 -r cat >&/dev/null ; done) &
done
for i in `seq 10`; do
(while :; do systemd-run --scope -q sleep 0.5 >/dev/null; done) &
done
Script2:
while true; do
date -Is
/usr/bin/time -f %e systemctl enable -q lighttpd.service ||
break
/usr/bin/time -f %e systemctl disable -q lighttpd.service ||
break
/usr/bin/time -f %e systemctl restart -q lighttpd.service ||
break
sleep 0.5 || break
done
- also soak testing to ensure that these patches don't introduce issues
Partial-Bug: 2016028
Signed-off-by: Jim Somerville <jim.somerville@windriver.com>
Change-Id: I6ad64cd7c90f756c6eb904065febfeb516e73009
120 lines
3.4 KiB
Diff
120 lines
3.4 KiB
Diff
From 1952b6d3b026943f0d922c9f8e7bf13b1f0c08f2 Mon Sep 17 00:00:00 2001
|
|
From: Ian Kent <raven@themaw.net>
|
|
Date: Fri, 16 Jul 2021 17:28:24 +0800
|
|
Subject: [PATCH] kernfs: use VFS negative dentry caching
|
|
|
|
If there are many lookups for non-existent paths these negative lookups
|
|
can lead to a lot of overhead during path walks.
|
|
|
|
The VFS allows dentries to be created as negative and hashed, and caches
|
|
them so they can be used to reduce the fairly high overhead alloc/free
|
|
cycle that occurs during these lookups.
|
|
|
|
Use the kernfs node parent revision to identify if a change has been
|
|
made to the containing directory so that the negative dentry can be
|
|
discarded and the lookup redone.
|
|
|
|
Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
|
|
Signed-off-by: Ian Kent <raven@themaw.net>
|
|
Link: https://lore.kernel.org/r/162642770420.63632.15791924970508867106.stgit@web.messagingengine.com
|
|
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Signed-off-by: Jim Somerville <jim.somerville@windriver.com>
|
|
---
|
|
fs/kernfs/dir.c | 55 +++++++++++++++++++++++++++++++------------------
|
|
1 file changed, 35 insertions(+), 20 deletions(-)
|
|
|
|
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
|
|
index 410fbbf797df..0bbd09af8520 100644
|
|
--- a/fs/kernfs/dir.c
|
|
+++ b/fs/kernfs/dir.c
|
|
@@ -1047,9 +1047,31 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
|
|
if (flags & LOOKUP_RCU)
|
|
return -ECHILD;
|
|
|
|
- /* Always perform fresh lookup for negatives */
|
|
- if (d_really_is_negative(dentry))
|
|
- goto out_bad_unlocked;
|
|
+ /* Negative hashed dentry? */
|
|
+ if (d_really_is_negative(dentry)) {
|
|
+ struct kernfs_node *parent;
|
|
+
|
|
+ /* If the kernfs parent node has changed discard and
|
|
+ * proceed to ->lookup.
|
|
+ */
|
|
+ mutex_lock(&kernfs_mutex);
|
|
+ spin_lock(&dentry->d_lock);
|
|
+ parent = kernfs_dentry_node(dentry->d_parent);
|
|
+ if (parent) {
|
|
+ if (kernfs_dir_changed(parent, dentry)) {
|
|
+ spin_unlock(&dentry->d_lock);
|
|
+ mutex_unlock(&kernfs_mutex);
|
|
+ return 0;
|
|
+ }
|
|
+ }
|
|
+ spin_unlock(&dentry->d_lock);
|
|
+ mutex_unlock(&kernfs_mutex);
|
|
+
|
|
+ /* The kernfs parent node hasn't changed, leave the
|
|
+ * dentry negative and return success.
|
|
+ */
|
|
+ return 1;
|
|
+ }
|
|
|
|
kn = kernfs_dentry_node(dentry);
|
|
mutex_lock(&kernfs_mutex);
|
|
@@ -1075,7 +1097,6 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
|
|
return 1;
|
|
out_bad:
|
|
mutex_unlock(&kernfs_mutex);
|
|
-out_bad_unlocked:
|
|
return 0;
|
|
}
|
|
|
|
@@ -1090,33 +1111,27 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
|
|
struct dentry *ret;
|
|
struct kernfs_node *parent = dir->i_private;
|
|
struct kernfs_node *kn;
|
|
- struct inode *inode;
|
|
+ struct inode *inode = NULL;
|
|
const void *ns = NULL;
|
|
|
|
mutex_lock(&kernfs_mutex);
|
|
-
|
|
if (kernfs_ns_enabled(parent))
|
|
ns = kernfs_info(dir->i_sb)->ns;
|
|
|
|
kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
|
|
-
|
|
- /* no such entry */
|
|
- if (!kn || !kernfs_active(kn)) {
|
|
- ret = NULL;
|
|
- goto out_unlock;
|
|
- }
|
|
-
|
|
/* attach dentry and inode */
|
|
- inode = kernfs_get_inode(dir->i_sb, kn);
|
|
- if (!inode) {
|
|
- ret = ERR_PTR(-ENOMEM);
|
|
- goto out_unlock;
|
|
+ if (kn && kernfs_active(kn)) {
|
|
+ inode = kernfs_get_inode(dir->i_sb, kn);
|
|
+ if (!inode)
|
|
+ inode = ERR_PTR(-ENOMEM);
|
|
}
|
|
-
|
|
- /* instantiate and hash dentry */
|
|
+ /* Needed only for negative dentry validation */
|
|
+ if (!inode)
|
|
+ kernfs_set_rev(parent, dentry);
|
|
+ /* instantiate and hash (possibly negative) dentry */
|
|
ret = d_splice_alias(inode, dentry);
|
|
- out_unlock:
|
|
mutex_unlock(&kernfs_mutex);
|
|
+
|
|
return ret;
|
|
}
|
|
|
|
--
|
|
2.25.1
|
|
|