From: "Darrick J. Wong" <djwong@kernel.org>
To: djwong@kernel.org
Cc: linux-xfs@vger.kernel.org
Subject: [PATCH 10/11] xfs: parallelize inode inactivation
Date: Wed, 10 Mar 2021 19:06:36 -0800 [thread overview]
Message-ID: <161543199635.1947934.2885924822578773349.stgit@magnolia> (raw)
In-Reply-To: <161543194009.1947934.9910987247994410125.stgit@magnolia>
From: Darrick J. Wong <djwong@kernel.org>
Split the inode inactivation work into per-AG work items so that we can
take advantage of parallelization.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_icache.c | 62 ++++++++++++++++++++++++++++++++++++++-------------
fs/xfs/xfs_mount.c | 3 ++
fs/xfs/xfs_mount.h | 4 ++-
fs/xfs/xfs_super.c | 1 -
4 files changed, 52 insertions(+), 18 deletions(-)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 594d340bbe37..d5f580b92e48 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -245,11 +245,13 @@ xfs_inode_clear_reclaim_tag(
/* Queue a new inode gc pass if there are inodes needing inactivation. */
static void
xfs_inodegc_queue(
- struct xfs_mount *mp)
+ struct xfs_perag *pag)
{
+ struct xfs_mount *mp = pag->pag_mount;
+
rcu_read_lock();
- if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_INACTIVE_TAG))
- queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work,
+ if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_INACTIVE_TAG))
+ queue_delayed_work(mp->m_gc_workqueue, &pag->pag_inodegc_work,
msecs_to_jiffies(xfs_inodegc_centisecs * 10));
rcu_read_unlock();
}
@@ -272,7 +274,7 @@ xfs_perag_set_inactive_tag(
spin_unlock(&mp->m_perag_lock);
/* schedule periodic background inode inactivation */
- xfs_inodegc_queue(mp);
+ xfs_inodegc_queue(pag);
trace_xfs_perag_set_inactive(mp, pag->pag_agno, -1, _RET_IP_);
}
@@ -2074,8 +2076,9 @@ void
xfs_inodegc_worker(
struct work_struct *work)
{
- struct xfs_mount *mp = container_of(to_delayed_work(work),
- struct xfs_mount, m_inodegc_work);
+ struct xfs_perag *pag = container_of(to_delayed_work(work),
+ struct xfs_perag, pag_inodegc_work);
+ struct xfs_mount *mp = pag->pag_mount;
int error;
/*
@@ -2095,25 +2098,44 @@ xfs_inodegc_worker(
xfs_err(mp, "inode inactivation failed, error %d", error);
sb_end_write(mp->m_super);
- xfs_inodegc_queue(mp);
+ xfs_inodegc_queue(pag);
}
-/* Force all queued inode inactivation work to run immediately. */
-void
-xfs_inodegc_force(
- struct xfs_mount *mp)
+/* Garbage collect all inactive inodes in an AG immediately. */
+static inline bool
+xfs_inodegc_force_pag(
+ struct xfs_perag *pag)
{
+ struct xfs_mount *mp = pag->pag_mount;
+
/*
* In order to reset the delay timer to run immediately, we have to
* cancel the work item and requeue it with a zero timer value. We
* don't care if the worker races with our requeue, because at worst
* we iterate the radix tree and find no inodes to inactivate.
*/
- if (!cancel_delayed_work(&mp->m_inodegc_work))
+ if (!cancel_delayed_work(&pag->pag_inodegc_work))
+ return false;
+
+ queue_delayed_work(mp->m_gc_workqueue, &pag->pag_inodegc_work, 0);
+ return true;
+}
+
+/* Force all queued inode inactivation work to run immediately. */
+void
+xfs_inodegc_force(
+ struct xfs_mount *mp)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+ bool queued = false;
+
+ for_each_perag_tag(mp, agno, pag, XFS_ICI_INACTIVE_TAG)
+ queued |= xfs_inodegc_force_pag(pag);
+ if (!queued)
return;
- queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work, 0);
- flush_delayed_work(&mp->m_inodegc_work);
+ flush_workqueue(mp->m_gc_workqueue);
}
/* Stop all queued inactivation work. */
@@ -2121,7 +2143,11 @@ void
xfs_inodegc_stop(
struct xfs_mount *mp)
{
- cancel_delayed_work_sync(&mp->m_inodegc_work);
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+
+ for_each_perag_tag(mp, agno, pag, XFS_ICI_INACTIVE_TAG)
+ cancel_delayed_work_sync(&pag->pag_inodegc_work);
}
/* Schedule deferred inode inactivation work. */
@@ -2129,5 +2155,9 @@ void
xfs_inodegc_start(
struct xfs_mount *mp)
{
- xfs_inodegc_queue(mp);
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+
+ for_each_perag_tag(mp, agno, pag, XFS_ICI_INACTIVE_TAG)
+ xfs_inodegc_queue(pag);
}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index cd015e3d72fc..a5963061485c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -127,6 +127,7 @@ __xfs_free_perag(
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
+ ASSERT(!delayed_work_pending(&pag->pag_inodegc_work));
ASSERT(atomic_read(&pag->pag_ref) == 0);
kmem_free(pag);
}
@@ -148,6 +149,7 @@ xfs_free_perag(
ASSERT(pag);
ASSERT(atomic_read(&pag->pag_ref) == 0);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
+ cancel_delayed_work_sync(&pag->pag_inodegc_work);
xfs_iunlink_destroy(pag);
xfs_buf_hash_destroy(pag);
call_rcu(&pag->rcu_head, __xfs_free_perag);
@@ -204,6 +206,7 @@ xfs_initialize_perag(
pag->pag_mount = mp;
spin_lock_init(&pag->pag_ici_lock);
INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
+ INIT_DELAYED_WORK(&pag->pag_inodegc_work, xfs_inodegc_worker);
INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
error = xfs_buf_hash_init(pag);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index ce00ad47b8ea..835c07d00cd7 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -177,7 +177,6 @@ typedef struct xfs_mount {
uint64_t m_resblks_avail;/* available reserved blocks */
uint64_t m_resblks_save; /* reserved blks @ remount,ro */
struct delayed_work m_reclaim_work; /* background inode reclaim */
- struct delayed_work m_inodegc_work; /* background inode inactive */
struct xfs_kobj m_kobj;
struct xfs_kobj m_error_kobj;
struct xfs_kobj m_error_meta_kobj;
@@ -370,6 +369,9 @@ typedef struct xfs_perag {
/* background prealloc block trimming */
struct delayed_work pag_blockgc_work;
+ /* background inode inactivation */
+ struct delayed_work pag_inodegc_work;
+
/* reference count */
uint8_t pagf_refcount_level;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 8d0142487fc7..566e5657c1b0 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1879,7 +1879,6 @@ static int xfs_init_fs_context(
mutex_init(&mp->m_growlock);
INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
- INIT_DELAYED_WORK(&mp->m_inodegc_work, xfs_inodegc_worker);
mp->m_kobj.kobject.kset = xfs_kset;
/*
* We don't create the finobt per-ag space reservation until after log
next prev parent reply other threads:[~2021-03-11 3:07 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-11 3:05 [PATCHSET v3 00/11] xfs: deferred inode inactivation Darrick J. Wong
2021-03-11 3:05 ` [PATCH 01/11] xfs: prevent metadata files from being inactivated Darrick J. Wong
2021-03-11 13:05 ` Christoph Hellwig
2021-03-22 23:13 ` Dave Chinner
2021-03-11 3:05 ` [PATCH 02/11] xfs: refactor the predicate part of xfs_free_eofblocks Darrick J. Wong
2021-03-11 13:09 ` Christoph Hellwig
2021-03-15 18:46 ` Christoph Hellwig
2021-03-18 4:33 ` Darrick J. Wong
2021-03-19 1:48 ` Darrick J. Wong
2021-03-11 3:05 ` [PATCH 03/11] xfs: don't reclaim dquots with incore reservations Darrick J. Wong
2021-03-15 18:29 ` Christoph Hellwig
2021-03-22 23:31 ` Dave Chinner
2021-03-23 0:01 ` Darrick J. Wong
2021-03-23 1:48 ` Dave Chinner
2021-03-11 3:06 ` [PATCH 04/11] xfs: decide if inode needs inactivation Darrick J. Wong
2021-03-15 18:47 ` Christoph Hellwig
2021-03-15 19:06 ` Darrick J. Wong
2021-03-11 3:06 ` [PATCH 05/11] xfs: rename the blockgc workqueue Darrick J. Wong
2021-03-15 18:49 ` Christoph Hellwig
2021-03-11 3:06 ` [PATCH 06/11] xfs: deferred inode inactivation Darrick J. Wong
2021-03-16 7:27 ` Christoph Hellwig
2021-03-16 15:47 ` Darrick J. Wong
2021-03-17 15:21 ` Christoph Hellwig
2021-03-17 15:49 ` Darrick J. Wong
2021-03-22 23:46 ` Dave Chinner
2021-03-22 23:37 ` Dave Chinner
2021-03-23 0:24 ` Darrick J. Wong
2021-03-23 1:44 ` Dave Chinner
2021-03-23 4:00 ` Darrick J. Wong
2021-03-23 5:19 ` Dave Chinner
2021-03-24 2:04 ` Darrick J. Wong
2021-03-24 4:57 ` Dave Chinner
2021-03-25 4:20 ` Darrick J. Wong
2021-03-24 17:53 ` Christoph Hellwig
2021-03-25 4:26 ` Darrick J. Wong
2021-03-11 3:06 ` [PATCH 07/11] xfs: expose sysfs knob to control inode inactivation delay Darrick J. Wong
2021-03-11 3:06 ` [PATCH 08/11] xfs: force inode inactivation and retry fs writes when there isn't space Darrick J. Wong
2021-03-15 18:54 ` Christoph Hellwig
2021-03-15 19:06 ` Darrick J. Wong
2021-03-11 3:06 ` [PATCH 09/11] xfs: force inode garbage collection before fallocate when space is low Darrick J. Wong
2021-03-11 3:06 ` Darrick J. Wong [this message]
2021-03-15 18:55 ` [PATCH 10/11] xfs: parallelize inode inactivation Christoph Hellwig
2021-03-15 19:03 ` Darrick J. Wong
2021-03-23 22:21 ` Dave Chinner
2021-03-24 3:52 ` Darrick J. Wong
2021-03-11 3:06 ` [PATCH 11/11] xfs: create a polled function to force " Darrick J. Wong
2021-03-23 22:31 ` Dave Chinner
2021-03-24 3:34 ` Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=161543199635.1947934.2885924822578773349.stgit@magnolia \
--to=djwong@kernel.org \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).