From: "Darrick J. Wong" <djwong@kernel.org>
To: djwong@kernel.org
Cc: linux-xfs@vger.kernel.org, david@fromorbit.com, hch@infradead.org
Subject: [PATCH 07/20] xfs: queue inodegc worker immediately when memory is tight
Date: Thu, 29 Jul 2021 11:44:32 -0700 [thread overview]
Message-ID: <162758427220.332903.7964745098855992435.stgit@magnolia> (raw)
In-Reply-To: <162758423315.332903.16799817941903734904.stgit@magnolia>
From: Darrick J. Wong <djwong@kernel.org>
If there is enough memory pressure that we're scheduling inodes for
inactivation from a shrinker, queue the inactivation worker immediately
to try to facilitate reclaming inodes. This patch prepares us for
adding a configurable inodegc delay in the next patch.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_icache.c | 34 ++++++++++++++++++++++++++++++++--
fs/xfs/xfs_trace.h | 1 +
2 files changed, 33 insertions(+), 2 deletions(-)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index abd95f16b697..e0803544ea19 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -212,6 +212,32 @@ xfs_reclaim_work_queue(
rcu_read_unlock();
}
+/*
+ * Compute the lag between scheduling and executing some kind of background
+ * garbage collection work. Return value is in ms.
+ */
+static inline unsigned int
+xfs_gc_delay_ms(
+ struct xfs_mount *mp,
+ unsigned int tag)
+{
+ switch (tag) {
+ case XFS_ICI_INODEGC_TAG:
+ /* If we're in a shrinker, kick off the worker immediately. */
+ if (current->reclaim_state != NULL) {
+ trace_xfs_inodegc_delay_mempressure(mp,
+ __return_address);
+ return 0;
+ }
+ break;
+ default:
+ ASSERT(0);
+ return 0;
+ }
+
+ return 0;
+}
+
/*
* Background scanning to trim preallocated space. This is queued based on the
* 'speculative_prealloc_lifetime' tunable (5m by default).
@@ -242,8 +268,12 @@ xfs_inodegc_queue(
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_INODEGC_TAG)) {
- trace_xfs_inodegc_queue(mp, 0);
- queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work, 0);
+ unsigned int delay;
+
+ delay = xfs_gc_delay_ms(mp, XFS_ICI_INODEGC_TAG);
+ trace_xfs_inodegc_queue(mp, delay);
+ queue_delayed_work(mp->m_gc_workqueue, &mp->m_inodegc_work,
+ msecs_to_jiffies(delay));
}
rcu_read_unlock();
}
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b4dfa7e7e700..d3f3f6a32872 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -192,6 +192,7 @@ DEFINE_FS_EVENT(xfs_inodegc_stop);
DEFINE_FS_EVENT(xfs_inodegc_worker);
DEFINE_FS_EVENT(xfs_inodegc_throttled);
DEFINE_FS_EVENT(xfs_fs_sync_fs);
+DEFINE_FS_EVENT(xfs_inodegc_delay_mempressure);
TRACE_EVENT(xfs_inodegc_requeue_mempressure,
TP_PROTO(struct xfs_mount *mp, unsigned long nr, void *caller_ip),
next prev parent reply other threads:[~2021-07-29 18:44 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-29 18:43 [PATCHSET v8 00/20] xfs: deferred inode inactivation Darrick J. Wong
2021-07-29 18:43 ` [PATCH 01/20] xfs: move xfs_inactive call to xfs_inode_mark_reclaimable Darrick J. Wong
2021-07-29 18:44 ` [PATCH 02/20] xfs: detach dquots from inode if we don't need to inactivate it Darrick J. Wong
2021-07-29 18:44 ` [PATCH 03/20] xfs: defer inode inactivation to a workqueue Darrick J. Wong
2021-07-30 4:24 ` Dave Chinner
2021-07-31 4:21 ` Darrick J. Wong
2021-08-01 21:49 ` Dave Chinner
2021-08-01 23:47 ` Dave Chinner
2021-08-03 8:34 ` [PATCH, alternative] xfs: per-cpu deferred inode inactivation queues Dave Chinner
2021-08-03 20:20 ` Darrick J. Wong
2021-08-04 3:20 ` [PATCH, alternative v2] " Darrick J. Wong
2021-08-04 10:03 ` [PATCH] xfs: inodegc needs to stop before freeze Dave Chinner
2021-08-04 12:37 ` Dave Chinner
2021-08-04 10:46 ` [PATCH] xfs: don't run inodegc flushes when inodegc is not active Dave Chinner
2021-08-04 16:20 ` Darrick J. Wong
2021-08-04 11:09 ` [PATCH, alternative v2] xfs: per-cpu deferred inode inactivation queues Dave Chinner
2021-08-04 15:59 ` Darrick J. Wong
2021-08-04 21:35 ` Dave Chinner
2021-08-04 11:49 ` [PATCH, pre-03/20 #1] xfs: introduce CPU hotplug infrastructure Dave Chinner
2021-08-04 11:50 ` [PATCH, pre-03/20 #2] xfs: introduce all-mounts list for cpu hotplug notifications Dave Chinner
2021-08-04 16:06 ` Darrick J. Wong
2021-08-04 21:17 ` Dave Chinner
2021-08-04 11:52 ` [PATCH, post-03/20 1/1] xfs: hook up inodegc to CPU dead notification Dave Chinner
2021-08-04 16:19 ` Darrick J. Wong
2021-08-04 21:48 ` Dave Chinner
2021-07-29 18:44 ` [PATCH 04/20] xfs: throttle inode inactivation queuing on memory reclaim Darrick J. Wong
2021-07-29 18:44 ` [PATCH 05/20] xfs: don't throttle memory reclaim trying to queue inactive inodes Darrick J. Wong
2021-07-29 18:44 ` [PATCH 06/20] xfs: throttle inodegc queuing on backlog Darrick J. Wong
2021-08-02 0:45 ` Dave Chinner
2021-08-02 1:30 ` Dave Chinner
2021-07-29 18:44 ` Darrick J. Wong [this message]
2021-07-29 18:44 ` [PATCH 08/20] xfs: expose sysfs knob to control inode inactivation delay Darrick J. Wong
2021-07-29 18:44 ` [PATCH 09/20] xfs: reduce inactivation delay when free space is tight Darrick J. Wong
2021-07-29 18:44 ` [PATCH 10/20] xfs: reduce inactivation delay when quota are tight Darrick J. Wong
2021-07-29 18:44 ` [PATCH 11/20] xfs: reduce inactivation delay when realtime extents " Darrick J. Wong
2021-07-29 18:44 ` [PATCH 12/20] xfs: inactivate inodes any time we try to free speculative preallocations Darrick J. Wong
2021-07-29 18:45 ` [PATCH 13/20] xfs: flush inode inactivation work when compiling usage statistics Darrick J. Wong
2021-07-29 18:45 ` [PATCH 14/20] xfs: parallelize inode inactivation Darrick J. Wong
2021-08-02 0:55 ` Dave Chinner
2021-08-02 21:33 ` Darrick J. Wong
2021-07-29 18:45 ` [PATCH 15/20] xfs: reduce inactivation delay when AG free space are tight Darrick J. Wong
2021-07-29 18:45 ` [PATCH 16/20] xfs: queue inodegc worker immediately on backlog Darrick J. Wong
2021-07-29 18:45 ` [PATCH 17/20] xfs: don't run speculative preallocation gc when fs is frozen Darrick J. Wong
2021-07-29 18:45 ` [PATCH 18/20] xfs: scale speculative preallocation gc delay based on free space Darrick J. Wong
2021-07-29 18:45 ` [PATCH 19/20] xfs: use background worker pool when transactions can't get " Darrick J. Wong
2021-07-29 18:45 ` [PATCH 20/20] xfs: avoid buffer deadlocks when walking fs inodes Darrick J. Wong
2021-08-02 10:35 ` [PATCHSET v8 00/20] xfs: deferred inode inactivation Dave Chinner
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=162758427220.332903.7964745098855992435.stgit@magnolia \
--to=djwong@kernel.org \
--cc=david@fromorbit.com \
--cc=hch@infradead.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).