public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 07/14] xfs: convert CIL busy extents to per-cpu
Date: Tue,  9 Nov 2021 12:52:33 +1100	[thread overview]
Message-ID: <20211109015240.1547991-8-david@fromorbit.com> (raw)
In-Reply-To: <20211109015240.1547991-1-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

To get them out from under the CIL lock.

This is an unordered list, so we can simply punt it to per-cpu lists
during transaction commits and reaggregate it back into a single
list during the CIL push work.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_log_cil.c | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 74717bdd992b..32b445a541f7 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -95,6 +95,11 @@ xlog_cil_pcp_aggregate(
 		ctx->ticket->t_unit_res += cilpcp->space_reserved;
 		cilpcp->space_reserved = 0;
 
+		if (!list_empty(&cilpcp->busy_extents)) {
+			list_splice_init(&cilpcp->busy_extents,
+					&ctx->busy_extents);
+		}
+
 		/*
 		 * We're in the middle of switching cil contexts.  Reset the
 		 * counter we use to detect when the current context is nearing
@@ -537,6 +542,9 @@ xlog_cil_insert_items(
 		atomic_add(cilpcp->space_used, &ctx->space_used);
 		cilpcp->space_used = 0;
 	}
+	/* attach the transaction to the CIL if it has any busy extents */
+	if (!list_empty(&tp->t_busy))
+		list_splice_init(&tp->t_busy, &cilpcp->busy_extents);
 	put_cpu_ptr(cilpcp);
 
 	/*
@@ -576,9 +584,6 @@ xlog_cil_insert_items(
 			list_move_tail(&lip->li_cil, &cil->xc_cil);
 	}
 
-	/* attach the transaction to the CIL if it has any busy extents */
-	if (!list_empty(&tp->t_busy))
-		list_splice_init(&tp->t_busy, &ctx->busy_extents);
 	spin_unlock(&cil->xc_cil_lock);
 
 	if (tp->t_ticket->t_curr_res < 0)
@@ -1612,6 +1617,8 @@ xlog_cil_pcp_dead(
 	}
 	cilpcp->space_reserved = 0;
 
+	if (!list_empty(&cilpcp->busy_extents))
+		list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents);
 	atomic_add(cilpcp->space_used, &ctx->space_used);
 	cilpcp->space_used = 0;
 	up_write(&cil->xc_ctx_lock);
@@ -1622,10 +1629,12 @@ xlog_cil_pcp_dead(
  */
 int
 xlog_cil_init(
-	struct xlog	*log)
+	struct xlog		*log)
 {
-	struct xfs_cil	*cil;
-	struct xfs_cil_ctx *ctx;
+	struct xfs_cil		*cil;
+	struct xfs_cil_ctx	*ctx;
+	struct xlog_cil_pcp	*cilpcp;
+	int			cpu;
 
 	cil = kmem_zalloc(sizeof(*cil), KM_MAYFAIL);
 	if (!cil)
@@ -1645,6 +1654,11 @@ xlog_cil_init(
 	if (!cil->xc_pcp)
 		goto out_destroy_wq;
 
+	for_each_possible_cpu(cpu) {
+		cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
+		INIT_LIST_HEAD(&cilpcp->busy_extents);
+	}
+
 	INIT_LIST_HEAD(&cil->xc_cil);
 	INIT_LIST_HEAD(&cil->xc_committing);
 	spin_lock_init(&cil->xc_cil_lock);
-- 
2.33.0


  parent reply	other threads:[~2021-11-09  1:52 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-09  1:52 [PATCH 00/14 v6] xfs: improve CIL scalability Dave Chinner
2021-11-09  1:52 ` [PATCH 01/14] xfs: use the CIL space used counter for emptiness checks Dave Chinner
2021-11-09  1:52 ` [PATCH 02/14] xfs: lift init CIL reservation out of xc_cil_lock Dave Chinner
2021-11-09  1:52 ` [PATCH 03/14] xfs: rework per-iclog header CIL reservation Dave Chinner
2021-11-09  1:52 ` [PATCH 04/14] xfs: introduce per-cpu CIL tracking structure Dave Chinner
2021-11-09  1:52 ` [PATCH 05/14] xfs: implement percpu cil space used calculation Dave Chinner
2021-11-09  1:52 ` [PATCH 06/14] xfs: track CIL ticket reservation in percpu structure Dave Chinner
2021-11-09  1:52 ` Dave Chinner [this message]
2021-11-09  1:52 ` [PATCH 08/14] xfs: Add order IDs to log items in CIL Dave Chinner
2021-11-09  1:52 ` [PATCH 09/14] xfs: convert CIL to unordered per cpu lists Dave Chinner
2021-11-09  1:52 ` [PATCH 10/14] xfs: convert log vector chain to use list heads Dave Chinner
2021-11-09  1:52 ` [PATCH 11/14] xfs: move CIL ordering to the logvec chain Dave Chinner
2021-11-09  1:52 ` [PATCH 12/14] xfs: avoid cil push lock if possible Dave Chinner
2021-11-09  1:52 ` [PATCH 13/14] xfs: xlog_sync() manually adjusts grant head space Dave Chinner
2021-11-09  1:52 ` [PATCH 14/14] xfs: expanding delayed logging design with background material Dave Chinner
2021-11-18 23:15 ` [PATCH 00/14 v6] xfs: improve CIL scalability Dave Chinner
  -- strict thread matches above, loose matches on Subject: below --
2022-06-15  7:53 [PATCH 00/14 v8] " Dave Chinner
2022-06-15  7:53 ` [PATCH 07/14] xfs: convert CIL busy extents to per-cpu 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=20211109015240.1547991-8-david@fromorbit.com \
    --to=david@fromorbit.com \
    --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