linux-xfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 31/39] xfs: track CIL ticket reservation in percpu structure
Date: Thu,  3 Jun 2021 15:22:32 +1000	[thread overview]
Message-ID: <20210603052240.171998-32-david@fromorbit.com> (raw)
In-Reply-To: <20210603052240.171998-1-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

To get it out from under the cil spinlock.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_log_cil.c  | 21 ++++++++++++++++-----
 fs/xfs/xfs_log_priv.h |  1 +
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 620824c6f7fa..f5ce7099afc5 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -91,12 +91,17 @@ xlog_cil_pcp_aggregate(
 	for_each_online_cpu(cpu) {
 		cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
 
+		ctx->ticket->t_curr_res += cilpcp->space_reserved;
+		ctx->ticket->t_unit_res += cilpcp->space_reserved;
+		cilpcp->space_reserved = 0;
+
 		/*
 		 * We're in the middle of switching cil contexts.  Reset the
 		 * counter we use to detect when the current context is nearing
 		 * full.
 		 */
 		cilpcp->space_used = 0;
+
 	}
 }
 
@@ -516,6 +521,7 @@ xlog_cil_insert_items(
 	 * based on how close we are to the hard limit.
 	 */
 	cilpcp = get_cpu_ptr(cil->xc_pcp);
+	cilpcp->space_reserved += ctx_res;
 	cilpcp->space_used += len;
 	if (space_used >= XLOG_CIL_SPACE_LIMIT(log) ||
 	    cilpcp->space_used >
@@ -526,10 +532,6 @@ xlog_cil_insert_items(
 	}
 	put_cpu_ptr(cilpcp);
 
-	spin_lock(&cil->xc_cil_lock);
-	ctx->ticket->t_unit_res += ctx_res;
-	ctx->ticket->t_curr_res += ctx_res;
-
 	/*
 	 * If we've overrun the reservation, dump the tx details before we move
 	 * the log items. Shutdown is imminent...
@@ -551,6 +553,7 @@ xlog_cil_insert_items(
 	 * We do this here so we only need to take the CIL lock once during
 	 * the transaction commit.
 	 */
+	spin_lock(&cil->xc_cil_lock);
 	list_for_each_entry(lip, &tp->t_items, li_trans) {
 
 		/* Skip items which aren't dirty in this transaction. */
@@ -1439,12 +1442,20 @@ xlog_cil_pcp_dead(
 	spin_lock(&xlog_cil_pcp_lock);
 	list_for_each_entry_safe(cil, n, &xlog_cil_pcp_list, xc_pcp_list) {
 		struct xlog_cil_pcp	*cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
+		struct xfs_cil_ctx	*ctx;
 
 		spin_unlock(&xlog_cil_pcp_lock);
 		down_write(&cil->xc_ctx_lock);
+		ctx = cil->xc_ctx;
+
+		atomic_add(cilpcp->space_used, &ctx->space_used);
+		if (ctx->ticket) {
+			ctx->ticket->t_curr_res += cilpcp->space_reserved;
+			ctx->ticket->t_unit_res += cilpcp->space_reserved;
+		}
 
-		atomic_add(cilpcp->space_used, &cil->xc_ctx->space_used);
 		cilpcp->space_used = 0;
+		cilpcp->space_reserved = 0;
 
 		up_write(&cil->xc_ctx_lock);
 		spin_lock(&xlog_cil_pcp_lock);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 373b7dbde4af..b80cb3a0edb7 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -232,6 +232,7 @@ struct xfs_cil_ctx {
  */
 struct xlog_cil_pcp {
 	uint32_t		space_used;
+	uint32_t		space_reserved;
 	struct list_head	busy_extents;
 	struct list_head	log_items;
 };
-- 
2.31.1


  parent reply	other threads:[~2021-06-03  5:23 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-03  5:22 [PATCH 00/39 v5] xfs: CIL and log optimisations Dave Chinner
2021-06-03  5:22 ` [PATCH 01/39] xfs: log stripe roundoff is a property of the log Dave Chinner
2021-06-03  5:22 ` [PATCH 02/39] xfs: separate CIL commit record IO Dave Chinner
2021-06-03  5:22 ` [PATCH 03/39] xfs: remove xfs_blkdev_issue_flush Dave Chinner
2021-06-03  5:22 ` [PATCH 04/39] xfs: async blkdev cache flush Dave Chinner
2021-06-03  5:22 ` [PATCH 05/39] xfs: CIL checkpoint flushes caches unconditionally Dave Chinner
2021-06-03  5:22 ` [PATCH 06/39] xfs: remove need_start_rec parameter from xlog_write() Dave Chinner
2021-06-03 22:29   ` Allison Henderson
2021-06-03  5:22 ` [PATCH 07/39] xfs: journal IO cache flush reductions Dave Chinner
2021-06-03 22:29   ` Allison Henderson
2021-06-04  5:15   ` [xfs] 80d287de7b: stress-ng.dir.ops_per_sec 80.1% improvement kernel test robot
2021-06-03  5:22 ` [PATCH 08/39] xfs: Fix CIL throttle hang when CIL space used going backwards Dave Chinner
2021-06-03 22:29   ` Allison Henderson
2021-06-03  5:22 ` [PATCH 09/39] xfs: xfs_log_force_lsn isn't passed a LSN Dave Chinner
2021-06-03 22:29   ` Allison Henderson
2021-06-03  5:22 ` [PATCH 10/39] xfs: AIL needs asynchronous CIL forcing Dave Chinner
2021-06-03 22:29   ` Allison Henderson
2021-06-03  5:22 ` [PATCH 11/39] xfs: CIL work is serialised, not pipelined Dave Chinner
2021-06-03  5:22 ` [PATCH 12/39] xfs: factor out the CIL transaction header building Dave Chinner
2021-06-03  5:22 ` [PATCH 13/39] xfs: only CIL pushes require a start record Dave Chinner
2021-06-03  5:22 ` [PATCH 14/39] xfs: embed the xlog_op_header in the unmount record Dave Chinner
2021-06-03  5:22 ` [PATCH 15/39] xfs: embed the xlog_op_header in the commit record Dave Chinner
2021-06-03  5:22 ` [PATCH 16/39] xfs: log tickets don't need log client id Dave Chinner
2021-06-03  5:22 ` [PATCH 17/39] xfs: move log iovec alignment to preparation function Dave Chinner
2021-06-03  5:22 ` [PATCH 18/39] xfs: reserve space and initialise xlog_op_header in item formatting Dave Chinner
2021-06-03  5:22 ` [PATCH 19/39] xfs: log ticket region debug is largely useless Dave Chinner
2021-06-03  5:22 ` [PATCH 20/39] xfs: pass lv chain length into xlog_write() Dave Chinner
2021-06-03  5:22 ` [PATCH 21/39] xfs: introduce xlog_write_single() Dave Chinner
2021-06-03  5:22 ` [PATCH 22/39] xfs:_introduce xlog_write_partial() Dave Chinner
2021-06-03  5:22 ` [PATCH 23/39] xfs: xlog_write() no longer needs contwr state Dave Chinner
2021-06-03  5:22 ` [PATCH 24/39] xfs: xlog_write() doesn't need optype anymore Dave Chinner
2021-06-03  5:22 ` [PATCH 25/39] xfs: CIL context doesn't need to count iovecs Dave Chinner
2021-06-03  5:22 ` [PATCH 26/39] xfs: use the CIL space used counter for emptiness checks Dave Chinner
2021-06-03  5:22 ` [PATCH 27/39] xfs: lift init CIL reservation out of xc_cil_lock Dave Chinner
2021-06-03  5:22 ` [PATCH 28/39] xfs: rework per-iclog header CIL reservation Dave Chinner
2021-06-03  5:22 ` [PATCH 29/39] xfs: introduce per-cpu CIL tracking structure Dave Chinner
2021-06-03  9:18   ` kernel test robot
2021-06-03 10:08   ` kernel test robot
2021-06-03 16:49   ` Darrick J. Wong
2021-06-03  5:22 ` [PATCH 30/39] xfs: implement percpu cil space used calculation Dave Chinner
2021-06-03 16:44   ` Darrick J. Wong
2021-06-03  5:22 ` Dave Chinner [this message]
2021-06-03 16:43   ` [PATCH 31/39] xfs: track CIL ticket reservation in percpu structure Darrick J. Wong
2021-06-03  5:22 ` [PATCH 32/39] xfs: convert CIL busy extents to per-cpu Dave Chinner
2021-06-03  5:22 ` [PATCH 33/39] xfs: Add order IDs to log items in CIL Dave Chinner
2021-06-03  5:22 ` [PATCH 34/39] xfs: convert CIL to unordered per cpu lists Dave Chinner
2021-06-03  5:22 ` [PATCH 35/39] xfs: convert log vector chain to use list heads Dave Chinner
2021-06-03 10:16   ` kernel test robot
2021-06-03  5:22 ` [PATCH 36/39] xfs: move CIL ordering to the logvec chain Dave Chinner
2021-06-03  5:22 ` [PATCH 37/39] xfs: avoid cil push lock if possible Dave Chinner
2021-06-03  5:22 ` [PATCH 38/39] xfs: xlog_sync() manually adjusts grant head space Dave Chinner
2021-06-03  5:22 ` [PATCH 39/39] xfs: expanding delayed logging design with background material Dave Chinner
2021-06-03 17:05 ` [PATCH 00/39 v5] xfs: CIL and log optimisations Darrick J. Wong
2021-06-03 22:43   ` Dave Chinner
  -- strict thread matches above, loose matches on Subject: below --
2021-05-19 12:12 [PATCH 00/39 v4] " Dave Chinner
2021-05-19 12:13 ` [PATCH 31/39] xfs: track CIL ticket reservation in percpu structure Dave Chinner
2021-05-27 18:48   ` 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=20210603052240.171998-32-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;
as well as URLs for NNTP newsgroup(s).