From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 06/14] xfs: track CIL ticket reservation in percpu structure
Date: Tue, 9 Nov 2021 12:52:32 +1100 [thread overview]
Message-ID: <20211109015240.1547991-7-david@fromorbit.com> (raw)
In-Reply-To: <20211109015240.1547991-1-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 | 20 +++++++++++++++-----
fs/xfs/xfs_log_priv.h | 1 +
2 files changed, 16 insertions(+), 5 deletions(-)
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ddc8d262d9f9..74717bdd992b 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -91,6 +91,10 @@ 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
@@ -524,6 +528,7 @@ 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 >
@@ -534,10 +539,6 @@ 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...
@@ -559,6 +560,7 @@ 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. */
@@ -1600,9 +1602,17 @@ xlog_cil_pcp_dead(
{
struct xfs_cil *cil = log->l_cilp;
struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
+ struct xfs_cil_ctx *ctx;
down_write(&cil->xc_ctx_lock);
- atomic_add(cilpcp->space_used, &cil->xc_ctx->space_used);
+ ctx = cil->xc_ctx;
+ if (ctx->ticket) {
+ ctx->ticket->t_curr_res += cilpcp->space_reserved;
+ ctx->ticket->t_unit_res += cilpcp->space_reserved;
+ }
+ cilpcp->space_reserved = 0;
+
+ atomic_add(cilpcp->space_used, &ctx->space_used);
cilpcp->space_used = 0;
up_write(&cil->xc_ctx_lock);
}
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index b9c96609705b..5150b4a7d086 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -236,6 +236,7 @@ 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;
};
--
2.33.0
next prev 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 ` Dave Chinner [this message]
2021-11-09 1:52 ` [PATCH 07/14] xfs: convert CIL busy extents to per-cpu Dave Chinner
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 06/14] xfs: track CIL ticket reservation in percpu structure 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=20211109015240.1547991-7-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