From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 30/39] xfs: implement percpu cil space used calculation
Date: Wed, 19 May 2021 22:13:08 +1000 [thread overview]
Message-ID: <20210519121317.585244-31-david@fromorbit.com> (raw)
In-Reply-To: <20210519121317.585244-1-david@fromorbit.com>
From: Dave Chinner <dchinner@redhat.com>
Now that we have the CIL percpu structures in place, implement the
space used counter with a fast sum check similar to the
percpu_counter infrastructure.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/xfs/xfs_log_cil.c | 61 ++++++++++++++++++++++++++++++++++++++-----
fs/xfs/xfs_log_priv.h | 2 +-
2 files changed, 55 insertions(+), 8 deletions(-)
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ba1c6979a4c7..72693fba929b 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -76,6 +76,24 @@ xlog_cil_ctx_alloc(void)
return ctx;
}
+/*
+ * Aggregate the CIL per cpu structures into global counts, lists, etc and
+ * clear the percpu state ready for the next context to use.
+ */
+static void
+xlog_cil_pcp_aggregate(
+ struct xfs_cil *cil,
+ struct xfs_cil_ctx *ctx)
+{
+ struct xlog_cil_pcp *cilpcp;
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
+ cilpcp->space_used = 0;
+ }
+}
+
static void
xlog_cil_ctx_switch(
struct xfs_cil *cil,
@@ -433,6 +451,8 @@ xlog_cil_insert_items(
struct xfs_log_item *lip;
int len = 0;
int iovhdr_res = 0, split_res = 0, ctx_res = 0;
+ int space_used;
+ struct xlog_cil_pcp *cilpcp;
ASSERT(tp);
@@ -469,8 +489,9 @@ xlog_cil_insert_items(
*
* This can steal more than we need, but that's OK.
*/
+ space_used = atomic_read(&ctx->space_used);
if (atomic_read(&cil->xc_iclog_hdrs) > 0 ||
- ctx->space_used + len >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
+ space_used + len >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
int split_res = log->l_iclog_hsize +
sizeof(struct xlog_op_header);
if (ctx_res)
@@ -480,16 +501,34 @@ xlog_cil_insert_items(
atomic_sub(tp->t_ticket->t_iclog_hdrs, &cil->xc_iclog_hdrs);
}
+ /*
+ * Update the CIL percpu pointer. This updates the global counter when
+ * over the percpu batch size or when the CIL is over the space limit.
+ * This means low lock overhead for normal updates, and when over the
+ * limit the space used is immediately accounted. This makes enforcing
+ * the hard limit much more accurate. The per cpu fold threshold is
+ * based on how close we are to the hard limit.
+ */
+ cilpcp = get_cpu_ptr(cil->xc_pcp);
+ cilpcp->space_used += len;
+ if (space_used >= XLOG_CIL_SPACE_LIMIT(log) ||
+ cilpcp->space_used >
+ ((XLOG_CIL_BLOCKING_SPACE_LIMIT(log) - space_used) /
+ num_online_cpus())) {
+ atomic_add(cilpcp->space_used, &ctx->space_used);
+ cilpcp->space_used = 0;
+ }
+ put_cpu_ptr(cilpcp);
+
spin_lock(&cil->xc_cil_lock);
- tp->t_ticket->t_curr_res -= ctx_res + len;
ctx->ticket->t_unit_res += ctx_res;
ctx->ticket->t_curr_res += ctx_res;
- ctx->space_used += len;
/*
* If we've overrun the reservation, dump the tx details before we move
* the log items. Shutdown is imminent...
*/
+ tp->t_ticket->t_curr_res -= ctx_res + len;
if (WARN_ON(tp->t_ticket->t_curr_res < 0)) {
xfs_warn(log->l_mp, "Transaction log reservation overrun:");
xfs_warn(log->l_mp,
@@ -846,6 +885,8 @@ xlog_cil_push_work(
xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
&bdev_flush);
+ xlog_cil_pcp_aggregate(cil, ctx);
+
/*
* Pull all the log vectors off the items in the CIL, and remove the
* items from the CIL. We don't need the CIL lock here because it's only
@@ -1043,6 +1084,7 @@ xlog_cil_push_background(
struct xlog *log) __releases(cil->xc_ctx_lock)
{
struct xfs_cil *cil = log->l_cilp;
+ int space_used = atomic_read(&cil->xc_ctx->space_used);
/*
* The cil won't be empty because we are called while holding the
@@ -1055,7 +1097,7 @@ xlog_cil_push_background(
* Don't do a background push if we haven't used up all the
* space available yet.
*/
- if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) {
+ if (space_used < XLOG_CIL_SPACE_LIMIT(log)) {
up_read(&cil->xc_ctx_lock);
return;
}
@@ -1084,10 +1126,10 @@ xlog_cil_push_background(
* The ctx->xc_push_lock provides the serialisation necessary for safely
* using the lockless waitqueue_active() check in this context.
*/
- if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log) ||
+ if (space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log) ||
waitqueue_active(&cil->xc_push_wait)) {
trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
- ASSERT(cil->xc_ctx->space_used < log->l_logsize);
+ ASSERT(space_used < log->l_logsize);
xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock);
return;
}
@@ -1391,9 +1433,14 @@ 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);
+
spin_unlock(&xlog_cil_pcp_lock);
down_write(&cil->xc_ctx_lock);
- /* move stuff on dead CPU to context */
+
+ atomic_add(cilpcp->space_used, &cil->xc_ctx->space_used);
+ cilpcp->space_used = 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 aaa1e7f7fb66..7dc6275818de 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -218,7 +218,7 @@ struct xfs_cil_ctx {
xfs_lsn_t start_lsn; /* first LSN of chkpt commit */
xfs_lsn_t commit_lsn; /* chkpt commit record lsn */
struct xlog_ticket *ticket; /* chkpt ticket */
- int space_used; /* aggregate size of regions */
+ atomic_t space_used; /* aggregate size of regions */
struct list_head busy_extents; /* busy extents in chkpt */
struct xfs_log_vec *lv_chain; /* logvecs being pushed */
struct list_head iclog_entry;
--
2.31.1
next prev parent reply other threads:[~2021-05-19 12:13 UTC|newest]
Thread overview: 88+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-19 12:12 [PATCH 00/39 v4] xfs: CIL and log optimisations Dave Chinner
2021-05-19 12:12 ` [PATCH 01/39] xfs: log stripe roundoff is a property of the log Dave Chinner
2021-05-28 0:54 ` Allison Henderson
2021-05-19 12:12 ` [PATCH 02/39] xfs: separate CIL commit record IO Dave Chinner
2021-05-28 0:54 ` Allison Henderson
2021-05-19 12:12 ` [PATCH 03/39] xfs: remove xfs_blkdev_issue_flush Dave Chinner
2021-05-28 0:54 ` Allison Henderson
2021-05-19 12:12 ` [PATCH 04/39] xfs: async blkdev cache flush Dave Chinner
2021-05-20 23:53 ` Darrick J. Wong
2021-05-28 0:54 ` Allison Henderson
2021-05-19 12:12 ` [PATCH 05/39] xfs: CIL checkpoint flushes caches unconditionally Dave Chinner
2021-05-28 0:54 ` Allison Henderson
2021-05-19 12:12 ` [PATCH 06/39] xfs: remove need_start_rec parameter from xlog_write() Dave Chinner
2021-05-19 12:12 ` [PATCH 07/39] xfs: journal IO cache flush reductions Dave Chinner
2021-05-21 0:16 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 08/39] xfs: Fix CIL throttle hang when CIL space used going backwards Dave Chinner
2021-05-19 12:12 ` [PATCH 09/39] xfs: xfs_log_force_lsn isn't passed a LSN Dave Chinner
2021-05-21 0:20 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 10/39] xfs: AIL needs asynchronous CIL forcing Dave Chinner
2021-05-21 0:33 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 11/39] xfs: CIL work is serialised, not pipelined Dave Chinner
2021-05-21 0:32 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 12/39] xfs: factor out the CIL transaction header building Dave Chinner
2021-05-19 12:12 ` [PATCH 13/39] xfs: only CIL pushes require a start record Dave Chinner
2021-05-19 12:12 ` [PATCH 14/39] xfs: embed the xlog_op_header in the unmount record Dave Chinner
2021-05-21 0:35 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 15/39] xfs: embed the xlog_op_header in the commit record Dave Chinner
2021-05-19 12:12 ` [PATCH 16/39] xfs: log tickets don't need log client id Dave Chinner
2021-05-21 0:38 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 17/39] xfs: move log iovec alignment to preparation function Dave Chinner
2021-05-19 12:12 ` [PATCH 18/39] xfs: reserve space and initialise xlog_op_header in item formatting Dave Chinner
2021-05-19 12:12 ` [PATCH 19/39] xfs: log ticket region debug is largely useless Dave Chinner
2021-05-19 12:12 ` [PATCH 20/39] xfs: pass lv chain length into xlog_write() Dave Chinner
2021-05-27 17:20 ` Darrick J. Wong
2021-06-02 22:18 ` Dave Chinner
2021-06-02 22:24 ` Darrick J. Wong
2021-06-02 22:58 ` [PATCH 20/39 V2] " Dave Chinner
2021-06-02 23:01 ` Darrick J. Wong
2021-05-19 12:12 ` [PATCH 21/39] xfs: introduce xlog_write_single() Dave Chinner
2021-05-27 17:27 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 22/39] xfs:_introduce xlog_write_partial() Dave Chinner
2021-05-27 18:06 ` Darrick J. Wong
2021-06-02 22:21 ` Dave Chinner
2021-05-19 12:13 ` [PATCH 23/39] xfs: xlog_write() no longer needs contwr state Dave Chinner
2021-05-19 12:13 ` [PATCH 24/39] xfs: xlog_write() doesn't need optype anymore Dave Chinner
2021-05-27 18:07 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 25/39] xfs: CIL context doesn't need to count iovecs Dave Chinner
2021-05-27 18:08 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 26/39] xfs: use the CIL space used counter for emptiness checks Dave Chinner
2021-05-19 12:13 ` [PATCH 27/39] xfs: lift init CIL reservation out of xc_cil_lock Dave Chinner
2021-05-19 12:13 ` [PATCH 28/39] xfs: rework per-iclog header CIL reservation Dave Chinner
2021-05-27 18:17 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 29/39] xfs: introduce per-cpu CIL tracking structure Dave Chinner
2021-05-27 18:31 ` Darrick J. Wong
2021-05-19 12:13 ` Dave Chinner [this message]
2021-05-27 18:41 ` [PATCH 30/39] xfs: implement percpu cil space used calculation Darrick J. Wong
2021-06-02 23:47 ` Dave Chinner
2021-06-03 1:26 ` Darrick J. Wong
2021-06-03 2:28 ` Dave Chinner
2021-06-03 3:01 ` Darrick J. Wong
2021-06-03 3:56 ` 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
2021-05-19 12:13 ` [PATCH 32/39] xfs: convert CIL busy extents to per-cpu Dave Chinner
2021-05-27 18:49 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 33/39] xfs: Add order IDs to log items in CIL Dave Chinner
2021-05-27 19:00 ` Darrick J. Wong
2021-06-03 0:16 ` Dave Chinner
2021-06-03 0:49 ` Darrick J. Wong
2021-06-03 2:13 ` Dave Chinner
2021-06-03 3:02 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 34/39] xfs: convert CIL to unordered per cpu lists Dave Chinner
2021-05-27 19:03 ` Darrick J. Wong
2021-06-03 0:27 ` Dave Chinner
2021-05-19 12:13 ` [PATCH 35/39] xfs: convert log vector chain to use list heads Dave Chinner
2021-05-27 19:13 ` Darrick J. Wong
2021-06-03 0:38 ` Dave Chinner
2021-06-03 0:50 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 36/39] xfs: move CIL ordering to the logvec chain Dave Chinner
2021-05-27 19:14 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 37/39] xfs: avoid cil push lock if possible Dave Chinner
2021-05-27 19:18 ` Darrick J. Wong
2021-05-19 12:13 ` [PATCH 38/39] xfs: xlog_sync() manually adjusts grant head space Dave Chinner
2021-05-19 12:13 ` [PATCH 39/39] xfs: expanding delayed logging design with background material Dave Chinner
2021-05-27 20:38 ` Darrick J. Wong
2021-06-03 0:57 ` Dave Chinner
2021-06-03 5:22 [PATCH 00/39 v5] xfs: CIL and log optimisations Dave Chinner
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
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=20210519121317.585244-31-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).