Linux NFS development
 help / color / mirror / Atom feed
From: Mike Snitzer <snitzer@kernel.org>
To: Anna Schumaker <anna@kernel.org>, Trond Myklebust <trondmy@kernel.org>
Cc: Mike Snitzer <snitzer@hammerspace.com>,
	linux-nfs@vger.kernel.org,
	Jonathan Flynn <jonathan.flynn@hammerspace.com>
Subject: [PATCH v3 04/12] NFSv4/flexfiles: make dss_info->start_time write-once
Date: Fri,  6 Nov 2026 13:20:52 -0500	[thread overview]
Message-ID: <20261106182105.78611-5-snitzer@kernel.org> (raw)
In-Reply-To: <20261106182105.78611-1-snitzer@kernel.org>

From: Mike Snitzer <snitzer@hammerspace.com>

nfs4_ff_layoutstat_start_io() writes start_time under the stripe lock,
and ff_layout_encode_ff_layoutupdate() reads it without the lock.

ffl_duration is measured from the stripe's first I/O, so start_time is
written once and then only read.  Make it an atomic64_t, publish it
with atomic64_try_cmpxchg() so that the first I/O sets it, and read it
with atomic64_read().  Later I/O sees the value is set and does not
write it.  ffl->last_report_time is already published this way.

start_time then does not depend on the stripe lock, which a later patch
splits in two.

Signed-off-by: Mike Snitzer <snitzer@hammerspace.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 16 +++++++++++++---
 fs/nfs/flexfilelayout/flexfilelayout.h |  5 +++--
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 57cd8b5d6d71d..dd493ff51d512 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -729,6 +729,17 @@ nfs4_ff_end_busy_timer(struct nfs4_ff_busy_timer *timer, ktime_t now)
 	return ktime_sub(now, start);
 }
 
+/* ffl_duration runs from the stripe's first I/O: publish start_time once. */
+static void
+nfs4_ff_layoutstat_set_start_time(struct nfs4_ff_layout_ds_stripe *dss_info,
+				  ktime_t now)
+{
+	s64 unset = 0;
+
+	if (!atomic64_read(&dss_info->start_time))
+		atomic64_try_cmpxchg(&dss_info->start_time, &unset, now);
+}
+
 static bool
 nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
 			    u32 dss_id,
@@ -740,8 +751,7 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
 	s64 last_report;
 
 	nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
-	if (!mirror->dss[dss_id].start_time)
-		mirror->dss[dss_id].start_time = now;
+	nfs4_ff_layoutstat_set_start_time(&mirror->dss[dss_id], now);
 	if (mirror->report_interval != 0)
 		report_interval = (s64)mirror->report_interval * 1000LL;
 	else if (layoutstats_timer != 0)
@@ -3083,7 +3093,7 @@ ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr,
 	/* nfstime4 */
 	ff_layout_encode_nfstime(xdr,
 				 ktime_sub(ktime_get(),
-					   dss_info->start_time));
+					   atomic64_read(&dss_info->start_time)));
 	/* bool */
 	p = xdr_reserve_space(xdr, 4);
 	*p = cpu_to_be32(false);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 9ce09e02f1ad9..90a0ed1dd822e 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -87,11 +87,12 @@ struct nfs4_ff_layout_ds_stripe {
 	const struct cred __rcu		*ro_cred;
 	const struct cred __rcu		*rw_cred;
 	struct nfs_file_localio		nfl;
-	/* Protects read_stat, write_stat and start_time below */
+	/* Protects read_stat and write_stat below */
 	spinlock_t			lock ____cacheline_aligned_in_smp;
 	struct nfs4_ff_layoutstat	read_stat;
 	struct nfs4_ff_layoutstat	write_stat;
-	ktime_t				start_time;
+	/* Published once by the first I/O; see nfs4_ff_layoutstat_set_start_time() */
+	atomic64_t			start_time;
 };
 
 struct nfs4_ff_layout_mirror {
-- 
2.52.0


  parent reply	other threads:[~2026-11-06 18:21 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-06 18:20 [PATCH v3 00/12] NFSv4/flexfiles: scale layoutstats for striped layouts Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 01/12] NFSv4/flexfiles: move layoutstats accounting to a per-stripe lock Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 02/12] NFSv4/flexfiles: drop the now-unused per-mirror lock Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 03/12] NFSv4/flexfiles: cacheline align the per-stripe layoutstats Mike Snitzer
2026-11-06 18:20 ` Mike Snitzer [this message]
2026-11-06 18:20 ` [PATCH v3 05/12] NFSv4/flexfiles: drop the redundant atomic from the busy timer Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 06/12] NFSv4/flexfiles: pair the in-flight count with the layoutstats updates Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 07/12] NFSv4/flexfiles: derive ffil_ops_requested rather than storing it Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 08/12] NFSv4/flexfiles: give each direction its own lock and cacheline Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 09/12] NFSv4/flexfiles: drop NFS4_FF_MIRROR_STAT_AVAIL Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 10/12] NFSv4/flexfiles: rotate LAYOUTSTATS reporting across a mirror's stripes Mike Snitzer
2026-11-06 18:20 ` [PATCH v3 11/12] NFSv4/flexfiles: take the report decision out of the critical section Mike Snitzer
2026-11-06 18:21 ` [PATCH v3 12/12] NFSv4/flexfiles: share one helper for the start of a read and a write Mike Snitzer

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=20261106182105.78611-5-snitzer@kernel.org \
    --to=snitzer@kernel.org \
    --cc=anna@kernel.org \
    --cc=jonathan.flynn@hammerspace.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=snitzer@hammerspace.com \
    --cc=trondmy@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