From: "Paul E. McKenney" <paulmck@linux.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
"Paul E. McKenney" <paulmck@linux.ibm.com>
Subject: [PATCH tip/core/rcu 01/10] rcutorture: Record grace periods in forward-progress histogram
Date: Wed, 9 Jan 2019 13:49:59 -0800 [thread overview]
Message-ID: <20190109215008.6401-1-paulmck@linux.ibm.com> (raw)
In-Reply-To: <20190109214944.GA5610@linux.ibm.com>
This commit records grace periods in rcutorture's n_launders_hist[]
histogram, thus allowing rcu_torture_fwd_cb_hist() to print out the
elapsed number of grace periods between buckets. This information
helps to determine whether a lack of forward progress is due to stalled
grace periods on the one hand or due to sluggish callback invocation on
the other.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
kernel/rcu/rcutorture.c | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f6e85faa4ff4..0955f3a20952 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1630,21 +1630,34 @@ static bool rcu_fwd_emergency_stop;
#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
-static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+struct rcu_launder_hist {
+ long n_launders;
+ unsigned long launder_gp_seq;
+};
+#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
+static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
+static unsigned long rcu_launder_gp_seq_start;
static void rcu_torture_fwd_cb_hist(void)
{
+ unsigned long gps;
+ unsigned long gps_old;
int i;
int j;
for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
- if (n_launders_hist[i] > 0)
+ if (n_launders_hist[i].n_launders > 0)
break;
pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
__func__, jiffies - rcu_fwd_startat);
- for (j = 0; j <= i; j++)
- pr_cont(" %ds/%d: %ld",
- j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+ gps_old = rcu_launder_gp_seq_start;
+ for (j = 0; j <= i; j++) {
+ gps = n_launders_hist[j].launder_gp_seq;
+ pr_cont(" %ds/%d: %ld:%ld",
+ j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
+ rcutorture_seq_diff(gps, gps_old));
+ gps_old = gps;
+ }
pr_cont("\n");
}
@@ -1666,7 +1679,8 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
if (i >= ARRAY_SIZE(n_launders_hist))
i = ARRAY_SIZE(n_launders_hist) - 1;
- n_launders_hist[i]++;
+ n_launders_hist[i].n_launders++;
+ n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
spin_unlock_irqrestore(&rcu_fwd_lock, flags);
}
@@ -1786,9 +1800,10 @@ static void rcu_torture_fwd_prog_cr(void)
n_max_cbs = 0;
n_max_gps = 0;
for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
- n_launders_hist[i] = 0;
+ n_launders_hist[i].n_launders = 0;
cver = READ_ONCE(rcu_torture_current_version);
gps = cur_ops->get_gp_seq();
+ rcu_launder_gp_seq_start = gps;
while (time_before(jiffies, stopat) &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
rfcp = READ_ONCE(rcu_fwd_cb_head);
--
2.17.1
next prev parent reply other threads:[~2019-01-09 21:50 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-09 21:49 [PATCH tip/core/rcu 0/10] Torture-test updates for v5.1 Paul E. McKenney
2019-01-09 21:49 ` Paul E. McKenney [this message]
2019-01-09 21:50 ` [PATCH tip/core/rcu 02/10] torture: Explain and simplify odd "for" loop in mkinitrd.sh Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 03/10] rcutorture: Add grace period after CPU offline Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 04/10] rcuperf: Stop abusing IS_ENABLED() Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 05/10] rcutorture/nolibc: Fix the clobbered registers in the MIPS syscall definition Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 06/10] rcutorture/nolibc: Fix some poor indentation and alignment Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 07/10] rcutorture/nolibc: Add a bit of documentation to explain how to use nolibc Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 08/10] tools headers: Move the nolibc header from rcutorture to tools/include/nolibc/ Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 09/10] MAINTAINERS: Add myself as the maintainer for the nolibc header file(s) Paul E. McKenney
2019-01-09 21:50 ` [PATCH tip/core/rcu 10/10] RCU/torture.txt: Remove section MODULE PARAMETERS Paul E. McKenney
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=20190109215008.6401-1-paulmck@linux.ibm.com \
--to=paulmck@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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
Powered by JetHome