All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ankit Kumar <ankit.kumar@samsung.com>
To: axboe@kernel.dk
Cc: fio@vger.kernel.org, vincentfu@gmail.com,
	Ankit Kumar <ankit.kumar@samsung.com>
Subject: [PATCH 1/1] backend: fix runtime when used with thinktime
Date: Fri, 17 Feb 2023 12:33:22 +0530	[thread overview]
Message-ID: <20230217070322.14163-2-ankit.kumar@samsung.com> (raw)
In-Reply-To: <20230217070322.14163-1-ankit.kumar@samsung.com>

Runtime for fio jobs when used in conjuction with thinktime,
thinktime_iotime and thinktime_spin were sometimes more than
what is specified. Add a fix so that fio doesn't spin or sleep
for any duration beyond runtime.

For the first cycle fio starts by doing I/O for
thinktime + thinktime_iotime, which should just be for
thinktime_iotime. Add a fix for that.

Signed-off-by: Ankit Kumar <ankit.kumar@samsung.com>
---
 backend.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/backend.c b/backend.c
index 0ccc7c2b..995be032 100644
--- a/backend.c
+++ b/backend.c
@@ -866,6 +866,7 @@ static void handle_thinktime(struct thread_data *td, enum fio_ddir ddir,
 			     struct timespec *time)
 {
 	unsigned long long b;
+	unsigned long long runtime_left;
 	uint64_t total;
 	int left;
 	struct timespec now;
@@ -874,7 +875,7 @@ static void handle_thinktime(struct thread_data *td, enum fio_ddir ddir,
 	if (td->o.thinktime_iotime) {
 		fio_gettime(&now, NULL);
 		if (utime_since(&td->last_thinktime, &now)
-		    >= td->o.thinktime_iotime + td->o.thinktime) {
+		    >= td->o.thinktime_iotime) {
 			stall = true;
 		} else if (!fio_option_is_set(&td->o, thinktime_blocks)) {
 			/*
@@ -897,11 +898,24 @@ static void handle_thinktime(struct thread_data *td, enum fio_ddir ddir,
 
 	io_u_quiesce(td);
 
+	left = td->o.thinktime_spin;
+	if (td->o.timeout) {
+		runtime_left = td->o.timeout - utime_since_now(&td->epoch);
+		if (runtime_left < (unsigned long long)left)
+			left = runtime_left;
+	}
+
 	total = 0;
-	if (td->o.thinktime_spin)
-		total = usec_spin(td->o.thinktime_spin);
+	if (left)
+		total = usec_spin(left);
 
 	left = td->o.thinktime - total;
+	if (td->o.timeout) {
+		runtime_left = td->o.timeout - utime_since_now(&td->epoch);
+		if (runtime_left < (unsigned long long)left)
+			left = runtime_left;
+	}
+
 	if (left)
 		total += usec_sleep(td, left);
 
@@ -930,8 +944,10 @@ static void handle_thinktime(struct thread_data *td, enum fio_ddir ddir,
 		fio_gettime(time, NULL);
 
 	td->last_thinktime_blocks = b;
-	if (td->o.thinktime_iotime)
+	if (td->o.thinktime_iotime) {
+		fio_gettime(&now, NULL);
 		td->last_thinktime = now;
+	}
 }
 
 /*
-- 
2.17.1


  parent reply	other threads:[~2023-02-17  7:08 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20230217070403epcas5p1f2c7eec62578c28429e8029681f7d341@epcas5p1.samsung.com>
2023-02-17  7:03 ` [PATCH 0/1] fix runtime when used with thinktime Ankit Kumar
     [not found]   ` <CGME20230217070403epcas5p2f01122718255b22f003ba9f77f92f3b2@epcas5p2.samsung.com>
2023-02-17  7:03     ` Ankit Kumar [this message]
2023-02-18  2:52   ` Jens Axboe

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=20230217070322.14163-2-ankit.kumar@samsung.com \
    --to=ankit.kumar@samsung.com \
    --cc=axboe@kernel.dk \
    --cc=fio@vger.kernel.org \
    --cc=vincentfu@gmail.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.