All of lore.kernel.org
 help / color / mirror / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: lkp@lists.01.org
Subject: Re: [mm] 8cc621d2f4: fio.write_iops -21.8% regression
Date: Tue, 07 Sep 2021 09:55:55 -0700	[thread overview]
Message-ID: <YTeZm71hmcbJp+E2@google.com> (raw)
In-Reply-To: <034fc860-d0d0-0c61-09d2-3c41c4f020c6@intel.com>

[-- Attachment #1: Type: text/plain, Size: 2471 bytes --]

Hi,

On Fri, Sep 03, 2021 at 03:11:33PM +0800, Xing, Zhengjun wrote:
> Hi Minchan,
> 
>     Do you have time to look at this? I re-test it in  v5.14, the regression
> still existed. Thanks.

Reminding me the issue, again, Xing. That's because the patch
was not merged yet so let me send it again.

Andrew?

>From 8caadeb49d82403a08643dfbdb0b7749017c00bb Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Tue, 25 May 2021 08:19:17 -0700
Subject: [PATCH] mm: fs: invalidate bh_lrus for only cold path

kernel test robot reported the regression of fio.write_iops[1]
with [2].

Since lru_add_drain is called frequently, invalidate bh_lrus
there could increase bh_lrus cache miss ratio, which needs
more IO in the end.

This patch moves the bh_lrus invalidation from the hot path(
e.g., zap_page_range, pagevec_release) to cold path(i.e.,
lru_add_drain_all, lru_cache_disable).

[1] https://lore.kernel.org/lkml/20210520083144.GD14190(a)xsang-OptiPlex-9020/
[2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration
Cc: Xing, Zhengjun <zhengjun.xing@intel.com>
Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 mm/swap.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 1958d5feb148..3e25d99a9dbb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);

 	activate_page_drain(cpu);
-	invalidate_bh_lrus_cpu(cpu);
 }

 /**
@@ -725,6 +724,17 @@ void lru_add_drain(void)
 	local_unlock(&lru_pvecs.lock);
 }

+static void lru_add_and_bh_lrus_drain(void)
+{
+	int cpu;
+
+	local_lock(&lru_pvecs.lock);
+	cpu = smp_processor_id();
+	lru_add_drain_cpu(cpu);
+	local_unlock(&lru_pvecs.lock);
+	invalidate_bh_lrus_cpu(cpu);
+}
+
 void lru_add_drain_cpu_zone(struct zone *zone)
 {
 	local_lock(&lru_pvecs.lock);
@@ -739,7 +749,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);

 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 }

 /*
@@ -880,7 +890,7 @@ void lru_cache_disable(void)
 	 */
 	__lru_add_drain_all(true);
 #else
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 #endif
 }

--
2.31.1.818.g46aad6cb9e-goog

WARNING: multiple messages have this Message-ID (diff)
From: Minchan Kim <minchan@kernel.org>
To: "Xing, Zhengjun" <zhengjun.xing@intel.com>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Goldsworthy <cgoldswo@codeaurora.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Laura Abbott <labbott@kernel.org>,
	David Hildenbrand <david@redhat.com>,
	John Dias <joaodias@google.com>,
	Matthew Wilcox <willy@infradead.org>,
	Michal Hocko <mhocko@suse.com>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	LKML <linux-kernel@vger.kernel.org>,
	lkp@lists.01.org, lkp@intel.com,
	Minchan Kim <minchan.kim@gmail.com>
Subject: Re: [LKP] Re: [mm] 8cc621d2f4: fio.write_iops -21.8% regression
Date: Tue, 7 Sep 2021 09:55:55 -0700	[thread overview]
Message-ID: <YTeZm71hmcbJp+E2@google.com> (raw)
In-Reply-To: <034fc860-d0d0-0c61-09d2-3c41c4f020c6@intel.com>

Hi,

On Fri, Sep 03, 2021 at 03:11:33PM +0800, Xing, Zhengjun wrote:
> Hi Minchan,
> 
>     Do you have time to look at this? I re-test it in  v5.14, the regression
> still existed. Thanks.

Reminding me the issue, again, Xing. That's because the patch
was not merged yet so let me send it again.

Andrew?

From 8caadeb49d82403a08643dfbdb0b7749017c00bb Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Tue, 25 May 2021 08:19:17 -0700
Subject: [PATCH] mm: fs: invalidate bh_lrus for only cold path

kernel test robot reported the regression of fio.write_iops[1]
with [2].

Since lru_add_drain is called frequently, invalidate bh_lrus
there could increase bh_lrus cache miss ratio, which needs
more IO in the end.

This patch moves the bh_lrus invalidation from the hot path(
e.g., zap_page_range, pagevec_release) to cold path(i.e.,
lru_add_drain_all, lru_cache_disable).

[1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/
[2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration
Cc: Xing, Zhengjun <zhengjun.xing@intel.com>
Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 mm/swap.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 1958d5feb148..3e25d99a9dbb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);

 	activate_page_drain(cpu);
-	invalidate_bh_lrus_cpu(cpu);
 }

 /**
@@ -725,6 +724,17 @@ void lru_add_drain(void)
 	local_unlock(&lru_pvecs.lock);
 }

+static void lru_add_and_bh_lrus_drain(void)
+{
+	int cpu;
+
+	local_lock(&lru_pvecs.lock);
+	cpu = smp_processor_id();
+	lru_add_drain_cpu(cpu);
+	local_unlock(&lru_pvecs.lock);
+	invalidate_bh_lrus_cpu(cpu);
+}
+
 void lru_add_drain_cpu_zone(struct zone *zone)
 {
 	local_lock(&lru_pvecs.lock);
@@ -739,7 +749,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);

 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 }

 /*
@@ -880,7 +890,7 @@ void lru_cache_disable(void)
 	 */
 	__lru_add_drain_all(true);
 #else
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 #endif
 }

--
2.31.1.818.g46aad6cb9e-goog


  reply	other threads:[~2021-09-07 16:55 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-20  8:31 [mm] 8cc621d2f4: fio.write_iops -21.8% regression kernel test robot
2021-05-20  8:31 ` kernel test robot
2021-05-20 18:36 ` Minchan Kim
2021-05-20 18:36   ` Minchan Kim
2021-05-21  5:29   ` Xing, Zhengjun
2021-05-24 17:37   ` Chris Goldsworthy
2021-05-24 17:37     ` Chris Goldsworthy
2021-05-25 15:16     ` Minchan Kim
2021-05-25 15:16       ` Minchan Kim
2021-05-25 16:39       ` Minchan Kim
2021-05-25 16:39         ` Minchan Kim
2021-05-25 16:57         ` Chris Goldsworthy
2021-05-25 16:57           ` Chris Goldsworthy
2021-09-03  7:11           ` Xing, Zhengjun
2021-09-03  7:11             ` [LKP] " Xing, Zhengjun
2021-09-07 16:55             ` Minchan Kim [this message]
2021-09-07 16:55               ` Minchan Kim
2021-09-07 18:46               ` Chris Goldsworthy
2021-09-07 18:46                 ` [LKP] " Chris Goldsworthy
2021-09-07 21:27                 ` Minchan Kim
2021-09-07 21:27                   ` [LKP] " Minchan Kim
2021-05-25 16:53       ` Chris Goldsworthy
2021-05-25 16:53         ` Chris Goldsworthy

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=YTeZm71hmcbJp+E2@google.com \
    --to=minchan@kernel.org \
    --cc=lkp@lists.01.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 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.