linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Laura Abbott <labbott@kernel.org>,
	Oliver Sang <oliver.sang@intel.com>,
	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>,
	linux-mm <linux-mm@kvack.org>,
	lkp@lists.01.org, lkp@intel.com, ying.huang@intel.com,
	feng.tang@intel.com, zhengjun.xing@intel.com,
	Minchan Kim <minchan@kernel.org>,
	Chris Goldsworthy <cgoldswo@codeaurora.org>
Subject: [PATCH v3] mm: fs: invalidate bh_lrus for only cold path
Date: Tue,  7 Sep 2021 14:23:47 -0700	[thread overview]
Message-ID: <20210907212347.1977686-1-minchan@kernel.org> (raw)

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
Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
* v2: https://lore.kernel.org/lkml/20210601145425.1396981-1-minchan@kernel.org/
* v1: https://lore.kernel.org/lkml/YK0oQ76zX0uVZCwQ@google.com/
 fs/buffer.c                 |  8 ++++++--
 include/linux/buffer_head.h |  4 ++--
 mm/swap.c                   | 19 ++++++++++++++++---
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index ab7573d72dd7..c615387aedca 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1425,12 +1425,16 @@ void invalidate_bh_lrus(void)
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
-void invalidate_bh_lrus_cpu(int cpu)
+/*
+ * It's called from workqueue context so we need a bh_lru_lock to close
+ * the race with preemption/irq.
+ */
+void invalidate_bh_lrus_cpu(void)
 {
 	struct bh_lru *b;
 
 	bh_lru_lock();
-	b = per_cpu_ptr(&bh_lrus, cpu);
+	b = this_cpu_ptr(&bh_lrus);
 	__invalidate_bh_lrus(b);
 	bh_lru_unlock();
 }
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 6486d3c19463..36f33685c8c0 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(int cpu);
+void invalidate_bh_lrus_cpu(void);
 bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
@@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
-static inline void invalidate_bh_lrus_cpu(int cpu) {}
+static inline void invalidate_bh_lrus_cpu(void) {}
 static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
diff --git a/mm/swap.c b/mm/swap.c
index 897200d27dd0..af3cad4e5378 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -620,7 +620,6 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 
 	activate_page_drain(cpu);
-	invalidate_bh_lrus_cpu(cpu);
 }
 
 /**
@@ -703,6 +702,20 @@ void lru_add_drain(void)
 	local_unlock(&lru_pvecs.lock);
 }
 
+/*
+ * It's called from per-cpu workqueue context in SMP case so
+ * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on
+ * the same cpu. It shouldn't be a problem in !SMP case since
+ * the core is only one and the locks will disable preemption.
+ */
+static void lru_add_and_bh_lrus_drain(void)
+{
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	local_unlock(&lru_pvecs.lock);
+	invalidate_bh_lrus_cpu();
+}
+
 void lru_add_drain_cpu_zone(struct zone *zone)
 {
 	local_lock(&lru_pvecs.lock);
@@ -717,7 +730,7 @@ 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();
 }
 
 /*
@@ -858,7 +871,7 @@ void lru_cache_disable(void)
 	 */
 	__lru_add_drain_all(true);
 #else
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 #endif
 }
 
-- 
2.33.0.309.g3052b89438-goog



             reply	other threads:[~2021-09-07 21:24 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-07 21:23 Minchan Kim [this message]
2021-09-20 22:33 ` Minchan Kim
2021-09-20 23:29 ` Linus Torvalds
2021-09-20 23:50   ` Minchan Kim
2021-09-21  0:23     ` Linus Torvalds
2021-09-21  1:03       ` Konstantin Ryabitsev

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=20210907212347.1977686-1-minchan@kernel.org \
    --to=minchan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgoldswo@codeaurora.org \
    --cc=david@redhat.com \
    --cc=feng.tang@intel.com \
    --cc=joaodias@google.com \
    --cc=labbott@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@intel.com \
    --cc=lkp@lists.01.org \
    --cc=mhocko@suse.com \
    --cc=oliver.sang@intel.com \
    --cc=surenb@google.com \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    --cc=zhengjun.xing@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox