LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Feng Tang <feng.tang@intel.com>
To: Qian Cai <cai@lca.pw>, Andrew Morton <akpm@linux-foundation.org>,
	Dennis Zhou <dennis@kernel.org>, Tejun Heo <tj@kernel.org>,
	Christoph Lameter <cl@linux.com>
Cc: kernel test robot <rong.a.chen@intel.com>,
	Michal Hocko <mhocko@suse.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Matthew Wilcox <willy@infradead.org>,
	Mel Gorman <mgorman@suse.de>, Kees Cook <keescook@chromium.org>,
	Luis Chamberlain <mcgrof@kernel.org>,
	Iurii Zaikin <yzaikin@google.com>,
	andi.kleen@intel.com, tim.c.chen@intel.com,
	dave.hansen@intel.com, ying.huang@intel.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, lkp@lists.01.org
Subject: Re: [mm] 4e2c82a409: ltp.overcommit_memory01.fail
Date: Mon, 6 Jul 2020 21:24:43 +0800
Message-ID: <20200706132443.GA34488@shbuild999.sh.intel.com> (raw)
In-Reply-To: <20200706023614.GA1231@lca.pw>

Hi All,

Please help to review this fix patch, thanks!

It is against today's linux-mm tree. For easy review, I put the fix
into one patch, and I could split it to 2 parts for percpu-counter
and mm/util.c if it's preferred.

From 593f9dc139181a7c3bb1705aacd1f625f400e458 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Mon, 6 Jul 2020 14:48:29 +0800
Subject: [PATCH] mm/util.c: sync vm_committed_as when changing memory policy
 to OVERCOMMIT_NEVER

With the patch to improve scalability of vm_committed_as [1], 0day reported
the ltp overcommit_memory test case could fail (fail rate is about 5/50) [2].
The root cause is when system is running with loose memory overcommit policy
like OVERCOMMIT_GUESS/ALWAYS, the deviation of vm_committed_as could be big,
and once the policy is runtime changed to OVERCOMMIT_NEVER, vm_committed_as's 
batch is decreased to 1/64 of original one, but the deviation is not
compensated accordingly, and following __vm_enough_memory() check for vm
overcommit could be wrong due to this deviation, which breaks the ltp
overcommit_memory case.

Fix it by forcing a sync for percpu counter vm_committed_as when overcommit
policy is changed to OVERCOMMIT_NEVER (sysctl -w vm.overcommit_memory=2).
The sync itself is not a fast operation, and is toleratable given user is
not expected to frequently changing policy to OVERCOMMIT_NEVER.

[1] https://lore.kernel.org/lkml/1592725000-73486-1-git-send-email-feng.tang@intel.com/
[2] https://marc.info/?l=linux-mm&m=159367156428286 (can't find a link in lore.kernel.org)

Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
---
 include/linux/percpu_counter.h |  4 ++++
 lib/percpu_counter.c           | 14 ++++++++++++++
 mm/util.c                      | 11 ++++++++++-
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 0a4f54d..01861ee 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -44,6 +44,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
 			      s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
 int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+void percpu_counter_sync(struct percpu_counter *fbc);
 
 static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
 {
@@ -172,6 +173,9 @@ static inline bool percpu_counter_initialized(struct percpu_counter *fbc)
 	return true;
 }
 
+static inline void percpu_counter_sync(struct percpu_counter *fbc)
+{
+}
 #endif	/* CONFIG_SMP */
 
 static inline void percpu_counter_inc(struct percpu_counter *fbc)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a66595b..02d87fc 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -98,6 +98,20 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 }
 EXPORT_SYMBOL(percpu_counter_add_batch);
 
+void percpu_counter_sync(struct percpu_counter *fbc)
+{
+	unsigned long flags;
+	s64 count;
+
+	raw_spin_lock_irqsave(&fbc->lock, flags);
+	count = __this_cpu_read(*fbc->counters);
+	fbc->count += count;
+	__this_cpu_sub(*fbc->counters, count);
+	raw_spin_unlock_irqrestore(&fbc->lock, flags);
+}
+EXPORT_SYMBOL(percpu_counter_sync);
+
+
 /*
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
diff --git a/mm/util.c b/mm/util.c
index 52ed9c1..5fb62c0 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -746,14 +746,23 @@ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
+static void sync_overcommit_as(struct work_struct *dummy)
+{
+	percpu_counter_sync(&vm_committed_as);
+}
+
 int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-	if (ret == 0 && write)
+	if (ret == 0 && write) {
+		if (sysctl_overcommit_memory == OVERCOMMIT_NEVER)
+			schedule_on_each_cpu(sync_overcommit_as);
+
 		mm_compute_batch();
+	}
 
 	return ret;
 }
-- 
2.7.4
     

On Sun, Jul 05, 2020 at 10:36:14PM -0400, Qian Cai wrote:
> > In my last email, I was not saying OVERCOMMIT_NEVER is not a normal case,
> > but I don't think user will too frequently runtime change the overcommit
> > policy. And the fix patch of syncing 'vm_committed_as' is only called when
> > user calls 'sysctl -w vm.overcommit_memory=2'.
> > 
> > > The question is now if any of those regression fixes would now regress
> > > performance of OVERCOMMIT_NEVER workloads or just in-par with the data
> > > before the patchset?
> > 
> > For the original patchset, it keeps vm_committed_as unchanged for
> > OVERCOMMIT_NEVER policy and enlarge it for the other 2 loose policies
> > OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS, and I don't expect the "OVERCOMMIT_NEVER
> > workloads" performance  will be impacted. If you have suggetions for this
> > kind of benchmarks, I can test them to better verify the patchset, thanks!
> 
> Then, please capture those information into a proper commit log when you
> submit the regression fix on top of the patchset, and CC PER-CPU MEMORY
> ALLOCATOR maintainers, so they might be able to review it properly.




  reply index

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-21  7:36 [PATCH v5 0/3] make vm_committed_as_batch aware of vm overcommit policy Feng Tang
2020-06-21  7:36 ` [PATCH v5 1/3] proc/meminfo: avoid open coded reading of vm_committed_as Feng Tang
2020-06-21  7:36 ` [PATCH v5 2/3] mm/util.c: make vm_memory_committed() more accurate Feng Tang
2020-06-21  7:36 ` [PATCH v5 3/3] mm: adjust vm_committed_as_batch according to vm overcommit policy Feng Tang
2020-06-22 13:25   ` [mm] 4e2c82a409: will-it-scale.per_process_ops 1894.6% improvement kernel test robot
     [not found]   ` <20200702063201.GG3874@shao2-debian>
2020-07-02  7:12     ` [mm] 4e2c82a409: ltp.overcommit_memory01.fail Feng Tang
2020-07-05  3:20       ` Qian Cai
2020-07-05  4:44       ` Feng Tang
2020-07-05 12:15         ` Qian Cai
2020-07-05 12:58           ` Feng Tang
2020-07-05 15:52             ` Qian Cai
2020-07-06  1:43               ` Feng Tang
2020-07-06  2:36                 ` Qian Cai
2020-07-06 13:24                   ` Feng Tang [this message]
2020-07-06 13:34                     ` Andi Kleen
2020-07-06 23:42                       ` Andrew Morton
2020-07-07  2:38                       ` Feng Tang
2020-07-07  4:00                         ` Huang, Ying
2020-07-07  5:41                           ` Feng Tang
2020-07-09  4:55                             ` Feng Tang
2020-07-09 13:40                               ` Qian Cai
2020-07-09 14:15                                 ` Feng Tang
2020-07-10  1:38                                   ` Feng Tang
2020-07-10  3:26                                     ` Qian Cai
2020-07-07  1:06                     ` Dennis Zhou
2020-07-07  3:24                       ` Feng Tang
2020-07-07 10:28               ` Michal Hocko
2020-06-24  9:45 ` [PATCH v5 0/3] make vm_committed_as_batch aware of vm overcommit policy Michal Hocko
2020-07-07 11:43 [mm] 4e2c82a409: ltp.overcommit_memory01.fail Qian Cai
2020-07-07 12:06 ` Michal Hocko
2020-07-07 13:04   ` Qian Cai
2020-07-07 13:56     ` Michal Hocko

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=20200706132443.GA34488@shbuild999.sh.intel.com \
    --to=feng.tang@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi.kleen@intel.com \
    --cc=cai@lca.pw \
    --cc=cl@linux.com \
    --cc=dave.hansen@intel.com \
    --cc=dennis@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=keescook@chromium.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@lists.01.org \
    --cc=mcgrof@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=rong.a.chen@intel.com \
    --cc=tim.c.chen@intel.com \
    --cc=tj@kernel.org \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    --cc=yzaikin@google.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git