Received-SPF: pass (google.com: domain of linux-kernel+bounces-187720-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Thu, 23 May 2024 08:34:09 -0700
From: Roman Gushchin <roman.gushchin@linux.dev>
To: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Muchun Song <muchun.song@linux.dev>,
	Yosry Ahmed <yosryahmed@google.com>, ying.huang@intel.com,
	feng.tang@intel.com, fengwei.yin@intel.com, oliver.sang@intel.com,
	kernel-team@meta.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] memcg: rearrage fields of mem_cgroup_per_node
Message-ID: <Zk9h8YFiYhqEWq1A@P9FQF9L96D.corp.robot.car>
References: <20240523034824.1255719-1-shakeel.butt@linux.dev>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240523034824.1255719-1-shakeel.butt@linux.dev>

On Wed, May 22, 2024 at 08:48:24PM -0700, Shakeel Butt wrote:
> Kernel test robot reported [1] performance regression for will-it-scale
> test suite's page_fault2 test case for the commit 70a64b7919cb ("memcg:
> dynamically allocate lruvec_stats"). After inspection it seems like the
> commit has unintentionally introduced false cache sharing.
> 
> After the commit the fields of mem_cgroup_per_node which get read on the
> performance critical path share the cacheline with the fields which
> get updated often on LRU page allocations or deallocations. This has
> caused contention on that cacheline and the workloads which manipulates
> a lot of LRU pages are regressed as reported by the test report.
> 
> The solution is to rearrange the fields of mem_cgroup_per_node such that
> the false sharing is eliminated. Let's move all the read only pointers
> at the start of the struct, followed by memcg-v1 only fields and at the
> end fields which get updated often.
> 
> Experiment setup: Ran fallocate1, fallocate2, page_fault1, page_fault2
> and page_fault3 from the will-it-scale test suite inside a three level
> memcg with /tmp mounted as tmpfs on two different machines, one a single
> numa node and the other one, two node machine.
> 
>  $ ./[testcase]_processes -t $NR_CPUS -s 50
> 
> Results for single node, 52 CPU machine:
> 
> Testcase        base        with-patch
> 
> fallocate1      1031081     1431291  (38.80 %)
> fallocate2      1029993     1421421  (38.00 %)
> page_fault1     2269440     3405788  (50.07 %)
> page_fault2     2375799     3572868  (50.30 %)
> page_fault3     28641143    28673950 ( 0.11 %)
> 
> Results for dual node, 80 CPU machine:
> 
> Testcase        base        with-patch
> 
> fallocate1      2976288     3641185  (22.33 %)
> fallocate2      2979366     3638181  (22.11 %)
> page_fault1     6221790     7748245  (24.53 %)
> page_fault2     6482854     7847698  (21.05 %)
> page_fault3     28804324    28991870 ( 0.65 %)
> 
> Fixes: 70a64b7919cb ("memcg: dynamically allocate lruvec_stats")
> Reported-by: kernel test robot <oliver.sang@intel.com>
> Closes: https://lore.kernel.org/oe-lkp/202405171353.b56b845-oliver.sang@intel.com
> Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>

Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>

Thanks!