Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <bdcf9676-7846-1f14-1dd1-80cb9dcb0794@bytedance.com>
Date:   Wed, 21 Sep 2022 11:55:59 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:102.0)
 Gecko/20100101 Thunderbird/102.2.1
Subject: Re: [PATCH v2] iommu/iova: Optimize alloc_iova with rbtree_augmented
To:     "wangjie (L)" <wangjie125@huawei.com>, joro@8bytes.org,
        will@kernel.org
Cc:     iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
        robin.murphy@arm.com, haifeng.zhao@linux.intel.com,
        john.garry@huawei.com
References: <20220824095139.66477-1-zhangpeng.00@bytedance.com>
 <42909903-5b6c-efe8-9ed3-3ac012f1a421@huawei.com>
From:   Peng Zhang <zhangpeng.00@bytedance.com>
In-Reply-To: <42909903-5b6c-efe8-9ed3-3ac012f1a421@huawei.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

> This patch seems to solve the performance issues i have.  Currently my 
> nic's rx performance is unstable in large-capacity scenarios. I applied 
> this patch to 5.19 rc4 and tested 8 times rx performance in these 
> scenes. Here are test results, "before" row is the result of 5.19 rc4. 
> "after" row means 5.19 rc4 with this patch, the unit is Mbits/s
> 
>      1    2    3    4    5    6    7    8
> before    55430    76701    84194    77560    88292    90106    87770    
> 77273
> after    92770    92767    92792    92764    92742    92696    92781    
> 92756
> 
> Obviously, after using this patch, the performance is stable.

Thank you for your test. Can you add a "Tested-by" token?
I plan to update the commit message in the next version.