Received-SPF: pass (google.com: domain of linux-kernel+bounces-60872-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <2880b448-2431-44be-94ba-32eb46526c66@kernel.org>
Date: Sun, 11 Feb 2024 09:59:18 -0700
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH V4 0/5] mlx5 ConnectX control misc driver
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jakub Kicinski <kuba@kernel.org>, Saeed Mahameed <saeed@kernel.org>,
 Arnd Bergmann <arnd@arndb.de>,
 Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
 Leon Romanovsky <leonro@nvidia.com>, Jiri Pirko <jiri@nvidia.com>,
 Leonid Bloch <lbloch@nvidia.com>, Itay Avraham <itayavr@nvidia.com>,
 Saeed Mahameed <saeedm@nvidia.com>,
 Aron Silverton <aron.silverton@oracle.com>,
 Christoph Hellwig <hch@infradead.org>, andrew.gospodarek@broadcom.com,
 linux-kernel@vger.kernel.org, netdev@vger.kernel.org
References: <20240207072435.14182-1-saeed@kernel.org>
 <20240207070342.21ad3e51@kernel.org> <ZcRgp76yWcDfEbMy@x130>
 <20240208181555.22d35b61@kernel.org>
 <2bdc5510-801a-4601-87a3-56eb941d661a@kernel.org>
 <20240210010129.GA1010957@nvidia.com>
Content-Language: en-US
From: David Ahern <dsahern@kernel.org>
In-Reply-To: <20240210010129.GA1010957@nvidia.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

On 2/9/24 6:01 PM, Jason Gunthorpe wrote:
> On Fri, Feb 09, 2024 at 03:42:16PM -0700, David Ahern wrote:
>> On 2/8/24 7:15 PM, Jakub Kicinski wrote:
>>>>> Ah yes, the high frequency counters. Something that is definitely
>>>>> impossible to implement in a generic way. You were literally in the
>>>>> room at netconf when David Ahern described his proposal for this.
>>
>> The key point of that proposal is host memory mapped to userspace where
>> H/W counters land (either via direct DMA by a H/W push or a
>> kthread/timer pulling in updates). That is similar to what is proposed here.
> 
> The counter experiment that inspired Saeed to write about it here was
> done using mlx5ctl interfaces and some other POC stuff on an RDMA
> network monitoring RDMA workloads, inspecting RDMA objects.
> 
> So if your proposal also considers how to select RDMA object counters,
> control the detailed sampling hardware with RDMA stuff, and works
> on a netdev-free InfiniBand network, then it might be interesting.

Response at netconf in September was mixed. As I recall Jakub for
example was shaking his head at 'yet another stats proposal', but since
he has referenced it a couple of times now maybe it is worth moving
beyond slides to a POC. The uapi discussed was netlink (genl) based;
driver hooks were not discussed. Perhaps I can get a working POC for
both stacks by netdevconf in July.