[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <9e2ee23c-d91b-45e4-a413-048f8d68970d@nvidia.com>
Date: Sun, 20 Oct 2024 18:26:38 +0300
From: Yonatan Maman <ymaman@...dia.com>
To: Zhu Yanjun <yanjun.zhu@...ux.dev>, Christoph Hellwig <hch@...radead.org>
Cc: nouveau@...ts.freedesktop.org, linux-kernel@...r.kernel.org,
linux-rdma@...r.kernel.org, linux-mm@...ck.org, herbst@...hat.com,
lyude@...hat.com, dakr@...hat.com, airlied@...il.com, simona@...ll.ch,
jgg@...pe.ca, leon@...nel.org, jglisse@...hat.com,
akpm@...ux-foundation.org, dri-devel@...ts.freedesktop.org,
apopple@...dia.com, bskeggs@...dia.com
Subject: Re: [PATCH v1 0/4] GPU Direct RDMA (P2P DMA) for Device Private Pages
On 18/10/2024 10:26, Zhu Yanjun wrote:
> External email: Use caution opening links or attachments
>
>
> 在 2024/10/16 17:16, Yonatan Maman 写道:
>>
>>
>> On 16/10/2024 7:23, Christoph Hellwig wrote:
>>> On Tue, Oct 15, 2024 at 06:23:44PM +0300, Yonatan Maman wrote:
>>>> From: Yonatan Maman <Ymaman@...dia.com>
>>>>
>>>> This patch series aims to enable Peer-to-Peer (P2P) DMA access in
>>>> GPU-centric applications that utilize RDMA and private device pages.
>>>> This
>>>> enhancement is crucial for minimizing data transfer overhead by
>>>> allowing
>>>> the GPU to directly expose device private page data to devices such as
>>>> NICs, eliminating the need to traverse system RAM, which is the native
>>>> method for exposing device private page data.
>>>
>>> Please tone down your marketing language and explain your factual
>>> changes. If you make performance claims back them by numbers.
>>>
>>
>> Got it, thanks! I'll fix that. Regarding performance, we’re achieving
>> over 10x higher bandwidth and 10x lower latency using perftest-rdma,
>> especially (with a high rate of GPU memory access).
>
> If I got this patch series correctly, this is based on ODP (On Demand
> Paging). And a way also exists which is based on non-ODP. From the
> following links, this way is implemented on efa, irdma and mlx5.
> 1. iRDMA
> https://lore.kernel.org/all/20230217011425.498847-1-yanjun.zhu@intel.com/
>
> 2. efa
> https://lore.kernel.org/lkml/20211007114018.GD2688930@ziepe.ca/t/
>
> 3. mlx5
> https://lore.kernel.org/all/1608067636-98073-5-git-send-email-
> jianxin.xiong@...el.com/
>
> Because these 2 methods are both implemented on mlx5, have you compared
> the test results with the 2 methods on mlx5?
>
> The most important results should be latency and bandwidth. Please let
> us know the test results.
>
> Thanks a lot.
> Zhu Yanjun
>
This patch-set aims to support GPU Direct RDMA for HMM ODP memory.
Compared to the dma-buf method, we achieve the same performance (BW and
latency), for GPU intensive test-cases (No CPU accesses during the test).
Powered by blists - more mailing lists