[中英对照]Introduction to Remote Direct Memory Access (RDMA) | RDMA概述

前言： 什么是RDMA? 简单来说，RDMA就是指不通过操作系统(OS)内核以及TCP/IP协议栈在网络上传输数据，因此延迟(latency)非常低，CPU消耗非常少。 下面给出一篇简单介绍RDMA的文章之中英文对照翻译。

Introduction to Remote Direct Memory Access (RDMA) | RDMA概述

1. What is RDMA? | 什么是RDMA

Direct memory access (DMA) is an ability of a device to access host memory directly, without the intervention of the CPU(s).

RDMA (Remote DMA) is the ability of accessing (i.e. reading from or writing to) memory on a remote machine without interrupting the processing of the CPU(s) on that system.

DMA(直接内存访问）指的是设备有能力直接访问主机内存，而不需要CPU的干预。

RDMA（远程直接内存访问）则指的是直接访问（读取或写入）远程主机内存的能力，不需要远程主机系统的CPU参与。

扩展 1： What is RDMA? (截图来源)

2. So? why is this so good? | 为嘛这么好呢

Using RDMA has the following major advantages:

• Zero-copy - applications can perform data transfer without the network software stack involvement and data is being send received directly to the buffers without being copied between the network layers.
• Kernel bypass - applications can perform data transfer directly from userspace without the need to perform context switches.
• No CPU involvement - applications can access remote memory without consuming any CPU in the remote machine. The remote memory machine will be read without any intervention of remote process (or processor). The caches in the remote CPU(s) won't be filled with the accessed memory content.
• Message based transactions - the data is handled as discrete messages and not as a stream, which eliminates the need of the application to separate the stream into different messages/transactions.
• Scatter/gather entries support - RDMA supports natively working with multiple scatter/gather entries i.e. reading multiple memory buffers and sending them as one stream or getting one stream and writing it to multiple memory buffers.

使用RDMA的优势所在：

• 零拷贝 - 应用程序能够直接执行数据传输，在不涉及到网络软件栈的情况下。数据能够被直接发送到缓冲区或者能够直接从缓冲区里接收，而不需要被复制到网络层。
• 内核旁路 - 应用程序可以直接在用户态执行数据传输，不需要在内核态与用户态之间做上下文切换。
• 不需要CPU干预 - 应用程序可以访问远程主机内存而不消耗远程主机中的任何CPU。远程主机内存能够被读取而不需要远程主机上的进程（或CPU)参与。远程主机的CPU的缓存(cache)不会被访问的内存内容所填充。
• 消息基于事务 - 数据被处理为离散消息而不是流，消除了应用程序将流切割为不同消息/事务的需求。
  
• 支持分散/聚合 - RDMA原生态支持分散/聚合。也就是说，读取多个内存缓冲区然后作为一个流发出去或者接收一个流然后写入到多个内存缓冲区里去。
  

扩展2: RDMA - How does it Work

3. Where can I find RDMA? | 哪里需要用到RDMA

You can find RDMA in industries that need at least one the following:

• Low latency - For example: HPC, financial services, web 2.0
• High Bandwidth - For example: HPC, medical appliances, storage and backup systems, cloud computing
• Small CPU footprint  - For example: HPC, cloud computing

And in many-many more other industries...

在业界，RDMA在下列场景中使用：

• 低延迟 - 例如： HPC, 金融服务，web 2.0
• 高带宽 - 例如： HPC, 医疗服务，存储与备份系统，云计算
• CPU占用小 - 例如： HPC， 云计算

还有很多的其他行业...

4. Which network protocols support RDMA? | 支持RDMA的网络协议有哪些

Today, there are several network protocols which support RDMA:

• InfiniBand (IB) - a new generation network protocol which supports RDMA natively from the beginning. Since this is a new network technology, it requires NICs and switches which supports this technology.
• RDMA Over Converged Ethernet (RoCE) - a network protocol which allows performing RDMA over Ethernet network. Its lower network headers are Ethernet headers and its upper network headers (including the data) are InfiniBand headers. This allows using RDMA over standard Ethernet infrastructure (switches). Only the NICs should be special and support RoCE.
• Internet Wide Area RDMA Protocol (iWARP) - a network protocol which allows performing RDMA over TCP. There are features that exist in IB and RoCE and aren't supported in iWARP. This allows using RDMA over standard Ethernet infrastructure (switches). Only the NICs should be special and support iWARP (if CPU offloads are used) otherwise, all iWARP stacks can be implemented in SW and loosing most of the RDMA performance advantages.

时至今日，支持RDMA的网络协议不止一个：

• IB - 从诞生之日起就支持RDMA的新一代网络协议。IB是一种新的网络技术，需要网卡和交换机都支持才行。
• RoCE - 允许在以太网网络中执行RDMA操作的网络协议(注：开始叫做IBoE, 后改为RoCE)。RoCE的较低的网络包头是以太网包头，较高的网络包头(包括数据)是IB包头。在标准的以太网基础设施(交换机)上就能跑RDMA，唯一特殊的地方就是网卡(NIC)必须支持RoCE。
• iWARP - 运行在TCP上执行RDMA操作的网络协议（即是RDMA over TCP）。IB和RoCE都支持的功能，iWARP并不支持。在标准的以太网基础设施(交换机)上就能跑RDMA,唯一特殊的地方就是网卡(NIC)必须支持iWARP(如果使用CPU offloads)。否则，所有的iWARP栈可以在软件上实现，那么就会失去大部分的RDMA性能优势。

5. Does it mean that I need to learn several programming APIs? | 需要学习好几种不同的编程API吗

No. Luckily, the same API (i.e. verbs) can be used for all the above-mentioned RDMA enabled network protocols. In *nix it is libibverbs and kernel verbs and in Windows it is Network Direct (ND).

不用。幸运的是，同一套API(也就是verbs)能够用于上面的支持RDMA的所有网络协议。在*nix平台，API是libibverbs和kernel verbs, 在Windows上则是ND。

6. Are those network protocols interoperable? | 网络协议可以互操作吗

Since those are different network protocols, their packets are completely different and they cannot send/receive messages directly without any router/gateway between them. However, the same code can support all of them. Since all those network protocols support libibverbs, the same binary can be used without even the need to recompile the source code.

不同的网络协议的数据包格式是完全不相同的。在不同的网络协议之间，如果没有路由器/网关，那么彼此之间不可能收发数据。然后，同一套代码能够支持所有网络协议，因为那些网络协议都支持libibverbs。甚至不需要编译源代码就可以使用同一个二进制文件。

7. Do I need to download special packages to use RDMA or is it part of the Operating System? | 用RDMA需要装额外的包吗 or RDMA是OS的一部分吗

For several Operating Systems, RDMA support is embedded within the kernel. For example, Linux which supports RDMA natively and all major Linux distributions support it. Other Operating Systems may need to download a package (such as OFED) to add RDMA support to it.

在不止一个操作系统上，RDMA支持被内嵌在OS内核中。例如，Linux原生态地支持RDMA, 所有主要的Linux发布版本都支持。其他操作系统，可能需要下载一个包(例如OFED)，然后增加对RDMA的支持。

推荐阅读：

1. InfiniBand的版本演进、基础观念、传量传速
2. RDMA : https://en.wikipedia.org/wiki/Remote_direct_memory_access
3. IB : https://en.wikipedia.org/wiki/InfiniBand
4. iSER : https://en.wikipedia.org/wiki/ISCSI_Extensions_for_RDMA
5. iWARP : https://en.wikipedia.org/wiki/IWARP
6. RoCE : https://en.wikipedia.org/wiki/RDMA_over_Converged_Ethernet
7. SDP : https://en.wikipedia.org/wiki/Sockets_Direct_Protocol
8. SRP : https://en.wikipedia.org/wiki/SCSI_RDMA_Protocol
9. A Critique of RDMA （对RDMA的批评）