AmazonEC2计算单元和GCEU(谷歌计算引擎单元)-AmazonEC2ComputeUnitandGCEU(GoogleComputeEngineUnit)

12  

According to Amazon,

根据亚马逊,

One EC2 Compute Unit provides the equivalent CPU capacity of a 1.0-1.2 GHz 2007 Opteron or 2007 Xeon processor. This is also the equivalent to an early-2006 1.7 GHz Xeon processor referenced in our original documentation.

一个EC2计算单元提供的CPU容量相当于1.0-1.2 GHz 2007 Opteron或2007 Xeon处理器。这也相当于我们原始文档中引用的2006年初的1.7 GHz Xeon处理器。

According to Google,

根据谷歌,

GCEU (Google Compute Engine Unit), or GQ for short, is a unit of CPU capacity that we use to describe the compute power of our instance types. We chose 2.75 GQ’s to represent the minimum power of one logical core (a hardware hyper-thread) on our Sandy Bridge platform.

GCEU(谷歌计算引擎单元)，简称GQ，是我们用来描述实例类型的计算能力的CPU容量单元。我们选择了2.75 GQ来表示Sandy Bridge平台上一个逻辑核心(一个硬件超线程)的最小功耗。

It's hard to make a 1:1 comparison with such a vague description from Google. Assuming Amazon and Google use the same CPUs, this would be as follows:

很难与谷歌中如此模糊的描述进行1:1的比较。假设Amazon和谷歌使用相同的cpu，这将如下所示:

Using Amazon's Cluster Compute Eight Extra Large Instance as an example, because it defines the CPU and the CU rating.

使用Amazon的集群计算8个额外的大型实例，因为它定义了CPU和CU的级别。

88 EC2 Compute Units (2 x Intel Xeon E5-2670, eight-core "Sandy Bridge" architecture)

88个EC2计算单元(2 x Intel Xeon E5-2670, 8核“Sandy Bridge”架构)

This is 32 logical cores, 2x 8 physical with hyperthreading. With Google's rating of one logical core being 2.75 GQ, this turns out to be in-line with Amazon, being 88 GQ in total.

这是32个逻辑内核，2x 8是带超线程的物理内核。谷歌对一个逻辑核心的评分是2.75 GQ，这与亚马逊的评分是一致的，总共88 GQ。

Again, this is assuming Google and Amazon would use the same CPU (which is likely), and would be impossible to know without an official statement from Google, or a CPU-stat from a running instance.

同样，假设谷歌和Amazon会使用相同的CPU(很可能)，如果没有谷歌的官方声明，或者运行实例中的CPU-stat，就不可能知道。

10  

The definition of 2.75 GCEUs is given in the developer documentation as the compute power given by a single processing core in the Intel's Sandy Bridge platform processors that Google has selected.

在开发人员的文档中给出了2.75 GCEUs的定义，它是由谷歌选择的Intel Sandy Bridge平台处理器中的单个处理核心提供的计算能力。

Amazon's documentation defines a single EC2 compute unit as "the equivalent CPU capacity of a 1.0-1.2 GHz 2007 Opteron or 2007 Xeon processor." In the description for one of the service levels, it defines 33 EC2 compute units as being roughly equivalent to eight cores worth of Intel's older Nehalem platform. It also defines 88 EC2 compute units as being roughly equivalent to 16 cores worth of Sandy Bridge.

Amazon的文档将单个EC2计算单元定义为“相当于1.0-1.2 GHz 2007 Opteron或2007 Xeon处理器的CPU容量”。在其中一个服务级别的描述中，它定义了33个EC2计算单元，大约相当于英特尔旧的Nehalem平台的8个核心。它还将88个EC2计算单元定义为大约相当于16个砂桥的核心。

Blindly assuming that Amazon and Google are using roughly the same processors in their Sandy Bridge setups (not necessarily a safe assumption), each Sandy Bridge core is about 5.5 EC2 compute units. We can now compare the two units: what happens when you divide 5.5 by 2.75? You get 2.

盲目地假设Amazon和谷歌在他们的Sandy Bridge安装中使用了大致相同的处理器(不一定是安全的假设)，每个Sandy Bridge的核心大约是5.5个EC2计算单元。现在我们可以比较这两个单位:当你将5.5除以2。75的时候会发生什么?你得到2。

tl;dr: One unit of GECU is probably about two units of EC2. This is utter and complete speculation and will need to be proven by real-world testing and use.

GECU的一个单位大概是EC2的两个单位。这是完全的推测，需要通过真实的测试和使用来证明。

4  

According to the Google Compute Engine FAQs, "one GCEU is at least as powerful as the CPU capacity of a 1.0-1.2 GHz 2007 Opteron." More info here:

根据谷歌计算引擎常见问题，“一个GCEU至少与1.0-1.2 GHz的Opteron的CPU容量一样强大。”更多信息:

https://developers.google.com/compute/docs/faq#morecompute

https://developers.google.com/compute/docs/faq morecompute

2  

The best answer would be your own benchmarks, as any other benchmark might give results optimized for a different use case.

最好的答案是您自己的基准测试，因为任何其他基准测试都可能给出针对不同用例优化的结果。

The second best answer are independent benchmarks, as http://gigaom.com/2013/03/15/by-the-numbers-how-google-compute-engine-stacks-up-to-amazon-ec2/.

第二个最佳答案是独立的基准，如http://gigaom.com/2013/03/15/by- number -how-google- computer -engine- stacks-amazs-amaz-ec2/。

Looking at those numbers, it makes sense to ponder if your code is CPU or IO bounded. With the same theoretical CPU, how much faster would your app work if persistent writes where 4 times faster? Or if network communications where 20 times faster?

看看这些数字，考虑您的代码是否有CPU或IO限制是有意义的。使用同样的理论CPU，如果持久化写的速度是原来的4倍，你的应用程序运行的速度会有多快?或者如果网络通信快20倍?

Fortunately quick tests in both and other platforms should be fast, and bring considerable cost savings in the long term.

幸运的是，两种平台和其他平台的快速测试应该很快，并且在长期内带来可观的成本节约。

2  

I know this is late, but maybe it will help someone. On a single benchmark run:

我知道这很晚了，但也许它能帮到别人。在单一基准测试运行:

Google Compute Engine: 0.185 s at 2014-11-28 10:17:16 on : 1 x Intel(R) Xeon(R) CPU @ 2.60GHz; 1.7 GB RAM; Ubuntu 14.04 (trusty); PHP ver.: 5.5.9-1ubuntu4.5 (small)

谷歌计算引擎:2014-11-28 10:17:16时0.185 s:1 x Intel(R) Xeon(R) CPU @ 2.6 ghz;1.7 GB内存;Ubuntu 14.04(可靠的);PHP版本。:5.5.9-1ubuntu4.5(小)

AWS: 0.167 s at 2014-12-01 11:00:18 on : 1 x Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz; 2 GB RAM; Ubuntu 14.04 (trusty); PHP ver.: 5.5.9-1ubuntu4.5 (small)

AWS: 0.167 s at 2014-12-01 11:00:18 on:1 x Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz;2 GB内存;Ubuntu 14.04(可靠的);PHP版本。:5.5.9-1ubuntu4.5(小)

DigitalOcean: 0.357 s at 2014-12-01 10:03:28 on : 2 x Intel(R) Xeon(R) CPU E5-2630L v2 @ 2.40GHz; 2 GB RAM; Ubuntu 14.04 (trusty); PHP ver.: 5.5.9-1ubuntu4.4 ($20 one)

数字海洋:2014-12-01 10:03:28 0.357 s on:2 x Intel(R) Xeon(R) CPU E5-2630L v2 @ 2.4 ghz;2 GB内存;Ubuntu 14.04(可靠的);PHP版本。:5.5.9-1ubuntu4.4(20美元)

With ApacheBench:

ApacheBench:

GCE:

全球教育运动:

• 100 100 = 3.14 #/s - 39 dropped connection
• 100 = 3.14 #/s - 39断开连接
• 200 200 = 4.7 #/s - 132 dropped
• 200 = 4.7 /s - 132下降
• 400 400 = 7.7 #/s - 144 dropped
• 400 = 7.7 #/s - 144下降

AWS:

AWS:

• 100 100 = 5.8 #/s - 32 dropped
• 100100 = 5.8 #/s - 32下降。
• 200 200 = 8.9 #/s - 110 dropped
• 200 = 8.9 /s - 110下降
• 400 400 = 17.6 #/s - 132 dropped
• 400 = 17.6 #/s - 132下降

DO:

做的事:

• 100 100 = 4.37 #/s - 31 dropped
• 100100 = 4.37 #/s - 31下降。
• 200 200 = 6.6 #/s - 131 dropped
• 200 = 6.6 /s - 131下降
• 400 400 = 13.5 #/s - 132 dropped connections
• 400 = 13.5 #/s - 132断开连接