本文介绍了Azure的计算能力:特大型VM慢的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

谁能给我提供任何见解,为什么我的云部署会比一个片premises电脑慢马力条款?

Can anyone offer me any insights into why my cloud deployment would be slower than an on-premises computer in "horsepower" terms?

我有使用工作的作用,开展百万计算的(并行)一个计算密集型应用程序。

I have a compute intensive application which uses a worker role to carry out millions of computations (in parallel).

目前在Azure中我使用一个额外的大(8核心,16GB)VM做加工测试。平均而言它,而在4内核上运行,8GB导通premises机器,仅需15分钟,同样的code仅需45分钟便可每次迭代。

Currently in Azure I'm testing using an Extra Large (8 core, 16GB) VM to do the processing. On average it's taking 45 minutes per iteration whereas the same code running on a 4 core, 8GB on-premises machine was taking only 15 minutes.

Azure的日志指示总处理器利用率为99%,但我有12GB的内存免费的,所以我肯定会尝试加载更多的数据到内存每次迭代。

Azure logs indicate total processor utilisation is 99% but I have 12GB memory free so I'll definitely try loading more data into memory for each iteration.

是8个内核只是个别极低的规范呢?是本地存储真的地方?也就是说,是本地存储真正不同的物理设备上,从而获取从文件,并写入结果数据到硬盘是慢?

Are the 8 cores just individually very low spec? Is local storage really local? That is, is local storage really on a different physical device and therefore fetching data from file and writing results to disk is slow?

推荐答案

斯科特格思里(在Windows Azure的队主力)给我结果
嗨伊万,

Scott Guthrie (main at Windows Azure team) to me
Hi Ivan,

我们有其他的虚拟机硬件配置以及 - 包括多proc和高内存选项。你会看到在未来更多的选择。

We have other VM HW configurations as well – including multi-proc and high memory options. You’ll see even more options in the future.

希望这有助于

斯科特

我的测试:(处理器时间的100%)

卢卡斯 - 莱默的数学计算。多线程版本使用的Parallel.For实施

Lucas-Lehmer math calculations. Multithread version uses Parallel.For implementation

家用电脑的酷睿i7 3770K(4核3.5GHz的点¯x)(赢8)

单线程(小学17号):11676毫秒(11.6秒)

SINGLETHREADED (17 primary numbers): 11676 ms (11.6 secs.)

MULTITHREADED(小学17号):2816毫秒(2.8秒)

MULTITHREADED (17 primary numbers): 2816 ms (2.8 secs.)

Azure的大型VM(4芯×1.6 GHZ)(赢2008年的)

单线程(小学17号):37275毫秒

SINGLETHREADED (17 primary numbers): 37275 ms

17 MULTITHREADED主要数字):10118毫秒

MULTITHREADED 17 primary numbers): 10118 ms

Azure的超大VM(8芯×1.6 GHZ)(赢2008年的)

单线程(小学17号):36232毫秒

SINGLETHREADED (17 primary numbers): 36232 ms

MULTITHREADED(小学17号):6498米

MULTITHREADED (17 primary numbers): 6498 m

工作电脑 - AMD FX 6100(6芯点¯x3.3 GHz)的(赢7瓦特UPD)

单线程(小学17号):48758毫秒

SINGLETHREADED (17 primary numbers): 48758 ms

MULTITHREADED(小学17号):16486毫秒

MULTITHREADED (17 primary numbers): 16486 ms

投票这个想法第一页http://www.mygreatwindowsazureidea.com/forums/34192-windows-azure-feature-voting/suggestions/3622286-upgrade-windows-azure-processor-from-1-6-ghz-to-mi

这篇关于Azure的计算能力:特大型VM慢的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!

10-21 12:42