CloudSpectator

Sponsor for Cloud Expo 2013 in NYC

Kenny — Tue, 12 Feb 2013 19:44:04 +0000

SYS-CON Events announced today that Cloud Spectator has been named “Media Sponsor” of SYS-CON’s 12th International Cloud Expo, which will take place on June 10-13, 2013, at the Javits Center in New York City, New York, and the 13th International Cloud Expo, which will take place on November 4-7, 2013, at the Santa Clara Convention Center in Santa Clara, CA.

Lunacloud, Amazon EC2, and Rackspace Cloud Compared

Kenny — Tue, 18 Dec 2012 06:37:48 +0000

Download the full report in PDF format

Introduction

We recently began benchmarking Lunacloud, an IaaS vendor based in Europe. We have found strong disk IO and networking performance for Lunacloud. Amazon’s performance remains unpredictable with periods of spikes, while Rackspace Cloud (not OpenStack Cloud) performs in a stable manner throughout the 30 days.

Findings

We tested on the following server configuration: 4 vCPUs, 16 GB RAM, 50 GB disk. While Lunacloud outperforms Amazon and Rackspace in many cases over the 30-day test, the service also prices itself much lower for such a configuration.

Key Findings

In the general server test, Lunacloud outperforms Amazon and Rackspace consistently over a period of 30 days.
Lunacloud disk performance scores up to 8x better than Amazon or Rackspace disk performance. This is an important consideration for database performance.
Lunacloud’s internal network throughput is 2x faster than Rackspace’s internal network throughput, and significantly more stable than Amazon in a period of 30 days. With applications requiring more than one server, internal network speed may be considered a bottleneck in many cases if other components of the server are optimized.
Amazon EC2’s CPU performance generally scores slightly better than Rackspace and Lunacloud CPU performance. CPU is a vital component of the server, and application performance depends significantly on CPU functionality.
Rackspace’s RAM is more consistent in performance than Amazon or Lunacloud, though it scores the lowest in performance over a period of 30 days. Though the processor speed is an important factor in server performance, RAM plays an equally important role. Because modern CPUs can perform many of the applications run today, bottleneck instances may actually occur with RAM.

Snapshot of Findings

To enlarge an image, please click on it below. To download a full report on our analysis, please click here.

General Server Comparison using UnixBench:
Amazon Average 30-day Score: 1,037 points
Rackspace Average 30-day Score: 955 points
Lunacloud Average 30-day Score: 1,305 points

Amazon CloudSpecs Score: 40
Rackspace CloudSpecs Score: 26
Lunacloud CloudSpecs Score: 100
The purpose of UnixBench is to provide a basic indicator of the performance of a Unix-like system; hence, multiple tests are used to test various aspects of the system’s performance. These test results are then compared to the scores from a baseline system to produce an index value, which is generally easier to handle than the raw scores. The entire set of index values is then combined to make an overall index for the system.

Methodology

As mentioned earlier, we monitor performance 4 times a day, 365 times a year with our CloudSpecs system, a software suite of open-source, industry-standard server performance tests. From those findings, we average performance in a period of time (for purposes of this post, it is 30 days). Using that average, we plug in pricing to figure out a value score based on how much the server cost us and how much performance we’re actually getting out of it. The best value IaaS cloud provider is given a score of 100, and every other IaaS provider has a score pegged to it, so the other IaaS providers’ scores are in relation to the best IaaS provider’s value.

Price:Performance CloudSpecs Score calculation methodology:

provider_value(P) = [Provider test score over a period of time] / [Provider price]
best_provider_value = max(provider_values)
Provider’s CloudSpecs Score = 100 * provider_value(P) / best_provider_value

Pricing/Server Cost:

Amazon’s XLarge Instance: $0.64 per hour
Rackspace’s 15GB Server: $0.96 per hour
Lunacloud’s Server: $0.32 per hour

Server configuration is a bit tricky because both Amazon and Rackspace only provide tiered structures, where you must select a pre-configured package (called “instances” on Amazon and “servers” on Rackspace) that contains a set amount of CPU, RAM, and disk space.

Server Configurations:

Amazon: 15GB RAM, 4vCPUs (8ECUs), 1,690GB Disk
Rackspace: 15GB RAM, 4vCPUs, 620GB Disk
Lunacloud: 16GB RAM, 4vCPUs, 50GB Disk

For more details into the methodology, please contact us.

Press Release: Cloud Spectator Compares Pricing Structure of IaaS Providers

Kenny — Tue, 06 Nov 2012 17:38:04 +0000

BOSTON, MA, Nov 06, 2012 (MARKETWIRE via COMTEX) — Cloud Spectator, a leading independent cloud computing analyst firm that provides research and data on Cloud Infrastructure as a Service (IaaS), today unveiled its newest research report, Infrastructure as a Service Market Metrics Report: Industry Pricing Comparison. The company conducted extensive cost analysis among 20 IaaS providers for different server configurations. The data found that Amazon EC2 did not score as the most cost-effective option for companies looking at short-term projects.

Read the entire story at Market Watch

3 Tips for Cloud Providers to Enhance User Experience: Windows Azure Case Study

Kenny — Wed, 17 Oct 2012 17:03:58 +0000

Don’t get me wrong, Microsoft; I love you guys. I think you stumbled on Windows Vista, but Windows 7 really made up for it. And your Microsoft Office Suite really makes life easier, though it could be a little less expensive.

But something you really need to improve is the Windows Azure user experience, especially for free trial members. Today, the key to user experience is simplicity. On websites, marketers want as little clicks as possible between a customer entering the site and purchasing a product. Here’s some tips for cloud providers on improving User Experience when signing on a new customer:

1. Sign Me Up Quickly, Please

No one likes deciphering those incomprehensible texts found on the “confirm you’re a human” pages; by the time I’m a pro at that, I’ll call myself a cryptographer. Look at the image below. Does it somehow make me more human if I can decrypt a longer series of random letters? Or is it possible that, if I can do the same for 3 letters, that can still, quite likely, prove that I’m somewhat human?

2. I’m Done Signing Up, Don’t Ask for More Information

I already went through the painful sign-up process. Now that I’ve entered my cell-phone number on my account, and verified my email, and you even told me that I’m ready to start my simple free trial, you’re going to ask me to verify my account again? Blood levels are rising, Windows. But I’ll play along and pretend I’m more patient than I am. Let me pull out my cell phone.

3. If It’s a “Free Trial” Don’t Ask for My Card Info

Seriously? Look at that image below; it’s worse than the first application I had to fill out (the one that got me my username, not the one that I had to fill out to verify my account the first time and not the one I had to fill out to verify that my account is verified). If this is a free trial why are you so eager grab my card information? Getting a bit suspicious, Windows. Sure, it might be the way some others do it, but aren’t you supposed to be a trend setter?

I’m not pulling out my wallet, reaching for my card, and wasting more time typing in all that credit card information; in fact, I’d rather put my time into writing a blog post on how cloud providers should enhance user experience for a satisfied customer, of which I am not.

This is an example of how you just lost a customer.

IaaS Cloud Performance Comparison: ProfitBricks VS. Amazon and Rackspace (UnixBench and Iperf)

Kenny — Sun, 09 Sep 2012 17:37:39 +0000

FULL DISCLOSURE: ProfitBricks hired Cloud Spectator to run a continuous UnixBench and Iperf benchmark for 15 days (4 times a day) from our CloudSpecs Performance Tests on their beta cloud IaaS servers, and compare the results to Amazon EC2 and Rackspace Cloud. We did not alter our methodology in any manner, and data presented in this post are meant only to report as information. Cloud Spectator does not endorse ProfitBricks or ProfitBricks services.

Abstract

New cloud IaaS providers, such as ProfitBricks, CloudSigma, and Cloud Provider USA are emerging rapidly in the expanding cloud IaaS market as a response to increased performance demands. This post describes the performance results of ProfitBricks against Amazon and Rackspace.

Introduction

New competitors are emerging in the cloud IaaS industry, bringing newer technologies and more powerful, reliable clouds. ProfitBricks, a German-based cloud IaaS provider with an emerging US arm, is an example. Leveraging its partnership with Mellanox, ProfitBricks takes advantage of InfiniBand technology to optimize its network speeds within the data center. It also gives its customers private cores, a fairly new concept in the IaaS market; in traditional IaaS providers such as Amazon EC2, virtualized cores are shared.

But what does this all mean? ProfitBricks hired us to run our CloudSpecs Performance Tests to be able to benchmark the true performance of their cloud server environment, to either prove or disprove their technological advantages. As mentioned in the disclaimer above, we do not endorse ProfitBricks nor its services, and all the data below is for informational purposes from our findings.

Comparison

UnixBench Results: ProfitBricks Outperforms Amazon EC2 and Rackspace Cloud
ProfitBricks’s UnixBench scores 227% better than Amazon and 247% better than Rackspace on average over a continuous period of 15 days.

The UnixBench suite is a collection of performance tests that are used to collectively calculate an overall UnixBench score of a Unix-like system, which gives the user an idea of the overall performance of the server.

UnixBench description from Google Code:
Multi-CPU systems are handled. If your system has multiple CPUs, the default behaviour is to run the selected tests twice — once with one copy of each test program running at a time, and once with N copies, where N is the number of CPUs. This is designed to allow you to assess:

the performance of your system when running a single task
the performance of your system when running multiple tasks
the gain from your system’s implementation of parallel processing

ProfitBricks Average UnixBench Score: 2,315

Amazon EC2 Average UnixBench Score: 1,016

Rackspace Average UnixBench Score: 936

Iperf Results: ProfitBricks Outperforms Amazon EC2 and Rackspace Cloud
ProfitBricks outperforms Amazon EC2 (by 694%) and Rackspace Cloud (by 1,165%) on average over the course of 15 consecutive days by leveraging and optimizing the InfiniBand technology.

Iperf is an industry-standard and time-tested performance that is effective for measuring TCP bandwidth. TCP is the most common of two types of Internet Protocol (IP) traffic; HTTP, FTP, and SMTP are examples of TCP. The other, UDP, is mainly used to transfer time-sensitive data such as VOIP and DNS.

The duration of our Iperf is 120 seconds, and results are calculated by transferring as much data as possible from that time frame.

ProfitBricks Average Iperf Score: 4602 mibits/s

Amazon EC2 Average Iperf Score: 523 mibits/s

Rackspace Average Iperf Score: 394 mibits/s

Methodology

The CloudSpecs Performance System, a software suite of open-source, industry-standard server performance tests monitors the performance of ProfitBricks US, Amazon EC2, and Rackspace Cloud 4 times a day over the period of August 15th, 2012 to the end of August 30th, 2012. Cloud Spectator anonymously creates a user for each of the services and installs the CloudSpecs system on to the provisioned cloud servers. From those findings, we average performance in a period of time. Individual points can be found by contacting us.

Server configuration is complicated because both Amazon and Rackspace only provide tiered structures, where you must select a pre-configured package (called “instances” on Amazon and “servers” on Rackspace) that contains a set amount of CPU, RAM, and disk space. ProfitBricks’ IaaS cloud is an independently scalable infrastructure, where resource amounts of CPU, RAM, and disk are all independently selected and adjusted.

Server Configurations for UnixBench:

ProfitBricks: 16GB RAM, 4vCPUs, 50GB Disk
Amazon: 15GB RAM, 4vCPUs (8ECUs), 1,690GB Disk
Rackspace: 15GB RAM, 6vCPUs, 620GB Disk

Iperf was conducted by creating 2 servers within the same data center and with the same client account. By creating a VPN with those servers, Iperf measures the connection speed between those two servers. The Small server acts as an agent to transmit data to the Large server.

Server Configurations for Iperf (SMALL):

ProfitBricks: 4GB RAM, 1vCPUs, 50GB Disk
Amazon: 3.75GB RAM, 1vCPUs (8ECUs), 410GB Disk
Rackspace: 4GB RAM, 2vCPUs, 160GB Disk

Server Configurations for Iperf (LARGE):

ProfitBricks: 16GB RAM, 4vCPUs, 50GB Disk
Amazon: 15GB RAM, 4vCPUs (8ECUs), 1,690GB Disk
Rackspace: 15GB RAM, 6vCPUs, 620GB Disk

For more details into the methodology, please contact us.

Cloud Performance: How to Interpret Benchmarks (Part 1)

Kenny — Wed, 05 Sep 2012 18:41:40 +0000

Part 1 provides an introduction to the post and a look into relevant open source performance tests for Video and Database applications. Part 2 will look at other industries and applications; i.e., Storage, Gaming, and general eCommerce.

Abstract

Performance results from open-source benchmark tests can only reveal certain details about the server(s) the tests are performed on. To really take advantage of the results, you have to understand which tests are relevant to the application(s) you want to run. This post provides examples of 5 different application-types, and suggests a collection of tests that would be beneficial for user running that application on the cloud.

Introduction

What is the best car?

Give up? Well, there is no right answer; after all, what is the best car… for what purpose? Are you looking for speed? Heavy lifting? All-terrain? Good gas mileage? So many factors come into play, and your “best” car is best because it fulfills all of your specific car requirements.

The same idea applies in cloud. There is no “best” cloud provider (at least not from what we’ve seen). There certainly are some that are better than others in virtual core performance, or network speed, or maybe even the service-side. But there are tests out there that can accurately assess how a cloud server will perform well for your needs. By looking at all the necessary tests relevant to your application, you can have an accurate measurement of how a cloud server will handle in performance.

Below are 5 different application-types and examples of what would be required. We understand this isn’t a one-size-fits-all deal, but it is a fair starting point for anyone interested in looking into cloud performance for his or her applications. For more details and performance results, please view our CloudSpecs Performance Test System.

1. Video

Think services like YouTube or NetFlix. These services are just a couple of example in the plethora of SaaS video applications in the Internet. A fast disk I/O, low-latency network access, as well as good video and audio conversion performance is important in selecting the right cloud IaaS provider. Here are some tests to look at:

VIDEO

NETWORK

AUDIO CONVERSION

2. Database

The database lies at the center of Internet applications, continuously transmitting and receiving data to and from other servers. Without a fast and functional database, performance can be dragged down, regardless of how great an application would be otherwise. Performance in Disk speed, CPU, RAM, and even internal network all factor into database performance; the truth is, databases can be so custom that the suggestions in this post is not a catch-all, but rather a basic rudimentary look into some benchmark measurements that can pinpoint key metrics in predicting database performance.

DISK I/O

Linux “dd” Command

fio

GENERAL PERFORMANCE

UnixBench

DATABASE BENCHMARKS

PostGres (pgbench)

Public IaaS Performance MUST be Monitored Over Time

Kenny — Mon, 03 Sep 2012 17:44:11 +0000

Abstract

Public IaaS cloud is a multi-tenant environment where users of that cloud must share resources. The leads to fluctuations in performance, especially as more users provision cloud environments on the same physical server. One simple performance measurement is not enough to predict performance over time.

Introduction

After our recent posts on 30-day results of internal network performance of Amazon VS. Zunicore and price-performance of Amazon VS. Rackspace, People have asked me why Cloud Spectator’s CloudSpecs Performance Test System doesn’t just provision a server, run all our tests on it, record the results, and move on. Thinking back, I should’ve made this point first. It’s simple: the majority of the public IaaS cloud market has not developed a level of steady performance that can overcome factors like multi-tenancy and over-provisioned servers. And by majority, I mean the gorilla taking up 70% of the market.

So what if it’s multi-tenant?

Let me put in into perspective for you by using an all-American addiction, coffee.

Keeping in mind legacy servers (whether in your own data center, colocation, or web-access dedicated servers), imagine a coffee maker. You have it in your own, and every morning at 6AM, you wake up, and your awesome coffee maker’s timer tells it to start brewing. By the time you’re done brushing your teeth and getting dressed, you go into the kitchen and that fresh cup of coffee is waiting for you. Now, you only need to time the coffee maker once to know that it will always take 40 seconds to prepare that coffee for you. You live happily ever after.

Now, let’s take a public IaaS scenario: you discover the coffee shop. Your coffee maker broke down, and you’re starting to get into espresso anyway, but don’t want to put down $300 for an espresso maker. Every morning, you go through your same tradition of cleaning and dressing yourself, and then driving off, but making a pit-stop at Starbucks this time. But here’s the question: how much time do you need to set aside for getting your coffee at the coffee shop? That’s impossible to predict because you just don’t know how many people are already piled up in that coffee shop, waiting for that same morning pick-me-up. Sometimes it’s 5 minutes if you get a good spot in line, other times it’s 10-15 minutes, but if you’re really lucky, you might just get it in 2. Point is, there’s no guarantee that you’ll reach your final destination at the exact same time each time.

Public IaaS clouds are coffee shops, and users are the customers who make use of the coffee to become a vital part of their daily function.

Internal Network: Zunicore VS. Amazon EC2

Kenny — Thu, 30 Aug 2012 12:00:56 +0000

Disclaimer: we were not paid by any party to write this blog post. If you would like more information on these or any other providers, or if you have any questions, please feel free to contact us.

Abstract

Cloud providers normally allow you to only select an allocation of CPU, RAM, and storage Another factor,though, can be the hidden bottleneck that may make or break your application’s performance: internal network performance. Using PEER 1 Hosting’s Zunicore and Amazon EC2 as examples from our CloudSpecs Performance Studies, we show you that not all cloud internal networks are created equally, and understanding the actual speed of your VPN is crucial in a cloud IaaS purchase decision.

Introduction

A colleague of mine, a system administrator, recently gave me a great example of how vital internal network performance can be in application performance. In his previous work, he managed servers for an RMV. Every time someone goes to get a picture taken for a license, that picture is sent to a server miles away. That isolated server then receives the picture and sends a message to another server, the database, saying, “Hey, I’m going to look through all your pictures and see if any of them match the one I have.”

The database responds, “alright, but I’m warning you: I have 6 million pictures you have to look through.”

Things just got complicated.

It doesn’t matter how fast or slow it can spin its hard disks, if it can only send 1 picture at a time and each picture takes a second to send… there’s no point in doing that math. It just won’t work.

When multi-server applications must maintain a stream of communication, the bottleneck that may occur in a network inside the VPN is a major consideration, and that performance must be reliable for complex and mission-critical applications running on the cloud. An application that must constantly read and write data from one or many servers depends on the speed of the internal network.

Though providers usually give you only a choice of the amount of CPU, RAM, storage, and servers you provision, don’t be fooled into thinking those are the only true difference among providers. As shown by this example of Zunicore and Amazon, though CPU performance may be around the same area, a drastic difference in internal network performance can be the deciding factor in your application’s performance.

Comparison

CPU Performance: Closely Matched
In regards to CPU, Zunicore and Amazon are closely matched, as shown by two of our tests below; one measures the compression performance using 7-zip as a compression tool, and the other one measures encoding performance using LAME MP3 as the encoding application.

Using 7-Zip’s integrated benchmark feature to measure the CPU compression performance of IaaS providers Zunicore and Amazon EC2.

Using LAME MP3 to measure CPU encoding performance of IaaS providers Zunicore and Amazon EC2 by using a file of ~80MB from WAV to MP3 format.

Network Performance: Zunicore Performs Better and More Steadily
As a side note, our CloudSpecs Performance Test System not only tests servers, but is automated to run those tests on servers 4 times a day, 365 days a year. This means we not only get to capture a single point in time, but an overall trend in performance to understand stability, predictability, deviations in performance, etc. which is extremely important in a multi-tenant environment where resources are shared, i.e., the public IaaS cloud. By putting two cloud IaaS servers in a virtual private network (VPN) and performing network tests between them, we can gather an idea of the performance of the cloud IaaS provider’s internal networks. Leveraging our method, we have discovered a surprising trend that will be summarized below.

Using Iperf as a tool to measure throughput, we see create a TCP data stream to transfer as much data as possible in 120 seconds.

Transfer of a 1 GB file to the RAMDisk. Doing this bypasses the disk, eliminating a possible bottleneck in performance from that point.

Transfer of a 5 GB file to the Disk and measuring the bandwidth.

Transfer of a 5 GB file from disk to disk using SCP. Unlike an FTP transfer, the SCP transfer goes through the extra step of encrypting data before it is transmitted, adding an extra layer of security.

Transfer of a 1 GB file to the Disk using an Apache2 web server by using the command wget.

Similar to the Apache test above, this test uses an Nginx web server to transfer 1 GB file to the Disk by using wget.

A simple ping between the two servers on the same VPN using the ping command: ping -c 100 -i 0.25 -s 0 -w 300 -W 5

Apart from the fact that Zunicore outperforms Amazon in every one of our CloudSpecs performance measurements gauging the performance of the internal networks, the idea that Amazon’s network performance fluctuates so drastically over time should fire up a red flag. Other notable performers with steady network performance that we have measured include Rackspace and Hosting.com.

Conclusion

Going back to my friend’s example, because the CPU is running just fine, the application sitting on the server is going to operate effectively. But would could fluctuate the performance? Let’s say my friend runs his facial-recognition application on Zunicore. Likely, if the software takes 10 seconds to pour through the database and confirm or deny a match, then the next day it will take around 10 seconds as well. But throwing it on Amazon EC2′s platform, 10 seconds one day may mean 60 seconds the next. Now multiply that by the thousands of faces the application much search for in a database of millions.

Methodology

Duration of Study

Begin date: July 30, 2012
End date: August 29, 2012
Total time: 30 days

Pricing/Server Cost:

Amazon’s XLarge Instance: $0.64 per hour
Zunicore Server: $0.50 per hour

Server configuration is a bit tricky because Amazon only provides tiered structures, where you must select a pre-configured package (called “instances” on Amazon) that contains a set amount of CPU, RAM, and disk space. Zunicore’s servers are highly configurable, so only required resources needed to be purchased. The Main Server runs all of the CloudSpecs tests that monitor each provider, and the Dummy Server acts as the server that communicates with the Main Server in network tests. The servers are set in the same VPN.

Server Configurations of the Main Server:

Amazon: 15GB RAM, 4vCPUs (8ECUs), 1,690GB Disk
Zunicore: 16GB RAM, 4vCPUs, 50GB Disk

Server Configurations of the Dummy Server:

Amazon: 3.75GB RAM, 1vCPU (2ECUs), 410GB Disk
Zunicore: 4GB RAM, 1vCPU, 50GB Disk

For more details into the methodology, please contact us.

Cloud IaaS Value: Rackspace VS. Amazon in Price and Performance

Kenny — Mon, 27 Aug 2012 17:06:23 +0000

Introduction

Disclaimer: We were not hired by any provider to write this blog post, and we do not endorse any cloud providers in this article. For more information on these providers and others, or if you have any questions, please contact us.

Rackspace, which integrated OpenStack with its cloud offering, recently lowered its pricing in the introduction of its Open Cloud. But has that change really affected the price-to-performance value for its customers? We analyze IaaS cloud industry pricing on a bi-monthly basis, and we record performance data 4x a day, 365 days a year with our CloudSpecs Performance system. From our observations, we have not seen a fluctuation in Rackspace performance, though pricing has dropped. With this new price change, Rackspace delivers a higher value for its clients in search of good performance. But how much price:performance value does the new Rackspace deliver, especially when compared to an industry giant like Amazon?

From a pure performance perspective, we’ve seen Amazon and Rackspace closely matched, though Amazon’s performance is spikey and unpredictable. But when taking pricing into account to calculate the value to the client, Amazon’s aggressive pricing has historically worked to their advantage.

Findings

Apart from the much smoother, predictable performance of Rackspace, its new pricing, though lower, does not amount to enough to compete against Amazon’s overall performance value. This does not, however, take into account the possible lack of predictability in performance, nor other, service-side factors, like support, which Rackspace is renowned for in the web hosting industry.

Rackspace

Strengths

Steady & predictable performance
Better average performance scores over 30 day period
Superior Disk and Internal Network Speed Performance

Weaknesses

Higher price
Lower or closely matched performance on CPU

Amazon

Strengths

Low Price
Better Price-to-Performance CloudSpecs values

Weaknesses

Spikey performance
Lower performance on Disk and Internal Network SPeed

Details

To enlarge an image, please click on it below. For CloudSpecs score, the higher the number, the better value of price-to-performance. Lower CloudSpecs score(s) are pegged to the highest score, which is 100.

CPU Performance Comparison using 7-Zip Compression:
Amazon Average 30-day Score: 6,952 MIPS
Rackspace Average 30-day Score: 5,786 MIPS

Amazon CloudSpecs Score: 100
Rackspace CloudSpecs Score: 59
A test of 7-zip, an open-source utility for manipulating archives, and its integrated benchmark feature.

Disk I/O Performance Comparison using DBench:
Amazon Average 30-day Score: 75 MiB/S
Rackspace Average 30-day Score: 130 MiB/S

Amazon CloudSpecs Score: 81
Rackspace CloudSpecs Score: 100
DBENCH is a tool to generate I/O workloads to either a filesystem or to a networked CIFS or NFS server. It can even talk to an iSCSI target. DBENCH can be used to stress a filesystem or a server to see which workload it becomes saturated and can also be used for preditcion analysis to determine “How many concurrent clients/applications performing this workload can my server handle before response starts to lag?”

RAM Performance Comparison using STREAM:
Amazon Average 30-day Score: 16,736
Rackspace Average 30-day Score: 6,616

Amazon CloudSpecs Score: 100
Rackspace CloudSpecs Score: 28
The STREAM Benchmark is the de facto industry standard benchmark for the measurement of computer memory (RAM) bandwidth.

Internal Network Performance Comparison using Iperf:
Amazon Average 30-day Score: 552 Mibit/S
Rackspace Average 30-day Score: 396 Mibit/S

Amazon CloudSpecs Score: 100
Rackspace CloudSpecs Score: 51
Iperf was developed by NLANR/DAST as a modern alternative for measuring maximum TCP and UDP bandwidth performance. Iperf allows the tuning of various parameters and UDP characteristics. Iperf reports bandwidth, delay jitter, datagram loss.

Methodology

Price:Performance CloudSpecs Score calculation methodology:

provider_value(P) = [Provider test score over a period of time] / [Provider price]
best_provider_value = max(provider_values)
Provider’s CloudSpecs Score = 100 * provider_value(P) / best_provider_value

Pricing/Server Cost:

Amazon’s XLarge Instance: $0.64 per hour
Rackspace’s 15GB Server: $0.90 per hour

Server Configurations:

Amazon: 15GB RAM, 4vCPUs (8ECUs), 1,690GB Disk
Rackspace: 15GB RAM, 6vCPUs, 620GB Disk

For more details into the methodology, please contact us.

Cloud Spectator’s TCO Analysis on OpenStack VS. OnApp: The WHIR

Kenny — Sun, 19 Aug 2012 23:40:01 +0000

The WHIR (Web Host Industry Review) recently published an article, written by the WHIR’s editor in chief Liam Eagle, summarizing our recent cloud management webinar with OnApp detailing the TCO for OpenStack VS. OnApp. The article can be found here: http://www.thewhir.com/web-hosting-news/cloud-hosting-software-onapp-touts-cost-advantages-versus-openstack. The TCO analyzes a period of

The actual webinar can be viewed here: http://www.thewhir.com/web-hosting-webinar/open-source-or-turnkey-cloud-whats-the-right-approach-for-service-providers