Performance Analysis: Benchmarks of Bare-Metal & Virtual Clouds
|
|
- April Hodges
- 8 years ago
- Views:
Transcription
1 Performance Analysis: Benchmarks of Bare-Metal & Virtual Clouds Benchmarking offerings from Internap, Amazon Web Services and By Cloud Spectator October 213
2 Table of Contents Abstract and Introduction 2 Executive Summary 4 System Performance 5 CPU Performance 6 RAM Performance 9 Internal Network Performance 1 Disk Performance 12 Database Performance 17 Price-Performance 18 Conclusion 2 Appendices 21 About Cloud Spectator 3 1
3 Abstract Virtualized infrastructure-as-a-service (IaaS) has drawn increasing attention and usage due to its granular billing, ease-ofuse, and broad network access. Bare-metal cloud services, which are essentially physical servers that can be deployed on demand and billed hourly, can offer significant improvements over virtualized IaaS in performance, consistency and cost efficiency for many applications. Benchmark tests comparing similarly sized virtual and bare-metal cloud configurations reveal that bare-metal cloud yields superior CPU, RAM, storage, and internal network performance. Predictably, solid-state drive () configurations showed substantially higher disk performance measures when compared with spinning serial ATA () drives, although processor, memory and network results between the two configurations were virtually identical. Cost efficiency, measured by performance-weighting the prices, was also measurably higher with the tested bare-metal cloud deployment inferring superior value from bare-metal cloud, all-elseequal. Introduction Bare-metal Cloud Bare-metal cloud offerings refer to a type of high-performance hosted-server offering that combines the advantages of traditional dedicated servers with those of IaaS virtual servers. With bare-metal cloud, the entire physical server s resources are dedicated to a single user, purportedly offering better performance than a comparable virtualized server. Since resources are not being shared, no hypervisor layer is needed, thereby allowing more of the server s processing power to be devoted to the application. Unlike typical dedicated servers, which can take days or weeks to deploy, baremetal cloud offerings can be provisioned in a matter of minutes. Bare-metal cloud servers are also able to be implemented using Application Programming Interface (API) methods or management portals and billed on a usagebased model. Similar to cloud IaaS virtual offerings, bare-metal cloud is billed only when the server is in use. This flexibility allows bare metal to accommodate for peak demand quickly similar to virtual cloud servers. Afterwards, additional resources can be deleted, with the customer only being charged for the hours of additional resources, compared to monthly fees typical with traditional dedicated servers. This study tests the degree of performance improvement and value enhancement that can be obtained using bare-metal cloud relative to two well-known virtualized IaaS offers. Bare metal vs. Virtual The difference between bare-metal cloud servers and virtual servers comes down to two key elements: the hypervisor and multi-tenancy. The hypervisor is used to virtualize the resources of physical machines, creating multiple virtual machines on each physical server for a multi-tenant environment. Bare-metal servers do not have a hypervisor; instead, the entire physical server s resources are reserved for a single tenant. However, bare-metal cloud is similar to virtual cloud in that the physical servers are linked together with an orchestration layer, so that the resources can be provisioned and scaled quickly using an API or other remote management tool. The level of flexibility for both offerings is similar as both operate in a usage-based billing model and offer similar features and services. It is commonly known that adding a hypervisor layer will result in some performance degradation for the virtual servers. Also, multi-tenancy and oversubscription of some services can cause an individual user to fight for shared resources on the server. In contrast, bare-metal cloud resources are fully dedicated to a single user. It follows that bare-metal cloud users routinely report greater processing power with more consistent disk and network I/O performance. 2
4 The Study Performance Testing Cloud Spectator monitors the CPU, RAM, storage, and internal network performance of over 2 of the world s most wellknown IaaS services to understand important aspects of virtual server performance. Tests are run at least three times per day, 365 days per year to capture variability in addition to performance level. Tests are chosen based on reliability and practicality. The goal is to provide an indication of where certain providers perform well relative to others. This can give consumers an indication of which services would be best for their application(s) by understanding the performance of provider resources most critical to that application. Singular benchmarks alone should not be the only deciding factor in the provider selection process. A feature set, configuration matches, pricing and ancillary services such as security, compliance, and disaster recovery should always factor into any vendor selection process. However, performance is a very important piece to the puzzle. The Comparison For the purpose of generating this document, Cloud Spectator measured the performance of Internap s bare-metal cloud offering against virtual offerings from Amazon and. The goal was to quantify how much of a performance penalty users are taking by choosing virtual cloud servers. Over a period of ten days, Cloud Spectator ran benchmark tests across Internap bare-metal cloud, AWS Elastic Compute Cloud (EC2) with Amazon Elastic Block Storage (EBS), and OpenCloud with Block Storage. Each test was run to understand the unique performance capabilities of each offering s CPU, internal network, RAM and disk. Cloud Spectator accounted for performance capability and stability for each provider to understand the value each one delivers to its users. Tests were run on 8GB servers for Internap and, and 7.5GB servers for Amazon (for more details, see Methodology section in Appendix B). While other factors can sway the perception of provider comparisons, including value-added services, features, support, security, etc., Cloud Spectator chose to focus objectively on performance to derive numerical relationships between the levels of service delivered from each provider. Performance testing and benchmarking of cloud computing platforms is a complex task, compounded by the differences between providers and the use cases of cloud infrastructure users. IaaS services are utilized by a large variety of industries, and performance metrics cannot be completely understood by simply representing cloud performance with a single value. When selecting a cloud computing provider, IT professionals consider many factors: feature-sets, cost, security, location and more. However, performance is a key issue that drives many others, including cost. In many cases, four primary resources affect overall server performance: central processing unit (CPU), random access memory (RAM), disk, and internal network. These four resources are what this comparison focuses on. vs. A growing number of service providers are now offering their customers the option to choose between solid-state drives () or traditional hard drives. While the focus of this study centers on comparing similarly priced virtual instances to Internap bare-metal cloud servers outfitted with a, it also assesses the relative performance of a lower-priced, bare-metal configuration. The results display that while CPU, RAM, and internal network performance are comparable between the bare-metal and instances, the disk tests show significant variation. Certain CPU or RAM-intense scenarios that require less disk IO could benefit from the lower-cost option relative to and/or virtual cloud instances (see Appendix A). 3
5 Executive Summary Overall Performance Internap bare-metal cloud has both higher performance and stability than Amazon and in nearly 7% of the benchmark tests across the 1-day testing period. System Performance Internap bare-metal cloud has both the highest performance and stability in the general system test. Internap bare-metal cloud scored 7x higher than the second best performing provider. Internap bare-metal cloud and have very stable system performance: Coefficient of Variation (CV) less than 1%. Internap bare-metal cloud outperformed by 7x and Amazon by 1.1x in the system test. CPU Performance Internap bare-metal cloud has both the highest performance and stability across all the CPU tests. Internap bare-metal cloud outperformed Amazon and in 3 out of 3 CPU tests. Internap bare-metal cloud was more stable than Amazon and in 3 out of 3 CPU tests. Internap bare-metal cloud outperformed by an average 2.5x and Amazon by 4.4x in the CPU tests. RAM Performance Internap bare-metal cloud has the highest performance across the RAM test and is also the most stable. Internap bare-metal cloud outperformed both Amazon and in the RAM test. Internap bare-metal cloud has very stable RAM performance: CV of 1% or less. Internap bare-metal cloud outperformed by 1.7x and Amazon by 2.1x in the RAM test. Internal Network Performance Internap bare-metal cloud has the highest performance and stability across the internal network tests, showing high throughput and low latency. Internap bare-metal cloud outperformed Amazon and in 2 out of 2 internal network tests. Internap bare-metal cloud was more stable than Amazon and in 2 out of 2 internal network tests. Internap bare-metal cloud outperformed by an average 2.5x and Amazon by 2.5x in the internal network tests. Disk Performance Internap bare-metal cloud has both the highest performance and stability in 6% of the disk performance tests. Internap bare-metal cloud outperformed Amazon and in 4 out of 5 disk tests. Internap bare-metal cloud was more stable than Amazon and in 4 out of 5 disk tests. Internap bare-metal cloud outperformed by an average 8.4x and Amazon by 4.9x in the disk tests. Database Performance Internap bare-metal cloud has the highest performance across the database test and has the second highest stability. Internap bare-metal cloud outperformed Amazon and in the database test. Internap bare-metal cloud was more stable than Amazon in the database test. Internap bare-metal cloud outperformed by 67% and Amazon by 65% in the database test. 4
6 System Performance UnixBench Test Description Unixbench runs a set of individual benchmark tests, aggregates the scores, and creates a final score to gauge the performance of Linux systems. According to the Unixbench homepage ( 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. The entire set of index values is then combined to make an overall index for the system. Some very simple graphics tests are included to measure the 2D and 3D graphics performance of the system. Multi-CPU systems are handled. If your system has multiple CPUs, the default behavior 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 Do be aware that this is a system benchmark, not a CPU, RAM or disk benchmark. The results will depend not only on your hardware, but on your operating system, libraries, and even compiler. System Performance Results The results of the Unixbench benchmark test show Internap bare-metal cloud outperforming Amazon and in speed and stability. Internap s bare-metal cloud has an average score of 6415, outperforming s average of 917 by 7x, and Amazon s average of 637 by 1.1x. For performance stability, Internap bare-metal cloud has the least variable performance, with the lowest Coefficient of Variation (CV) of.4%, followed by with.8%, and Amazon with 9.9% SYSTEM TEST - Unixbench: Internap bare-metal vs. Amazon vs. Score Amazon Internap Bare Metal Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares system performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the UnixBench benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap % Amazon % %
7 CPU Performance File Compression Test Description With p7zip s integrated benchmark feature, we test the performance of the virtual CPU by measuring the millions of instructions per second (MIPS) that it can handle when compressing a file. This benchmark test is a multi-threaded CPU test. File Compression Performance Results The results of the File Compression benchmark show Internap bare-metal cloud outperforming Amazon and in speed and stability. Internap bare-metal cloud has an average speed of MIPS, outperforming s average of 5983 MIPS by 3x and Amazon s average of 2831 MIPS by 6.2x. For performance stability, Internap bare-metal cloud has the lowest Coefficient of Variation (CV) of 1.8%, followed by with 2.9%, and Amazon with 14.3%. CPU TEST - File Compression: Internap bare-metal cloud vs. Amazon vs MIPS Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 Amazon Internap The graph above compares CPU performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the File Compression benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap MIPS 322 MIPS 1.8% 1822 MIPS MIPS Amazon 2831 MIPS 45 MIPS 14.3% 355 MIPS 2136 MIPS 5983 MIPS 173 MIPS 2.9% 6254 MIPS 561 MIPS 6
8 Audio Encoding Test Description From the Phoronix Benchmark Test Suite, this test times how long it takes to encode a WAV file to MP3 format using LAME, an MP3 encoder. This encoding test is single-threaded, indicating the CPU performance of a single core on each provider. To compare the performance difference between single-core and multi-core encoding of each provider, see results for CPU Test: Video Encoding. Audio Encoding Performance Results The results of the Audio Encoding benchmark show Internap bare-metal cloud outperforming Amazon and in speed and stability. Internap bare-metal cloud has an average time of 15 seconds, outperforming s average of 34 seconds, and Amazon s average of 37 seconds. For performance stability, Internap bare-metal cloud has the lowest CV of.1%, followed by with 1.6% and Amazon with 9.9%. CPU TEST - Audio Encoding: Internap bare-metal cloud vs. Amazon vs. Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 5 Seconds Amazon Internap The graph above compares CPU performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Audio Encoding benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 15 Seconds Seconds.1% 15 Seconds 15 Seconds Amazon 37 Seconds 4 Seconds 9.9% 4 Seconds 3 Seconds 34 Seconds 1 Seconds 1.6% 36 Seconds 34 Seconds 7
9 Video Encoding Test Description By using the x264 Video Encoding Test within the Phoronix Benchmark Suite, we can test the performance of the CPU through the compute-intensive task of converting video, and score the provider s virtual CPU performance based on how many frames are converted per second, i.e., Frames Per Second (FPS). To compare the performance difference between single-core and multi-core encoding of each provider, see results for CPU Test: Audio Encoding. Video input format: YUV4MPEG2 Video output format: H.264/MPEG-4 AVC format Video Encoding Performance Results The results of the Video Encoding benchmark show Internap bare-metal cloud outperforming Amazon and in speed and stability. Internap bare-metal cloud has an average of 132 FPS, outperforming s average of 44 FPS by 3x and Amazon s average of 24 FPS by 5.5x. For performance stability, Internap bare-metal cloud has the lowest CV of.5%, followed by with 3.8%, and Amazon with 9.% CPU TEST - Video Encoding: Internap bare-metal cloud vs. Amazon vs. Frames Per Second Amazon Internap 2 Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares CPU performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Video Encoding benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 132 FPS 1 FPS.5% 134 FPS 131 FPS Amazon 24 FPS 2 FPS 9.% 29 FPS 21 FPS 44 FPS 2 FPS 3.8% 46 FPS 41 FPS 8
10 RAM Performance RAMSpeed SMP Test Description The RAMSpeed test is an aggregate of several tests that measure COPY, SCALE, ADD and TRIAD functions for both integer and floating point values. More information on COPY, SCALE, ADD, and TRIAD: COPY transfers data from one memory location to another (A = B) SCALE multiplies the data with a constant value before writing it (A = Bn) ADD reads results from two different locations, adds those results and writes then to the new location (A = B + C) TRIAD merges ADD and SCALE. It reads data from the first memory location, scales it (multiplies it), then adds data from the second one and writes to the new location (A = Bn + C) Each test results in a score in MB/s. All scores are averaged to come up with the final score. RAMspeed SMP Performance Results The results of the RAMspeed Test show Internap bare-metal cloud with the highest performance and stability throughout the testing period, followed by, then Amazon. Internap bare-metal cloud has an average of Mb/s, outperforming s average of 7299 Mb/s by 72% and Amazon s average of 67 Mb/s by 2.1x. Internap baremetal cloud has nearly zero instability with a CV of.1%, followed by with a CV of 2.4% and Amazon proving its instability with a CV of 45.2%. RAM TEST - RAMspeed SMP Test: Internap bare-metal cloud vs. Amazon vs MiBytes/sec Amazon Internap 2 Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares RAM performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the RAMspeed SMP benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the majority of the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap Mb/sec 16 Mb/sec.1% Mb/sec 1257 Mb/sec Amazon 67 Mb/sec 2716 Mb/sec 45.2% Mb/sec 332 Mb/sec 7299 Mb/sec 175 Mb/sec 2.4% 7526 Mb/sec 6894 Mb/sec 9
11 Internal Network Performance Iperf Test Description Running Iperf tests the network throughput between two virtual machines (VMs) within the same private network inside the data center. The results are important in understanding the possible network bottlenecks. Applications that require databases, which may pull from storage located off of the local server, need a large pipe to transfer data as efficiently as possible to load quickly from the server side. This is especially true for big data applications like Hadoop, which push massive amounts of data. Throughput and bandwidth are often confused; while both measure the size of the pipe, bandwidth is the theoretical capacity, while throughput is the actual bandwidth the user actually receives. This is an important distinction for a cloud environment, where a 1GBit pipe may be split among many users, thereby resulting in lower actual throughput per user. Internal Network Throughput Results The results of the Iperf benchmark show Internap bare-metal cloud with the highest throughput speed and stability. Internap bare-metal cloud has an average network throughput of 913 Mbits/sec, outperforming Amazon s average of 289 Mbits/sec by 3.2x and s average of 288 Mbits/sec by 3.2x. Internap bare-metal cloud has zero instability with a CV of.%. Amazon and are both stable, with CVs of 1.5% and.6% respectively. NETWORK TEST - Iperf Test: Internap bare-metal cloud vs. Amazon vs. Mibits/sec Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 Amazon Internap The graph above compares internal network performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Iperf benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. Amazon and s performance are nearly identical, resulting in s trendline to overlap Amazon s in the graph above. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 913 Mbits/sec Mbits/sec.% 913 Mbits/sec 913 Mbits/sec Amazon 289 Mbits/sec 4 Mbits/sec 1.5% 294 Mbits/sec 276 Mbits/sec 288 Mbits/sec 2 Mbits/sec.6% 291 Mbits/sec 283 Mbits/sec 1
12 Ping Test Description In contrast to throughput testing, ping commands can be used to measure the latency between nodes on a private network. Higher latency severely degrades application performance in a distributed computing environment, and can adversely impact user experience, especially with regard to time-sensitive applications. 1 microseconds is 1 millisecond. Cloud Spectator runs the ping test from the Linux Terminal with the following parameters: ping c 1 i.25 s w 3 W 5 Latency Results The results of the Ping benchmark show the relative stability of Internap Bare Metal, while Amazon and s performance was erratic and unstable for the duration. Internap bare-metal cloud has the lowest average latency of 271 microseconds, performing 8% better than s average latency of 1381 microseconds, and 87% better than Amazon s average latency of 2153 microseconds. Internap bare-metal cloud has the most stable latency with a CV of.8%, followed Amazon with 22.2% and with 36.4%. NETWORK TEST - Ping: Internap bare-metal cloud vs. Amazon vs. Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 5 Microseconds Amazon Internap The graph above compares internal network performance on a Linux server between Internap bare-metal, Amazon and. The graph shows the scores from the Ping benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap baremetal has the least amount of latency compared to Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 271 µs 2 µs.8% 274 µs 265 µs Amazon 2153 µs 478 µs 22.2% 3823 µs 1825 µs 1381 µs 52 µs 36.4% 276 µs 699 µs 11
13 Disk Performance IOzone Test Description IOzone measures HDD Performance read and write speed. This test produces measurements from a variety of file operations and is used in the general file system analysis of a system. The average between HDD read and write speeds make up the final score. IOzone performs the following operations: read, write, re-read, re-write, read backwards, read strided, fread, fwrite, random read, pread, nmap, aio_read, and aio_write. IOzone Performance Results The results of the IOzone benchmark show Internap bare-metal cloud with the highest performance throughout the testing period, outperforming Amazon and by about 6x. Internap bare-metal cloud leads with an average of 4453 Mb/s, outperforming Amazon s average of 73 Mb/s by 6.3x, and s average of 7 Mb/s by 6.4x. Internap bare-metal cloud has the most stable performance for the testing period with a CV of 1.7%, followed by with 6.9% and Amazon with 13.%. DISK TEST - IOzone Test: Internap bare-metal cloud vs. Amazon vs MiBytes/sec Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 Amazon Internap The graph above compares disk performance on a Linux server between Internap bare-metal, Amazon and. The graph shows the scores from the IOzone benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 4453 Mb/sec 74 Mb/sec 1.7% 4536 Mb/sec 4279 Mb/sec Amazon 73 Mb/sec 91 Mb/sec 13.% 938 Mb/sec 619 Mb/sec 7 Mb/sec 48 Mb/sec 6.9% 726 Mb/sec 531 Mb/sec 12
14 MongoPerf Read w/out Cache Test Description Cloud Spectator tests disk read operations per second with Mongoperf, MongoDB s native benchmarking tool for gauging disk IO performance. By eliminating the cache functionality, data must always be read directly from the disk, eliminating the added benefit of RAM, for a true measure of disk IO. Database environments are particularly concerned about disk IO because of the frequency of read and write operations. If the disk is slow, the entire application may lag while waiting. The parameters run: nthreads:32, filesizemb:2, mmf:false, r:true, w:false, recsize:4, syncdelay:1 MongoPerf Read w/out Cache Performance Results The results of the Read without Cache benchmark show Internap bare-metal cloud with the highest performance throughout the testing period, followed by Amazon then. Internap bare-metal cloud has the highest average of 245 Ops/sec, outperforming Amazon s average of 5399 Ops/sec by 3.7x, and s average of 693 Ops/sec by 28.9x. While having the lowest performance, has the most stable performance throughout the testing period with a CV of 17.6%, followed by Internap bare-metal cloud with a CV of 22.3%, and Amazon proving to be very unstable with a CV of 75.6% DISK TEST - Read w/out Cache Test: Internap bare-metal cloud vs. Amazon vs. Operations/sec Amazon Internap Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares disk performance on a Linux server between Internap bare-metal, Amazon and. The graph shows the scores from the Read w/out Cache benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 245 Ops/sec 4469 Ops/sec 22.3% 273 Ops/sec 146 Ops/sec Amazon 5399 Ops/sec 484 Ops/sec 75.6% Ops/sec 57 Ops/sec 693 Ops/sec 122 Ops/sec 17.6% 1136 Ops/sec 563 Ops/sec 13
15 MongoPerf Write w/out Cache Test Description Cloud Spectator tests disk write operations per second with Mongoperf, MongoDB s native benchmarking tool for gauging disk IO performance. By eliminating the cache functionality, data must always be written directly to the disk, eliminating the added benefit of RAM, for a true measure of disk IO. Database environments are particularly concerned about disk IO because of the frequency of read and write operations. If the disk is slow, the entire application may lag while waiting. The parameters run: nthreads:32, filesizemb:2, mmf:false, r:false, w:true, recsize:4, syncdelay:1 MongoPerf Write w/out Cache Performance Results The results of the Write without Cache benchmark show Internap bare-metal cloud with the highest performance throughout the testing period, followed by, and then Amazon. Internap bare-metal cloud has an average of 2292 Ops/sec, outperforming s average of 15 Ops/sec by 53%, and Amazon s average of 1157 Ops/sec by 98%. Internap bare-metal cloud also has the most stable performance throughout the testing period with a CV of.5%, followed by with 7.1%, and Amazon with 9.5%. 25 DISK TEST - Write w/out Cache Test: Internap bare-metal cloud vs. Amazon vs. 2 Operations/sec Amazon Internap Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares disk performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Write without Cache benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 2292 Ops/sec 11 Ops/sec.5% 23 Ops/sec 2267 Ops/sec Amazon 1157 Ops/sec 19 Ops/sec 9.5% 136 Ops/sec 78 Ops/sec 15 Ops/sec 16 Ops/sec 7.1% 1583 Ops/sec 981 Ops/sec 14
16 MongoPerf Read w/ Cache Test Description Cloud Spectator tests disk read operations per second with Mongoperf, MongoDB s native benchmarking tool for gauging disk IO performance. Database environments are particularly concerned about disk IO because of the frequency of read and write operations. If the disk is slow, the entire application may lag while waiting. The parameters run: nthreads:32, filesizemb:2, mmf:true, r:true, w:false, recsize:4, syncdelay:6 MongoPerf Read w/ Cache Performance Results The results of the Read with Cache benchmark show Amazon with the highest performance throughout the testing period, followed by Internap Bare Metal, and then. Amazon has an average of Ops/sec, outperforming Internap Bare Metal s average of Ops/sec by 49%, and s average of Ops/sec by 5.9x. While Amazon is the highest performing, it is also the least stable with a CV of 31.9%. Internap bare-metal cloud is the most stable with a CV of 1.3%, followed by with 8.8%. 25 DISK TEST - Read w/ Cache Test: Internap bare-metal cloud vs. Amazon vs. 2 Operations/sec Amazon Internap Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares disk performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Read w/ Cache benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Amazon outperforms Internap bare-metal cloud and over the majority of the test period. Amazon is also the most variable over the test period compared to the other providers. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap Ops/sec 1.3% Ops/sec Ops/sec Ops/sec Amazon Ops/sec 31.9% Ops/sec Ops/sec Ops/sec Ops/sec Ops/sec 8.8% Ops/sec Ops/sec 15
17 MongoPerf Write w/ Cache Test Description Cloud Spectator tests disk write operations per second with Mongoperf, MongoDB s native benchmarking tool for gauging disk IO performance. Database environments are particularly concerned about disk IO because of the frequency of read and write operations. If the disk is slow, the entire application may lag while waiting. The parameters run: nthreads:32, filesizemb:2, mmf:true, r:false, w:true, recsize:4, syncdelay:6 MongoPerf Write w/ Cache Performance Results The results of the Write with Cache benchmark show Internap bare-metal cloud with the highest performance throughout the testing period, followed by, then Amazon. Internap bare-metal cloud has an average of Ops/sec, outperforming s average of Ops/sec by 26%, and Amazon s average of Ops/sec by 11.9x. Internap bare-metal cloud has the most stable performance throughout the test period with a CV of 1.1%, followed by Amazon with 24.5% and proving to be very unstable with a CV of 6.% DISK TEST - Write w/ Cache Test: Internap bare-metal cloud vs. Amazon vs. Operations/sec Amazon Internap Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 The graph above compares disk performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the Write w/ Cache benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap baremetal cloud outperforms Amazon and over the majority of the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap Ops/sec 2222 Ops/sec 1.1% Ops/sec 2152 Ops/sec Amazon Ops/sec 4231 Ops/sec 24.5% Ops/sec Ops/sec Ops/sec Ops/sec 6.% Ops/sec Ops/sec 16
18 Database Performance MySQL Test Description The MySQL Performance test is MySQL s native benchmarking tool. This tests time to completion of MySQL s database queries/commands (alter, insert, update, and delete). Lower scores are better. MySQL Performance Results The results of the MySQL Performance benchmark show Internap bare-metal cloud outperforming Amazon and throughout the testing period. Internap bare-metal cloud outperformed the other offerings by approximately 3x with an average of 6 seconds, with Amazon and following with average scores of 17 seconds, 18 seconds respectively. has the most stable performance with a CV of 6.3%, followed by Internap bare-metal cloud with 9.5%, and Amazon with 12.%. DATABASE TEST - MySQL Performance Test: Internap bare-metal cloud vs. Amazon vs. Sep 26 Sep 27 Sep 28 Sep 29 Sep 3 Oct 1 Oct 2 Oct 3 Oct 4 Oct 5 Seconds Amazon Internap 2 25 The graph above compares database performance on a Linux server between Internap bare-metal cloud, Amazon and. The graph shows the scores from the MySQL Performance benchmark test for each provider over a period of 1 days, with two data points shown for each day. As shown above, Internap bare-metal cloud outperforms Amazon and over the test period. PROVIDER AVERAGE STANDARD DEVIATION CV 1-Day HIGH 1-Day LOW Internap 6 Seconds 1 Seconds 9.5% 7 Seconds 4 Seconds Amazon 17 Seconds 2 Seconds 12.% 2 Seconds 12 Seconds 18 Seconds 1 Seconds 6.3% 21 Seconds 16 Seconds 17
19 Price-Performance Measuring Value Raw performance numbers do not always tell the full story. While some users may have performance as their first priority and be willing to pay extra for a quality solution, others have value in mind. These users try to understand which services give the best resource performance for their dollar. Users focused solely on price may not get the best value. If one virtual server has twice the CPU performance of another with an identical configuration, but is priced only 5% more, then this offering provides better value to the user. Instead of paying for two or more servers to get sufficient performance, the user only pays for one and saves money. Extrapolating this idea to a much bigger distributed environment like a Hadoop cluster enhances the importance of accounting for price-performance value. The Calculation After obtaining the correct performance metrics, the calculation for each test is quite simple: Performance/price = price-performance value To further simplify, we take the highest price-performance metric and divide that into all other price-performance metrics for the given test. Then we multiply by 1. This gives the offering providing the most value for that test a score of 1, and pegs all other offerings in relativity to that top score of 1. We call this value out of 1 the CloudSpecs Score. This represents our final price-performance score. For example, this is how we calculate price-performance for the UnixBench test: Offering Score Divided by Price Divided by Highest Score Multiply by 1 UnixBench CloudSpecs Score Internap bare-metal cloud ($.36/hour) 6,415/$.36 = 17,818 17,818/17,818 = 1. 1.*1 = Amazon ($.25/hour) 637/$.25 = 2,548 2,548/17,818 = *1 = ($.49/hour) 917/$.49 = 1,871 1,871/17,818 =.15.15*1 = These scores indicate that for the UnixBench test, Internap s bare-metal cloud provides: 7x more value than Amazon 9.5x more value than The Results The following tables provide price-performance results for all tests involving Internap bare-metal cloud servers outfitted with versus nominal virtual instances of Amazon and. System CPU RAM UnixBench Compression Audio Encoding Video Encoding RAMSpeed INTERNAP
20 Storage IOzone Read(w/o Cache) Write(w/o Cache) Read(w/ Cache) Write(w/ Cache) INTERNAP Internal Network Database Iperf Ping MySQL INTERNAP Results Summary Internap s bare-metal cloud offers the best price-performance ratio in 12 out of 13 total tests. 1/1 system test 3/3 CPU tests 1/1 RAM test 4/5 storage tests 2/2 internal network tests 1/1 database test 19
Cloud Analysis: Performance Benchmarks of Linux & Windows Environments
Cloud Analysis: Performance Benchmarks of Linux & Windows Environments Benchmarking comparable offerings from HOSTING, Amazon EC2, Rackspace Public Cloud By Cloud Spectator July 2013 Table of Contents
More informationCLOUDSPECS PERFORMANCE REPORT LUNACLOUD, AMAZON EC2, RACKSPACE CLOUD AUTHOR: KENNY LI NOVEMBER 2012
CLOUDSPECS PERFORMANCE REPORT LUNACLOUD, AMAZON EC2, RACKSPACE CLOUD AUTHOR: KENNY LI NOVEMBER 2012 EXECUTIVE SUMMARY This publication of the CloudSpecs Performance Report compares cloud servers of Amazon
More informationCloud Server Performance A Comparative Analysis of 5 Large Cloud IaaS Providers
Cloud Server Performance A Comparative Analysis of 5 Large Cloud IaaS Providers Cloud Spectator Study June 5, 2013 With a lack of standardization in the IaaS industry, providers freely use unique terminology
More informationChoosing Between Commodity and Enterprise Cloud
Choosing Between Commodity and Enterprise Cloud With Performance Comparison between Cloud Provider USA, Amazon EC2, and Rackspace Cloud By Cloud Spectator, LLC and Neovise, LLC. 1 Background Businesses
More informationComparison of Windows IaaS Environments
Comparison of Windows IaaS Environments Comparison of Amazon Web Services, Expedient, Microsoft, and Rackspace Public Clouds January 5, 215 TABLE OF CONTENTS Executive Summary 2 vcpu Performance Summary
More informationIaaS Performance and Value Analysis A study of performance among 14 top public cloud infrastructure providers
IaaS Performance and Value Analysis A study of performance among top public cloud infrastructure providers By Cloud Spectator and the Cloud Advisory Council October 5, 3 Table of Contents Executive Summary
More informationPerformance Analysis: Benchmarking Public Clouds
Performance Analysis: Benchmarking Public Clouds Performance comparison of web server and database VMs on Internap AgileCLOUD and Amazon Web Services By Cloud Spectator March 215 PERFORMANCE REPORT WEB
More informationBy Cloud Spectator July 2013
Benchmark Report: Performance Analysis of VS. Amazon EC2 and Rackspace Cloud A standardized, side-by-side comparison of server performance, file IO, and internal network throughput. By Cloud Spectator
More informationComparing major cloud-service providers: virtual processor performance. A Cloud Report by Danny Gee, and Kenny Li
Comparing major cloud-service providers: virtual processor performance A Cloud Report by Danny Gee, and Kenny Li Comparing major cloud-service providers: virtual processor performance 09/03/2014 Table
More informationCloud IaaS Performance & Price-Performance
Cloud IaaS Performance & Price-Performance Comparing Linux Compute Performance of 1&1, Amazon AWS, Aruba Cloud, CloudSigma, and Microsoft Azure Prepared for 1&1 on Behalf of SolidFire Commercial Report
More informationCloud IaaS Performance & Price-Performance
Cloud IaaS Performance & Price-Performance Comparing Linux Compute Performance of 1&1, Amazon AWS, Aruba Cloud, CloudSigma, and Microsoft Azure Prepared for 1&1 on Behalf of SolidFire Commercial Report
More informationRackspace Cloud Servers Analysis A comparison of cloud servers across Generations of Rackspace Cloud Offerings
Rackspace Cloud Servers Analysis A comparison of cloud servers across Generations of Rackspace Cloud Offerings By Cloud Spectator November 7, 2013 Section Page Number Introduction 2 Key Findings 2 To Consider
More informationOn- Prem MongoDB- as- a- Service Powered by the CumuLogic DBaaS Platform
On- Prem MongoDB- as- a- Service Powered by the CumuLogic DBaaS Platform Page 1 of 16 Table of Contents Table of Contents... 2 Introduction... 3 NoSQL Databases... 3 CumuLogic NoSQL Database Service...
More informationWWW.PROFITBRICKS.COM. The Secret World of Cloud IaaS Pricing: How to Compare Apples and Oranges Among Cloud Providers
The Secret World of Cloud IaaS Pricing: How to Compare Apples and Oranges Among Cloud Providers TABLE OF CONTENTS Executive Summary:...3 Part 1: The Current State of Cloud Computing IaaS Pricing and Packaging...3
More informationCloud Computing Workload Benchmark Report
Cloud Computing Workload Benchmark Report Workload Benchmark Testing Results Between ProfitBricks and Amazon EC2 AWS: Apache Benchmark, nginx Benchmark, SysBench, pgbench, Postmark October 2014 TABLE OF
More informationGenerational Performance Comparison: Microsoft Azure s A- Series and D-Series. A Buyer's Lens Report by Anne Qingyang Liu
Generational Performance Comparison: Microsoft Azure s A- Series and D-Series A Buyer's Lens Report by Anne Qingyang Liu Generational Performance Comparison: Microsoft Azure s A-Series and D-Series 02/06/2015
More informationUBUNTU DISK IO BENCHMARK TEST RESULTS
UBUNTU DISK IO BENCHMARK TEST RESULTS FOR JOYENT Revision 2 January 5 th, 2010 The IMS Company Scope: This report summarizes the Disk Input Output (IO) benchmark testing performed in December of 2010 for
More informationNetwork Performance Between Geo-Isolated Data Centers. Testing Trans-Atlantic and Intra-European Network Performance between Cloud Service Providers
Network Performance Between Geo-Isolated Data Centers Testing Trans-Atlantic and Intra-European Network Performance between Cloud Service Providers Published on 4/1/2015 Network Performance Between Geo-Isolated
More informationDimension Data Enabling the Journey to the Cloud
Dimension Data Enabling the Journey to the Cloud Grant Morgan General Manager: Cloud 14 August 2013 Client adoption: What our clients were telling us The move to cloud services is a journey over time and
More informationPARALLELS CLOUD SERVER
PARALLELS CLOUD SERVER Performance and Scalability 1 Table of Contents Executive Summary... Error! Bookmark not defined. LAMP Stack Performance Evaluation... Error! Bookmark not defined. Background...
More informationVirtualization Performance on SGI UV 2000 using Red Hat Enterprise Linux 6.3 KVM
White Paper Virtualization Performance on SGI UV 2000 using Red Hat Enterprise Linux 6.3 KVM September, 2013 Author Sanhita Sarkar, Director of Engineering, SGI Abstract This paper describes how to implement
More informationCloud Performance Benchmark Series
Cloud Performance Benchmark Series Amazon EC2 CPU Speed Benchmarks Kalpit Sarda Sumit Sanghrajka Radu Sion ver..7 C l o u d B e n c h m a r k s : C o m p u t i n g o n A m a z o n E C 2 2 1. Overview We
More information2016 TOP 10 CLOUD VENDOR BENCHMARK. EUROPE REPORT Price-Performance Analysis of the Top 10 Public IaaS Vendors
216 TOP 1 CLOUD VENDOR BENCHMARK EUROPE REPORT Price-Performance Analysis of the Top 1 Public IaaS Vendors TABLE OF CONTENTS INTRODUCTION 3 WHY IS THIS INFORMATION NECESSARY? 4 MISCONCEPTIONS ABOUT PERFORMANCE
More informationThe Secret World of Cloud IaaS Pricing in 2014: How to Compare Apples and Oranges Among Cloud Providers
The Secret World of Cloud IaaS Pricing in 2014: How to Compare Apples and Oranges Among Cloud Providers TABLE OF CONTENTS: EXECUTIVE SUMMARY... 3 PART 1: THE CURRENT STATE OF CLOUD COMPUTING IAAS: PRICING
More informationCloud Computing Performance Benchmarking Report. Comparing ProfitBricks and Amazon EC2 using standard open source tools UnixBench, DBENCH and Iperf
Cloud Computing Performance Benchmarking Report Comparing and Amazon EC2 using standard open source tools UnixBench, DBENCH and Iperf October 2014 TABLE OF CONTENTS The Cloud Computing Performance Benchmark
More informationEnabling Database-as-a-Service (DBaaS) within Enterprises or Cloud Offerings
Solution Brief Enabling Database-as-a-Service (DBaaS) within Enterprises or Cloud Offerings Introduction Accelerating time to market, increasing IT agility to enable business strategies, and improving
More informationStACC: St Andrews Cloud Computing Co laboratory. A Performance Comparison of Clouds. Amazon EC2 and Ubuntu Enterprise Cloud
StACC: St Andrews Cloud Computing Co laboratory A Performance Comparison of Clouds Amazon EC2 and Ubuntu Enterprise Cloud Jonathan S Ward StACC (pronounced like 'stack') is a research collaboration launched
More informationBenchmark Results of Fengqi.Asia
Benchmark Results of Fengqi.Asia Fengqi.Asia SmartOS SmartMachine vs. Popular Cloud Platforms(Part A) Fengqi.Asia VirtualMachine vs. Popular Cloud Platforms(Part B) Prepared by Fengqi.Asia Copyright owned
More information9/26/2011. What is Virtualization? What are the different types of virtualization.
CSE 501 Monday, September 26, 2011 Kevin Cleary kpcleary@buffalo.edu What is Virtualization? What are the different types of virtualization. Practical Uses Popular virtualization products Demo Question,
More informationBest Practices for Optimizing Your Linux VPS and Cloud Server Infrastructure
Best Practices for Optimizing Your Linux VPS and Cloud Server Infrastructure Q1 2012 Maximizing Revenue per Server with Parallels Containers for Linux www.parallels.com Table of Contents Overview... 3
More informationTechnical Paper. Moving SAS Applications from a Physical to a Virtual VMware Environment
Technical Paper Moving SAS Applications from a Physical to a Virtual VMware Environment Release Information Content Version: April 2015. Trademarks and Patents SAS Institute Inc., SAS Campus Drive, Cary,
More informationCloud Computing through Virtualization and HPC technologies
Cloud Computing through Virtualization and HPC technologies William Lu, Ph.D. 1 Agenda Cloud Computing & HPC A Case of HPC Implementation Application Performance in VM Summary 2 Cloud Computing & HPC HPC
More informationOracle Database Scalability in VMware ESX VMware ESX 3.5
Performance Study Oracle Database Scalability in VMware ESX VMware ESX 3.5 Database applications running on individual physical servers represent a large consolidation opportunity. However enterprises
More informationPrimaryIO Application Performance Acceleration Date: July 2015 Author: Tony Palmer, Senior Lab Analyst
ESG Lab Spotlight PrimaryIO Application Performance Acceleration Date: July 215 Author: Tony Palmer, Senior Lab Analyst Abstract: PrimaryIO Application Performance Acceleration (APA) is designed to provide
More informationScaling Database Performance in Azure
Scaling Database Performance in Azure Results of Microsoft-funded Testing Q1 2015 2015 2014 ScaleArc. All Rights Reserved. 1 Test Goals and Background Info Test Goals and Setup Test goals Microsoft commissioned
More informationTechnical Investigation of Computational Resource Interdependencies
Technical Investigation of Computational Resource Interdependencies By Lars-Eric Windhab Table of Contents 1. Introduction and Motivation... 2 2. Problem to be solved... 2 3. Discussion of design choices...
More informationBenchmarking Hadoop & HBase on Violin
Technical White Paper Report Technical Report Benchmarking Hadoop & HBase on Violin Harnessing Big Data Analytics at the Speed of Memory Version 1.0 Abstract The purpose of benchmarking is to show advantages
More informationCloud Computing Performance. Benchmark Testing Report. Comparing ProfitBricks vs. Amazon EC2
Cloud Computing Performance Benchmark Testing Report Comparing vs. Amazon EC2 April 2014 Contents The Cloud Computing Performance Benchmark report is divided into several sections: Topics.Page Introduction...
More informationWhite Paper. Recording Server Virtualization
White Paper Recording Server Virtualization Prepared by: Mike Sherwood, Senior Solutions Engineer Milestone Systems 23 March 2011 Table of Contents Introduction... 3 Target audience and white paper purpose...
More informationAmazon EC2 Product Details Page 1 of 5
Amazon EC2 Product Details Page 1 of 5 Amazon EC2 Functionality Amazon EC2 presents a true virtual computing environment, allowing you to use web service interfaces to launch instances with a variety of
More informationEnabling Technologies for Distributed and Cloud Computing
Enabling Technologies for Distributed and Cloud Computing Dr. Sanjay P. Ahuja, Ph.D. 2010-14 FIS Distinguished Professor of Computer Science School of Computing, UNF Multi-core CPUs and Multithreading
More informationGetting The Most Value From Your Cloud Provider
Getting The Most Value From Your Cloud Provider Cloud computing has taken IT by storm and it s not going anywhere. According to the International Data Corporation (IDC), cloud spending will surge by 5%
More informationVirtualCenter Database Performance for Microsoft SQL Server 2005 VirtualCenter 2.5
Performance Study VirtualCenter Database Performance for Microsoft SQL Server 2005 VirtualCenter 2.5 VMware VirtualCenter uses a database to store metadata on the state of a VMware Infrastructure environment.
More informationDIABLO TECHNOLOGIES MEMORY CHANNEL STORAGE AND VMWARE VIRTUAL SAN : VDI ACCELERATION
DIABLO TECHNOLOGIES MEMORY CHANNEL STORAGE AND VMWARE VIRTUAL SAN : VDI ACCELERATION A DIABLO WHITE PAPER AUGUST 2014 Ricky Trigalo Director of Business Development Virtualization, Diablo Technologies
More informationEvaluation Methodology of Converged Cloud Environments
Krzysztof Zieliński Marcin Jarząb Sławomir Zieliński Karol Grzegorczyk Maciej Malawski Mariusz Zyśk Evaluation Methodology of Converged Cloud Environments Cloud Computing Cloud Computing enables convenient,
More informationCloud Vendor Benchmark 2015. Price & Performance Comparison Among 15 Top IaaS Providers Part 1: Pricing. April 2015 (UPDATED)
Cloud Vendor Benchmark 2015 Price & Performance Comparison Among 15 Top IaaS Providers Part 1: Pricing April 2015 (UPDATED) Table of Contents Executive Summary 3 Estimating Cloud Spending 3 About the Pricing
More informationDeep Dive: Maximizing EC2 & EBS Performance
Deep Dive: Maximizing EC2 & EBS Performance Tom Maddox, Solutions Architect 2015, Amazon Web Services, Inc. or its affiliates. All rights reserved What we ll cover Amazon EBS overview Volumes Snapshots
More informationOTM in the Cloud. Ryan Haney
OTM in the Cloud Ryan Haney The Cloud The Cloud is a set of services and technologies that delivers real-time and ondemand computing resources Software as a Service (SaaS) delivers preconfigured applications,
More informationAmazon Cloud Storage Options
Amazon Cloud Storage Options Table of Contents 1. Overview of AWS Storage Options 02 2. Why you should use the AWS Storage 02 3. How to get Data into the AWS.03 4. Types of AWS Storage Options.03 5. Object
More informationChoosing the Right Cloud Provider for Your Business
Choosing the Right Cloud Provider for Your Business Abstract As cloud computing becomes an increasingly important part of any IT organization s delivery model, assessing and selecting the right cloud provider
More informationParallels Virtuozzo Containers
Parallels Virtuozzo Containers White Paper Top Ten Considerations For Choosing A Server Virtualization Technology www.parallels.com Version 1.0 Table of Contents Introduction... 3 Technology Overview...
More informationCloud Spectator Comparative Performance Report July 2014
Performance Analysis: Benchmarking a NoSQL Database on Bare-Metal and Virtualized Public Cloud Aerospike NoSQL Database on Internap Bare Metal, Amazon EC2 and Rackspace Cloud Cloud Spectator Comparative
More informationThe State of Cloud Storage
205 Industry Report A Benchmark Comparison of Speed, Availability and Scalability Executive Summary Both 203 and 204 were record-setting years for adoption of cloud services in the enterprise. More than
More informationHRG Assessment: Stratus everrun Enterprise
HRG Assessment: Stratus everrun Enterprise Today IT executive decision makers and their technology recommenders are faced with escalating demands for more effective technology based solutions while at
More informationRestricted Document. Pulsant Technical Specification
Pulsant Technical Specification Title Pulsant Government Virtual Server IL2 Department Cloud Services Contributors RR Classification Restricted Version 1.0 Overview Pulsant offer two products based on
More informationUsing VMware VMotion with Oracle Database and EMC CLARiiON Storage Systems
Using VMware VMotion with Oracle Database and EMC CLARiiON Storage Systems Applied Technology Abstract By migrating VMware virtual machines from one physical environment to another, VMware VMotion can
More informationDatacenters and Cloud Computing. Jia Rao Assistant Professor in CS http://cs.uccs.edu/~jrao/cs5540/spring2014/index.html
Datacenters and Cloud Computing Jia Rao Assistant Professor in CS http://cs.uccs.edu/~jrao/cs5540/spring2014/index.html What is Cloud Computing? A model for enabling ubiquitous, convenient, ondemand network
More informationBenchmarking Large Scale Cloud Computing in Asia Pacific
2013 19th IEEE International Conference on Parallel and Distributed Systems ing Large Scale Cloud Computing in Asia Pacific Amalina Mohamad Sabri 1, Suresh Reuben Balakrishnan 1, Sun Veer Moolye 1, Chung
More informationPERFORMANCE ANALYSIS OF KERNEL-BASED VIRTUAL MACHINE
PERFORMANCE ANALYSIS OF KERNEL-BASED VIRTUAL MACHINE Sudha M 1, Harish G M 2, Nandan A 3, Usha J 4 1 Department of MCA, R V College of Engineering, Bangalore : 560059, India sudha.mooki@gmail.com 2 Department
More informationEnabling Technologies for Distributed Computing
Enabling Technologies for Distributed Computing Dr. Sanjay P. Ahuja, Ph.D. Fidelity National Financial Distinguished Professor of CIS School of Computing, UNF Multi-core CPUs and Multithreading Technologies
More informationBenchmark Performance Test Results for Magento Enterprise Edition 1.14.1
Benchmark Performance Test Results for Magento Enterprise Edition 1.14.1 March 2015 Table of Contents 01 EXECUTIVE SUMMARY 03 TESTING METHODOLOGY 03 TESTING SCENARIOS & RESULTS 03 Compare different Enterprise
More informationPart 1: Price Comparison Among The 10 Top Iaas Providers
Part 1: Price Comparison Among The 10 Top Iaas Providers Table of Contents Executive Summary 3 Estimating Cloud Spending 3 About the Pricing Report 3 Key Findings 3 The IaaS Providers 3 Provider Characteristics
More informationBest Practices for Using MySQL in the Cloud
Best Practices for Using MySQL in the Cloud Luis Soares, Sr. Software Engineer, MySQL Replication, Oracle Lars Thalmann, Director Replication, Backup, Utilities and Connectors THE FOLLOWING IS INTENDED
More informationAmadeus SAS Specialists Prove Fusion iomemory a Superior Analysis Accelerator
WHITE PAPER Amadeus SAS Specialists Prove Fusion iomemory a Superior Analysis Accelerator 951 SanDisk Drive, Milpitas, CA 95035 www.sandisk.com SAS 9 Preferred Implementation Partner tests a single Fusion
More informationTHE DEFINITIVE GUIDE FOR AWS CLOUD EC2 FAMILIES
THE DEFINITIVE GUIDE FOR AWS CLOUD EC2 FAMILIES Introduction Amazon Web Services (AWS), which was officially launched in 2006, offers you varying cloud services that are not only cost effective, but also
More informationBuilding Docker Cloud Services with Virtuozzo
Building Docker Cloud Services with Virtuozzo Improving security and performance of application containers services in the cloud EXECUTIVE SUMMARY Application containers, and Docker in particular, are
More informationPARALLELS CLOUD SERVER
PARALLELS CLOUD SERVER An Introduction to Operating System Virtualization and Parallels Cloud Server 1 Table of Contents Introduction... 3 Hardware Virtualization... 3 Operating System Virtualization...
More informationI/O PERFORMANCE COMPARISON OF VMWARE VCLOUD HYBRID SERVICE AND AMAZON WEB SERVICES
I/O PERFORMANCE COMPARISON OF VMWARE VCLOUD HYBRID SERVICE AND AMAZON WEB SERVICES Businesses are rapidly transitioning to the public cloud to take advantage of on-demand resources and potential cost savings.
More informationRed Hat Satellite Management and automation of your Red Hat Enterprise Linux environment
Red Hat Satellite Management and automation of your Red Hat Enterprise Linux environment WHAT IS IT? Red Hat Satellite server is an easy-to-use, advanced systems management platform for your Linux infrastructure.
More informationEvaluating HDFS I/O Performance on Virtualized Systems
Evaluating HDFS I/O Performance on Virtualized Systems Xin Tang xtang@cs.wisc.edu University of Wisconsin-Madison Department of Computer Sciences Abstract Hadoop as a Service (HaaS) has received increasing
More informationHYPER-CONVERGED INFRASTRUCTURE STRATEGIES
1 HYPER-CONVERGED INFRASTRUCTURE STRATEGIES MYTH BUSTING & THE FUTURE OF WEB SCALE IT 2 ROADMAP INFORMATION DISCLAIMER EMC makes no representation and undertakes no obligations with regard to product planning
More informationVirtualization Technologies and Blackboard: The Future of Blackboard Software on Multi-Core Technologies
Virtualization Technologies and Blackboard: The Future of Blackboard Software on Multi-Core Technologies Kurt Klemperer, Principal System Performance Engineer kklemperer@blackboard.com Agenda Session Length:
More informationWITH A FUSION POWERED SQL SERVER 2014 IN-MEMORY OLTP DATABASE
WITH A FUSION POWERED SQL SERVER 2014 IN-MEMORY OLTP DATABASE 1 W W W. F U S I ON I O.COM Table of Contents Table of Contents... 2 Executive Summary... 3 Introduction: In-Memory Meets iomemory... 4 What
More informationComparison of Hybrid Flash Storage System Performance
Test Validation Comparison of Hybrid Flash Storage System Performance Author: Russ Fellows March 23, 2015 Enabling you to make the best technology decisions 2015 Evaluator Group, Inc. All rights reserved.
More informationThe Benefits of Using VSwap
Best Practices for Parallels Containers for Linux: Q1 2013 Using Virtual Swap to Maximize Container Performance www.parallels.com Table of Contents Introduction... 3 How VSwap Works... 3 Using VSwap with
More informationIBM Spectrum Scale vs EMC Isilon for IBM Spectrum Protect Workloads
89 Fifth Avenue, 7th Floor New York, NY 10003 www.theedison.com @EdisonGroupInc 212.367.7400 IBM Spectrum Scale vs EMC Isilon for IBM Spectrum Protect Workloads A Competitive Test and Evaluation Report
More informationPerformance Characteristics of VMFS and RDM VMware ESX Server 3.0.1
Performance Study Performance Characteristics of and RDM VMware ESX Server 3.0.1 VMware ESX Server offers three choices for managing disk access in a virtual machine VMware Virtual Machine File System
More informationIBM Platform Computing Cloud Service Ready to use Platform LSF & Symphony clusters in the SoftLayer cloud
IBM Platform Computing Cloud Service Ready to use Platform LSF & Symphony clusters in the SoftLayer cloud February 25, 2014 1 Agenda v Mapping clients needs to cloud technologies v Addressing your pain
More informationCloud Server. Parallels. An Introduction to Operating System Virtualization and Parallels Cloud Server. White Paper. www.parallels.
Parallels Cloud Server White Paper An Introduction to Operating System Virtualization and Parallels Cloud Server www.parallels.com Table of Contents Introduction... 3 Hardware Virtualization... 3 Operating
More informationBENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB
BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB Planet Size Data!? Gartner s 10 key IT trends for 2012 unstructured data will grow some 80% over the course of the next
More informationDirections for VMware Ready Testing for Application Software
Directions for VMware Ready Testing for Application Software Introduction To be awarded the VMware ready logo for your product requires a modest amount of engineering work, assuming that the pre-requisites
More informationAccelerating Enterprise Applications and Reducing TCO with SanDisk ZetaScale Software
WHITEPAPER Accelerating Enterprise Applications and Reducing TCO with SanDisk ZetaScale Software SanDisk ZetaScale software unlocks the full benefits of flash for In-Memory Compute and NoSQL applications
More informationSolidFire SF3010 All-SSD storage system with Citrix CloudPlatform 3.0.5 Reference Architecture
SolidFire SF3010 All-SSD storage system with Citrix CloudPlatform 3.0.5 Reference Architecture 2 This reference architecture is a guideline for deploying Citrix CloudPlatform, powered by Apache CloudStack,
More informationSolving I/O Bottlenecks to Enable Superior Cloud Efficiency
WHITE PAPER Solving I/O Bottlenecks to Enable Superior Cloud Efficiency Overview...1 Mellanox I/O Virtualization Features and Benefits...2 Summary...6 Overview We already have 8 or even 16 cores on one
More informationWhy Computers Are Getting Slower (and what we can do about it) Rik van Riel Sr. Software Engineer, Red Hat
Why Computers Are Getting Slower (and what we can do about it) Rik van Riel Sr. Software Engineer, Red Hat Why Computers Are Getting Slower The traditional approach better performance Why computers are
More informationMicrosoft Dynamics NAV 2013 R2 Sizing Guidelines for Multitenant Deployments
Microsoft Dynamics NAV 2013 R2 Sizing Guidelines for Multitenant Deployments February 2014 Contents Microsoft Dynamics NAV 2013 R2 3 Test deployment configurations 3 Test results 5 Microsoft Dynamics NAV
More informationBest Practices for Monitoring Databases on VMware. Dean Richards Senior DBA, Confio Software
Best Practices for Monitoring Databases on VMware Dean Richards Senior DBA, Confio Software 1 Who Am I? 20+ Years in Oracle & SQL Server DBA and Developer Worked for Oracle Consulting Specialize in Performance
More informationRed Hat Network Satellite Management and automation of your Red Hat Enterprise Linux environment
Red Hat Network Satellite Management and automation of your Red Hat Enterprise Linux environment WHAT IS IT? Red Hat Network (RHN) Satellite server is an easy-to-use, advanced systems management platform
More informationBilling for OpenStack Cloud Services
A bill for cloud services is created by applying a rate plan to the metered data consumed by the customer. This document provides an overview of the metered data and rate plan options for billing and showback
More informationIntroduction. Need for ever-increasing storage scalability. Arista and Panasas provide a unique Cloud Storage solution
Arista 10 Gigabit Ethernet Switch Lab-Tested with Panasas ActiveStor Parallel Storage System Delivers Best Results for High-Performance and Low Latency for Scale-Out Cloud Storage Applications Introduction
More informationPrice Comparison ProfitBricks / AWS EC2 M3 Instances
Price Comparison / AWS EC2 M3 Instances Produced by, Inc. Additional Information and access to a 14- day trial are avaialble at: http://www.profitbricks.com Getting Started: Comparing Infrastructure- as-
More informationMonitoring Databases on VMware
Monitoring Databases on VMware Ensure Optimum Performance with the Correct Metrics By Dean Richards, Manager, Sales Engineering Confio Software 4772 Walnut Street, Suite 100 Boulder, CO 80301 www.confio.com
More informationStratusphere Solutions
Stratusphere Solutions Deployment Best Practices Guide Introduction This guide has been authored by experts at Liquidware Labs in order to provide a baseline as well as recommendations for a best practices
More informationHow swift is your Swift? Ning Zhang, OpenStack Engineer at Zmanda Chander Kant, CEO at Zmanda
How swift is your Swift? Ning Zhang, OpenStack Engineer at Zmanda Chander Kant, CEO at Zmanda 1 Outline Build a cost-efficient Swift cluster with expected performance Background & Problem Solution Experiments
More informationThe IT benefits of bare-metal clouds
The IT benefits of bare-metal clouds Paul Burns December 15, 2014 This report is underwritten by SoftLayer. TABLE OF CONTENTS Executive summary... 3 The value of public clouds... 4 The importance of cloud
More informationBenchmarking Cassandra on Violin
Technical White Paper Report Technical Report Benchmarking Cassandra on Violin Accelerating Cassandra Performance and Reducing Read Latency With Violin Memory Flash-based Storage Arrays Version 1.0 Abstract
More informationSTeP-IN SUMMIT 2013. June 18 21, 2013 at Bangalore, INDIA. Performance Testing of an IAAS Cloud Software (A CloudStack Use Case)
10 th International Conference on Software Testing June 18 21, 2013 at Bangalore, INDIA by Sowmya Krishnan, Senior Software QA Engineer, Citrix Copyright: STeP-IN Forum and Quality Solutions for Information
More informationInternational Journal of Computer & Organization Trends Volume20 Number1 May 2015
Performance Analysis of Various Guest Operating Systems on Ubuntu 14.04 Prof. (Dr.) Viabhakar Pathak 1, Pramod Kumar Ram 2 1 Computer Science and Engineering, Arya College of Engineering, Jaipur, India.
More informationCOM 444 Cloud Computing
COM 444 Cloud Computing Lec 3: Virtual Machines and Virtualization of Clusters and Datacenters Prof. Dr. Halûk Gümüşkaya haluk.gumuskaya@gediz.edu.tr haluk@gumuskaya.com http://www.gumuskaya.com Virtual
More informationIs Hyperconverged Cost-Competitive with the Cloud?
Economic Insight Paper Is Hyperconverged Cost-Competitive with the Cloud? An Evaluator Group TCO Analysis Comparing AWS and SimpliVity By Eric Slack, Sr. Analyst January 2016 Enabling you to make the best
More information