AMAZON S3 & EC2 PERFORMANCE REPORT
OVERVIEW
A frequently asked question regarding the Amazon Web Services (AWS) cloud computing platform is how well their storage system (S3) performs with their computing platform (EC2). As an FTP service that runs entirely within the AWS cloud, HostedFTP.com has, based on our internal performance data, created this report to discuss the performance you can expect when storing and retrieving files between an EC2 instance and S3. We will also be reporting on how the AWS infrastructure performs over time. Each month we will publish updates to the data to give you an insider’s view on how well AWS scales as they continue to add capacity and customers.
THE PERFORMANCE MODEL
When storing or retrieving a file with S3 we expect the performance to be comprised of two parts: a fixed cost that is not related to file size and a variable cost that is related to file size. In other words, we expect a linear performance model for storing and retrieving files between S3 and EC2. With a linear performance model in mind we need to determine two values: the fixed cost and the variable cost. The variable cost will be related to the size of the file being stored or retrieved, the fixed cost can be thought of as an overhead or transaction cost.
1
Amazon S3 and EC2 Performance Report Presented By HostedFTP.com - February 2009
AMAZON S3 & EC2 PERFORMANCE REPORT
ANALYSIS
Our analysis focuses on the data presented in Appendix A and B
STORING FILES
(SEE APPENDIX A)
For larger files the performance is much faster than with smaller files, implying that there is a significant fixed cost for each storage operation. To determine the fixed cost we can perform a linear regression. The following chart illustrates:
This chart shows that the fixed cost when storing a file is around 140 ms and the variable cost is between 10 and 12 MB/s.
RETRIEVING FILES
(SEE APPENDIX B )
The performance is consistent across all file sizes, implying there is no significant fixed cost when retrieving a file. The variable cost is the same as when storing a file at between 10 and 12 MB/s.
CONCLUSION
From our analysis we can conclude the following: 1. The variable cost when storing and retrieving files is between 10 and 12 MB/s 2. The fixed cost when storing a file is roughly 140 ms and negligible when retrieving a file As we move forward we will keep an eye on how these two values change.
ABOUT HOSTEDFTP.COM
HostedFTP.com is your hosted FTP service that runs 100% within the cloud infrastructure of AWS. Designed for use with both web browsers and FTP clients, HostedFTP.com improves your network security and saves your business money. For more information please visit our website www.hostedftp.com
2
Amazon S3 and EC2 Performance Report Presented By HostedFTP.com - February 2009
AMAZON S3 & EC2 PERFORMANCE REPORT
METHODOLOGY
We tracked the number of milliseconds (ms) it takes to store and retrieve files from S3 using large EC2 instances in the us-east-1a availability zone.We used the JetS3t Java Library to handle the actual storing and retrieving of files which in turn uses the Commons HttpClient Library. We started the timer at the point when the file is being stored or retrieved to S3. We included 50,000 total data points (stores and retrieves) in our analysis, drawn randomly from the month of February. These data points cover all days of the week and hours of the day.
LIMITATIONS AND OTHER CONSIDERATIONS
The maximum throughput (around 50 MB/s) you can expect when using S3 from a large EC2 instance is discussed here. Since we actively load balance our instances we don’t anticipate that this limit had any discernible impact on our results. To track the time it takes to store and retrieve a file we use the Java System.currentTimeMillis() function. From the documentation on this function: Note that while the unit of time of the return value is a millisecond, the granularity of the value depends on the underlying operating system and may be larger. For example, many operating systems measure time in units of tens of milliseconds. Since we have a large number of data points at small file sizes this should have a very limited impact on our results. Our times do not include failed attempts to store or retrieve a file from S3.
3
Amazon S3 and EC2 Performance Report Presented By HostedFTP.com - February 2009
AMAZON S3 & EC2 PERFORMANCE REPORT
APPENDIX A
STORING A FILE
FIlE SIzE rANgE FroM 0 KB 100 KB 200 KB 300 KB 400 KB 500 KB 600 KB 700 KB 800 KB 900 KB 1.0 MB 1.1 MB 1.2 MB 1.3 MB 1.4 MB 1.5 MB 1.6 MB 3.2 MB 6.4 MB 12.8 MB 25.6 MB 51.2 MB 102.4 MB to 100 KB 200 KB 300 KB 400 KB 500 KB 600 KB 700 KB 800 KB 900 KB 1.0 MB 1.1 MB 1.2 MB 1.3 MB 1.4 MB 1.5 MB 1.6 MB 3.2 MB 6.4 MB 12.8 MB 25.6 MB 51.2 MB 102.4 MB 5 GB
SAMPlE SIzE
AvErAgE FIlE SIzE 44 KB 157 KB 250 KB 347 KB 451 KB 546 KB 655 KB 721 KB 845 KB 959 KB 1.02 MB 1.13 MB 1.22 MB 1.32 MB 1.42 MB 1.52 MB 2.25 MB 4.7 MB 8.4 MB 15.9 MB 36.1 MB 70.7 MB 449.5 MB
AvErAgE tIME (MS) 122 146 138 206 177 173 287 192 429 327 332 243 224 315 281 261 554 536 1132 1522 3367 6741 37883
PErForMANcE (MB/S) 0.36 1.05 1.77 1.65 2.49 3.08 2.23 3.66 1.92 2.86 3.09 4.62 5.47 4.18 5.03 5.81 4.06 8.81 7.40 10.44 10.71 10.49 11.86
7658 1922 1574 1562 1014 431 545 204 113 101 118 88 78 89 88 92 1450 862 182 792 340 147 81
4
Amazon S3 and EC2 Performance Report Presented By HostedFTP.com - February 2009
AMAZON S3 & EC2 PERFORMANCE REPORT
APPENDIX B
RETRIEVING A FILE
FIlE SIzE rANgE FroM 0 KB 100 KB 200 KB 300 KB 400 KB 500 KB 600 KB 700 KB 800 KB 900 KB 1.0 MB 1.1 MB 1.2 MB 1.3 MB 1.4 MB 1.5 MB 1.6 MB 3.2 MB 6.4 MB 12.8 MB 25.6 MB 51.2 MB 102.4 MB to 100 KB 200 KB 300 KB 400 KB 500 KB 600 KB 700 KB 800 KB 900 KB 1.0 MB 1.1 MB 1.2 MB 1.3 MB 1.4 MB 1.5 MB 1.6 MB 3.2 MB 6.4 MB 12.8 MB 25.6 MB 51.2 MB 102.4 MB 5 GB
SAMPlE SIzE
AvErAgE FIlE SIzE 53 KB 157 KB 245 KB 345 KB 452 KB 552 KB 654 KB 719 KB 844 KB 957 KB 1.02 MB 1.12 MB 1.22 MB 1.32 MB 1.41 MB 1.52 MB 2.30 MB 4.63 MB 8.43 MB 16.11 MB 35.90 MB 69.71 MB 390.47 MB
AvErAgE tIME (MS) 5 16 27 36 45 52 60 66 71 71 93 106 125 117 159 140 186 435 833 1405 3878 7003 35081
PErForMANcE (MB/S) 10.18 9.52 8.72 9.30 9.80 10.28 10.69 10.60 11.57 13.17 11.03 10.57 9.80 11.26 8.87 10.84 12.37 10.63 10.12 11.47 9.26 9.95 11.13
11363 3754 2420 2299 1282 603 1007 531 185 167 202 271 168 156 125 148 2043 1382 485 935 636 202 105
5
Amazon S3 and EC2 Performance Report Presented By HostedFTP.com - February 2009