Estimating Throughput Targets
• Throughput is the number of operations that a server farm can perform per second.
• Throughput is measured in requests per second (RPS). RPS measurements can be converted to the total number of users.
• Variables that affect Throughput :
• Concurrency
• Request Rate
Calculating Throughput
• Throughput = simultaneous users/request rate
Example
• Total online users - 1000
• Simultaneous users (10% of online users) - 100
• Estimated requests per user per hour - 36
(1 request per user per 100 seconds)
• Throughput - 1 RPS
(simultaneous users/request rate)
• Therefore, 1 RPS can support up to 1,000 users, each making 36 requests per hour
Throughput Targets
• Throughput is the number of operations that a server farm can perform per second.
• Throughput is measured in requests per second (RPS). RPS measurements can be converted to the total number of users.
• Variables that affect Throughput :
• Concurrency
• Request Rate
Calculating Throughput
• Throughput = simultaneous users/request rate
Example
• Total online users - 1000
• Simultaneous users (10% of online users) - 100
• Estimated requests per user per hour - 36
(1 request per user per 100 seconds)
• Throughput - 1 RPS
(simultaneous users/request rate)
• Therefore, 1 RPS can support up to 1,000 users, each making 36 requests per hour
Throughput Targets
Performance Optimization
• Performance Considerations
• Caching
• Output Caching - Memory Based
• BLOB Caching - Disk Based
• Object caching - Memory Based
• IIS Compression
• Working with Large Lists
• Code Optimization and Guidelines
• 64-bit considerations
• Architectural Considerations
