Micro-second accuracy, up-to two years history
With PerformanceVision all network flows and application transactions are identified, classified and measured in real-time. Every session, every transaction detail at over 10Gbps per appliance in production, with 40Gbps links support is analyzed by our solution. We provide continuous real-time measuring of network health, response times and transaction details.
End-user complaint diagnosis can be performed in a few clicks through a drill down to detailed infrastructure, system and application levels, without the need to manipulate packets. Having both network and application performance metrics in one single appliance significantly accelerates performance diagnostics.
Current issues can be compared to historical data on a daily, weekly, monthly or yearly basis to speed-up troubleshooting. Historical data is retained for up to two years to help in identifying usage trends.
To cover such a long period of time the retention of statistical analysis requires the storage of large amounts of data. This data must be stored over extended periods of time to expose overall trends. To minimize storage space while still making it possible to reveal trends over weeks, months or even years, PerformanceVision automatically summarizes the collected data through a process called aggregation.
This process occurs automatically. Whenever PerformanceVision displays a chart or a table, it uses data that is already aggregated. To display this information, it first decides on an aggregation granularity to use, depending on both the length of the period you requested and how far back into the past it goes.
When computing performance metrics at the sniffer level, the granularity unit is the microsecond, which provides extreme accuracy. Every minute, these metrics data are aggregated into the central database.
Three levels of granularity are available in PerformanceVision:
- 1-minute granularity for up to 1 month of in-depth history;
- 1-hour granularity for up to 100 days of mid-term history;
- 1-day granularity for up to two years of long-term history.
Once a level is full, the oldest data is automatically moved to the next level in a process that is completely transparent for the end-user.