|
|||||||||||
GiAPAGlobal iSeries Application Performance Analysis iSeries professionals
consider application performance optimization a complex task, normally requiring
expensive external experts. However, GiAPA's automatic data collection and
analysis makes it easy for the average operator, programmer or systems analyst
to locate and diagnose the vast majority of performance inefficiencies.
GiAPA assists in locating and diagnosing performance inefficiencies
in applications running under i5/OS. GiAPA will assist you in using your
existing computer resources in an optimal way, without the need to purchase
additional hardware to meet the growth of users or applications.
Using less than 0.1 percent of one CPU, GiAPA collects performance data
for all active jobs and tasks, automatically storing additional details
down to thread level for the jobs using the most resources.
GiAPA allows you to collect comprehensive performance data continuously
at merely no cost. This means that when a performance problem has occurred
(e.g. a user complains about bad response times during the morning), you
can pinpoint the cause within the available GiAPA data. GiAPA is designed to tell you:
GiAPA is used for much more than speeding up applicationsSince GiAPA keeps details
on the movements of all jobs, it is commonly used by operations to follow
up on the every day load on the server (who did what and when), or to
supply management trends on resource usage.
Other Benefits:
How does GiAPA Work?
GiAPA's data collection retrieves performance
details for all jobs and tasks every 15 seconds. Additional call stack and
file usage data is collected automatically for any job causing a "HotSpot",
i.e. exceeding user-defined limits for CPU percentage or Disk-I/Os within
a 15 second interval. Data collection consumes typically somewhat less than
0.1 % CPU.
The collected performance data stored in compressed
binary format is expanded and analyzed. Jobs suffering from or potentially
causing performance problems are kept individually by GiAPA for further
analysis - other jobs or tasks are kept summarized by type and interval.
A large number of exception and detailed reports, including pie, bar, line, and column charts, can be requested interactively, often down to the source statement number. This will show where to correct which performance problems, or where additional resources are used.
|
|
||||||
|
Software Engineering of America Inc., |
|||||||
|
Contact Information | |
|
Before viewing our whitepapers, please fill out the form below with your contact information. |