Oracle® Solaris Studio 12.4: Performance Analyzer

Exit Print View

Updated: January 2015

Timeline View

The Timeline view shows a chart of the events and the sample points recorded as a function of time. Data is displayed in horizontal bars. By default, for each experiment there is one bar for CPU Utilization Samples at the top and a set of profiling data bars for each thread. The data shown for each thread is determined by the data you collected when you profiled your application.

You might see the following data bars:

CPU Utilization Samples

When an experiment includes sample data, the top bar displayed is CPU Utilization Samples. Data in a sample point represents CPU time spent between that point and the previous point. Samples data include microstate information, which is available on Oracle Solaris systems.

Oracle Solaris operating systems use a technology called microstate accounting to gather statistics about the execution state for every event. The timing metrics for events shown by Performance Analyzer correspond to the relative amount of time spent in each state. CPU Utilization Samples displays a summary of the timing metrics for all the threads in the experiment. Click a sample to display the timing metrics for that sample in Selection Details panel on the right.

Profiling and Tracing Data Bars

The data bars for clock profiling, hardware counter profiling, and tracing data show an event marker for each event recorded. The event markers consist of a color-coded representation of the call stack that was recorded with the event.

Click an event marker to see information about the event in the Selection Details panel and the call stack functions in the Call Stack panel. Double-click functions in the Call Stack panel to go to the Source view and see the source for the function along with metrics.

For some kinds of data, events can overlap and not be visible. Whenever two or more events would appear at exactly the same position, only one can be drawn; if there are two or more events within one or two pixels, all are drawn, although they may not be visually distinguishable. In either case, a small gray tick mark is displayed below the event indicating the boundaries of that event. You can zoom in to see the events. You can use the left and right arrow keys to move the event selection in either direction and make hidden events become visible. You can see more information about events by displaying event density.

Event States

Events states are shown in a bar chart that shows the distribution of application time spent in various states as a function of time.

For clock profiling data recorded on Oracle Solaris, the event state chart shows Oracle Solaris microstates. The color coding for event states is the same as for the CPU Utilization Samples bar.

Event states are displayed by default. You can hide them by clicking the Timeline Settings button Timeline settings icon in the Timeline toolbar and deselecting Event States in the Timeline area of the Settings dialog box.

Event Density

Event density is indicated by a blue line that displays frequency of events as a function of time.

To show event density, click the Timeline Settings button Timeline settings icon in the timeline toolbar and select Event Density in the Timeline area of the Settings dialog box.

Event density is then displayed immediately below the timeline data bar for each data type. Event density displays the count of events that occurred in each horizontal time slice. The scale of the vertical axis of the line chart is 0 to the highest event count for that specific data bar in the visible time range.

When the timeline's zoom setting is such that there are many events in each visible time slice, event density can be used to identify periods of high event frequency. To explore such a period, you can zoom in. Then you can right-click and select a context filter to include only data from the visible time range, and analyze that data from that specific period using the other Performance Analyzer data views.