All Threads

The All Threads table contains information about all the threads found in all the javacore files in the data set. Note that the thread is identified by a combination of its ID and name. This makes sense for pool threads that may be reused for unrelated tasks. Two tasks with different thread names are therefore treated as separate threads for the purpose of this report, even if they are executed in the scope of the same Thread java object. The table can be sorted by clicking on any column header. The following information is displayed for each thread:

• Thread name The name is clickable, and when clicked it opens a view that allows you to see the stack trace of the code that the thread was executing in each of the javacores in which it appears. Note that there may be multiple threads with the same name, since the names of threads are not unique over time, and may be reused.
• Total CPU usage is the total number of seconds the thread was using CPU time since the first javacore, in which the thread appears until the last.
• % CPU Usage is the total CPU usage of the thread, expressed as percentage of a single processor core. A thread can only use one CPU core at a time, the maximum possible value is therefore 100%.
• Average memory allocated since last GC is the amount of memory, in megabytes, allocated by the thread since the last GC cycle, averaged across all the javacores. Note that this number does not represent the total amount of memory allocated by a thread and is only suitable for relative comparison between threads. This number is only meaningful if a sufficient number of javacores is present in the data set, 10 being the absolute minimum in most cases.
• Average stack depth is the depth of the stack of the thread, averaged across all the javacore files in the data set, in which the thread appears.
• Blocking information includes a list of links to threads which are blocking or being blocked by the given thread