Abstract: In general, techniques are described for monitoring memory usage in computing devices. A computing device comprising a memory and a control unit that executes a kernel of an operating system having kernel sub-systems may implement the techniques. A memory manager kernel subsystem, in response to requests for amounts of the memory from other one kernel sub-systems, allocates memory blocks from the memory. The memory manager, in response to requests to de-allocate one or more of the allocated memory blocks, determines the corresponding requested amounts of memory and sizes of the de-allocated blocks. The memory manager then generates memory usage information based on the determined requested amounts of memory and the determined ones of the two or more different sizes. The memory usage information specifies usage of the memory in terms of the two or more different sizes of the allocated plurality of memory blocks.

Abstract: In general, techniques of this disclosure relate to measuring scheduling performance of monitored threads in an operating system with improved precision. In one example, a method includes inserting, by an operating system kernel, a monitored thread into a queue comprising one or more threads and recording an insertion time that the monitored thread is inserted into the run queue; receiving, by the kernel, an event to remove the monitored thread from the run queue; responsive to receiving the event, determining, by the kernel, an amount of time that the monitored thread is stored on the run queue based on the insertion time and a removal time at which the monitored thread was removed from the run queue; and when the amount of time the monitored thread is stored on the run queue is greater than or equal to a specified threshold, sending a notification to a notification listener.