System Data Definitions

This content describes the System Data metrics in Resolve > Blackbox.

Name	Definition
Total CPU %	Percentage of elapsed time that all processors are busy executing non-idle threads.
User CPU %	User-centric CPU usage, initiated by user actions and user run applications. Look at application CPU usage for clues.
Kernel CPU %	System or Kernel CPU process execution. Prolonged high kernel CPU usage might indicate underlying issues with device drivers, hardware, or the need for system optimizations.
Interrupt CPU %	Percentage of elapsed time that all processors on the system spent handling hardware interrupts. A malfunctioning hardware component or device driver can cause many interrupts, causing the processor to spend too much time in interrupt service routines.
DPC CPU %	Percentage of elapsed time that all processors on the system spend servicing deferred procedure calls (DPCs). A DPC executes below interrupt priority and thus permits other interrupts to occur. No application thread executes any code until all the pending DPCs execute. If a busy processor is spending a large amount of time servicing interrupts and DPCs, it is likely the processor cannot function effectively and a probable processor bottleneck will develop.
Throttle CPU %	Current throttle level of the CPU. For physical endpoints, lower values are usually caused by cooling issues, speed/energy saving software, or bios power management.
Processor Queue	A measure of the length of the microprocessor queue in units of threads. If the Processor Queue is higher than the number of cores, then the computer is not fast enough for the user's computing needs. You can check the Hardware tool to see the number of cores on the system. It could also be related to drivers. Make sure to use OEM drivers rather than generic, and that the drivers are updated with the OS upgrades.
Process Count	The number of processes counted at the time of data collection - this is an instantaneous count, not averaged. A high number here might be normal for certain systems but could also indicate presence of resource-intensive applications, background processes, memory leaks, or even malware.
Thread Count	Number of concurrently running threads at the focus time. High thread count could also be normal for an efficiently multi-tasking machine. Resource-intensive tasks and automations could contribute to a high count.
Interrupt/sec	Number of hardware device interrupts that the system is experiencing per second. Keyboard and mouse inputs, applications calling for hardware, CPU dealing with I/O request with any other hardware and local peripherals could all contribute to this being high. Look at faulting drivers or newly added devices.
DPCs/sec	Rate at which interrupt handlers in device drivers add deferred procedure call (DPC) requests to the system DPC queue. If a busy processor is spending a large amount of time servicing interrupts and DPCs, the processor probably cannot function effectively and a processor bottleneck is likely to develop. A malfunctioning hardware component or device driver can erroneously cause many DPCs to be queued.
Ctx Switches/sec	The combined rate at which all processors on the computer are switched from one thread to another. Context switches occur when a running thread voluntarily relinquishes the processor, is pre-empted by a higher priority ready thread, or switches between user-mode and privileged (kernel) mode to use an Executive or subsystem service. A high rate can indicate that many threads are contending for processor time.
Memory Used MB	Total Memory in use by all processes on the system.
Available Memory MB	Measure of free memory; the available memory within the OS available for processes.
Committed Memory MB	Total amount of memory committed by the OS and all processes running on the system. The memory is considered in use, but does not mean the memory has been written to. Some processes and applications will reserve memory in anticipation of optimizing performance, regardless of whether it is needed.
Commit Ratio %	The size of the virtual memory that has been committed as a percentage of the total virtual memory that can be committed without having to extend the page file.
Commit Limit MB	The total sum of physical memory and paging memory combined for the system. It is the maximum amount of physical resources that the system can use to back committed memory. This can increase if the page file is set to automatically extend.
Cache Faults/sec	The number of times per second that the cache manager fails to find a file's page in the immediate cache. This rule measures the rate at which faults occur when a page sought in the file system cache is not found and must be retrieved from elsewhere in memory (a soft fault) or from disk (a hard fault).
Active Sessions	The number of sessions either on the machine in questions (local console session), or connected to a remote session, via Horizon, Citrix Virtual Desktop or Apps, or RDSH/Terminal services. Also used on the server to show sessions in play.
State	The current session usage state on the system. Active or Inactive.
Server Connections	Instantaneous count of server connections.
Reboot Pending	Whether the machine requires a reboot or not, such as with pending updates, etc.
Graphics Apps	The number of processes running that require graphical acceleration.
Server Open Files	Number of files open within the active server session connections.
Pagefile Usage %	Percentage of active page file usage.
Pagefile Peak %	Peak usage of the page file.
Trans Faults/sec	The rate at which page faults are resolved by recovering pages that were in transition.
Page Faults/sec	Page Faults/sec is the overall rate at which faulted pages are handled by the processor. A page fault occurs when a process requires code or data that is not in its working set (its space in physical memory) in main memory.
Trans Faults Ratio %	The Transition Faults/sec to Page Faults/sec ratio indicates how often the computer moves data between active memory and storage. In low-memory situations, the system quickly writes modified data to disk, causing transition faults. A high ratio suggests a memory shortage, which is less desirable. In an ideal scenario, we aim for a lower ratio for smoother operations.
Sys Calls	Number of active kernel service requests on the system. A system call is a way for programs to interact with the operation system. A computer program makes a system call when it makes a request to the operating system's kernel. System call provides the services of the operating system to the user programs via Application Program Interface (API).
Pages In/Sec	The rate at which pages are read from the disk to resolve memory references to pages that were not in memory at the time of the reference. This counter includes paging traffic on behalf of the system cache to access file data for applications. Excessive paging may result from excessive memory pressure ('thrashing'). Pages Input/sec, however, also accounts for such activity as the sequential reading of memory mapped files, whether cached or not.
Pages Out/sec	The rate at which pages are written to disk to free up space in physical memory. Pages are written back to disk only if they are changed in physical memory, so they are likely to hold data (which frequently modified by processes), not code (which is usually not modified). A high Page Output rate often indicates a memory shortage. A high Page Output rate indicates that most faulting activity is for data pages and that memory is becoming scarce.
Page Reads/sec	The rate at which read operations from disk are initiated to resolve hard page faults. Hard page faults occur when a process requires code or data that is not in its working set or elsewhere in physical memory, and the code or data must be retrieved from disk. This statistic is a measure of the rate of read operations, without regard to the numbers of pages retrieved by each operation.
Page Writes/sec	The rate at which write operations to the disk are initiated to free up space in physical memory. Pages are written to disk only if they are changed while in physical memory, so they are likely to hold data (frequently modified by processes), not code (usually not modified). This measures the write operations rate, without regard to the number of pages written in each operation. High Page Write rate indicates that most faulting activity is for data pages and that memory is becoming scarce.
File Data Ops/sec	The combined rate of read and write operations on all logical disks on the computer.
File Cntl Ops/sec	Shows the combined rate of file system operations that are neither read nor write operations, such as file system control requests and requests for information about device characteristics or status.