xref: /xnu-10063.121.3/doc/observability/cpu_counters.md (revision 2c2f96dc2b9a4408a43d3150ae9c105355ca3daa)
1*2c2f96dcSApple OSS Distributions# CPU Counters
2*2c2f96dcSApple OSS Distributions
3*2c2f96dcSApple OSS DistributionsThe xnu subsystems that manage CPU performance counters.
4*2c2f96dcSApple OSS Distributions
5*2c2f96dcSApple OSS Distributions## Overview
6*2c2f96dcSApple OSS Distributions
7*2c2f96dcSApple OSS DistributionsCPU performance counters are hardware registers that count events of interest to efficient CPU execution.
8*2c2f96dcSApple OSS DistributionsCounters that measure events closely correlated with each CPU's execution pipeline are managed by the Core Performance Monitoring Unit (CPMU).
9*2c2f96dcSApple OSS DistributionsThe CPMU contains both fixed instructions and cycles counters, as well as configurable counters that can be programmed to count any of several hundred possible events.
10*2c2f96dcSApple OSS DistributionsIn addition to the CPMU, the Last Level Cache (LLC) hosts the Uncore Performance Monitoring Unit (UPMU), which measures effects that aren't necessarily correlated to a single CPU.
11*2c2f96dcSApple OSS DistributionsAll counters in the UPMU are configurable.
12*2c2f96dcSApple OSS Distributions
13*2c2f96dcSApple OSS DistributionsCounters are typically used in one of two ways:
14*2c2f96dcSApple OSS Distributions
15*2c2f96dcSApple OSS Distributions1. In "counting" mode, their counts are periodically queried and tallied up for a duration of interest.
16*2c2f96dcSApple OSS Distributions2. In "sampling" mode, the counters are programmed to generate a Performance Monitor Interrupt (PMI) periodically, during which the currently running code can be sampled, like a time profiler.
17*2c2f96dcSApple OSS Distributions
18*2c2f96dcSApple OSS Distributions## Subsystems
19*2c2f96dcSApple OSS Distributions
20*2c2f96dcSApple OSS DistributionsThere are several subsystems that provide access to CPU counter hardware:
21*2c2f96dcSApple OSS Distributions
22*2c2f96dcSApple OSS Distributions- kpc: The Kernel Performance Counter system is the oldest subsystem and still manages the configurable CPMU counters.
23*2c2f96dcSApple OSS DistributionsIt can use PMIs from these counters to trigger kperf samples and counter values can be recorded in kperf samples.
24*2c2f96dcSApple OSS Distributions
25*2c2f96dcSApple OSS Distributions- Monotonic: The Monotonic system provides access to the fixed CPMU counters with limited support for PMIs.
26*2c2f96dcSApple OSS DistributionsAdditionally, the UPMU is entirely provided by a Monotonic dev node interface.
27*2c2f96dcSApple OSS Distributions
28*2c2f96dcSApple OSS Distributions- cpc: The CPU Performance Counter subsystem provides a policy layer on top of kpc and Monotonic to prevent malicious use of the hardware.
29*2c2f96dcSApple OSS Distributions
30*2c2f96dcSApple OSS DistributionsEventually, cpc will subsume kpc's and Monotonic's roles in the system.
31*2c2f96dcSApple OSS Distributions
32*2c2f96dcSApple OSS Distributions## Integrations
33*2c2f96dcSApple OSS Distributions
34*2c2f96dcSApple OSS Distributions- The Recount subsystem makes extensive use of the fixed CPMU counters to attribute CPU resources back to threads and processes.
35*2c2f96dcSApple OSS Distributions
36*2c2f96dcSApple OSS Distributions- Microstackshot telemetry is sampled periodically using the CPMU's cycle PMI trigger.
37*2c2f96dcSApple OSS Distributions
38*2c2f96dcSApple OSS Distributions- Stackshot includes cycles and instructions for each thread container in its kcdata.
39*2c2f96dcSApple OSS Distributions
40*2c2f96dcSApple OSS Distributions- The kperf profiling system can trigger samples of thread states and call stacks using CPMU PMIs, allowing it to sample thread states and call stacks.
41*2c2f96dcSApple OSS DistributionsAnd CPU counter values can be sampled by kperf on other triggers, like timers or kdebug events.
42*2c2f96dcSApple OSS Distributions
43*2c2f96dcSApple OSS Distributions## See Also
44*2c2f96dcSApple OSS Distributions
45*2c2f96dcSApple OSS Distributions- <doc:recount>
46