Module cpu 

Structs

CfsQuota 🔒

Effective CPU limit from CFS quota (None = unlimited).

CpuCollector

Snapshot 🔒

Enums

CpuSource 🔒

Which CPU accounting source is available for system-level utilization.

Functions

aggregate_util_cores 🔒

Aggregate utilization expressed as fractional cores in use (0.0..n_cores). Not clamped: kernel rounding can produce values very slightly above n_cores.

core_util_pct 🔒

Per-core utilization percentage (0.0–100.0, clamped).

cpu_idle 🔒

cpu_total 🔒

detect_cfs_quota 🔒

Read the CFS quota to determine effective core limit.

detect_cpu_source 🔒

Detect the best available CPU accounting source. Preference: cgroupv2 > cgroupv1 > /proc/stat

process_tree_io 🔒

Per-process cumulative disk I/O bytes from /proc/pid/io. Returns { pid -> (read_bytes, write_bytes) }. PIDs whose /proc/pid/io is unreadable (e.g. different UID without ptrace) are silently omitted – the delta for those PIDs will be 0.

process_tree_memory_mib 🔒

Sum of PSS and VmRSS across all given PIDs, each converted to MiB. One Process::open per PID reads both sources. PSS matches Python memory_mib; RSS is retained for consumers that need resident set size.

process_tree_ticks 🔒

Returns a map of { pid to (utime, stime) } for every process in the tree rooted at root_pid (root included). Processes that have already exited are silently skipped: this is a TOCTOU race we accept.

read_cgroup_usage_secs 🔒

Read cgroup CPU usage as fractional seconds (cumulative). Returns None if the detected source is ProcStat or reads fail.

read_cgroupv1_usage_ns 🔒

Read cgroupv1 cpuacct.usage (nanoseconds, cumulative).

read_cgroupv2_usage_usec 🔒

Read cgroupv2 cpu.stat usage_usec (microseconds, cumulative).

util_pct_from_ticks 🔒

Pure math: percentage of non-idle ticks between two snapshots (0.0–100.0 before any clamping). Takes raw pre-computed totals/idles so it can be unit-tested without constructing a CpuTime (which has private fields).

Type Aliases

Result 🔒