//! Linux RAPL against the hardware (feature `rapl`): this host's powercap //! counters, or its energy-status MSRs where powercap lists no package, read by //! the meter and by an oracle the tests declare here. //! //! In a test binary of its own, so the RAPL probe runs in this process, and //! the tests take one lock: each burns CPU and reads machine-wide counters. //! The oracle reads `/sys/class/powercap` itself — every zone's `name`, //! `energy_uj` and `max_energy_range_uj` — and applies the sustained-advance //! rule to the top-level package zones (`package-`, or `package--die-` //! on a multi-die package) on its own. Where powercap lists no package it reads //! the RAPL MSRs itself (`oracle::msr`), each domain on its first CPU: per //! package on AMD and Hygon, per die on Intel. None of these tests //! passes without asserting: where the counters cannot be read (no powercap; //! a CI container, whose `/sys/devices/virtual/powercap` Docker masks), the //! liveness must say so and agree with the oracle; where they are live, both //! must say live, the counter must be the meter's active one, and its //! readings must be `HwShunt` over `CpuPkg` (the CPU package, not the GPU), //! the figure over a CPU burn inside the oracle's package-only bracket and //! clearly below package+psys and package+core. #![cfg(all(target_os = "linux", feature = "rapl"))] use std::path::Path; use std::sync::{Mutex, MutexGuard}; use std::time::Duration; use jouleclaw_energy::rapl::{rapl_liveness, RaplCounter}; use jouleclaw_energy::{meter, CounterLiveness, EnergyCounter, EnergyDomain, Provenance}; /// One test at a time: each burns CPU and reads machine-wide counters. static SERIAL: Mutex<()> = Mutex::new(()); fn serial() -> MutexGuard<'static, ()> { SERIAL.lock().unwrap_or_else(|poisoned| poisoned.into_inner()) } /// The tests' own reading of `/sys/class/powercap`: every zone listed, its /// `name`, `energy_uj` and `max_energy_range_uj`, read here and nowhere else, /// and the sustained-advance verdict over the package zones by the family's /// rule. Nothing in it comes from the crate under test. #[allow(dead_code)] mod oracle { use std::os::raw::{c_int, c_long}; use std::path::{Path, PathBuf}; use std::time::{Duration, Instant}; /// Where the kernel lists its powercap zones. pub const POWERCAP: &str = "/sys/class/powercap"; #[repr(C)] struct Timespec { tv_sec: c_long, tv_nsec: c_long, } unsafe extern "C" { fn clock_gettime(clock_id: c_int, tp: *mut Timespec) -> c_int; } /// `CLOCK_THREAD_CPUTIME_ID` in Linux ``. const CLOCK_THREAD_CPUTIME_ID: c_int = 3; /// This thread's CPU time. pub fn thread_cpu() -> Duration { let mut ts = Timespec { tv_sec: 0, tv_nsec: 0 }; assert_eq!(unsafe { clock_gettime(CLOCK_THREAD_CPUTIME_ID, &mut ts) }, 0, "clock_gettime"); Duration::new(ts.tv_sec as u64, ts.tv_nsec as u32) } /// Spin this thread until it has used `d` of its own CPU time, or `wall_cap` /// of wall time has passed. Returns the CPU it got. pub fn burn(d: Duration, wall_cap: Duration) -> Duration { let (started, wall) = (thread_cpu(), Instant::now()); let mut acc: u64 = 0; while thread_cpu() - started < d && wall.elapsed() < wall_cap { for _ in 0..1_000 { acc = std::hint::black_box(acc.wrapping_add(1)); } } thread_cpu() - started } /// One entry of the powercap directory. #[derive(Debug, Clone)] pub struct Zone { /// The directory entry: `intel-rapl:0`, `intel-rapl:0:0`, `intel-rapl-mmio:0`, ... pub dir: String, pub name: Option, pub energy_uj: Option, pub max_uj: Option, } fn text(p: PathBuf) -> Option { std::fs::read_to_string(p).ok().map(|s| s.trim().to_string()) } fn number(p: PathBuf) -> Option { text(p)?.parse().ok() } /// Every entry under `root`, in name order. pub fn zones(root: &Path) -> Vec { let Ok(entries) = std::fs::read_dir(root) else { return Vec::new() }; let mut zones: Vec = entries .flatten() .map(|e| { let dir = e.file_name().to_string_lossy().into_owned(); let p = e.path(); Zone { name: text(p.join("name")), energy_uj: number(p.join("energy_uj")), max_uj: number(p.join("max_energy_range_uj")), dir } }) .collect(); zones.sort_by(|a, b| a.dir.cmp(&b.dir)); zones } fn digits(s: &str) -> bool { !s.is_empty() && s.bytes().all(|b| b.is_ascii_digit()) } /// A top-level RAPL zone: `intel-rapl:`. Not a sub-zone, not MMIO. pub fn top_level(z: &Zone) -> bool { z.dir.strip_prefix("intel-rapl:").is_some_and(digits) } /// A package zone: top-level, named `package-`, or `package--die-` /// (one zone per die of a multi-die Intel package). pub fn is_package(z: &Zone) -> bool { top_level(z) && z.name.as_deref().and_then(|n| n.strip_prefix("package-")).is_some_and(|n| match n.split_once("-die-") { Some((package, die)) => digits(package) && digits(die), None => digits(n), }) } /// The platform zone. pub fn is_psys(z: &Zone) -> bool { top_level(z) && z.name.as_deref() == Some("psys") } /// A package's `core` sub-zone (`intel-rapl::` named `core`). pub fn is_core(z: &Zone) -> bool { z.dir.strip_prefix("intel-rapl:").is_some_and(|r| r.contains(':')) && z.name.as_deref() == Some("core") } /// One zone's energy between two reads, modulo its own range. pub fn delta(e0: u64, e1: u64, max: Option) -> Option { if e1 >= e0 { Some(e1 - e0) } else { max.filter(|&m| m > 0)?.checked_sub(e0)?.checked_add(e1) } } /// `energy_uj` of each of `dirs` under `root`, in order; `None` if any fails. pub fn read(root: &Path, dirs: &[&Zone]) -> Option> { dirs.iter().map(|z| number(root.join(&z.dir).join("energy_uj"))).collect() } /// The summed energy of `which` of `set` between two reads of `set`. pub fn energy(set: &[&Zone], before: &[u64], after: &[u64], which: impl Fn(&Zone) -> bool) -> u64 { set.iter() .zip(before.iter().zip(after)) .filter(|(z, _)| which(z)) .map(|(z, (&b, &a))| delta(b, a, z.max_uj).expect("a zone fell with no readable range")) .sum() } /// What the oracle concluded about the package counters under a root. #[derive(Debug, Clone, Copy, PartialEq, Eq)] pub enum Verdict { /// No top-level zone's `energy_uj` reads (no powercap, a masked or /// root-only tree). Unreadable, /// Top-level zones read, but none is a package. NoPackage, /// Every package read, but not every one kept advancing. Frozen, /// Every package advanced in at least five intervals, at least 80% of /// them, over at least 300 ms. Live, } /// The oracle's sustained-advance run over the package zones under `root`. #[derive(Debug)] pub struct Watch { pub verdict: Verdict, pub packages: Vec, pub intervals: u32, pub advances: Vec, pub window: Duration, } impl Watch { /// The verdict and each package's advances, for the test's log line. pub fn summary(&self) -> String { let per: Vec = self.packages.iter().zip(&self.advances).map(|(p, a)| format!("{p} advanced {a}/{}", self.intervals)).collect(); format!("{:?} ({} over {} ms)", self.verdict, per.join(", "), self.window.as_millis()) } } /// Sample every package's `energy_uj` under `root`, burning 25 ms of this /// thread's CPU between samples (capped at 500 ms of wall time), until every /// package has advanced in at least five intervals, at least 80% of those /// observed, over at least 300 ms; or one second has passed with at least /// five intervals; or five seconds have. pub fn watch(root: &Path) -> Watch { let all = zones(root); let packages: Vec<&Zone> = all.iter().filter(|z| is_package(z)).collect(); let names: Vec = packages.iter().map(|z| z.dir.clone()).collect(); if packages.is_empty() { let readable = all.iter().any(|z| top_level(z) && z.energy_uj.is_some()); return Watch::none(if readable { Verdict::NoPackage } else { Verdict::Unreadable }, names); } watch_with(names, || read(root, &packages)) } /// [`watch`] over this host: its powercap package zones, or, where powercap /// lists none, its RAPL MSRs ([`msr::domains`]), sampled the same way. pub fn watch_host() -> Watch { let root = Path::new(POWERCAP); if zones(root).iter().any(is_package) { return watch(root); } match msr::domains() { Some(domains) => { let names = domains.iter().map(|d| d.name.clone()).collect(); watch_with(names, || msr::read_all(&domains)) } None => { let w = watch(root); Watch::none(w.verdict, w.packages) } } } impl Watch { fn none(verdict: Verdict, packages: Vec) -> Watch { Watch { verdict, packages, intervals: 0, advances: Vec::new(), window: Duration::ZERO } } } /// The sustained-advance run over the counters `read` returns, one per name. fn watch_with(names: Vec, mut read: impl FnMut() -> Option>) -> Watch { let started = Instant::now(); let Some(mut prev) = read() else { return Watch::none(Verdict::Unreadable, names) }; let mut advances = vec![0u32; names.len()]; let mut intervals = 0u32; let live = |adv: &[u32], n: u32, w: Duration| { w >= Duration::from_millis(300) && adv.iter().all(|&a| a >= 5 && u64::from(a) * 5 >= u64::from(n) * 4) }; loop { let el = started.elapsed(); if live(&advances, intervals, el) || el >= Duration::from_secs(5) || (el >= Duration::from_secs(1) && intervals >= 5) { break; } burn(Duration::from_millis(25), Duration::from_millis(500)); if let Some(now) = read() { intervals += 1; for ((a, n), p) in advances.iter_mut().zip(&now).zip(&prev) { *a += u32::from(n > p); } prev = now; } } let window = started.elapsed(); let verdict = if live(&advances, intervals, window) { Verdict::Live } else { Verdict::Frozen }; Watch { verdict, packages: names, intervals, advances, window } } /// The oracle's own reading of the RAPL energy-status MSRs, for a host /// whose powercap lists no package: each domain's count through the `msr` /// driver's device file of its first CPU. A domain is a package on AMD and /// Hygon (a per-package counter) and a die of a package on Intel (the /// kernel's die-scope RAPL MSRs). pub mod msr { use super::number; use std::os::unix::fs::FileExt; use std::path::{Path, PathBuf}; /// One RAPL domain's energy-status MSR. pub struct Domain { pub name: String, device: PathBuf, register: u64, shift: u32, } fn read(device: &Path, register: u64) -> Option { let file = std::fs::File::open(device).ok()?; let mut raw = [0u8; 8]; file.read_exact_at(&mut raw, register).ok()?; Some(u64::from_le_bytes(raw)) } /// Every domain whose power-unit and energy-status MSRs read with a /// non-zero unit; `None` when the CPU's MSRs are not known here, no /// topology is listed, or any domain cannot be read. pub fn domains() -> Option> { let cpuinfo = std::fs::read_to_string("/proc/cpuinfo").ok()?; let field = |key: &str| { cpuinfo.lines().find_map(|l| l.split_once(':').filter(|(k, _)| k.trim() == key).map(|(_, v)| v.trim())) }; let family: u32 = field("cpu family")?.parse().ok()?; let (unit, energy, per_die) = match field("vendor_id")? { "GenuineIntel" if family == 6 => (0x606, 0x611, true), "AuthenticAMD" | "HygonGenuine" if family >= 0x17 => (0xC001_0299, 0xC001_029B, false), _ => return None, }; let mut first = std::collections::BTreeMap::<(u64, u64), u32>::new(); for entry in std::fs::read_dir("/sys/devices/system/cpu").ok()?.flatten() { let Some(cpu) = entry.file_name().to_str().and_then(|n| n.strip_prefix("cpu")?.parse::().ok()) else { continue; }; let topology = entry.path().join("topology"); let Some(package) = number(topology.join("physical_package_id")) else { continue }; let die = if per_die { number(topology.join("die_id")).unwrap_or(0) } else { 0 }; let lowest = first.entry((package, die)).or_insert(cpu); *lowest = (*lowest).min(cpu); } if first.is_empty() { return None; } first .into_iter() .map(|((package, die), cpu)| { let device = PathBuf::from(format!("/dev/cpu/{cpu}/msr")); let shift = ((read(&device, unit)? >> 8) & 0x1F) as u32; if shift == 0 { return None; } read(&device, energy)?; Some(Domain { name: format!("msr package-{package}-die-{die} (cpu {cpu})"), device, register: energy, shift }) }) .collect() } /// One domain's count, in µJ. fn uj(d: &Domain) -> Option { read(&d.device, d.register).map(|raw| ((u128::from(raw & 0xFFFF_FFFF) * 1_000_000) >> d.shift) as u64) } /// Every domain's count, in µJ; `None` if one fails. pub fn read_all(domains: &[Domain]) -> Option> { domains.iter().map(uj).collect() } /// The domains' summed energy between two reads, each modulo its 2^32 counts. pub fn energy(domains: &[Domain], before: &[u64], after: &[u64]) -> u64 { domains .iter() .zip(before.iter().zip(after)) .map(|(d, (&b, &a))| { let range = (((1u128 << 32) * 1_000_000) >> d.shift) as u64; super::delta(b, a, Some(range)).expect("an MSR count above its range") }) .sum() } } /// The zones under `root`, as one line for the log. pub fn listing(root: &Path) -> String { zones(root) .iter() .map(|z| { let kind = if is_package(z) { "package" } else if is_psys(z) { "psys" } else if is_core(z) { "core sub-zone" } else if top_level(z) { "top-level" } else { "not summed" }; let e = z.energy_uj.map_or("unreadable".to_string(), |e| e.to_string()); let m = z.max_uj.map_or("-".to_string(), |m| m.to_string()); format!("{}={} [{kind}] energy_uj={e} max={m}", z.dir, z.name.as_deref().unwrap_or("?")) }) .collect::>() .join("; ") } /// The CI container's view of the host's powercap directory: the same /// entries, each a symlink into `/sys/devices/virtual/powercap`, which /// Docker masks with an empty tmpfs, so every target is missing. Built /// from this host's own listing; removed when dropped. pub struct MaskedView(pub PathBuf); impl MaskedView { /// Build the masked view of this host's powercap entries in a /// temporary directory named by `tag` and this process. pub fn of_host(tag: &str) -> MaskedView { let root = std::env::temp_dir().join(format!("{tag}-masked-powercap-{}", std::process::id())); let _ = std::fs::remove_dir_all(&root); std::fs::create_dir_all(&root).expect("create the masked view"); let masked = root.join("masked-devices-virtual-powercap"); for z in zones(Path::new(POWERCAP)) { std::os::unix::fs::symlink(masked.join(&z.dir), root.join(&z.dir)).expect("symlink"); } MaskedView(root) } } impl Drop for MaskedView { fn drop(&mut self) { let _ = std::fs::remove_dir_all(&self.0); } } /// A bracket of reads around the meter's two reads: every package, psys /// and core zone read at four points, outer and inner on each side. pub struct Bracket<'a> { pub set: Vec<&'a Zone>, pub reads: [Vec; 4], } impl Bracket<'_> { /// The packages' energy over the outer bracket, in µJ: the most a /// package-only figure read inside it can be. pub fn package_outer(&self) -> u64 { energy(&self.set, &self.reads[0], &self.reads[3], is_package) } /// The packages' energy over the inner bracket, in µJ: the least a /// package-only figure read around it can be. pub fn package_inner(&self) -> u64 { energy(&self.set, &self.reads[1], &self.reads[2], is_package) } /// The psys zone's energy over the inner bracket, in µJ. pub fn psys_inner(&self) -> u64 { energy(&self.set, &self.reads[1], &self.reads[2], is_psys) } /// The core sub-zones' energy over the inner bracket, in µJ. pub fn core_inner(&self) -> u64 { energy(&self.set, &self.reads[1], &self.reads[2], is_core) } /// Whether the bracket read a zone of the kind `which` picks. pub fn has(&self, which: impl Fn(&Zone) -> bool) -> bool { self.set.iter().any(|z| which(z)) } } /// The family's rule on a figure `uj` the meter read between the /// bracket's inner and outer reads: no less than the packages' energy /// over the inner bracket, no more than over the outer one, and below /// package+psys and package+core where those zones exist. A figure that /// added a zone reads at least the packages' and that zone's energy over /// the inner bracket, so `uj < inner + zone` is the double-count test; it /// can only be put where the zone moved more over the burn than the /// packages did in the gap between the outer and inner reads (else a /// correct figure could reach it too), and the line says when it could /// not. Returns the figures, for the log. pub fn assert_package_only(b: &Bracket, uj: u64) -> String { let (inner, outer, psys, core) = (b.package_inner(), b.package_outer(), b.psys_inner(), b.core_inner()); let gap = outer - inner; let mut line = format!( "meter {uj} µJ; oracle package-only inner {inner} outer {outer} µJ (gap {gap}); psys inner {psys} µJ; \ core inner {core} µJ" ); assert!(inner > 0, "the packages did not advance over the burn: {line}"); assert!(inner <= uj && uj <= outer, "the figure is outside the package-only bracket: {line}"); for (zone, present, moved) in [("psys", b.has(is_psys), psys), ("core", b.has(is_core), core)] { if !present { continue; } assert!(moved > 0, "{zone} did not advance: {line}"); if moved > gap { assert!(uj < inner + moved, "the figure reaches package+{zone}: {zone} was added: {line}"); line.push_str(&format!("; below package+{zone}")); } else { line.push_str(&format!("; {zone} moved less than the gap, so only the outer bound tests it")); } } line } /// Every package, psys and core zone of `all` whose counter reads. pub fn bracket_set(all: &[Zone]) -> Vec<&Zone> { all.iter().filter(|z| (is_package(z) || is_psys(z) || is_core(z)) && z.energy_uj.is_some()).collect() } /// One oracle read of every zone of `set`; panics if one fails. pub fn read_all(set: &[&Zone]) -> Vec { read(Path::new(POWERCAP), set).expect("an oracle read of the bracket zones") } /// Read the bracket around `meter_read` (called twice) and `work`: /// outer, meter, inner, work, inner, meter, outer. pub fn around<'a, M>(set: Vec<&'a Zone>, mut meter_read: impl FnMut() -> M, work: impl FnOnce()) -> (Bracket<'a>, M, M) { let o0 = read_all(&set); let m0 = meter_read(); let o1 = read_all(&set); work(); let o2 = read_all(&set); let m1 = meter_read(); let o3 = read_all(&set); (Bracket { set, reads: [o0, o1, o2, o3] }, m0, m1) } } use oracle::Verdict; /// The liveness agrees with the oracle's own verdict, and only a live /// counter is available and is the meter's active one. #[test] fn the_rapl_liveness_agrees_with_the_oracle_and_gates_the_counter() { let _one = serial(); let liveness = rapl_liveness(); let watch = oracle::watch_host(); let counter = RaplCounter::new(); let composite = meter::detect_meter(); eprintln!( "rapl hardware: {}; oracle {}; liveness={liveness:?} available={} active={} meters={:?}", oracle::listing(Path::new(oracle::POWERCAP)), watch.summary(), counter.is_available(), composite.active_name(), composite.names() ); assert_eq!(liveness == CounterLiveness::Live, watch.verdict == Verdict::Live, "the liveness disagrees with the oracle"); match watch.verdict { Verdict::Unreadable | Verdict::NoPackage => assert_eq!(liveness, CounterLiveness::Unavailable), Verdict::Frozen => assert_eq!(liveness, CounterLiveness::Frozen), Verdict::Live => {} } assert_eq!(counter.liveness(), liveness, "the counter was built on another verdict"); assert_eq!(counter.is_available(), liveness == CounterLiveness::Live, "availability disagrees with the liveness"); assert_eq!(composite.active_name() == "rapl", liveness == CounterLiveness::Live, "the meter's choice disagrees"); if !counter.is_available() { assert!(counter.read().is_err(), "a counter that is not live read"); } } /// Over a 300 ms one-thread CPU burn, the counter's readings are `HwShunt` /// over `CpuPkg`, and its figure sits inside the oracle's package-only /// bracket and clearly below package+psys and package+core. #[test] fn a_cpu_burn_reads_inside_the_package_only_bracket() { let _one = serial(); let counter = RaplCounter::new(); if !counter.is_available() { let watch = oracle::watch_host(); eprintln!("rapl burn: counter {:?}; oracle {}", counter.liveness(), watch.summary()); assert_ne!(watch.verdict, Verdict::Live, "the oracle saw live packages, yet the counter is not available"); assert!(counter.read().is_err()); return; } let all = oracle::zones(Path::new(oracle::POWERCAP)); if !all.iter().any(oracle::is_package) { // No powercap package: the counter reads the MSRs, and so does the oracle, // outer and inner around the meter's reads. let domains = oracle::msr::domains().expect("the counter reads the MSRs, so the oracle can"); let read = || oracle::msr::read_all(&domains).expect("an oracle MSR read"); let o0 = read(); let r0 = counter.read().expect("a live counter reads"); let o1 = read(); let cpu = oracle::burn(Duration::from_millis(300), Duration::from_secs(10)); let o2 = read(); let r1 = counter.read().expect("a live counter reads"); let o3 = read(); for r in [&r0, &r1] { assert_eq!((r.domain, r.provenance), (EnergyDomain::CpuPkg, Provenance::HwShunt), "{r:?}"); } let (uj, inner, outer) = (r1.uj - r0.uj, oracle::msr::energy(&domains, &o1, &o2), oracle::msr::energy(&domains, &o0, &o3)); let names: Vec<&str> = domains.iter().map(|d| d.name.as_str()).collect(); eprintln!("rapl burn (MSR {names:?}): {cpu:?} of thread CPU; meter {uj} µJ; oracle inner {inner} outer {outer} µJ"); assert!(inner > 0, "the domains did not advance over the burn"); assert!(inner <= uj && uj <= outer, "the figure {uj} µJ is outside the oracle's MSR bracket [{inner}, {outer}]"); assert!(cpu >= Duration::from_millis(300), "the burn got only {cpu:?} of CPU"); return; } let mut cpu = Duration::ZERO; let (b, r0, r1) = oracle::around( oracle::bracket_set(&all), || counter.read().expect("a live counter reads"), || cpu = oracle::burn(Duration::from_millis(300), Duration::from_secs(10)), ); for r in [&r0, &r1] { assert_eq!((r.domain, r.provenance), (EnergyDomain::CpuPkg, Provenance::HwShunt), "{r:?}"); } eprintln!("rapl burn: {cpu:?} of thread CPU; {}", oracle::assert_package_only(&b, r1.uj - r0.uj)); assert!(cpu >= Duration::from_millis(300), "the burn got only {cpu:?} of CPU"); } /// What a CI container sees: Docker masks `/sys/devices/virtual/powercap` /// with an empty tmpfs, so every entry of `/sys/class/powercap` is a symlink /// to nothing. On that view of this host's own listing the counter is /// unavailable and reads nothing, and the oracle agrees. #[test] fn the_ci_containers_masked_view_is_unavailable() { let _one = serial(); let view = oracle::MaskedView::of_host("jouleclaw-energy"); let watch = oracle::watch(&view.0); let counter = RaplCounter::with_root(&view.0); eprintln!("rapl masked view: oracle {}; counter {:?} available={}", watch.summary(), counter.liveness(), counter.is_available()); assert!(matches!(watch.verdict, Verdict::Unreadable | Verdict::NoPackage), "{watch:?}"); assert_eq!((counter.liveness(), counter.is_available()), (CounterLiveness::Unavailable, false)); assert!(counter.read().is_err()); }