Struct PeakBytes 

#[repr(transparent)]
pub struct PeakBytes(pub u64);

Lifetime high-water mark, bytes. Same Maxable-only contract as PeakNs but Bytes-typed so the renderer routes through the IEC binary auto-scale ladder (B → KiB → MiB → GiB → TiB) instead of the ns ladder.

The kernel’s taskstats interface (/proc/<tid>/stat does NOT expose these — they require the genetlink TASKSTATS_CMD_GET path; see crate::taskstats::TaskstatsClient) carries hiwater_rss and hiwater_vm as KB-truncated lifetime watermarks. The capture pipeline multiplies by 1024 at the boundary so the wire-format value is in bytes, matching the existing Bytes newtype unit.

Cross-thread vs cross-snapshot semantics

Sibling threads of the same tgid see the same value: xacct_add_tsk (kernel/tsacct.c::xacct_add_tsk, lines 99-104) fills hiwater_rss and hiwater_vm from get_mm_hiwater_rss(mm) / get_mm_hiwater_vm(mm) — both read from the shared mm_struct, so every thread of a given tgid reports the same lifetime watermark. A Max reduction across sibling threads of the same process is therefore a no-op on the watermark itself; the meaningful Max is the one across DIFFERENT processes, where each tgid carries its own mm_struct and an independent watermark history. Use Max expecting “the biggest process’s watermark in the bucket”, not “the worst-behaving thread of any process”.

Kernel threads (mm == NULL) report zero: the same xacct_add_tsk path guards the assignments behind if (mm) (line 100), so kernel threads (PF_KTHREAD) leave the field at the kernel-side zero.

In COMPARE mode the per-thread PeakBytes delta between two snapshots is peak_after - peak_before — the kernel only ever raises the field, so the delta is non-negative and represents the AMOUNT BY WHICH THE LIFETIME WATERMARK GREW during the (capture-A, capture-B) interval, NOT the allocation size during that interval. A new allocation only moves the watermark if its peak RSS exceeds the prior lifetime maximum; an interval full of small allocations that stayed under peak_before shows a zero delta.

Summing watermarks across threads is a category error — does not implement Summable. Implements Maxable.

u64 backing

Bytes are non-negative by definition; the kernel-side __u64 hiwater_rss / __u64 hiwater_vm in struct taskstats (include/uapi/linux/taskstats.h) are u64 KB counts, and the post-multiply byte count fits comfortably in u64 across any realistic per-process memory footprint.

Tuple Fields

0: u64

Trait Implementations

impl Clone for PeakBytes

fn clone(&self) -> PeakBytes

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for PeakBytes

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for PeakBytes

fn default() -> PeakBytes

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for PeakBytes

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for PeakBytes

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl From<PeakBytes> for u64

fn from(v: PeakBytes) -> Self

Converts to this type from the input type.

impl From<u64> for PeakBytes

fn from(v: u64) -> Self

Converts to this type from the input type.

impl Hash for PeakBytes

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Maxable for PeakBytes

fn max_across(items: impl IntoIterator<Item = Self>) -> Option<Self>

impl Ord for PeakBytes

fn cmp(&self, other: &PeakBytes) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl PartialEq for PeakBytes

fn eq(&self, other: &PeakBytes) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl PartialOrd for PeakBytes

fn partial_cmp(&self, other: &PeakBytes) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

Tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

Tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

Tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl Serialize for PeakBytes

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for PeakBytes

impl Eq for PeakBytes

impl StructuralPartialEq for PeakBytes