Struct SpillCtx 

pub struct SpillCtx {
    pub file_map: Arc<Mmap>,
    pub file: Arc<File>,
    pub pinned_remaining: usize,
    pub n_pinned: usize,
    pub n_mmap: usize,
    pub mmap_bytes: usize,
}

Shared load-time spill context (SPILLING-PLAN §2 step 4). Built ONCE per model load when the disk tier is on, then handed by &mut to each HostExps::load so all layers/projections share ONE file mmap and draw down a single running pinned-RAM budget. Greedy in load order: pin until pinned_remaining is exhausted, then spill every later expert to Mmap.

Fields

file_map: Arc<Mmap>

One MAP_SHARED mmap of the whole GGUF, shared (Arc) across every spilled expert block.

file: Arc<File>

The same opened inode backing file_map, retained for future positioned expert reads.

pinned_remaining: usize

Pinned-RAM budget still available (bytes); decremented as experts are pinned.

n_pinned: usize

Diagnostics: how many experts landed pinned vs. mmap’d, and total disk-tier bytes.

n_mmap: usize

mmap_bytes: usize

Implementations

impl SpillCtx

pub fn open(g: &GgufFile, budget: &MemBudget) -> Result<Self, Box<dyn Error>>

Clone the parsed GGUF’s opened inode, create a MAP_SHARED mmap from it, and seed the pinned budget from a live MemBudget probe. The whole-map expert advice defaults to random (the historical behavior); setting MEMRA_MOE_MMAP_ADVICE=normal restores ordinary Linux readahead. SPILLING-PLAN §1.