TL;DR: The resident set size on my finite element solver hit 8GB during a full run on a 10-million-node mesh. The working set — the actual data I was pushing through the solver — should have been closer to 3.

📖 Reading time: ~39 min

What's in this article

The Problem: My Simulation Was Leaking 4GB Per Run and I Had No Idea Why

Quick Background: What Box Actually Does at the Allocator Level

Technique 1: Swapping the Global Allocator (jemalloc vs mimalloc)

Technique 2: Box<[T]> and Flattening Vec> Into Contiguous Memory

Technique 3: Arena Allocation to Eliminate Per-Box Overhead

The Problem with 10,000 Individual Allocations

Technique 4: Pinning and Box> for Self-Referential Structures

The Real Reason You Encounter Pin in HPC Code

The Problem: My Simulation Was Leaking 4GB Per Run and I Had No Idea Why

The resident set size on my finite element solver hit 8GB during a full run on a 10-million-node mesh.…