Virtual-Memory Assisted Buffer Management In Tiered Memory

TL;DR

This paper introduces vmcache^n, a virtual-memory-based buffer management system for multi-tier memory architectures, improving query throughput by up to 4 times through efficient page migration control.

Contribution

It generalizes two-tier buffer management to n-tier systems and introduces move_pages2 for fine-grained page migration control.

Findings

Up to 4× higher query throughput with vmcache^n.

Effective page migration reduces bottlenecks in multi-tier memory.

Demonstrates benefits in TPC-C workloads.

Abstract

Tiered memory architectures have gained significant traction in the database community in recent years. In these architectures, the on-chip DRAM of the host processor is typically referred to as local memory, and forms the primary tier. Additional byte-addressable, cache-coherent memory resources, collectively referred to as remote memory (RMem, for short), form one or more secondary tiers. RMem is slower than local DRAM but faster than disk, e.g., NUMA memory located on a remote socket, chiplet-attached memory, and memory attached via high-performance interconnect protocols, e.g., RDMA and CXL. In this paper, we discuss how traditional two-tier (DRAM-Disk) virtual-memory assisted Buffer Management techniques generalize to an $n$-tier setting (DRAM-RMem-Disk). We present vmcache$^n$, an $n$-tier virtual-memory-assisted buffer pool that leverages the virtual memory subsystem and operating system calls to migrate pages across memory tiers. In this setup, page migration can become a bottleneck. To address this limitation, we introduce the move_pages2 system call that provides vmcache$^n$ with fine-grained control over the page migration process. Experiments show that vmcache$^n$ can achieve up to 4$\times$ higher query throughput over vmcache for TPC-C workloads.