Lock-based or Lock-less: Which Is Fresh?

2023-04-23

IEEE Conference on Computer Communications

AI Summary

This work investigates how synchronization mechanisms affect state freshness under coupled position and application updates in shared memory. To address read–write contention in the Forwarding Information Base (FIB), we propose the first stochastic hybrid system (SHS) model featuring coupled dual age metrics, enabling quantitative comparison of Read-Copy-Update (RCU) and reader–writer locks (RWL) in terms of update timeliness. Theoretical analysis and numerical evaluation reveal a fundamental trade-off: RWL significantly improves application-update freshness under high position-update rates, whereas RCU ensures more timely application delivery and lower packet loss due to stale addresses under low update rates. This study is the first to formally characterize the timeliness–synchronization–frequency trade-off, establishing a quantifiable foundation for designing network state synchronization mechanisms.

Abstract

We examine status updating systems in which time-stamped status updates are stored/written in shared-memory. Specifically, we compare Read-Copy-Update (RCU) and Readers-Writer lock (RWL) as shared-memory synchronization primitives on the update freshness. To demonstrate the tension between readers and writers accessing shared-memory, we consider a network scenario with a pair of coupled updating processes. Location updates of a mobile terminal are written to a shared-memory Forwarder Information Base (FIB) at a network forwarder. An application server sends "app updates" to the mobile terminal via the forwarder. Arriving app updates at forwarder are addressed (by reading the FIB) and forwarded to the mobile terminal. If a FIB read returns an outdated address, the misaddressed app update is lost in transit. We redesign these reader and writer processes using preemption mechanisms that improve the timeliness of updates. We present a Stochastic Hybrid System (SHS) framework to analyze location and app update age processes and show how these two age processes are coupled through synchronization primitives. Our analysis shows that using a lock-based primitive (RWL) can serve fresher app updates to the mobile terminal at higher location update rates while lock-less (RCU) mechanism favors timely delivery of app updates at lower location update rates.

Problem

• Shared Memory
• Update Freshness
• Networked Systems

Innovation

• Read-Copy-Update (RCU)
• Readers-Writer lock (RWL)
• Stochastic Hybrid System (SHS)