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

TL;DR

The paper tackles freshness (AoI) in shared-memory status-update systems by comparing Read-Copy-Update (RCU) and Readers-Writer Lock (RWL) synchronization within a forwarder that maintains a Forwarder Information Base (FIB). It develops a stochastic hybrid system (SHS) framework to model two coupled age processes—location updates in memory and app updates at the destination—and analyzes preemptive and non-preemptive variants for both primitives. Through SHS-based age balance equations, it derives closed-form-like fixed-point conditions to compute average ages $\mathbb{E}[\hat{\Delta}]$ and $\mathbb{E}[\Delta]$, and then presents numerical results showing regime-dependent performance: lock-based RWL can yield fresher app updates at high location-update rates, while lock-less RCU can deliver timelier updates at lower location-update rates. The work quantifies the trade-offs between concurrency and freshness in shared-memory systems, providing guidance for designing AoI-sensitive network devices and software libraries that rely on fast, synchronized shared state. \(\text{Key metrics involve } \hat{\Delta}, \Delta, \text{ and delivery probability } P_{\text{delivery}}\) and parameterize reads, writes, and arrival rates to reveal when each primitive is advantageous.

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 If a FIB read returns an outdated address, the misaddressed app update is lost in transit.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.

Figures (6)

• Figure 1: Packet forwarding application with mobile users
• Figure 2: SHS Markov chain for (a) RCU mechanism and for (b) RWL mechanism.
• Figure 3: AoI at mobile client when using RCU preemption (rcu -p) and RWL preemption (rwl-p) as a function of normalized write request rate $\hat{\rho}=\hat{\lambda}/\hat{\mu}$, against different values of normalized read rate $\beta=\lambda/\hat{\mu}$ and $\sigma_{\text{RCU}} = 10$ with (a)$\sigma_{\text{RWL}} = 1$, and (b)$\sigma_{\text{RWL}}=10$.
• Figure 4: Probability that an app update arriving at router is delivered correctly when $\sigma_{\text{RCU}} = 10$ and when (a)$\sigma_{\text{RWL}}=1$ and (b)$\sigma_{\text{RWL}}=10$.
• Figure 5: AoI performance with and without preemption for (a) RCU with $\sigma_{\text{RCU}}=10$, and (b) RWL with $\sigma_{\text{RWL}} = 1$.

Theorems & Definitions (1)

• Theorem 1