SearcharxivSearch

arXiv subjects

Ruihong Wang

Publications and source records attributed to Ruihong Wang.

6 recordsLinked to original sources

Cache Coherence Over Disaggregated Memory

Disaggregating memory from compute offers the opportunity to better utilize stranded memory in cloud data centers. It is important to cache data in the compute nodes and maintain cache coherence across multiple compute nodes. However, the limited computing power on disaggregated memory servers makes traditional cache coherence protocols suboptimal, particularly in the case of stranded memory. This paper introduces SELCC; a Shared-Exclusive Latch Cache Coherence protocol that maintains cache coherence without imposing any computational burden on the remote memory side. It aligns the state machine of the shared-exclusive latch protocol with the MSI protocol , thereby ensuring both atomicity of data access and cache coherence with sequential consistency. SELCC embeds cache-ownership metadata directly into the RDMA latch word, enabling efficient cache ownership management via RDMA atomic operations. SELCC can serve as an abstraction layer over disaggregated memory with APIs that resemble main-memory accesses. A concurrent B-tree and three transaction concurrency control algorithms are realized using SELCC's abstraction layer. Experimental results show that SELCC significantly outperforms Remote-Procedure-Call-based protocols for cache coherence under limited remote computing power. Applications on SELCC achieve comparable or superior performance over disaggregated memory compared to competitors.

cs.DB

An Adaptive Hotspot-Aware Index for Oscillating Write-Heavy and Read-Heavy Workloads

HTAP systems are designed to handle transactional and analytical workloads. Besides a mixed workload at any given time, the workload can also change over time. A popular type of continuously changing workload is one that oscillates between being write-heavy at times and being read-heavy at other times. Oscillating workloads can be observed in many applications. Indexes, e.g., the B+-tree and the LSM-tree, cannot perform equally well all the time. Conventional adaptive indexing does not solve this issue as it focuses on adapting in one direction. This paper studies how to support oscillating workloads with adaptive indexes that adapt the underlying index structures in both directions. With the observation that real-world datasets are skewed, the focus is to optimize the index within the hotspot regions. The Adaptive Hotspot-Aware Tree (or AHA-tree, for short) is introduced, where its adaptation is bi-directional. Experimental evaluation show that AHA-tree can behave competitively as compared to an LSM-tree for write-heavy transactional workloads. Upon switching to a read-heavy analytical workload, AHA-tree can gradually adapt and behave competitively, and can match the B+-tree in read performance.

cs.DB

Rumor Forwarding Prediction Model Based on Uncertain Time Series

The rapid spread of rumors in social media is mainly caused by individual retweets. This paper applies uncertainty time series analysis (UTSA) to analyze a rumor retweeting behavior on Weibo. First, the rumor forwarding is modeled using uncertain time series, including order selection, parameter estimation, residual analysis, uncertainty hypothesis testing and forecast, and the validity of using uncertain time series analysis is further supported by analyzing the characteristics of the residual plot. The experimental results show that the uncertain time series can better predict the next stage of rumor forwarding. The results of the study have important practical significance for rumor management and the management of social media information dissemination.

cs.SI

The Case for Distributed Shared-Memory Databases with RDMA-Enabled Memory Disaggregation

Memory disaggregation (MD) allows for scalable and elastic data center design by separating compute (CPU) from memory. With MD, compute and memory are no longer coupled into the same server box. Instead, they are connected to each other via ultra-fast networking such as RDMA. MD can bring many advantages, e.g., higher memory utilization, better independent scaling (of compute and memory), and lower cost of ownership. This paper makes the case that MD can fuel the next wave of innovation on database systems. We observe that MD revives the great debate of "shared what" in the database community. We envision that distributed shared-memory databases (DSM-DB, for short) - that have not received much attention before - can be promising in the future with MD. We present a list of challenges and opportunities that can inspire next steps in system design making the case for DSM-DB.

cs.DB

Revisit on the thermodynamic stability of Hořava-Lifshitz black hole

We study the thermodynamic properties of the black hole derived in Hořava-Lifshitz (HL) gravity without the detailed-balance condition. The parameter $Ξ=ε^2$ in the HL black hole plays the same role as that of the electric charge in the RN-AdS black hole. By analogy, we treat the parameter $Ξ$ as the thermodynamic variable and obtain the first law of thermodynamics for the HL black hole. Although the HL black hole and the RN-AdS black hole have the similar mass and temperature, due to their very different entropy the two black holes have very different thermodynamic properties. By calculating the heat capacity and the free energy we analyze the thermodynamic stability of the HL black hole.

gr-qc

Neutrino mass matrices with one texture equality and one vanishing neutrino mass

In the light of latest data of neutrino oscillation experiments, we carry out a systematic investigation on the texture structures of Majorana neutrino mass matrix $M_ν$, which contain one vanishing neutrino mass and an equality between two matrix elements. Among 15 logically possible patterns, it is found that for norm order ($m_{3}>m_{2}>m_{1}=0$) of neutrino masses only five of them are compatible with recent experimental data at the $3σ$ level, while for inverted order ($m_{2}>m_{1}>m_{3}=0$) ten patterns is phenomenologically allowed. In the numerical analysis, we perform a scan over the parameter space of all viable patterns to get a large sample of scattering points. We present the implications of each allowed pattern for three mixing angles $(θ_{12},θ_{2},θ_{3})$, leptonic CP violation and neutrinoless double-beta decay, predicting strong correlations between oscillation parameters. The theoretical realization of a concrete example is discussed in the framework of Froggatt-Nielsen mechanism.

hep-ph