In large-scale data-parallel analytics, shuffle operations often become performance bottlenecks due to network overhead from all-to-all data movement and disk I/O overhead from write/read of persistent intermediate data. Push-based shuffle is widely adopted to mitigate this overhead by enabling sequential I/O through early transmission and pre-merge. However, existing push-based-shuffle scheduling strategies based on single-shuffle-based workload prediction and task scheduling fails to account for hierarchical data dependencies in practical scenarios involving complex DAG workflows, leading to load imbalance and poor data locality.

While intelligent applications (e.g., recommendation systems) prefer different CPU-GPU ratios, GPU pooling technique that decouples the GPU and CPU resources yields substantial flexibility when serving diverse applications. With such architecture, DNN-based recommendation services often offload the compute-intensive neural network layers to the remote GPU pool for high resource utilization. However, such a paradigm results in the long end-to-end latency due to two causes: 1) the intermediate data is copied for multiple times during the entire process in current GPU pooling practices, incurring heavy overheads; 2) the content transferred to the GPU pool involves multiple small tensors, suffering from poor bandwidth efficiency. To solve these problems, we design Zero, a runtime system that incorporates a zero-copy transmission mechanism as well as a dynamic tensor merging policy. The zero-copy transmission mechanism unifies memory management across the inference framework and the RPC framework, accompanied by an elaborated serialization protocol to fully eliminate redundant data copying. Meanwhile, the tensor merging policy deliberately organizes small tensors into larger data blocks, so as to transfer them with higher efficiency. Experimental results show that, compared with prior work, Zero reduces the latency of typical recommendation models by up to 15.1% (10.1% on average).

With the explosive growth of data in cloud storage systems, Erasure Codes (ECs) have become a typical data redundancy technology because of its low storage cost and high reliability. However, due to a large amount of complex computations and transmissions among massive data and parities, the recovery of lost data in erasure coded storage systems incurs high I/O latency. Although several fast recovery approaches devote to mitigating the recovery time from the application level or device level, the performance of file level recovery is still restricted. It is because a part of the complicated relationships among data, parity and files are ignored in the design of recovery process. To address the above problems, we propose a novel File-aware Graph Recovery (FAGR) scheme, to improve the file level recovery performance during the reconstruction process. The key idea of FAGR is establishing a graph with the mappings among files, blocks, stripes, parities, nodes and the access frequencies of files, and guides the recovery process from file point of view. A corresponding model is established to analyze the cost efficiency of recovery process, which guarantees that FAGR reconstructs the popular files in advance to accelerate the recovery. To demonstrate the effectiveness of FAGR, we conduct several numerical analysis and experiments in clusters. The results show that, compared to typical fast recovery methods, FAGR reduces the average response time of files by up to 81.63 % and improves the throughput by up to 4.44 ×.

Observations on the citation networks often confirm a core-periphery structure: A clustered group of artifacts possess the core knowledge to the field, which is widely cited by artifacts at periphery. We explain this as an outcome resulted from decentralized knowledge contributions from individuals who maximize their own utilities. Our model sheds insights on how knowledge creation, knowledge citation, and knowledge heterogeneity affect the emergence of knowledge core, in both cases of direct and indirect citations. We find through simulations that the core-periphery architecture of citation networks is robust to generalizations on knowledge heterogeneity and knowledge creativity. By studying the incentive rationale that underlies the growth of citation networks, our research has potential implications on the design and administration of intellectual communities.