The commoditization of high-performance networking has sparked research interest in the RDMA capability of this hardware. One-sided RDMA primitives, in particular, have generated substantial excitement due to the ability to directly access remote memory from within an application without involving the TCP/IP stack or the remote CPU. This paper considers how to leverage RDMA to improve the analytical performance of parallel database systems. To shuffle data efficiently using RDMA, one needs to consider a complex design space that includes (1) the number of open connections, (2) the contention for the shared network interface, (3) the RDMA transport function, and (4) how much memory should be reserved to exchange data between nodes during query processing. We contribute six designs that capture salient trade-offs in this design space. We comprehensively evaluate how transport-layer decisions impact the query performance of a database system for different generations of InfiniBand. We find that a shuffling operator that uses the RDMA Send/Receive transport function over the Unreliable Datagram transport service can transmit data up to 4× faster than an RDMA-capable MPI implementation in a 16-node cluster. The response time of TPC-H queries improves by as much as 2×.

Spinal cord injury (SCI) refers to a major worldwide cause of accidental death and disability. However, the complexity of the pathophysiological mechanism can result in less-effective clinical treatment. Growth differentiation factor 11 (GDF-11), an antiageing factor, was reported to affect the development of neurogenesis and exert a neuroprotective effect after cerebral ischaemic injury. The present work is aimed at investigating the influence of GDF-11 on functional recovery following SCI, in addition to the potential mechanisms involved. We employed a mouse model of spinal cord contusion injury and assessed functional outcomes via the Basso Mouse Scale and footprint analysis following SCI. Using western blot assays and immunofluorescence, we analysed the levels of pyroptosis, autophagy, necroptosis, and molecules related to the AMPK-TRPML1-calcineurin signalling pathway. The results showed that GDF-11 noticeably optimized function-related recovery, increased autophagy, inhibited pyroptosis, and alleviated necroptosis following SCI. Furthermore, the conducive influences exerted by GDF-11 were reversed with the application of 3-methyladenine (3MA), an autophagy suppressor, indicating that autophagy critically impacted the therapeutically related benefits of GDF-11 on recovery after SCI. In the mechanistic study described herein, GDF-11 stimulated autophagy improvement and subsequently inhibited pyroptosis and necroptosis, which were suggested to be mediated by TFE3; this effect resulted from the activity of TFE3 through the AMPK-TRPML1-calcineurin signalling cascade. Together, GDF-11 protects the injured spinal cord by suppressing pyroptosis and necroptosis via TFE3-mediated autophagy augmentation and is a potential agent for SCI therapy.

Recent trends show that cloud computing is growing to span more and more globally distributed data centers. For geo-distributed data centers, there is an increasing need for scheduling algorithms to place tasks across data centers, by jointly considering data and computation. This scheduling must deal with situations such as wide-area distributed data, data sharing, WAN bandwidth costs and data center capacity limits, while also minimizing completion time. However, this kind of scheduling problems is known to be NP-Hard. In this paper, inspired by real applications in astronomy field, we propose a two-phase scheduling algorithm that addresses these challenges. The mapping phase groups tasks considering the data-sharing relations, and dispatches groups to data centers by way of one-to-one correspondence. The reassigning phase balances the completion time across data centers according to relations between tasks and groups. We utilize the real China-Astronomy-Cloud model and typical applications to evaluate our proposal. Simulations show that our algorithm obtains up to 22% better completion time and effectively reduces the amount of data transfers compared with other similar scheduling algorithms. 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing 978-1-4799-8006-2/15 $31.00

No abstract

The commoditization of high-performance networking has sparked research interest in the RDMA capability of this hardware. One-sided RDMA primitives, in particular, have generated substantial excitement due to the ability to directly access remote memory from within an application without involving the TCP/IP stack or the remote CPU. This article considers how to leverage RDMA to improve the analytical performance of parallel database systems. To shuffle data efficiently using RDMA, one needs to consider a complex design space that includes (1) the number of open connections, (2) the contention for the shared network interface, (3) the RDMA transport function, and (4) how much memory should be reserved to exchange data between nodes during query processing. We contribute eight designs that capture salient tradeoffs in this design space as well as an adaptive algorithm to dynamically manage RDMA-registered memory. We comprehensively evaluate how transport-layer decisions impact the query performance of a database system for different generations of InfiniBand. We find that a shuffling operator that uses the RDMA Send/Receive transport function over the Unreliable Datagram transport service can transmit data up to 4× faster than an RDMA-capable MPI implementation in a 16-node cluster. The response time of TPC-H queries improves by as much as 2×.