Related papers: Varuna: Enabling Failure-Type Aware RDMA Failover
RDMA is vital for efficient distributed training across datacenters, but millisecond-scale latencies complicate the design of its reliability layer. We show that depending on long-haul link characteristics, such as drop rate, distance and…
Nowadays, avoiding system calls during cluster communication (e.g., in Data Centers and High Performance Computing) in modern high-speed interconnection networks has become a necessity, due to the high overhead of multiple data copies…
Link failures occur frequently in Internet Service Provider (ISP) networks and pose significant challenges for Traffic Engineering (TE). Existing TE schemes either reroute traffic over vulnerable static paths, leading to performance…
Due to the rapid development of IoT technology, automatic guided vehicles (AGVs) interact with an industrial control system (ICS) through the wireless network to support the freight distribution in the automated warehouse. However, the…
Despite the trend towards ubiquitous wireless connectivity, there are scenarios where the communications infrastructure is damaged and wireless coverage is insufficient or does not exist, such as in natural disasters and temporary crowded…
In networks, availability is of paramount importance. As link failures are disruptive, modern networks in turn provide Fast ReRoute (FRR) mechanisms to rapidly restore connectivity. However, existing FRR approaches heavily impact…
To fulfill the low latency requirements of today's applications, deployment of RDMA in datacenters has become prevalent over the recent years. However, the in-order delivery requirement of RDMAs prevents them from leveraging powerful…
Automatic Repeat Request (ARQ) is an effective technique for reliable transmission of packets in wireless networks. In ARQ, however, only a few erroneous bits in a packet will cause the entire packet to be discarded at the receiver. In this…
Systems for training massive deep learning models (billions of parameters) today assume and require specialized "hyper-clusters": hundreds or thousands of GPUs wired with specialized high-bandwidth interconnects such as NV-Link and…
In order to deliver high performance in cloud computing, we generally exploit and leverage RDMA (Remote Direct Memory Access) in networking and NVM (Non-Volatile Memory) in end systems. Due to no involvement of CPU, one-sided RDMA becomes…
Failures in optical network backbone can lead to major disruption of internet data traffic. Hence, minimizing such failures is of paramount importance for the network operators. Even better, if the network failures can be predicted and…
The past century of telecommunications has shown that failures in networks are prevalent. Although much has been done to prevent failures, network nodes and links are bound to fail eventually. Failure recovery processes are therefore…
Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving. However, recent findings indicate that transient hardware faults may…
Remote Direct Memory Access (RDMA) is becoming widely available in data centers. This technology allows a process to directly read and write the memory of a remote host, with a mechanism to control access permissions. In this paper, we…
After power is switched on, recovering the interrupted program from the initial state can cause negative impact. Some programs are even unrecoverable. To rapid recovery of program execution under power failures, the execution states of…
Under gang scheduling for large-scale distributed large language model (LLM) training, a single network anomaly can stall or abort an entire job. Current network fault tolerance mechanisms typically adopt a ``fallback and bypass'' approach…
From hardware offloads like RDMA to software ones like eBPF, offloads are everywhere and their value is in performance. However, there is evidence that fully offloading -- even when feasible -- does not always give the expected speedups.…
Modern network applications demand low-latency traffic engineering in the presence of network failure while preserving the quality of service constraints like delay and capacity. Fast Re-Route (FRR) mechanisms are widely used for traffic…
Main-memory database management systems (DBMS) can achieve excellent performance when processing massive volume of on-line transactions on modern multi-core machines. But existing durability schemes, namely, tuple-level and…
AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel…