Search

We present a thorough analysis of the use of CXL-based heterogeneous systems. We built a cluster of server systems that combines different vendor's CPUs and various types of CXL devices. We further developed a heterogeneous memory benchmark suite, Heimdall, to profile the performance of such heterogeneous systems. By leveraging Heimdall, we unveiled the detailed architecture design in these systems, drew observations on optimizing performance for workloads, and pointed out directions for future development of CXL-based heterogeneous systems.

Datacenter applications often rely on remote procedure calls (RPCs) for fast, efficient, and secure communication. However, RPCs are slow, inefficient, and hard to use as they require expensive serialization and compression to communicate over a packetized serial network link. Compute Express Link 3.0 (CXL) offers an alternative solution, allowing applications to share data using a cache-coherent, shared-memory interface across clusters of machines. RPCool is a new framework that exploits CXL's shared memory capabilities. RPCool avoids serialization by passing pointers to data structures in shared memory. While avoiding serialization is useful, directly sharing pointer-rich data eliminates the isolation that copying data over traditional networks provides, leaving the receiver vulnerable to invalid pointers and concurrent updates to shared data by the sender. RPCool restores this safety with careful and efficient management of memory permissions. Another significant challenge with CXL shared memory capabilities is that they are unlikely to scale to an entire datacenter. RPCool addresses this by falling back to RDMA-based communication. Overall, RPCool reduces the round-trip latency by 1.93$\times$ and 7.2$\times$ compared to state-of-the-art RDMA and CXL-based RPC mechanisms, respectively. Moreover, RPCool performs either comparably or better than other RPC mechanisms across a range of workloads.

While Compute Express Link (CXL) enables support for cache-coherent shared memory among multiple nodes, it also introduces new types of failures--processes can fail before data does, or data might fail before a process does. The lack of a failure model for CXL-based shared memory makes it challenging to understand and mitigate these failures. To solve these challenges, in this paper, we describe a model categorizing and handling the CXL-based shared memory's failures: data and process failures. Data failures in CXL-based shared memory render data inaccessible or inconsistent for a currently running application. We argue that such failures are unlike data failures in distributed storage systems and require CXL-specific handling. To address this, we look into traditional data failure mitigation techniques like erasure coding and replication and propose new solutions to better handle data failures in CXL-based shared memory systems. Next, we look into process failures and compare the failures and potential solutions with PMEM's failure model and programming solutions. We argue that although PMEM shares some of CXL's characteristics, it does not fully address CXL's volatile nature and low access latencies. Finally, taking inspiration from PMEM programming solutions, we propose techniques to handle these new failures. Thus, this paper is the first work to define the CXL-based shared memory failure model and propose tailored solutions that address challenges specific to CXL-based systems.

Crash consistency using persistent memory programming libraries requires programmers to use complex transactions and manual annotations. In contrast, the failure-atomic msync() (FAMS) interface is much simpler as it transparently tracks updates and guarantees that modified data is atomically durable on a call to the failure-atomic variant of msync(). However, FAMS suffers from several drawbacks, like the overhead of msync() and the write amplification from page-level dirty data tracking. To address these drawbacks while preserving the advantages of FAMS, we propose Snapshot, an efficient userspace implementation of FAMS. Snapshot uses compiler-based annotation to transparently track updates in userspace and syncs them with the backing byte-addressable storage copy on a call to msync(). By keeping a copy of application data in DRAM, Snapshot improves access latency. Moreover, with automatic tracking and syncing changes only on a call to msync(), Snapshot provides crash-consistency guarantees, unlike the POSIX msync() system call. For a KV-Store backed by Intel Optane running the YCSB benchmark, Snapshot achieves at least 1.2$\times$ speedup over PMDK while significantly outperforming conventional (non-crash-consistent) msync(). On an emulated CXL memory semantic SSD, Snapshot outperforms PMDK by up to 10.9$\times$ on all but one YCSB workload, where PMDK is 1.2$\times$ faster than Snapshot. Further, Kyoto Cabinet commits perform up to 8.0$\times$ faster with Snapshot than its built-in, msync()-based crash-consistency mechanism., Comment: A shorter version of this paper appeared in the Proceedings of ICCD 2023

In this paper, we argue that current work has failed to provide a comprehensive and maintainable in-memory representation for persistent memory. PM data should be easily mappable into a process address space, shareable across processes, shippable between machines, consistent after a crash, and accessible to legacy code with fast, efficient pointers as first-class abstractions. While existing systems have provided niceties like mmap()-based load/store access, they have not been able to support all these necessary properties due to conflicting requirements. We propose Puddles, a new persistent memory abstraction, to solve these problems. Puddles provide application-independent recovery after a power outage; they make recovery from a system failure a system-level property of the stored data rather than the responsibility of the programs that access it. Puddles use native pointers, so they are compatible with existing code. Finally, Puddles implement support for sharing and shipping of PM data between processes and systems without expensive serialization and deserialization. Compared to existing systems, Puddles are at least as fast as and up to 1.34$\times$ faster than PMDK while being competitive with other PM libraries across YCSB workloads. Moreover, to demonstrate Puddles' ability to relocate data, we showcase a sensor network data-aggregation workload that results in a 4.7$\times$ speedup over PMDK., Comment: To appear in EuroSys 2024

Hyperscalars run services across a large fleet of servers, serving billions of users worldwide. These services, however, behave differently than commonly available benchmark suites, resulting in server architectures that are not optimized for cloud workloads. With datacenters becoming a primary server processor market, optimizing server processors for cloud workloads by better understanding their behavior has become crucial. To address this, in this paper, we present MemProf, a memory profiler that profiles the three major reasons for stalls in cloud workloads: code-fetch, memory bandwidth, and memory latency. We use MemProf to understand the behavior of cloud workloads and propose and evaluate micro-architectural and memory system design improvements that help cloud workloads' performance. MemProf's code analysis shows that cloud workloads execute the same code across CPU cores. Using this, we propose shared micro-architectural structures--a shared L2 I-TLB and a shared L2 cache. Next, to help with memory bandwidth stalls, using workloads' memory bandwidth distribution, we find that only a few pages contribute to most of the system bandwidth. We use this finding to evaluate a new high-bandwidth, small-capacity memory tier and show that it performs 1.46x better than the current baseline configuration. Finally, we look into ways to improve memory latency for cloud workloads. Profiling using MemProf reveals that L2 hardware prefetchers, a common solution to reduce memory latency, have very low coverage and consume a significant amount of memory bandwidth. To help improve hardware prefetcher performance, we built a memory tracing tool to collect and validate production memory access traces.

Clinical trials are an integral component of medical research. Trials require careful design to, for example, maintain the safety of participants, use resources efficiently and allow clinically meaningful conclusions to be drawn. Adaptive clinical trials (i.e. trials that can be altered based on evidence that has accrued) are often more efficient, informative and ethical than standard or non-adaptive trials because they require fewer participants, target more promising treatments, and can stop early with sufficient evidence of effectiveness or harm. The design of adaptive trials requires the pre-specification of adaptions that are permissible throughout the conduct of the trial. Proposed adaptive designs are then usually evaluated through simulation which provides indicative metrics of performance (e.g. statistical power and type-1 error) under different scenarios. Trial simulation requires assumptions about the data generating process to be specified but correctly specifying these in practice can be difficult, particularly for new and emerging diseases. To address this, we propose an approach to design adaptive clinical trials without needing to specify the complete data generating process. To facilitate this, we consider a general Bayesian framework where inference about the treatment effect on a time-to-event outcome can be performed via the partial likelihood. As a consequence, the proposed approach to evaluate trial designs is robust to the specific form of the baseline hazard function. The benefits of this approach are demonstrated through the redesign of a recent clinical trial to evaluate whether a third dose of a vaccine provides improved protection against gastroenteritis in Australian Indigenous infants.