More Like this

1. CodedBulk: Inter-Datacenter Bulk Transfers using Network Coding

   Tseng, Shih-Hao; Agarwal, Saksham; Agarwal, Rachit; Ballani, Hitesh; Tang, Ao (April 2021, USENIX Symposium on Networked Systems Design and Implementation)

   null (Ed.)

   This paper presents CodedBulk, a system for high-throughput inter-datacenter bulk transfers. At its core, CodedBulk uses network coding, a technique from the coding theory community, that guarantees optimal throughput for individual bulk transfers. Prior attempts to using network coding in wired networks have faced several pragmatic and fundamental barriers. CodedBulk resolves these barriers by exploiting the unique properties of inter-datacenter networks, and by using a custom-designed hop-by-hop flow control mechanism that enables efficient realization of network coding atop existing transport protocols. An end-to end CodedBulk implementation running on a geo-distributed inter-datacenter network improves bulk transfer throughput by 1.2−2.5× compared to state-of-the-art mechanisms that do not use network coding. 

   more » « less
2. CBMM: Financial Advice for Kernel Memory Managers

   Mark Mansi, Bijan Tabatabai (August 2022, Proceedings of the USENIX Annual Technical Conference)

   First-party datacenter workloads present new challenges to kernel memory management (MM), which allocates and maps memory and must balance competing performance concerns in an increasingly complex environment. In a datacenter, performance must be both good and consistent to satisfy service-level objectives. Unfortunately, current MM designs often exhibit inconsistent, opaque behavior that is difficult to reproduce, decipher, or fix, stemming from (1) a lack of high-quality information for policymaking, (2) the cost-unawareness of many current MM policies, and (3) opaque and distributed policy implementations that are hard to debug. For example, the Linux huge page implementation is distributed across 8 files and can lead to page fault latencies in the 100s of ms. In search of a MM design that has consistent behavior, we designed Cost-Benefit MM (CBMM), which uses empirically based cost-benefit models and pre-aggregated profiling information to make MM policy decisions. In CBMM, policy decisions follow the guiding principle that userspace benefits must outweigh userspace costs. This approach balances the performance benefits obtained by a kernel policy against the cost of applying it. CBMM has competitive performance with Linux and HawkEye, a recent research system, for all the workloads we ran, and in the presence of fragmentation, CBMM is 35% faster than Linux on average. Meanwhile, CBMM nearly always has better tail latency than Linux or HawkEye, particularly on fragmented systems. It reduces the cost of the most expensive soft page faults by 2-3 orders of magnitude for most of our workloads, and reduces the frequency of 10-1000 us-long faults by around 2 orders of magnitude for multiple workloads. 

   more » « less
3. CBMM: Financial Advice for Kernel Memory Managers

   Mark Mansi, Bijan Tabatabai (January 2022, Proceedings of the USENIX Annual Technical Conference)

   First-party datacenter workloads present new challenges to kernel memory management (MM), which allocates and maps memory and must balance competing performance concerns in an increasingly complex environment. In a datacenter, performance must be both good \textit{and} consistent to satisfy service-level objectives. Unfortunately, current MM designs often exhibit inconsistent, opaque behavior that is difficult to reproduce, decipher, or fix, stemming from (1) a lack of high-quality information for policymaking, (2) the cost-unawareness of many current MM policies, and (3) opaque and distributed policy implementations that are hard to debug. For example, the Linux huge page implementation is distributed across 8 files and can lead to page fault latencies in the 100s of ms. In search of a MM design that has consistent behavior, we designed Cost-Benefit MM (CBMM), which uses empirically based cost-benefit models and pre-aggregated profiling information to make MM policy decisions. In CBMM, policy decisions follow the guiding principle that \textit{userspace benefits must outweigh userspace costs}. This approach balances the performance benefits obtained by a kernel policy against the cost of applying it. CBMM has competitive performance with Linux and HawkEye, a recent research system, for all the workloads we ran, and in the presence of fragmentation, CBMM is 35% faster than Linux on average. Meanwhile, CBMM nearly always has better tail latency than Linux or HawkEye, particularly on fragmented systems. It reduces the cost of the most expensive soft page faults by 2-3 orders of magnitude for most of our workloads, and reduces the frequency of 10-1000 mu s-long faults by around 2 orders of magnitude for multiple workloads. 

   more » « less
4. Scaling beyond packet switch limits with multiple dataplanes

   https://doi.org/10.1145/3555050.3569141  

   Guo, Yibo; Mellette, William M.; Snoeren, Alex C.; Porter, George (November 2022, CoNEXT '22: Proceedings of the 18th International Conference on emerging Networking EXperiments and Technologies)

   Scale-out datacenter network fabrics enable network operators to translate improved link and switch speeds directly into end-host throughput. Unfortunately, limits in the underlying CMOS packet switch chip manufacturing roadmap mean that NICs, links, and switches are not getting faster fast enough to meet demand. As a result, operators have introduced alternative, parallel fabric designs in the core of the network that deliver N-times the bandwidth by simply forwarding traffic over any of N parallel network fabrics. In this work, we consider extending this parallel network idea all the way to the end host. Our initial impressions found that direct application of existing path selection and forwarding techniques resulted in poor performance. Instead, we show that appropriate path selection and forwarding protocols can not only improve the performance of existing, homogeneous parallel fabrics, but enable the development of heterogeneous parallel network fabrics that can deliver even higher bandwidth, lower latency, and improved resiliency than traditional designs constructed from the same constituent components. 

   more » « less
5. Impacts of climate change on multiple use management of Bureau of Land Management land in the Intermountain West, USA

   https://doi.org/10.1002/ecs2.3286  

   Brice, Elaine_M; Miller, Brett_A; Zhang, Hongchao; Goldstein, Kirsten; Zimmer, Scott_N; Grosklos, Guenchik_J; Belmont, Patrick; Flint, Courtney_G; Givens, Jennifer_E; Adler, Peter_B; et al (November 2020, Ecosphere)

   Abstract Although natural resource managers are concerned about climate change, many are unable to adequately incorporate climate change science into their adaptation strategies or management plans, and are not always aware of or do not always employ the most current scientific knowledge. One of the most prominent natural resource management agencies in the United States is the Bureau of Land Management (BLM), which is tasked with managing over 248 million acres (>1 million km²) of public lands for multiple, often conflicting, uses. Climate change will affect the sustainability of many of these land uses and could further increase conflicts between them. As such, the purpose of our study was to determine the extent to which climate change will affect public land uses, and whether the BLM is managing for such predicted effects. To do so, we first conducted a systematic review of peer‐reviewed literature that discussed potential impacts of climate change on the multiple land uses the BLM manages in the Intermountain West, USA, and then expanded these results with a synthesis of projected vegetation changes. Finally, we conducted a content analysis of BLM Resource Management Plans in order to determine how climate change is explicitly addressed by BLM managers, and whether such plans reflect changes predicted by the scientific literature. We found that active resource use generally threatens intrinsic values such as conservation and ecosystem services on BLM land, and climate change is expected to exacerbate these threats in numerous ways. Additionally, our synthesis of vegetation modeling suggests substantial changes in vegetation due to climate change. However, BLM plans rarely referred to climate change explicitly and did not reflect the results of the literature review or vegetation model synthesis. Our results suggest there is a disconnect between management of BLM lands and the best available science on climate change. We recommend that the BLM actively integrates such research into on‐the‐ground management plans and activities, and that researchers studying the effects of climate change make a more robust effort to understand the practices and policies of public land management in order to effectively communicate the management significance of their findings. 

   more » « less