Datacenters need to reduce embodied carbon emissions, particularly for flash, which accounts for 40% of embodied carbon in servers. However, decreasing flash’s embodied emissions is challenging due to flash’s limited write endurance, which more than halves with each generation of denser flash. Reducing embodied emissions requires extending flash lifetime, stressing its limited write endurance even further. The legacy Logical Block-Addressable Device (LBAD) interface exacerbates the problem by forcing devices to perform garbage collection, leading to even more writes. Flash-based caches in particular write frequently, limiting the lifetimes and densities of the devices they use. These flash caches illustrate the need to break away from LBAD and switch to the new Write-Read-Erase iNterfaces (WREN) now coming to market. WREN affords applications control over data placement and garbage collection. We present Fairy Wren , 1 a flash cache designed for WREN. Fairy Wren reduces writes by co-designing caching policies and flash garbage collection. Fairy Wren provides a 12.5× write reduction over state-of-the-art LBAD caches. This decrease in writes allows flash devices to last longer, decreasing flash cost by 35% and flash carbon emissions by 33%.

Parallelizable jobs typically consist of multiple phases of computation, where the job is more parallelizable in some phases and less parallelizable in others. For example, in a database, a query may consist of a highly parallelizable table scan, followed by a less parallelizable table join. In the past, this phase-varying parallelizability was summarized by a single sub-linear speedup curve that measures a job’s average parallelizability over its entire lifetime. Today, however, modern systems have fine-grained knowledge of the exact phase each job is in at every moment in time. Unfortunately, these systems do not fully leverage this real-time feedback when scheduling parallelizable jobs. Theory has failed to produce practical phase-aware scheduling policies, and thus scheduling in current systems is largely heuristic. A phase-aware scheduling policy must decide, given its knowledge of each job’s current phase, how many servers or cores to allocate to each job in the system at every moment in time. This paper provides the first stochastic model of a system processing parallelizable jobs composed of phases. Using our model, we derive an optimal phase-aware scheduling policy that minimizes the mean response time across jobs. Our provably optimal policy, Inelastic-First (IF), gives strict priority to jobs that are currently in less parallelizable phases. We validate our theoretical results using a simulation of a database running queries from the Star Schema Benchmark. We compare IF to a range of policies from both systems and theory, and show that IF reduces mean response time by up to a factor of 3.

Many social-media and IoT services have very large working sets consisting of billions of tiny (≈100 B) objects. Large, flash-based caches are important to serving these working sets at acceptable monetary cost. However, caching tiny objects on flash is challenging for two reasons: (i) SSDs can read/write data only in multi-KB “pages” that are much larger than a single object, stressing the limited number of times flash can be written; and (ii) very few bits per cached object can be kept in DRAM without losing flash’s cost advantage. Unfortunately, existing flash-cache designs fall short of addressing these challenges: write-optimized designs require too much DRAM, and DRAM-optimized designs require too many flash writes. We present Kangaroo , a new flash-cache design that optimizes both DRAM usage and flash writes to maximize cache performance while minimizing cost. Kangaroo combines a large, set-associative cache with a small, log-structured cache. The set-associative cache requires minimal DRAM, while the log-structured cache minimizes Kangaroo’s flash writes. Experiments using traces from Meta and Twitter show that Kangaroo achieves DRAM usage close to the best prior DRAM-optimized design, flash writes close to the best prior write-optimized design, and miss ratios better than both. Kangaroo’s design is Pareto-optimal across a range of allowed write rates, DRAM sizes, and flash sizes, reducing misses by 29% over the state of the art. These results are corroborated by analytical models presented herein and with a test deployment of Kangaroo in a production flash cache at Meta.

Many social-media and IoT services have very large working sets consisting of billions of tiny (≈100 B) objects. Large, flash-based caches are important to serving these working sets at acceptable monetary cost. However, caching tiny objects on flash is challenging for two reasons: (i) SSDs can read/write data only in multi-KB "pages" that are much larger than a single object, stressing the limited number of times flash can be written; and (ii) very few bits per cached object can be kept in DRAM without losing flash's cost advantage. Unfortunately, existing flash-cache designs fall short of addressing these challenges: write-optimized designs require too much DRAM, and DRAM-optimized designs require too many flash writes.

Modern data centers are tasked with processing heterogeneous workloads consisting of various classes of jobs. These classes differ in their arrival rates, size distributions, and job parallelizability. With respect to parallelizability, some jobs are elastic, meaning they can parallelize linearly across any number of servers. Other jobs are inelastic, meaning they can only run on a single server. Although job classes can differ drastically, they are typically forced to share a single cluster. When sharing a cluster among heterogeneous jobs, one must decide how to allocate servers to each job at every moment in time. In this paper, we design and analyze allocation policies which aim to minimize the mean response time across jobs, where a job's response time is the time from when it arrives until it completes.

Modern data centers serve workloads which are capable of exploiting parallelism. When a job parallelizes across multiple servers it will complete more quickly, but jobs receive diminishing returns from being allocated additional servers. Because allocating multiple servers to a single job is inefficient, it is unclear how best to allocate a fixed number of servers between many parallelizable jobs. This paper provides the first optimal allocation policy for minimizing the mean slowdown of parallelizable jobs of known size when all jobs are present at time 0. Our policy provides a simple closed form formula for the optimal allocations at every moment in time. Minimizing mean slowdown usually requires favoring short jobs over long ones (as in the SRPT policy). However, because parallelizable jobs have sublinear speedup functions, system efficiency is also an issue. System efficiency is maximized by giving equal allocations to all jobs and thus competes with the goal of prioritizing small jobs. Our optimal policy, high-efficiency SRPT (heSRPT), balances these competing goals. heSRPT completes jobs according to their size order, but maintains overall system efficiency by allocating some servers to each job at every moment in time. Our results generalize to also provide the optimal allocation policy with respect to mean flow time. Finally, we consider the online case where jobs arrive to the system over time. While optimizing mean slowdown in the online setting is even more difficult, we find that heSRPT provides an excellent heuristic policy for the online setting. In fact, our simulations show that heSRPT significantly outperforms state-of-the-art allocation policies for parallelizable jobs.