Apache Spark is a popular cluster computing framework for iterative analytics workloads due to its use of Resilient Distributed Datasets (RDDs) to cache data for in-memory processing. We have revealed that the performance of Spark RDD cache can be severely limited if its capacity falls short to the needs of the workloads. In this paper, we have explored different memory hybridization strategies to leverage emergent Non-Volatile Memory (NVM) devices for Spark's RDD cache. We have found that a simple layered hybridization approach does not offer an effective solution. Therefore, we have designed a flat hybridization scheme to leverage NVM for caching RDD blocks, along with several architectural optimizations such as dynamic memory allocation for block unrolling, asynchronous migration with preemption, and opportunistic eviction to disk. We have performed an extensive set of experiments to evaluate the performance of our proposed flat hybridization strategy and found it to be robust in handling different system and NVM characteristics. Our proposed approach uses DRAM for a fraction of the hybrid memory system and yet manages to keep the increase in execution time to be within 10% on average. Moreover, our opportunistic eviction of blocks to disk improves performance by up to 7.5% when utilized alongside the current mechanism.
more »
« less
Intermediate Data Caching Optimization for Multi-Stage andParallel Big Data Frameworks
In the era of big data and cloud computing, large
amounts of data are generated from user applications and need
to be processed in the datacenter. Data-parallel computing frameworks,
such as Apache Spark, are widely used to perform such
data processing at scale. Specifically, Spark leverages distributed
memory to cache the intermediate results, represented as Resilient
Distributed Datasets (RDDs). This gives Spark an advantage
over other parallel frameworks for implementations of iterative
machine learning and data mining algorithms, by avoiding
repeated computation or hard disk accesses to retrieve RDDs. By
default, caching decisions are left at the programmer’s discretion,
and the LRU policy is used for evicting RDDs when the cache is
full. However, when the objective is to minimize total work, LRU
is woefully inadequate, leading to arbitrarily suboptimal caching
decisions. In this paper, we design an algorithm for multi-stage
big data processing platforms to adaptively determine and cache
the most valuable intermediate datasets that can be reused in the
future. Our solution automates the decision of which RDDs to
cache: this amounts to identifying nodes in a direct acyclic graph
(DAG) representing computations whose outputs should persist
in the memory. Our experiment results show that our proposed
cache optimization solution can improve the performance of
machine learning applications on Spark decreasing the total work
to recompute RDDs by 12%.
more »
« less
- Award ID(s):
- 1718355
- NSF-PAR ID:
- 10067678
- Date Published:
- Journal Name:
- IEEE International Conference on Cloud Computing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In parallel with big data processing and analysis dominating the usage of distributed and cloud infrastructures, the demand for distributed metadata access and transfer has increased. In many application domains, the volume of data generated exceeds petabytes, while the corresponding metadata amounts to terabytes or even more. In this paper, we propose a novel solution for efficient and scalable metadata access for distributed applications across wide-area networks, dubbed SMURF. Our solution combines novel pipelining and concurrent transfer mechanisms with reliability, provides distributed continuum caching and prefetching strategies to sidestep fetching latency, and achieves scalable and high-performance metadata fetch/prefetch services in the cloud. We also study the phenomenon of semantic locality in real trace logs which is not well utilized in metadata access prediction. We implement our predictor based on this observation and compare it with three existing state-of-the-art prefetch schemes on Yahoo! Hadoop audit traces. By effectively caching and prefetching metadata based on the access patterns, our continuum caching and prefetching mechanism greatly improves local cache hit rate and reduces the average fetching latency. We replayed approximately 20 Million metadata access operations from real audit traces, in which our system achieved 80% accuracy during prefetch prediction and reduced the average fetch latency 50% compared to the state-of-the-art mechanisms.more » « less
-
In parallel with big data processing and analysis dominating the usage of distributed and Cloud infrastructures, the demand for distributed metadata access and transfer has increased. The volume of data generated by many application domains exceeds petabytes, while the corresponding metadata amounts to terabytes or even more. This paper proposes a novel solution for efficient and scalable metadata access for distributed applications across wide-area networks, dubbed SMURF. Our solution combines novel pipelining and concurrent transfer mechanisms with reliability, provides distributed continuum caching and semantic locality-aware prefetching strategies to sidestep fetching latency, and achieves scalable and high-performance metadata fetch/prefetch services in the Cloud. We incorporate the phenomenon of semantic locality awareness for increased prefetch prediction rate using real-life application I/O traces from Yahoo! Hadoop audit logs and propose a novel prefetch predictor. By effectively caching and prefetching metadata based on the access patterns, our continuum caching and prefetching mechanism significantly improves the local cache hit rate and reduces the average fetching latency. We replay approximately 20 Million metadata access operations from real audit traces, where SMURF achieves 90% accuracy during prefetch prediction and reduced the average fetch latency by 50% compared to the state-of-the-art mechanisms.more » « less
-
To process real-world datasets, modern data-parallel systems often require extremely large amounts of memory, which are both costly and energy inefficient. Emerging non-volatile memory (NVM) technologies offer high capacity compared to DRAM and low energy compared to SSDs. Hence, NVMs have the potential to fundamentally change the dichotomy between DRAM and durable storage in Big Data processing. However, most Big Data applications are written in managed languages and executed on top of a managed runtime that already performs various dimensions of memory management. Supporting hybrid physical memories adds a new dimension, creating unique challenges in data replacement. This article proposes Panthera, a semantics-aware, fully automated memory management technique for Big Data processing over hybrid memories. Panthera analyzes user programs on a Big Data system to infer their coarse-grained access patterns, which are then passed to the Panthera runtime for efficient data placement and migration. For Big Data applications, the coarse-grained data division information is accurate enough to guide the GC for data layout, which hardly incurs overhead in data monitoring and moving. We implemented Panthera in OpenJDK and Apache Spark. Based on Big Data applications’ memory access pattern, we also implemented a new profiling-guided optimization strategy, which is transparent to applications. With this optimization, our extensive evaluation demonstrates that Panthera reduces energy by 32–53% at less than 1% time overhead on average. To show Panthera’s applicability, we extend it to QuickCached, a pure Java implementation of Memcached. Our evaluation results show that Panthera reduces energy by 28.7% at 5.2% time overhead on average.more » « less
-
The performance of modern Big Data frameworks, e.g. Spark, depends greatly on high-speed storage and shuffling, which impose a significant memory burden on production data centers. In many production situations, the persistence and shuffling intensive applications can suffer a major performance loss due to lack of memory. Thus, the common practice is usually to over-allocate the memory assigned to the data workers for production applications, which in turn reduces overall resource utilization. One efficient way to address the dilemma between the performance and cost efficiency of Big Data applications is through data center computing resource disaggregation. This paper proposes and implements a system that incorporates the Spark Big Data framework with a novel in-memory distributed file system to achieve memory disaggregation for data persistence and shuffling. We address the challenge of optimizing performance at affordable cost by co-designing the proposed in-memory distributed file system with large-volume DIMM-based persistent memory (PMEM) and RDMA technology. The disaggregation design allows each part of the system to be scaled independently, which is particularly suitable for cloud deployments. The proposed system is evaluated in a production-level cluster using real enterprise-level Spark production applications. The results of an empirical evaluation show that the system can achieve up to a 3.5- fold performance improvement for shuffle-intensive applications with the same amount of memory, compared to the default Spark setup. Moreover, by leveraging PMEM, we demonstrate that our system can effectively increase the memory capacity of the computing cluster with affordable cost, with a reasonable execution time overhead with respect to using local DRAM only.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
