An efficient multi-tier tablet server storage architecture

Spillane, Richard P.; Shetty, Pradeep; Zadok, Erez; Dixit, Sagar; Archak, Shrikar

doi:10.1145/2038916.2038917

Cited by 20 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCP [14] uses a pipelined compaction procedure to fully utilize both CPUs and I/O devices to speed up the compaction procedure. GTSSL [18] develops techniques to adapt to changing read-write ratios and adapting to hybrid disk-flash systems.…”

Section: Improvement On Write Performancementioning

confidence: 99%

“…CacheOblivious Lookahead Arrays (COLA) [17] and FD-tree [19]. (d) other optimizations like GTSSL [18] uses the reclamation and re-insert techniques to put KV items in upper levels to decrease the count of levels that point queries go through. The partitioned exponential file [13] partition the key range into multiple sub-key ranges, and then point queries just search one smaller sub-key range.…”

Section: Improvement On Read Performancementioning

confidence: 99%

See 1 more Smart Citation

dCompaction: Delayed Compaction for the LSM-Tree

Pan

Yue

Xiong

2016

Int J Parallel Prog

View full text Add to dashboard Cite

Key-value (KV) stores have become a backbone of large-scale applications in today's data centers. Write-optimized data structures like the Log-Structured Mergetree (LSM-tree) and their variants are widely used in KV storage systems like BigTable and RocksDB. Conventional LSM-tree organizes KV items into multiple, successively larger components, and uses compaction to push KV items from one smaller component to another adjacent larger component until the KV items reach the largest component. Unfortunately, current compaction scheme incurs significant write amplification due to repeated KV item reads and writes, and then results in poor throughput. We propose a new compaction scheme, delayed compaction (dCompaction), that decreases write amplification. dCompaction postpones some compactions and gather them into the following compaction. In this way, it avoids KV item reads and writes during compaction, and consequently improves the throughput of LSM-tree based KV stores. We implement dCompaction on RocksDB, and conduct extensive experiments. Validation using YCSB framework shows that compared with RocksDB dCompaction has about 30% write performance improvements and also comparable read performance. B Fengfeng Pan

show abstract

Section: Improvement On Write Performancementioning

confidence: 99%

Section: Improvement On Read Performancementioning

confidence: 99%

dCompaction: Delayed Compaction for the LSM-Tree

Pan

Yue

Xiong

2016

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…Multi-tier storage systems. Multi-tier storage systems are widely used today, such as FAST [24], Easy Tier [28], 3PAR [26], and some recent work [25,38,47,52]. These systems migrate data among traditional storages, while GRANDET works with cloud storage services.…”

Section: Related Workmentioning

confidence: 99%

Grandet

Tang

Yuan

et al. 2016

Proceedings of the Seventh ACM Symposium on Cloud Computing

View full text Add to dashboard Cite

Web applications are getting ubiquitous every day because they offer many useful services to consumers and businesses. Many of these web applications are quite storage-intensive. Cloud computing offers attractive and economical choices for meeting their storage needs. Unfortunately, it remains challenging for developers to best leverage them to minimize cost. This paper presents GRANDET, an extensible storage system that significantly reduces storage cost for web applications deployed in the cloud. GRANDET provides both a key-value interface and a file system interface, supporting a broad spectrum of web applications. Under the hood, it supports multiple heterogeneous stores and unifies them by placing each data object at the store deemed most economical. We implemented GRANDET on Amazon Web Services and evaluated GRANDET on a diverse set of four popular open-source web applications. Our results show that GRANDET reduces their cost by an average of 42.4%, and it is fast, scalable, and easy to use. The source code of GRANDET is at http://columbia.github.io/grandet.

show abstract

“…RAM-Cloud [40] stores data in RAM and utilizes fast network connections to rapidly restore failed replicas. TSSL [54] utilizes a multi-tier storage hierarchy to exploit cache-oblivious algorithms in the storage layer. Masstree [35] uses concatenated B + trees to service millions of queries per second.…”

Section: Related Workmentioning

confidence: 99%

HyperDex

Escriva

Wong

Sirer

2012

SIGCOMM Comput. Commun. Rev.

View full text Add to dashboard Cite

Distributed key-value stores are now a standard component of high-performance web services and cloud computing applications. While key-value stores offer significant performance and scalability advantages compared to traditional databases, they achieve these properties through a restricted API that limits object retrieval-an object can only be retrieved by the (primary and only) key under which it was inserted. This paper presents HyperDex, a novel distributed key-value store that provides a unique search primitive that enables queries on secondary attributes. The key insight behind HyperDex is the concept of hyperspace hashing in which objects with multiple attributes are mapped into a multidimensional hyperspace. This mapping leads to efficient implementations not only for retrieval by primary key, but also for partially-specified secondary attribute searches and range queries. A novel chaining protocol enables the system to achieve strong consistency, maintain availability and guarantee fault tolerance. An evaluation of the full system shows that HyperDex is 12-13× faster than Cassandra and MongoDB for finding partially specified objects. Additionally, HyperDex achieves 2-4× higher throughput for get/put operations.

show abstract

An efficient multi-tier tablet server storage architecture

Cited by 20 publications

References 45 publications

dCompaction: Delayed Compaction for the LSM-Tree

dCompaction: Delayed Compaction for the LSM-Tree

Grandet

HyperDex

Contact Info

Product

Resources

About