More Like this

1. A Set-aware Key-Value Store on Shingled Magnetic Recording Drives with Dynamic Band

   Yao, T ; Tan, Z ; Wan, J ; Huang, P ; Zhang, Y ; Xie, C ; He, X ( May 2018 , the 32nd IEEE International Parallel and Distributed Processing Symposium (IPDPS))

   Key-value (KV) stores play an increasingly critical role in supporting diverse large-scale applications in modern data centers hosting terabytes of KV items which even might reside on a single server due to virtualization purpose. The combination of ever growing volume of KV items and storage/application consolidation is driving a trend of high storage density for KV stores. Shingled Magnetic Recording (SMR) represents a promising technology for increasing disk capacity, but it comes at a cost of poor random write performance and severe I/O amplification. Applications/software working with SMR devices need to be designed and optimized in an SMR-friendly manner. In this work, we present SEALDB, a Log-Structured Merge tree (LSM-tree) based key-value store that is specifically op- timized for and works well with SMR drives via adequately addressing the poor random writes and severe I/O amplification issues. First, for LSM-trees, SEALDB concatenates SSTables of each compaction, and groups them into sets. Taking sets as the basic unit for compactions, SEALDB improves compaction efficiency by mitigating random I/Os. Second, SEALDB creates varying size bands on HM-SMR drives, named dynamic bands. Dynamic bands not only accommodate the storage of sets, but also eliminate the auxiliary write amplification from SMR drives. We demonstrate the advantages of SEALDB via extensive experiments in various workloads. Overall, SEALDB delivers impressive performance improvement. Compared with LevelDB, SEALDB is 3.42× faster on random load due to improved compaction efficiency and eliminated auxiliary write amplification on SMR drives. 

   more » « less
2. ChameleonDB: a key-value store for optane persistent memory

   https://doi.org/10.1145/3447786.3456237  

   Zhang, Wenhui ; Zhao, Xingsheng ; Jiang, Song ; Jiang, Hong ( April 2021 , EuroSys '21: Proceedings of the Sixteenth European Conference on Computer Systems)

   null (Ed.)

   The emergence of Intel's Optane DC persistent memory (Optane Pmem) draws much interest in building persistent key-value (KV) stores to take advantage of its high throughput and low latency. A major challenge in the efforts stems from the fact that Optane Pmem is essentially a hybrid storage device with two distinct properties. On one hand, it is a high-speed byte-addressable device similar to DRAM. On the other hand, the write to the Optane media is conducted at the unit of 256 bytes, much like a block storage device. Existing KV store designs for persistent memory do not take into account of the latter property, leading to high write amplification and constraining both write and read throughput. In the meantime, a direct re-use of a KV store design intended for block devices, such as LSM-based ones, would cause much higher read latency due to the former property. In this paper, we propose ChameleonDB, a KV store design specifically for this important hybrid memory/storage device by considering and exploiting these two properties in one design. It uses LSM tree structure to efficiently admit writes with low write amplification. It uses an in-DRAM hash table to bypass LSM-tree's multiple levels for fast reads. In the meantime, ChameleonDB may choose to opportunistically maintain the LSM multi-level structure in the background to achieve short recovery time after a system crash. ChameleonDB's hybrid structure is designed to be able to absorb sudden bursts of a write workload, which helps avoid long-tail read latency. Our experiment results show that ChameleonDB improves write throughput by 3.3× and reduces read latency by around 60% compared with a legacy LSM-tree based KV store design. ChameleonDB provides performance competitive even with KV stores using fully in-DRAM index by using much less DRAM space. Compared with CCEH, a persistent hash table design, ChameleonDB provides 6.4× higher write throughput. 

   more » « less
3. Cross-Referenced Dictionaries and the Limits of Write Optimization

   https://doi.org/10.1137/1.9781611974782.99  

   Afshani, Peyman ; Bender, Michael ; Farach-Colton, Martin ; Fineman, Jeremy ; Goswami, Mayank ; Tsai, Meng-Tsung Tsai ( January 2017 , Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms)

   Dictionaries remain the most well studied class of data structures. A dictionary supports insertions, deletions, membership queries, and usually successor, predecessor, and extract-min. In a RAM, all such operations take O(log n) time on n elements. Dictionaries are often cross-referenced as follows. Consider a set of tuples {〈ai,bi,ci…〉}. A database might include more than one dictionary on such a set, for example, one indexed on the a ‘s, another on the b‘s, and so on. Once again, in a RAM, inserting into a set of L cross-referenced dictionaries takes O(L log n) time, as does deleting. The situation is more interesting in external memory. On a Disk Access Machine (DAM), B-trees achieve O(logB N) I/Os for insertions and deletions on a single dictionary and K-element range queries take optimal O(logB N + K/B) I/Os. These bounds are also achievable by a B-tree on cross-referenced dictionaries, with a slowdown of an L factor on insertion and deletions. In recent years, both the theory and practice of external- memory dictionaries has been revolutionized by write- optimization techniques. A dictionary is write optimized if it is close to a B-tree for query time while beating B-trees on insertions. The best (and optimal) dictionaries achieve a substantially improved insertion and deletion cost of amortized I/Os on a single dictionary while maintaining optimal O(log1+B∊ N + K/B)- I/O range queries. Although write optimization still helps for insertions into cross-referenced dictionaries, its value for deletions would seem to be greatly reduced. A deletion into a cross- referenced dictionary only specifies a key a. It seems to be necessary to look up the associated values b, c … in order to delete them from the other dictionaries. This takes Ω(logB N) I/Os, well above the per-dictionary write-optimization budget of So the total deletion cost is In short, for deletions, write optimization offers an advantage over B-trees in that L multiplies a lower order term, but when L = 2, write optimization seems to offer no asymptotic advantage over B-trees. That is, no known query- optimal solution for pairs of cross-referenced dictionaries seem to beat B-trees for deletions. In this paper, we show a lower bound establishing that a pair of cross-referenced dictionaries that are optimal for range queries and that supports deletions cannot match the write optimization bound available to insert-only dictionaries. This result thus establishes a limit to the applicability of write-optimization techniques on which many new databases and file systems are based. Read More: http://epubs.siam.org/doi/10.1137/1.9781611974782.99 

   more » « less
4. HOOP: Efficient Hardware-Assisted Out-of-Place Update for Non-Volatile Memory

   https://doi.org/10.1109/ISCA45697.2020.00055  

   Cai, Miao ; Coats, Chance C. ; Huang, Jian ( May 2020 , 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA))

   Byte-addressable non-volatile memory (NVM) is a promising technology that provides near-DRAM performance with scalable memory capacity. However, it requires atomic data durability to ensure memory persistency. Therefore, many techniques, including logging and shadow paging, have been proposed. However, most of them either introduce extra write traffic to NVM or suffer from significant performance overhead on the critical path of program execution, or even both. In this paper, we propose a transparent and efficient hardware-assisted out-of-place update (HOOP) mechanism that supports atomic data durability, without incurring much extra writes and performance overhead. The key idea is to write the updated data to a new place in NVM, while retaining the old data until the updated data becomes durable. To support this, we develop a lightweight indirection layer in the memory controller to enable efficient address translation and adaptive garbage collection for NVM. We evaluate HOOP with a variety of popular data structures and data-intensive applications, including key-value stores and databases. Our evaluation shows that HOOP achieves low critical-path latency with small write amplification, which is close to that of a native system without persistence support. Compared with state-of-the-art crash-consistency techniques, it improves application performance by up to 1.7×, while reducing the write amplification by up to 2.1×. HOOP also demonstrates scalable data recovery capability on multi-core systems. 

   more » « less
5. LBE: A Computational Load Balancing Algorithm for Speeding up Parallel Peptide Search in Mass-Spectrometry Based Proteomics

   https://doi.org/10.1109/IPDPSW.2019.00040  

   Haseeb, Muhammad ; Afzali, Fatima ; Saeed, Fahad ( May 2019 , Proceedings of 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW))

   The most commonly employed method for peptide identification in mass-spectrometry based proteomics involves comparing experimentally obtained tandem MS/MS spectra against a set of theoretical MS/MS spectra. The theoretical MS/MS spectra data are predicted using protein sequence database. Most state-of-the-art peptide search algorithms index theoretical spectra data to quickly filter-in the relevant (similar) indexed spectra when searching an experimental MS/MS spectrum. Data filtration substantially reduces the required number of computationally expensive spectrum-to-spectrum comparison operations. However, the number of predicted (and indexed) theoretical spectra grows exponentially with increase in post-translational modifications creating a memory and I/O bottleneck. In this paper, we present a parallel algorithm, called LBE, for efficient partitioning of theoretical spectra data on a distributed-memory architecture. Our proposed algorithm first groups the similar theoretical spectra. The groups are then finely split across the system allowing machines to perform almost equal amount of work when querying a MS/MS spectrum. Our results show that the compute load imbalance using LBE based data distribution is ≤ 20% allowing speedups of order of magnitudes over existing methods. The proposed algorithm has been implemented on a compute cluster using MPI library. Experimental results for increasing index sizes are reported in terms of execution time, speedups and memory footprint. To the best of our knowledge, LBE is the first load-balancing technique for MS/MS proteomics data on memory-distributed clusters that incorporates proteomics domain knowledge for efficient load-balancing. Source code is made available at: https://github.com/pcdslab/lbdslim/tree/mpi. 

   more » « less