Mars: The Design of a Main Memory Database Machine

Eich, Margaret H.

doi:10.1007/978-1-4613-1679-4_24

Cited by 39 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other techniques for main memory applicability appear in [BHT87]. Complete systems include TimesTen [Tim07], DataBlitz [BBK+98], and MARS [Eic87]. A survey of this area appears in [GS92].…”

Section: Cache-conscious B-treesmentioning

confidence: 99%

OLTP through the looking glass, and what we found there

Harizopoulos

Abadi

Madden

2008

Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data

205

View full text Add to dashboard Cite

Online Transaction Processing (OLTP) databases include a suite of features -disk-resident B-trees and heap files, locking-based concurrency control, support for multi-threading -that were optimized for computer technology of the late 1970's. Advances in modern processors, memories, and networks mean that today's computers are vastly different from those of 30 years ago, such that many OLTP databases will now fit in main memory, and most OLTP transactions can be processed in milliseconds or less. Yet database architecture has changed little.Based on this observation, we look at some interesting variants of conventional database systems that one might build that exploit recent hardware trends, and speculate on their performance through a detailed instruction-level breakdown of the major components involved in a transaction processing database system (Shore) running a subset of TPC-C. Rather than simply profiling Shore, we progressively modified it so that after every feature removal or optimization, we had a (faster) working system that fully ran our workload. Overall, we identify overheads and optimizations that explain a total difference of about a factor of 20x in raw performance. We also show that there is no single "high pole in the tent" in modern (memory resident) database systems, but that substantial time is spent in logging, latching, locking, Btree, and buffer management operations.

show abstract

“…Other techniques for main memory applicability appear in [BHT87]. Complete systems include TimesTen [Tim07], DataBlitz [BBK+98], and MARS [Eic87]. A survey of this area appears in [GS92].…”

Section: Cache-conscious B-treesmentioning

confidence: 99%

OLTP through the looking glass, and what we found there

Harizopoulos

Abadi

Madden

2008

Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data

205

View full text Add to dashboard Cite

show abstract

“…But, it reduce other transaction's lock waiting time waiting for a possessed lock by corresponding transaction and it has the advantage of improving concurrency of transaction performance than group commit [8].…”

Section: Log Techniquementioning

confidence: 99%

“…In transaction is partially commit status, it used pre-commit that transaction REDO log in system global log buffer is moved and it is unlocked before record log on dick. In Dali, it has a disadvantage of performance degradation using act consistent checkpoint technique [8].…”

Section: A Dalimentioning

confidence: 99%

Recovery Methods in Main Memory DBMS

Kim¹,

Kang²,

Lee³

2012

International journal of advanced smart convergence

View full text Add to dashboard Cite

Recently, to efficiently support the real-time requirements of RTLS( Real Time Location System) services, interest in the main memory DBMS is rising. In the main memory DBMS, because all data can be lost when the system failure happens, the recovery method is very important for the stability of the database. Especially, disk I/O in executing the log and the checkpoint becomes the bottleneck of letting down the total system performance. Therefore, it is urgently necessary to research about the recovery method to reduce disk I/O in the main memory DBMS. Therefore, In this paper, we analyzed existing log techniques and check point techniques and existing main memory DBMSs' recovery techniques for recovery techniques research for main memory DBMS.

show abstract

“…The volume cost of the dictionary is not significant considering the volume of the views when they are fully materialized. Table 1 shows the volume of the dictionary compared to the raw data and the materialized views for the TPC-D benchmark dataset [36], Table 2 has a single relation that describes the characteristics of a number of chips. If this is stored as a file of records, we have to make each field of these records big enough to hold the largest value that any of the records stores in that field.…”

Section: Applying Compression In Data Warehousingmentioning

confidence: 99%

Compact Representation: An Approach to Efficient Implementation for the Data Warehouse Architecture

Kotsis

McGregor

1999

DataWarehousing and Knowledge Discovery

View full text Add to dashboard Cite

Abstract. Data Warehousing requires effective methods for processing and storing large amounts of data. OLAP applications form an additional tier in the data warehouse architecture and in order to interact acceptably with the user, typically data pre-computation is required. In such a case compressed representations have the potential to improve storage and processing efficiency. This paper proposes a compressed database system which aims to provide an effective storage model. We show that in several other stages of the Data Warehouse architecture compression can also be employed. Novel systems engineering is adopted to ensure that compression/decompression overheads are limited, and that data reorganisations are of controlled complexity and can be carried out incrementally. The basic architecture is described and experimental results on the TPC-D and other datasets show the performance of our system.

show abstract

Mars: The Design of a Main Memory Database Machine

Cited by 39 publications

References 5 publications

OLTP through the looking glass, and what we found there

OLTP through the looking glass, and what we found there

Recovery Methods in Main Memory DBMS

Compact Representation: An Approach to Efficient Implementation for the Data Warehouse Architecture

Contact Info

Product

Resources

About