Database Persistence, Without The Performance Penalty
Some applications require higher data durability than in-memory storage provides. What if DRAM could be made persistent? AgigA Tech’s AGIGARAM non-volatile DIMM (NVDIMM) delivers that capability. McObject benchmarked the eXtremeDB In-Memory Database System using AGIGARAM as storage, including “pulling the plug” mid-execution, and comparing the NVDIMM to transaction logging as a solution for data durability/recoverability. This paper presents the benchmark tests and results.
More on IMDS Storage, Performance and Data Durability/Recoverability:
Benchmarking In-Memory & On-Disk Databases With Hard-Disk, SSD and Memory-Tier NAND Flash
Eliminating latency, including data management latency, within the trade cycle makes a huge difference for trading success. In-memory database systems (IMDSs) deliver unparalleled speed, via volatile RAM-based storage. To add data durability, IMDSs offer transaction logging. Are they still significantly faster than “traditional” (on-disk) DBMSs? McObject’s benchmark research answers this question and measures the performance impact of different storage options (HDD, SSD and state-of-the-art memory-tier flash device), to inform your decisions on data management, storage, low-latency and volatility in trading system design.
White Paper: Pipelining Vector-Based Statistical Functions for In-Memory Analytics
Columnar data handling accelerates time series analysis (including market data analysis) by maximizing the proportion of relevant data brought into the CPU cache with each fetch. As explained in this white paper, McObject’s eXtremeDB Financial Edition delivers columnar data handling, and builds on it with pipelining technology that enables multiple vector-based statistical functions to work on a given data sequence (time series) within the CPU cache, without the need to “materialize” interim results as output in main memory. This eliminates the latency caused by back-and-forth transfers between CPU cache and memory.
Short video: Pipelining Vector-Based Statistical Functions
Get the gist of columnar data handling and pipelining vector-based statistical functions in just two minutes.
See a complete list of white papers from the DBMS professionals at McObject.