核心概念
Efficient indexing structure DynaWarp offers significant storage savings and faster query throughput for large-scale log data processing.
摘要
現代の大規模な監視システムは、巨大なログデータをリアルタイムで処理および保存する必要があります。Dynatraceの新しいDynaWarpメンバーシップスケッチは、既存のインデックス構造に比べて93%以上のストレージ節約と高速なクエリスループットを実現します。この革新的な構造は、大規模なログデータセットに対して効率的で効果的な索引付けを提供します。
统计
DynaWarp required up to 93% less storage space than the tested state-of-the-art inverted index.
DynaWarp achieved up to 250 times higher query throughput than the tested inverted index.
DynaWarp had up to four orders of magnitude less false-positives than the tested state-of-the-art membership sketch.
引用
"Traditional RDBMS have been mainly developed to store relational data with well-defined schemas and to support transactional reads and updates. However, monitoring data, like logs or metrics, is typically never updated and its attributes are dynamic and high-dimensional."
"DynaWarp introduces a novel algorithm for efficient, online deduplication of posting lists and postings within individual lists."
"Our lead research question is how can queries on compressed log data be supported efficiently in terms of storage, memory, and processing overhead during ingest and query execution?"