Iraklis Psaroudakis
Iraklis Psaroudakis is working remotely from Greece as a Principal Software Engineer at Elastic, focusing on the distributed scalability of Elasticsearch. Previously, he was a Principal Member of Technical Staff at Oracle Labs in Zürich, Switzerland, concentrating on parallel and distributed programming and on graph-based analytical and machine learning workloads, especially in financial crime and compliance applications. Prior to Oracle, he completed his Ph.D. at the DIAS lab of EPFL in Lausanne, focusing on scaling up highly concurrent analytical database workloads on multisocket multicore servers through: a) sharing data and work across concurrent queries; and b) adaptive Non‑Uniform Memory Access–aware (NUMA-aware) data placement and task scheduling. As he worked on his Ph.D., he collaborated with the SAP HANA database team. Before earning his Ph.D., he completed his studies in Electrical & Computer Engineering at NTUA in Athens.
How Elasticsearch Serverless hollow shards cut indexing-node shutdowns by 30%
Idle indexing shards in Elasticsearch Serverless now drop their Lucene writers and segment readers from memory until the next write, freeing indexing-tier heap at the cost of a median 218ms wait on that first write.
The stateless architecture of Elasticsearch Serverless
Exploring the stateless architecture of Elasticsearch Serverless. Learn how the stateful architecture was transformed into stateless for Serverless.