Unconference Session: Pains of Multi-Tenancy
summary
RISE runs an internal OpenSearch platform serving many projects and faces concrete pains: tenants duplicate log volume overnight forcing emergency capacity scale-outs, shard sizes grow unevenly requiring manual reindexing, and a proposed JSON log standard is ignored so dozens of dashboard templates fail. Ingestion uses Logstash ingestion controlled by ops after tenants broke parsing, access relies on OpenSearch security plugin wired to two LDAP schemes, and data protection finds personal data forcing technical and organizational measures while workload management is not yet implemented.
AI-written summary · about
chapters (11)
- 0:00Multi-tenancy pains
- 1:04User onboarding challenges
- 2:28Permission systems
- 2:49Log format inconsistencies
- 3:52Data protection struggles
- 4:58Shard sizing burdens
- 6:21Therapy session sharing
- 7:04Noisy neighbors
- 8:30Workload management
- 9:12Zero-downtime migrations
- 10:14Legacy permission systems
related talks
24mReimagining Search : Scaling OpenSearch Across an Enterprise - Platform C...
43mMulti-tenancy for all workloads
09mUnconference: OpenSearch is not a database!
35mInnovating at Scale: Lessons from Pegasystems' OpenSearch Journey
44mScaling OpenSearch at Uber: Operating Resilient, Fault-Tolerant, High-Performance Clus...
41mDynamoDB, Neptune and OpenSearch: A Unified Approach to Collaborative Editing and Search #JSConfAM25
28mRunning OpenSearch at Scale in High-Traffic Gaming Systems
36mScaling Log Management: PB-Scale Migration From Elasticsearch To...