Case Study Deskcasestudydesk.com
Cybersecurity / asset intelligenceSourced

Case Study: How Armis cut data pipeline cost 70% with SingleStore

Armis Case StudySourced & dated by Case Study Desk
Key facts · TL;DR
Company
Armis
Industry
Cybersecurity / asset intelligence
Challenge
A 160-node Elasticsearch pipeline ingesting 100 billion events a day was costly and slow.
Headline result
70% lower data pipeline cost after moving off Elasticsearch

Key results

70%
Lower data pipeline cost
vs. Elasticsearch pipeline
100 billion
Events ingested per day
<10 sec
Queries that timed out in Elasticsearch
Now complete
~1 million
Rows per second loaded
Complex data

The challenge

Armis originally launched on PostgreSQL, then migrated its time-based dataset from 400+ databases into a 160-node Elasticsearch cluster ingesting 100 billion events per day. That pipeline required extensive supporting infrastructure and frequent full reindexes, costing more than $1 million annually while delivering poor query performance.

The solution

Armis consolidated onto SingleStore, running SingleStore Helios on AWS alongside SingleStore Self-Managed for FedRAMP environments, to unify high-volume ingestion and querying in a single platform.

We moved from the entire data pipeline including ElasticSearch costing more than $1 million annually to paying a fraction of that for SingleStore Helios, reducing our data pipeline cost by 70%.

AC
Aviram Cohen
Chief R&D Officer, Armis

The results, in context

Armis reports a 70% reduction in data pipeline cost after replacing its Elasticsearch pipeline with SingleStore Helios, moving from more than $1 million annually to a fraction of that. The platform ingests 100 billion events and 1.2 billion sessions per day and loads roughly 1 million rows per second, with queries that previously timed out in Elasticsearch now completing in under 10 seconds.

Products used

SingleStore SingleStore HeliosSingleStore SingleStore Self-Managed