# Scaling our Observability platform beyond 100 Petabytes by embracing wide events and replacing OTel

DevFeed: [Scaling our Observability platform beyond 100 Petabytes by embracing wide events and replacing OTel](<https://devfeed.tech/articles/scaling-our-observability-platform-beyond-100-petabytes-by-embracing-wide-events-and-replacing-otel-5556.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/scaling-observability-beyond-100pb-wide-events-replacing-otel>)

Author: Rory Crispin; Dale McDiarmid

Published: 2025-06-19T13:55:13Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [observability](<https://devfeed.tech/topics/observability.md>), [log management](<https://devfeed.tech/topics/log-management.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>)

Tags: [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cost](<https://devfeed.tech/tags/cost.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [logging](<https://devfeed.tech/tags/logging.md>), [logs](<https://devfeed.tech/tags/logs.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>)

## AI overview

The article describes how ClickHouse scaled its internal observability platform from 19 PiB to more than 100 petabytes and nearly 500 trillion rows. It explains why OpenTelemetry parsing and marshalling became a bottleneck, how a native ClickHouse-to-ClickHouse pipeline and wide events enabled a 20x increase in event volume while using less than 10% of the previous CPU, and how HyperDX and ClickStack changed the observability user experience.

## Source excerpt

Read how we scaled our observability platform from 19PB to 100PB and 500 trillion rows by replacing OpenTelemetry with a native ClickHouse-to-ClickHouse pipeline, embracing wide events and cutting CPU usage by 90%.