cockroachdb / cockroachdb/cockroach
Capture and surface TCP retransmit metrics to help users monitor/alert and identify network-related issues
Open
C-enhancement
T-supportability
- Dominant language
- Go
- Stars
- 32.5k
- Forks
- 4.1k
- PR merge metrics
- PR metrics pending
Description
It's difficult for operators and developers to quickly identify networking issues that could be impacting CockroachDB. This issue tracks additional observability, specifically metrics to help users monitor/alert and identify network-related issues.
We should evaluate metrics from:
- /proc/net/netstat
- /proc/net/tcp (specifically TCP retransmits)
Other metrics:
- ICMP messages and fragmentation
Related issues
- https://github.com/cockroachdb/cockroach/issues/115458
- https://github.com/cockroachdb/cockroach/pull/116712#issuecomment-1862461376
Jira issue: CRDB-36652
Contributor guide
Assessment
This issue has not been assessed yet.