[IMPALA-9033] Log metrics for slow I/Os

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: Impala 3.4.0
• Component/s: Backend
• Target Version: Impala 3.4.0
• Epic Color: ghx-label-12
• Assignee: Tim Armstrong
• Reporter: Tim Armstrong
• Created: 09/Oct/19 17:21
• Updated: 04/Mar/20 03:10
• Resolved: 11/Oct/19 00:15

Description

We should detect I/Os that take longer than a configurable threshold, e.g 10 seconds might be reasonable and then log some extra information about them - any of the metrics we get from the HDFS client.

This will help debug certain perf issues and hangs.

Issue Links

• breaks: IMPALA-9060 Slow I/O logging is quite verbose on S3
• is related to: IMPALA-9458 Improve runtime profile counters for slow IO from remote stores