yugabyte/yugabyte-db

[DocDB] Expand events for slow disk access to all reads and writes

Open

#16 828 ouverte le 12 avr. 2023

Voir sur GitHub
 (1 commentaire) (0 réactions) (1 assigné)C (1 003 forks)batch import
area/docdbgood first issuekind/enhancementpriority/medium

Métriques du dépôt

Stars
 (8 229 stars)
Métriques de merge PR
 (Merge moyen 17j 21h) (92 PRs mergées en 30 j)

Description

Jira Link: DB-6178

Description

Related to #16827, we could then also add special logging, for "too slow" events, across all IO! This could be similar to how we have "slow fsync" events, at the WAL level...

If we had proper metrics at the lower level, of the env disk access abstraction, we should be able to push down even the slow fsync event, from the log.cc level.

Warning: Please confirm that this issue does not contain any sensitive information

  • I confirm this issue does not contain any sensitive information.

Guide contributeur