Uploaded image for project: 'Couchbase Server'
  1. Couchbase Server
  2. MB-26307

Improve periodic CPU spikes on indexer nodes during moi disk snapshot persistence

    XMLWordPrintable

Details

    • Bug
    • Resolution: Fixed
    • Critical
    • 5.5.0
    • 4.5.1, 4.6.0, 4.6.1, 4.6.4, 4.6.2, 4.6.3, 4.6.5, 5.0.0, 5.0.1, 5.1.0, 5.1.1, 5.1.2
    • storage-engine
    • Yes
    • CBSS Sprint 03-16-2018

    Description

      Background

      Every 10 mins GSI indexes writes a snapshot is to disk.

      Problem

      When snapshotting is happening the CPU usage burst to 100%, there is a a suggestion that this could have an impact on index scan latency and to the other services running on the node (Data, Query, Search, etc)

      Workaround

      Decrease the number of persistence thread(this workaround is only effective if "number of indexes" < "number of cores" as minimum 1 persistence thread gets assigned to each index) 

      curl -X POST -u <user:pass> http://localhost:9102/settings --data '{"indexer.settings.moi.persistence_threads": 1}'
      

      Attachments

        Issue Links

          No reviews matched the request. Check your Options in the drop-down menu of this sections header.

          Activity

            People

              mahesh.mandhare Mahesh Mandhare (Inactive)
              jeelan.poola Jeelan Poola
              Votes:
              0 Vote for this issue
              Watchers:
              14 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved:

                Gerrit Reviews

                  There are no open Gerrit changes

                  PagerDuty