Uploaded image for project: 'Couchbase Server'
  1. Couchbase Server
  2. MB-17004

Long pauses are observed during n1ql performance regression tests

    XMLWordPrintable

Details

    • Bug
    • Resolution: Fixed
    • Critical
    • 4.1.1, 4.5.0
    • 4.0.0, 4.1.0
    • forestdb
    • Security Level: Public
    • Untriaged
    • Yes
    • ForestDB: Oct 17 - Nov 4

    Description

      We have observed long pauses in a few n1ql performance tests during the 4.1 regression run.

      • Q2: stale=ok, throughput test
      • Q2: stale=false, throughput test
      • Q3: stale=ok, throughput test
      • Q3: stale=false, throughput test

      Attachments

        Issue Links

          blocks

          Task - A task that needs to be done. MB-17211 4.1.1 Minor Release

          • Major - Major loss of function.
          • Closed
          relates to

          Bug - A problem which impairs or prevents the functions of the product. MB-15908 Forestdb fdb_get_kvs_info() call can take 90s after compaction

          • Critical - Crashes, loss of data, severe memory leak.
          • Closed

          Improvement - An improvement or enhancement to an existing feature or task. MB-16219 Reuse stale blocks / support circular reuse

          • Major - Major loss of function.
          • Resolved
          For Gerrit Dashboard: MB-17004
          # Subject Branch Project Status CR V
          57800,1 MB-17004: Add debugging support for long pause observed during n1ql scan test Change-Id: Ia61fb053707b94a74c13de94472f5f6a61caf72c testing indexing Status: MERGED +2 +1
          58131,7 MB-17004: Prune old doc's seqnum from Sequence index on WAL flush master forestdb Status: ABANDONED 0 +1
          58327,3 MB-17004 Use number of delta blocks to determine the last phase of compaction sherlock forestdb Status: ABANDONED 0 -1
          58344,1 MB-17004 Restore all commit headers up to the point when compact_upto is made sherlock forestdb Status: ABANDONED -1 0
          58356,7 MB-17004 Don't flush the WAL for each commit in fdb_compact_upto sherlock forestdb Status: MERGED +2 +1
          58414,1 MB-17004: skip wal on 1st compaction phase sherlock forestdb Status: ABANDONED -1 0
          58723,3 Merge remote-tracking branch 'origin/sherlock' master forestdb Status: MERGED +2 +1
          58928,1 Revert "MB-17004 Don't flush the WAL for each commit in fdb_compact_upto" sherlock forestdb Status: MERGED +2 +1
          58931,1 Merge remote-tracking branch 'origin/sherlock' master forestdb Status: MERGED +2 +1
          59105,1 MB-17004 Don't flush the old file's WAL during the last phase of compaction master forestdb Status: ABANDONED 0 +1
          59780,4 MB-17004: Prune an old doc's seqnum from sequence index on WAL flush master forestdb Status: MERGED +2 +1

          Activity

            People

              wayne Wayne Siu
              wayne Wayne Siu
              Votes:
              0 Vote for this issue
              Watchers:
              10 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved:

                PagerDuty