Uploaded image for project: 'Cassandra'
  1. Cassandra
  2. CASSANDRA-14953

Failed to reclaim the memory and too many MemtableReclaimMemory pending task

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Normal
    • Resolution: Information Provided
    • Fix Version/s: None
    • Component/s: Local/Memtable
    • Labels:
      None
    • Environment:

      version : cassandra 2.1.15

      jdk: 8

      os:suse

    • Severity:
      Normal

      Description

      We found that Cassandra has a lot of write accumulation in the production environment, and our business has experienced a lot of write failures.
      Through the system.log, it was found that MemtableReclaimMemory was pending at the beginning, and then a large number of MutationStage stacks appeared at a certain moment.
      Finally, the heap memory is full, the GC time reaches tens of seconds, the node status is DN through nodetool, but the Cassandra process is still running.We killed the node and restarted the node, and the above situation disappeared.

       

      Also the number of Active MemtableReclaimMemory threads seems to stay at 1.

      (you can see the 1.PNG)

      a large number of MutationStage stacks appeared at a certain moment.

      (you can see the 2.PNG)

       

      long GC time:

       - MemtableReclaimMemory 1 156 24565 0 0

      • G1 Old Generation GC in 87121ms. G1 Old Gen: 51175946656 -> 50082999760;
      • MutationStage 128 11931622 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Young Generation GC in 969ms. G1 Eden Space: 1090519040 -> 0; G1 Old Gen: 50082999760 -> 51156741584;
      • MutationStage 128 11953653 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Old Generation GC in 84785ms. G1 Old Gen: 51173518800 -> 50180911432;
      • MutationStage 128 11967484 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Young Generation GC in 611ms. G1 Eden Space: 989855744 -> 0; G1 Old Gen: 50180911432 -> 51153989960;
      • MutationStage 128 11975849 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Old Generation GC in 85845ms. G1 Old Gen: 51170767176 -> 50238295416;
      • MutationStage 128 11978192 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Young Generation GC in 602ms. G1 Eden Space: 939524096 -> 0; G1 Old Gen: 50238295416 -> 51161042296;
      • MutationStage 128 11994295 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
      • G1 Old Generation GC in 85307ms. G1 Old Gen: 51177819512 -> 50288829624; Metaspace: 36544536 -> 36525696
      • MutationStage 128 12001932 1983820772 0 0
      • CounterMutationStage 0 0 0 0 0
        66 - MutationStage 128 12004395 1983820772 0 0
        66 - CounterMutationStage 0 0 0 0 0
      • MemtableReclaimMemory 1 156 24565 0 0
        66 - MemtableReclaimMemory 1 156 24565 0 0
      • G1 Young Generation GC in 610ms. G1 Eden Space: 889192448 -> 0; G1 Old Gen: 50288829624 -> 51178022072;
      • MutationStage 128 12023677 1983820772 0 0

      Why is this happening? 

        Attachments

        1. cassandra.yaml
          49 kB
          HUANG DUICAN
        2. cassandra_20190105.zip
          58 kB
          HUANG DUICAN
        3. 2.PNG
          86 kB
          HUANG DUICAN
        4. 1.PNG
          66 kB
          HUANG DUICAN

          Activity

            People

            • Assignee:
              Unassigned
              Reporter:
              h00382097 HUANG DUICAN
            • Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: