Uploaded image for project: 'Core Server'
  1. Core Server
  2. SERVER-6785

Possible mongos memory leak

    XMLWordPrintable

Details

    • Bug
    • Status: Closed
    • Major - P3
    • Resolution: Fixed
    • 2.2.0-rc1
    • 2.2.0-rc2, 2.3.0
    • Sharding
    • None
    • CentOS 6.2
    • Linux

    Description

      I setup a 2 shard cluster with auth. With a continuous query load of around 1000/sec the mongos process seems to keep chewing up memory until the OS kills the process:

      Out of memory: Kill process 2567 (mongos) score 950 or sacrifice child
      Killed process 2567, UID 502, (mongos) total-vm:8987492kB, anon-rss:7738860kB, file-rss:16kB

      In this case I had upgraded the test server to 8GB of ram to make sure it would still occur and with 8GB it took right around an hour to use up all the memory and swap space before the OS killed it.

      Attachments

        1. investigation-mongos-with-google-profiler.tgz
          195 kB
        2. momngos-t1.pdf
          14 kB
        3. momngos-t2.pdf
          13 kB
        4. momngos-t3.pdf
          13 kB
        5. mongos.tgz
          18.67 MB

        Issue Links

          Activity

            People

              benjamin.becker Ben Becker
              alaphoid Jonathan Schneider
              Votes:
              0 Vote for this issue
              Watchers:
              8 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: