Is the glusterfs Process Having a Memory Leak in gf_fuse_mt_iov_base pool?

Solution Verified - Updated -

Issue

  • The resident size of the glusterfs process is taking a huge amount of memory:

    1 USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
    129 root      1843  6.5 42.9 5932272 5240248 ?     Ssl  Mar23 3114:47 /usr/sbin/glusterfs --volfile-server=gluster-node1 --volfile-server=gluster-node2 --volfile-server=gluster-node3 --volfile-id=/gluster-volume /mnt
    
  • A statedump captured shows that the highest amount of memory allocation is at pool gf_fuse_mt_iov_base

    406 [mount/fuse.fuse - usage-type gf_fuse_mt_iov_base memusage]
    407 size=4288679774 --> Note there're approx 4.2 GB of memory allocated here
    408 num_allocs=1
    409 max_size=4294967286
    410 max_num_allocs=39
    411 total_allocs=997593869
    
  • For information on how to gather a statedump, please consult the admin guide

  • However, checking the size of the mallinfo_arena, this is not big at all:

    [mallinfo]
    mallinfo_arena=598016  --->
    mallinfo_ordblks=7
    mallinfo_smblks=3
    mallinfo_hblks=5
    mallinfo_hblkhd=11993088
    mallinfo_usmblks=0
    mallinfo_fsmblks=304
    mallinfo_uordblks=574192
    mallinfo_fordblks=23824
    mallinfo_keepcost=17584
    

Is this a cause of concern?

Environment

  • Red Hat Gluster Storage 3.x

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase of over 48,000 articles and solutions.

Current Customers and Partners

Log in for full access

Log In