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 showed 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?