lightly loaded system eats swap space

[tech-lists]

On 18/06/2018 00:04, Adam wrote:
> Based upon the output neither ram nor swap seems like similar spec so I 
> wonder if you could say what you mean by that.

server with the problem:

last pid: 62387;  load averages:  0.07,  0.10,  0.08 
 
 
                              up 30+01:30:01  12:46:40
48 processes:  1 running, 47 sleeping
CPU:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  100% idle
Mem: 5404K Active, 1218M Inact, 4927M Laundry, 117G Wired, 1392M Buf, 
2116M Free
ARC: 109G Total, 2982M MFU, 105G MRU, 288K Anon, 385M Header, 638M Other
      104G Compressed, 105G Uncompressed, 1.01:1 Ratio
Swap: 4096M Total, 3383M Used, 713M Free, 82% Inuse

This server runs 1 bhyve instance using 16GB. It has 128GB RAM.

server without a problem:

last pid: 84491;  load averages:  0.03,  0.02,  0.02 
 
 
                              up 17+14:39:31  12:47:33
27 processes:  1 running, 26 sleeping
CPU:     % user,     % nice,     % system,     % interrupt,     % idle
Mem: 2915M Active, 25G Inact, 9947M Laundry, 28G Wired, 1572M Buf, 59G Free
ARC: 22G Total, 3379M MFU, 19G MRU, 781K Anon, 64M Header, 974K Other
      22G Compressed, 29G Uncompressed, 1.33:1 Ratio, 121M Overhead
Swap: 35G Total, 3747M Used, 32G Free, 10% Inuse

This server runs 10 bhyve instances of various RAM sizes, from 4GB to 
32GB. It also has 128GB RAM installed. This is what I mean by "similar 
spec", I mean in terms of RAM.

This server doesn't usually show swap as being in use, but I can 
actually account for this, as there is memory overcommitment here.

My point is that 'server with problem' should not show a resources issue 
with just one bhyve instance using 16GB RAM but apparently it is, and I 
don't know why. I am starting the VMs by hand, without any third-party 
application, and I'm not wiring memory on the command line.

thanks,
-- 
J.