64/128 bucket allocation failures

[Michael Butler]

I'm seeing these allocation failures on a -current box (today's) with more
than enough free RAM ..

imb at toshi:/home/imb> vmstat -z
ITEM                     SIZE     LIMIT      USED      FREE  REQUESTS 
FAILURES

UMA Kegs:                 128,        0,       76,       14,       76,    
   0
UMA Zones:                480,        0,       76,        4,       76,    
   0
UMA Slabs:                 64,        0,     2647,        8,    25743,    
   0
UMA RCntSlabs:            104,        0,      237,       22,      237,    
   0
UMA Hash:                 128,        0,        5,       25,        8,    
   0
16 Bucket:                 76,        0,       52,       48,       70,    
   0
32 Bucket:                140,        0,       63,       21,       83,    
   0
64 Bucket:                268,        0,      116,       10,      165,    
  11
128 Bucket:               524,        0,      591,        4,     1316,   
11270

 [ .. snip .. ]

imb at toshi:/home/imb> top -d 1
last pid: 22624;  load averages:  0.00,  0.00,  0.00                      
                                                          up 0+03:13:42 
14:31:16
49 processes:  1 running, 48 sleeping
CPU states:     % user,     % nice,     % system,     % interrupt,     % idle
Mem: 97M Active, 606M Inact, 246M Wired, 844K Cache, 112M Buf, 1044M Free
Swap: 1024M Total, 1024M Free

Any ideas?

     Michael