On 21 Nov, Alister Waller scribbled:
-> I have a customer who says that his systems seems to be very memory hungry.
-> Looking at the output below I can see that there is on 70MB of memory left
-> out of 517MB.
-> 
-> I was wondering if anyone could decipher the below output and suggest
-> reasons for what is going on or for more reports I can produce to pintpoint
-> whats eating memory.
-> 
-> regards
-> 
-> Alister
-> 
-> 
-> ************************************************
-> Hear is a dump of vmstat, with 35 users. It is a bit better today with 73
-> meg free, Yesterday it had 42 user with about 3meg free and it alway seems
-> to be using the swap file.
-> I have been monitoring this a even at night with only one or two users the
-> free memory is often only 10 to 20meg.
-> 
-> I also noticed that the cpu usage for user programs always seems to site
-> around 50% (the first day or two it never got above 10%) The only program I
-> can see using this is klogd as you can see from TOP.
-> 
-> 
-> 
-> Feel free to dialin and have look.
-> 
-> 
-> Steve
-> 
-> Last login: Tue Nov 21 15:36:56 2000 from
-> [root@booth3 /root]# vmstat 2 10
->    procs                      memory    swap          io     system
-> cpu
->  r  b  w   swpd   free   buff  cache  si  so    bi    bo   in    cs  us  sy
-> id
->  5  0  0   9972  73728 135660 219680   0   0    13    12   62    53  40   0
-> 60
->  3  0  0   9972  73684 135664 219720   0   0     5     0  157   568  54   4
-> 43
->  1  0  0   9972  73684 135664 219720   0   0     9    21  171   443  54   3
-> 43
->  1  0  0   9972  73684 135664 219720   0   0     0     0  155   381  51   3
-> 46
->  1  0  0   9972  73760 135664 219716   0   0     0     0  138   343  50   3
-> 47
->  1  0  0   9972  73756 135664 219712   0   0     5    30  188   321  50   3
-> 46
->  1  0  0   9972  75244 135664 219708   0   0     1     4  132   155  50   4
-> 46
->  1  0  0   9972  75232 135668 219716   0   0     8    22  163   239  55   4
-> 40
->  1  0  0   9972  75164 135676 219776   0   0     8     0  146   590  52   4
-> 44
->  1  0  0   9972  75164 135676 219776   0   0     0     0  133   142  50   3
-> 47
-> [root@booth3 /root]# uptime
->   3:37pm  up 3 days, 18:49, 35 users,  load average: 1.03, 1.06, 1.02
-> [root@booth3 /root]#
-> 
-> [root@booth3 /root]# free
->              total       used       free     shared    buffers     cached
-> Mem:        517124     442692      74432     110428     135888     220292
-> -/+ buffers/cache:      86512     430612
-> Swap:      1999968       9972    1989996

hes' onyl really using 86MB of memory address space - the rest is memory
that sunused by processes and so the kernel sues it for buffers and
cache.

->   3:41pm  up 3 days, 18:53, 35 users,  load average: 1.08, 1.06, 1.01
-> 219 processes: 217 sleeping, 2 running, 0 zombie, 0 stopped
-> CPU states: 50.8% user,  2.7% system,  0.0% nice, 46.3% idle
-> Mem:   517124K av,  443376K used,   73748K free,  110740K shrd,  136056K
-> buff
-> Swap: 1999968K av,    9972K used, 1989996K free                  220584K
-> cached
-> 
->   PID USER     PRI  NI  SIZE  RSS SHARE STAT  LIB %CPU %MEM   TIME COMMAND
->   434 root      12   0   384   12     4 R       0 98.6  0.0  4295m klogd
-> 28886 root       7   0   968  968   668 R       0  3.6  0.1   0:01 top
-> 22589 rr         0   0  1224 1224   476 S       0  0.9  0.2   0:33 runcobol
-> 28855 root       0   0  1528 1484  1184 S       0  0.9  0.2   0:00 sshd
-> 20723 rr         0   0  1260 1260   476 S       0  0.7  0.2   1:41 runcobol
-> 20919 rr         0   0  1288 1288   476 S       0  0.7  0.2   0:11 runcobol
->    10 root     -20 -20     0    0     0 SW<     0  0.5  0.0   9:47 raid5d
-> 20678 root       0   0   760  760   604 S       0  0.3  0.1   0:08
-> in.telnetd
-> 22544 root       0   0   760  760   604 S       0  0.1  0.1   0:06
-> in.telnetd
-> 25918 root       0   0   760  760   604 S       0  0.1  0.1   0:02
-> in.telnetd
-> 28150 root       1   0   760  760   604 S       0  0.1  0.1   0:01
-> in.telnetd
->     1 root       0   0   120   68    52 S       0  0.0  0.0   0:08 init
->     2 root       0   0     0    0     0 SW      0  0.0  0.0   0:24 kflushd
->     3 root       0   0     0    0     0 SW      0  0.0  0.0   0:49 kupdate
->     4 root       0   0     0    0     0 SW      0  0.0  0.0   0:00 kpiod
->     5 root       0   0     0    0     0 SW      0  0.0  0.0   0:28 kswapd
->     6 root     -20 -20     0    0     0 SW<     0  0.0  0.0   0:00
-> mdrecoveryd
->   347 bin        0   0   372  352   304 S       0  0.0  0.0   0:00 portmap

you're definitely missing processes here (hit "shift-M" to display in
order of memory address space size) 

-- 
--------------- Codito, ergo sum - "I code, therefore I am" --------------------
The Rasterman (Carsten Haitzler)    [EMAIL PROTECTED]     [EMAIL PROTECTED]
                                    [EMAIL PROTECTED] [EMAIL PROTECTED]
                                    [EMAIL PROTECTED]




-- 
SLUG - Sydney Linux User Group Mailing List - http://slug.org.au/
More Info: http://slug.org.au/lists/listinfo/slug

Reply via email to