AIX 7.1 high page faults


 
Thread Tools Search this Thread
Operating Systems AIX AIX 7.1 high page faults
# 1  
Old 10-31-2012
AIX 7.1 high page faults

hi guys i hope you can help me with this situation.

i have 2 lpar with aix 7.1 and oracle 11gr2 in grid mode.

when i start nmon to check the current system health i notice that page fault are over 3000/s. than i have opened a case with ibm and they say that the problem is not paging nor pinning nor memory but heavy i/o on disks from an application.

infact i have 30% of free memory and 0.3% of page space used and 16,7& of pinned memory.

now i thinks oracle arc is the cause, but how can determine exactly which application is creating those page faults?

i have tried with noon with t option and then 5(for i/o) but it seems all normally.

any suggest would be appreciated.
Thanks
# 2  
Old 10-31-2012
Are these errors showing up on a console or in system logs? Most Unix systems I have worked with will log page errors to /var/log/messages by default. I usually can see the device or get a PID that I can cross reference against dumps of the ps command or similar.
# 3  
Old 10-31-2012
hi thanks for flash reply Smilie

those errors shows on nmon like this:
Code:
  Code    Resource            Stats   Now       Warn    Danger                                                                  │
│      OK -> CPU               %busy   3.6%      >80%    >90%                                                                    │
│      OK -> Paging size       %free  99.7%      <20%    <10%                                                                    │
│      OK -> Paging Space      RAM:pg103.1%      <50%    <10%                                                                    │
│  DANGER -> Page Faults       faults 1915.0     >16/s   >160/s

but page faults can up to 100000/s sometimes....
# 4  
Old 10-31-2012
@zer0sig: this might be the case with Linux, but AIX is quite different. There is no /var/log/messages to begin with.

@Thread O/P:

looks like this can't be solved without additional data.

Post the output of:

vmstat -wT 1 (let it run for 20-30 seconds)
iostat 1 | grep -v ' 0\.0' (for the same timespan)
vmstat -vs

I hope this helps.

bakunin
# 5  
Old 10-31-2012
here what you have requested

Code:
System configuration: lcpu=8 mem=32768MB

 kthr          memory                         page                       faults           cpu       time  
------- --------------------- ------------------------------------ ------------------ ----------- --------
  r   b        avm        fre    re    pi    po    fr     sr    cy    in     sy    cs us sy id wa hr mi se
  3   0    5419309    2443083     0     0     0     0      0     0    68  23226  9504  5  4 90  0 12:00:31
  2   0    5419345    2443045     0     0     0     0      0     0   152  21588  9172  6  4 88  2 12:00:32
  1   0    5419489    2442900     0     0     0     0      0     0    23  23683  8998  5  4 91  0 12:00:33
  7   0    5419489    2442900     0     0     0     0      0     0    23  30577 10250  6  6 88  0 12:00:34
  5   0    5419488    2442901     0     0     0     0      0     0    45  25708  9020  6  5 89  0 12:00:35
  5   0    5425603    2436785     0     0     0     0      0     0  1636  28791 10364 16  7 77  0 12:00:36
  0   0    5424859    2437528     0     0     0     0      0     0  1916  29239 11410 14  7 77  2 12:00:37
 15   0    5425578    2436802     0     0     0     0      0     0   161  29950  8977 17  7 77  0 12:00:38
  0   0    5424858    2437521     0     0     0     0      0     0   126  31529 10265  9  7 84  0 12:00:39
  4   0    5424858    2437521     0     0     0     0      0     0    72  21206  9001  4  4 92  0 12:00:40
  2   0    5429901    2432476     0     0     0     0      0     0   241  25462  8919 21  6 73  0 12:00:41
  3   0    5430051    2432327     0     0     0     0      0     0   764  29312  9763 26  9 65  0 12:00:42
  3   0    5430131    2432242     0     0     0     0      0     0   210 160845  8870 12  9 79  0 12:00:43
  2   0    5431184    2431196     0     0     0     0      0     0   149 181693  9884 40 16 44  0 12:00:44
  0   0    5432255    2430124     0     0     0     0      0     0    27  94288  9541 11  7 81  0 12:00:45
  8   0    5431184    2431195     0     0     0     0      0     0    40  23088  9296 10  5 85  0 12:00:46
  0   0    5430076    2432302     0     0     0     0      0     0    76  23561  9473  6  4 90  0 12:00:47
  2   0    5433497    2428880     0     0     0     0      0     0   742  25640  9872 24  6 69  1 12:00:48
  2   0    5430101    2432275     0     0     0     0      0     0   297  30404 10511  9  9 81  0 12:00:49
  2   0    5430035    2432339     0     0     0     0      0     0   132  27075  9550 11  6 82  0 12:00:50
 kthr          memory                         page                       faults           cpu       time  
------- --------------------- ------------------------------------ ------------------ ----------- --------
  r   b        avm        fre    re    pi    po    fr     sr    cy    in     sy    cs us sy id wa hr mi se
  3   0    5429956    2432416     0     0     0     0      0     0    54  23457  9651  6  4 90  0 12:00:51
  3   0    5429945    2432426     0     0     0     0      0     0   243  22004  9562  6  4 89  0 12:00:52
  2   0    5433131    2429240     0     0     0     0      0     0   244  25251  8972 19  5 76  0 12:00:53
  1   0    5433160    2429105     0     0     0     0      0     0   215  32130 10733  6  7 86  0 12:00:54
  4   0    5433165    2429099     0     0     0     0      0     0    57  25387  8959  5  5 90  0 12:00:55
  2   0    5433256    2429005     0     0     0     0      0     0   232  23550  9176 19  5 76  0 12:00:56
  3   0    5434183    2428078     0     0     0     0      0     0   137  26520  8972 32  6 62  0 12:00:57
  3   0    5433670    2428591     0     0     0     0      0     0   131  21800  8601 13  4 82  0 12:00:58
  1   0    5433670    2428590     0     0     0     0      0     0   204  38504 10179  8  7 85  0 12:00:59
  0   0    5433670    2428591     0     0     0     0      0     0   146  22071  9297  5  4 90  0 12:01:00
  1   0    5433671    2428588     0     0     0     0      0     0   111  22748  8940  6  4 90  0 12:01:01
  1   0    5433671    2428588     0     0     0     0      0     0    75  21475  9099  5  4 91  0 12:01:02

Code:
System configuration: lcpu=8 drives=10 paths=31 vdisks=1

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           3.0     192.0      12.0        192         0
hdisk3           2.0     160.0      10.0        160         0
hdisk1           3.0     336.0      21.0        320        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      64.0       4.0         64         0

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0      48.0       3.0         48         0
hdisk0           3.0      40.0       8.0          0        40

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           1.0      28.0       7.0          0        28

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0     161.0      25.0        112        49

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0     144.0       9.0        144         0
hdisk1           1.0     228.0      16.0        208        20
hdisk0           1.0      28.0       7.0          0        28

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      80.0       5.0         64        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      80.0       5.0         64        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           1.0       4.0       1.0          0         4

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           3.0     256.0      16.0        240        16
hdisk0           2.0     1276.0     109.0          0      1276

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0      36.0       3.0         16        20
hdisk1           1.0      96.0       6.0         80        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0     112.0       7.0         96        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0     116.0      11.0        112         4
hdisk1           1.0     224.0      14.0        208        16
hdisk0           1.0      40.0       5.0          0        40

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           1.0      80.0      20.0          0        80

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           2.0     208.0      13.0        192        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      66.0       7.0         48        18

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      80.0       5.0         64        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           1.0      60.0      15.0         40        20

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0      16.0       1.0         16         0
hdisk3           1.0      32.0       2.0         32         0
hdisk1           1.0      96.0       6.0         96         0

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0      64.0       4.0         64         0
hdisk0           5.0     860.0     215.0          0       860

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk3           1.0      16.0       1.0         16         0

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           9.0     9128.0      41.0       9104        24
hdisk3           8.0     8064.0      32.0       8064         0
hdisk1           9.0     13136.0      59.0      13104        32
hdisk0           1.0      28.0       7.0          0        28

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           4.0     412.0     103.0          0       412

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk0           1.0      28.0       7.0          0        28

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk1           1.0      64.0       5.0         48        16
hdisk0           4.0     2928.0     567.0          0      2928

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           1.0      80.0       5.0         80         0
hdisk1           1.0     160.0      10.0        144        16

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk6           1.0     320.0      68.0        320         0
hdisk7           1.0     320.0      68.0        320         0

tty:      tin         tout    avg-cpu: % user % sys % idle % iowait

Disks:        % tm_act     Kbps      tps    Kb_read   Kb_wrtn
hdisk2           8.0     208.0      14.0        208         0
hdisk3          11.0     240.0      15.0        240         0
hdisk1           8.0     368.0      23.0        352        16
hdisk0           2.0     332.0      83.0          0       332

Code:
          2323024746 total address trans. faults
               462190 page ins
              6958561 page outs
                    0 paging space page ins
                    0 paging space page outs
                    0 total reclaims
            856457822 zero filled pages faults
             93763059 executable filled pages faults
                    0 pages examined by clock
                    0 revolutions of the clock hand
                    0 pages freed by the clock
             22398240 backtracks
                    0 free frame waits
                    0 extend XPT waits
               236328 pending I/O waits
              7420752 start I/Os
              4288502 iodones
           3934680209 cpu context switches
             64041885 device interrupts
             62118494 software interrupts
           1923454125 decrementer interrupts
             24698541 mpc-sent interrupts
             24698541 mpc-receive interrupts
              1200083 phantom interrupts
                    0 traps
          13938141199 syscalls
              8388608 memory pages
              8058736 lruable pages
              2428935 free pages
                    1 memory pools
              1404618 pinned pages
                 90.0 maxpin percentage
                  3.0 minperm percentage
                 90.0 maxperm percentage
                  4.7 numperm percentage
               384661 file pages
                  0.0 compressed percentage
                    0 compressed pages
                  4.7 numclient percentage
                 90.0 maxclient percentage
               384661 client pages
                    0 remote pageouts scheduled
                    5 pending disk I/Os blocked with no pbuf
                    0 paging space I/Os blocked with no psbuf
                 2228 filesystem I/Os blocked with no fsbuf
                 1537 client filesystem I/Os blocked with no fsbuf
                 4155 external pager filesystem I/Os blocked with no fsbuf
                 66.5 percentage of memory used for computational pages

# 6  
Old 11-24-2012
Code:
462190 page ins
6958561 page outs
...
856457822 zero filled pages faults

There is very little physical paging activity. What is happening a lot is the application is using memory for the first time and/or doing malloc.

Also, when physical i/o activity is taking place, you are writing 14x for each read
Code:
6958561/462190 (pages out / pages in)

Your high number is just showing what I hope is normal startup activity. You have lots of memory free - so file caching is easy (also explains why writes dominate read activity)

Last edited by MichaelFelt; 11-24-2012 at 12:35 PM.. Reason: correct layout of pasted data
# 7  
Old 11-25-2012
then i must consider that a normal activity, or i can configure the system to have minimum page faults?

you said that file caching is easy, can you explain better and eventually where i can find documentation that focus on this?

Thank you so much

p.s. i have opened a case with ibm/oracle and no one cannot solve/explain this problem..
Login or Register to Ask a Question

Previous Thread | Next Thread

10 More Discussions You Might Find Interesting

1. UNIX for Beginners Questions & Answers

New to AIX: How do I setup high availability on an AIX System

I am new to AIX but not new to unix. I have an interview for an AIX systems admin position and I know they want someone who has knowledge of High Availability, Failover and LPARs From my research so far, It appear powerha is used to setup high availability and failover on Power systems but is... (2 Replies)
Discussion started by: mathisecure
2 Replies

2. Solaris

Page faults on OS

Hi guys, I have a zone on a M5000 server running solaris 10. The zone has an SAP application running on it and facing some performance issues. As part of the troubleshooting, I've been recommended to look for any paging on the OS. Please advise how to look for the paging. I've been looking at... (4 Replies)
Discussion started by: frum
4 Replies

3. AIX

AIX high availability 1-3/69

Hi, Can someone help and give the answer for the following questions: 1. When PowerHA SystemMirror 7.1 is installed on AIX 7.1, what RSCT component does Cluster Aware AIX (CAA) replace? A. Group Services B. Resource Manager C. Topology Services D. Resource Monitoring and Control... (2 Replies)
Discussion started by: walterchang100
2 Replies

4. AIX

Lots of page faults on AIX mySQL lpar

Hi, OS = AIX 5.3 Large number of page faults recently start to occure on AIX 5.3 lpar with mysql database installed. I need help in setting AIX OS parameter to solve the paging problem and some guidance on interpreting my stats t Code: # vmstat... (5 Replies)
Discussion started by: crosys
5 Replies

5. AIX

Lots of page faults and free memory

Hello, I've been reading your forums for quite a while and the great amount of information I find here always come in hand.This time however, I need some specific help... I have a doubt with an AIX server which I'm failing to understand as I'm new to its concept of memory management... ... (8 Replies)
Discussion started by: flpgdt
8 Replies

6. Solaris

High Page In and Executable page In

Hi, Currently I'm experience very high page ins on my system running on solaris 10. From vmstat, the page ins figure is very high, further drill down shows the page ins are from file system and occassional spike in executable page ins. Details as follow: oracle@perch:/files>> vmstat 5... (9 Replies)
Discussion started by: srage
9 Replies

7. Solaris

Page Fault very high

Hi, We are running SUN sparc 5.8, notice frequent "Page Faults" message from our monitor s/w "ServerVantage" coming but no message display in SUN syslog or messages log. Any ideas why or what to check? thanks, Ahmad (2 Replies)
Discussion started by: Ahmad
2 Replies

8. AIX

High Page Faults

Sorry my poor english In 570 pseries nmon shows excessive page faults, ascents of something more than 30000 Page faults. System: AIX 5.2 ML5 Processor Type: PowerPC_POWER5 Number Of Processors: 2 Processor Clock Speed: 1656 MHz CPU Type: 64-bit Kernel Type: 64-bit Memory Size: 2816 MB ... (1 Reply)
Discussion started by: daviguez
1 Replies

9. HP-UX

Intransient blocking page faults

Hi, Will anybody tell me what is this 'intransient blocking page faults' in HP-UX, it is in the structure _pst_vminfo in the header file /ust/include/sys/pstat/vm_pstat_body.h? (4 Replies)
Discussion started by: sushaga
4 Replies

10. HP-UX

Copy on Write page faults

Hello Please can you tell me how to access COPY ON WRITE page faults in HP -UNIX. I found the structure in /usr/include/sys/vmmeter with the structure name vmmeter. Please tell me the function to fill the values to this structure and also the arguments for function.:: (5 Replies)
Discussion started by: manjunath
5 Replies
Login or Register to Ask a Question