Hello listers, In the mon_procd task summary I have found data that was not what I had expected. We are running SLES10 SP2, kernel level 2.6.16.60.
The fields for disk read/write (mem_pgpgin, mem_pgpgout) and swappages in/out (swap_pswpin, swap_pswpout) looks like to be cumulative fields. So in my calculations I subtract the previous value to get the actual KB read or written for that minute. After we restarted the guest in a different LPAR the cumulative VM data, such as DASD IO and various samples, is reset so the counters start at 0. But the fields in mon_procd look like to continue counting. So instead of starting at 0 they start at whatever value they were when shutdown. Time mem_pgpgin mem_pgpgout 00:14 27747899416 5773305824 00:15 27747900536 5773311568 ... guest logged off ... 00:19 27747901064 5773337360 00:20 27747905464 5773342720 Why are these fields not reset to 0 after a reboot? Met vriendelijke groet/With kind regards, Berry van Sleeuwen Flight Forum 3000 5657 EW Eindhoven * +31 (0)6 22564276 [cid:325312309@02022011-28C1] [cid:325312309@02022011-28C8] ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For more information on Linux on System z, visit http://wiki.linuxvm.org/
<<inline: image001.gif>>
<<inline: image002.jpg>>
