Subject: | |
From: | |
Reply To: | |
Date: | Thu, 10 Aug 2000 08:22:57 -0700 |
Content-Type: | text/plain |
Parts/Attachments: |
|
|
Michael wrote:
>From time to time, or randomly throughout the day I have seen (In GLANCE) P11 MANAGER.SYS >take up all our DISC I/O. The event will
last for a minute or two, and in that period of time all other >process seem to hang. After P11 finishes doing whatever it was
doing, everything continues to run >fine. My question is; Can anyone tell me what P11 is doing. The machine in question is run
MPE/iX >5.5 pp7.
This is probably the xm check point server. The way to tell is to have Glance produce
a stack trace or, in DEBUG you can do this:
$1 ($7f) nmdebug > pin #11;tr,d,i
------------------
And you could see something like this if Pin 11 is waited at the time you do it:
PC=a.0018170c enable_int+$2c
NM* 0) SP=41636770 RP=a.00f68908 notify_dispatcher.block_current_process+$324
NM 1) SP=41636770 RP=a.00f6ad90 notify_dispatcher+$264
NM 2) SP=416366f0 RP=a.001b1c20 wait_for_active_port+$ec
NM 3) SP=416365f0 RP=a.001b28a0 receive_from_port+$534
NM 4) SP=41636570 RP=a.00355efc extend_receive+$494
NM 5) SP=41636370 RP=a.00606c70 xm_static_checkpoint_server+$80
NM 6) SP=416361f0 RP=a.0052fbf0 outer_block+$14c
NM 7) SP=41636130 RP=a.00000000
(end of NM stack)
If this process is actively running at the time you attempt the trace you may see other
procedures listed above 'xm_static_checkpoint_server' (naturally!).
If you have a lot of activity (changes) in files covered by XM such as Image data
bases or KSAM/XL files the XM checkpoint server will need to run often. This is a
typical reason for XM overhead but certainly not the only reason.
I hope this helps!
Bill
HP/CSY
|
|
|