Howdy!
I was doing some stress testing of a SCSI chain on a 4.6.2 system
with 2 big RAID volumes by just having lots of processes moving lots
of data over the SCSI buss.
The box has fxp network interfaces with polling enabled.
the kernel config has
options HZ=1000.
kern.polling.user_frac = 50
During the testing the following messages started to appear in the logs.
/kernel: poll stalled [65] in phase 2
/kernel: poll stalled [66] in phase 2
/kernel: poll stalled [67] in phase 2
.. etc
Also I was unable to ssh to the box during this period. So I
figure that the polling system needs to be tuned. Do I need increase
the clock (options HZ) and/or increase/decrease kern.polling.user_frac?
or is this symtpmatic of some other problem?
-steve
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-stable" in the body of the message
