Update to my original post:
I found the following in vmstat truss output...
20157: open("/dev/kstat", O_RDONLY) = 3
20157: ioctl(3, KSTAT_IOC_CHAIN_ID, 0x00000000) = 59532
20157: ioctl(3, KSTAT_IOC_READ, "kstat_headers") Err#12 ENOMEM
And I found some references that suggest that maybe the buffer cache is too
large and should be tuned down via bufhwm in the system file. The server has
32G of memory and thousands of disks. Does anyone have experience tuning bufhwm
and could anyone provide any guidelines for managing buffer cache size.
Thanks,
Vic
--
This message posted from opensolaris.org
_______________________________________________
opensolaris-discuss mailing list
opensolaris-discuss@opensolaris.org
