Jonathan Edwards wrote: > > On Mar 1, 2008, at 4:14 PM, Bill Shannon wrote: >> Ok, that's much better! At least I'm getting output when I touch files >> on zfs. However, even though zpool iostat is reporting activity, the >> above program isn't showing any file accesses when the system is idle. >> >> Any ideas? > > assuming that you're running an interval (ie: zpool iostat -v 5) and > skipping past the initial summary .. you know it's not file read/write > activity .. you might want to check other vop calls .. eg: > http://blogs.sun.com/erickustarz/resource/zvop_times_fsid.d > > to see what's happening .. scrubs or silvering perhaps?
I ended up combining a few programs (cut & paste programming without really understanding what I was doing!) and ended up with a program that traces all the zfs_* entry points. Based on the data I'm getting from that, correlated with the zpool iostat output, it appears that the culprit is ksh93! It seems that ksh93 is doing a setattr call of some sort on the .history file. I think I've reached the limit of what I can do remotely. Now I have to repeat all these experiments when I'm sitting next to the disk and can actually hear it and see if the correlation remains. Then, it may be time to dig into the ksh93 code and figure out what it thinks it's doing. Fortunately, I've been there before... Thanks everyone for the help! _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
