On Mar 1, 2008, at 7:22 PM, Roch Bourbonnais wrote: > That's not entirely accurate. I believe ZFS does lead to > bdev_strategy being called and io:::start > will fire for ZFS I/Os. The problem is that a ZFS I/O can be > servicing a number of ZFS operations on a > number of different files (which is a great performance enabler). > Given that we can't map an I/O to a file, > iosnoop does not report the file info.
yep - bdev_strategy gets called through ldi_strategy, but this is only going to happen after the ZIO pipeline in vdev_io_start() .. and since the ZIO pipeline gets filled from the dmu_tx routines (for the whole pool), i guess it would make the most sense to look at the dmu_tx_create() entry from vnops (as Jeff already pointed out.) --- jonathan _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
