Philippe Magerus - SUN Service - Luxembourg wrote:
there should be a tunable for max number of cached znodes/dnodes as there is in other file systems.
...
As for arc.c_max, it should be settable via /etc/system.
No, there should not be tunables. The system should simply work. We need to diagnose down to the root cause of this problem, not simply introduce workarounds.
zio... caches should be skipped by the dump process.
Yep, there is a bug on this: 4894692 "caching data in heap inflates crash dump"
--matt _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
