Fix manual description of zfs_arc_dnode_limit

In arc_evict_state() we start pruning when arc_dnode_size >
arc_dnode_limit, i.e. arc_dnode_limit is a ceiling rather than a
floor.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chris Dunlop <chris@onthe.net.au>
Closes #6228
This commit is contained in:
chrisrd 2017-06-15 06:23:02 +10:00 committed by Brian Behlendorf
parent 8f7933fec9
commit 627791f3c0

View File

@ -412,7 +412,7 @@ Default value: \fB2\fR.
.RS 12n
When the number of bytes consumed by dnodes in the ARC exceeds this number of
bytes, try to unpin some of it in response to demand for non-metadata. This
value acts as a floor to the amount of dnode metadata, and defaults to 0 which
value acts as a ceiling to the amount of dnode metadata, and defaults to 0 which
indicates that a percent which is based on \fBzfs_arc_dnode_limit_percent\fR of
the ARC meta buffers that may be used for dnodes.