File tree Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Original file line number Diff line number Diff line change @@ -1778,7 +1778,7 @@ Normally disabled because these datasets may be missing key data.
1778
1778
.It Sy zfs_min_metaslabs_to_flush Ns = Ns Sy 1 Pq u64
1779
1779
Minimum number of metaslabs to flush per dirty TXG.
1780
1780
.
1781
- .It Sy zfs_metaslab_fragmentation_threshold Ns = Ns Sy 85 Ns % Pq uint
1781
+ .It Sy zfs_metaslab_fragmentation_threshold Ns = Ns Sy 77 Ns % Pq uint
1782
1782
Allow metaslabs to keep their active state as long as their fragmentation
1783
1783
percentage is no more than this value.
1784
1784
An active metaslab that exceeds this threshold
Original file line number Diff line number Diff line change @@ -146,7 +146,7 @@ static uint_t zfs_mg_fragmentation_threshold = 95;
146
146
* active metaslab that exceeds this threshold will no longer keep its active
147
147
* status allowing better metaslabs to be selected.
148
148
*/
149
- static uint_t zfs_metaslab_fragmentation_threshold = 85 ;
149
+ static uint_t zfs_metaslab_fragmentation_threshold = 77 ;
150
150
151
151
/*
152
152
* When set will load all metaslabs when pool is first opened.
@@ -2901,7 +2901,7 @@ metaslab_fini(metaslab_t *msp)
2901
2901
* Conversely, if the metric is low, then most of the free space is in
2902
2902
* large segments.
2903
2903
*
2904
- * This table defines 0% fragmented space using 1G segments. Using this value,
2904
+ * This table defines 0% fragmented space using 512M segments. Using this value,
2905
2905
* we derive the rest of the table. This table originally went up to 16MB, but
2906
2906
* with larger recordsizes, larger ashifts, and use of raidz3, it is possible
2907
2907
* to have significantly larger allocations than were previously possible.
You can’t perform that action at this time.
0 commit comments