diff options
| -rw-r--r-- | man/man5/zfs-module-parameters.5 | 2 | ||||
| -rw-r--r-- | module/zfs/metaslab.c | 25 |
2 files changed, 21 insertions, 6 deletions
diff --git a/man/man5/zfs-module-parameters.5 b/man/man5/zfs-module-parameters.5 index 5bca12e06..282563f13 100644 --- a/man/man5/zfs-module-parameters.5 +++ b/man/man5/zfs-module-parameters.5 @@ -1817,7 +1817,7 @@ this value. If a metaslab group exceeds this threshold then it will be skipped unless all metaslab groups within the metaslab class have also crossed this threshold. .sp -Default value: \fB85\fR. +Default value: \fB95\fR. .RE .sp diff --git a/module/zfs/metaslab.c b/module/zfs/metaslab.c index ec89810b4..d1d5a243f 100644 --- a/module/zfs/metaslab.c +++ b/module/zfs/metaslab.c @@ -103,12 +103,27 @@ int zfs_mg_noalloc_threshold = 0; /* * Metaslab groups are considered eligible for allocations if their - * fragmenation metric (measured as a percentage) is less than or equal to - * zfs_mg_fragmentation_threshold. If a metaslab group exceeds this threshold - * then it will be skipped unless all metaslab groups within the metaslab - * class have also crossed this threshold. + * fragmenation metric (measured as a percentage) is less than or + * equal to zfs_mg_fragmentation_threshold. If a metaslab group + * exceeds this threshold then it will be skipped unless all metaslab + * groups within the metaslab class have also crossed this threshold. + * + * This tunable was introduced to avoid edge cases where we continue + * allocating from very fragmented disks in our pool while other, less + * fragmented disks, exists. On the other hand, if all disks in the + * pool are uniformly approaching the threshold, the threshold can + * be a speed bump in performance, where we keep switching the disks + * that we allocate from (e.g. we allocate some segments from disk A + * making it bypassing the threshold while freeing segments from disk + * B getting its fragmentation below the threshold). + * + * Empirically, we've seen that our vdev selection for allocations is + * good enough that fragmentation increases uniformly across all vdevs + * the majority of the time. Thus we set the threshold percentage high + * enough to avoid hitting the speed bump on pools that are being pushed + * to the edge. */ -int zfs_mg_fragmentation_threshold = 85; +int zfs_mg_fragmentation_threshold = 95; /* * Allow metaslabs to keep their active state as long as their fragmentation |