From c55b2932878c444e1bc627a7071787a0e5023d63 Mon Sep 17 00:00:00 2001 From: Alexander Motin Date: Wed, 4 May 2022 14:33:42 -0400 Subject: Improve mg_aliquot math When calculating mg_aliquot alike to #12046 use number of unique data disks in the vdev, not the total number of children vdev. Increase default value of the tunable from 512KB to 1MB to compensate. Before this change each disk in striped pool was getting 512KB of sequential data, in 2-wide mirror -- 1MB, in 3-wide RAIDZ1 -- 768KB. After this change in all the cases each disk should get 1MB. Reviewed-by: Brian Behlendorf Reviewed-by: Ryan Moeller Signed-off-by: Alexander Motin Sponsored-By: iXsystems, Inc. Closes #13388 --- module/zfs/metaslab.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'module') diff --git a/module/zfs/metaslab.c b/module/zfs/metaslab.c index f9c16f00d..ab32bfec1 100644 --- a/module/zfs/metaslab.c +++ b/module/zfs/metaslab.c @@ -48,10 +48,10 @@ /* * Metaslab granularity, in bytes. This is roughly similar to what would be * referred to as the "stripe size" in traditional RAID arrays. In normal - * operation, we will try to write this amount of data to a top-level vdev - * before moving on to the next one. + * operation, we will try to write this amount of data to each disk before + * moving on to the next top-level vdev. */ -static unsigned long metaslab_aliquot = 512 << 10; +static unsigned long metaslab_aliquot = 1024 * 1024; /* * For testing, make some blocks above a certain size be gang blocks. @@ -899,7 +899,8 @@ metaslab_group_activate(metaslab_group_t *mg) if (++mg->mg_activation_count <= 0) return; - mg->mg_aliquot = metaslab_aliquot * MAX(1, mg->mg_vd->vdev_children); + mg->mg_aliquot = metaslab_aliquot * MAX(1, + vdev_get_ndisks(mg->mg_vd) - vdev_get_nparity(mg->mg_vd)); metaslab_group_alloc_update(mg); if ((mgprev = mc->mc_allocator[0].mca_rotor) == NULL) { -- cgit v1.2.3