summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_zone_alloc.c
diff options
context:
space:
mode:
authorChristoph Hellwig <hch@lst.de>2025-10-17 05:45:49 +0200
committerChristian Brauner <brauner@kernel.org>2025-10-29 15:54:31 +0100
commit015a54407782309c11655e1938bcbcef131ebf87 (patch)
treeeb814e06688a4d12c06424a60d497738b5a47c73 /fs/xfs/xfs_zone_alloc.c
parent90db4d4441f58d433ecf74f7e3bd17e0a553c20c (diff)
xfs: set s_min_writeback_pages for zoned file systems
Set s_min_writeback_pages to the zone size, so that writeback always writes up to a full zone. This ensures that writeback does not add spurious file fragmentation when writing back a large number of files that are larger than the zone size. Fixes: 4e4d52075577 ("xfs: add the zoned space allocator") Signed-off-by: Christoph Hellwig <hch@lst.de> Link: https://patch.msgid.link/20251017034611.651385-4-hch@lst.de Reviewed-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'fs/xfs/xfs_zone_alloc.c')
-rw-r--r--fs/xfs/xfs_zone_alloc.c28
1 files changed, 26 insertions, 2 deletions
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 1147bacb2da8..c342595acc3e 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -1215,6 +1215,7 @@ xfs_mount_zones(
.mp = mp,
};
struct xfs_buftarg *bt = mp->m_rtdev_targp;
+ xfs_extlen_t zone_blocks = mp->m_groups[XG_TYPE_RTG].blocks;
int error;
if (!bt) {
@@ -1245,10 +1246,33 @@ xfs_mount_zones(
return -ENOMEM;
xfs_info(mp, "%u zones of %u blocks (%u max open zones)",
- mp->m_sb.sb_rgcount, mp->m_groups[XG_TYPE_RTG].blocks,
- mp->m_max_open_zones);
+ mp->m_sb.sb_rgcount, zone_blocks, mp->m_max_open_zones);
trace_xfs_zones_mount(mp);
+ /*
+ * The writeback code switches between inodes regularly to provide
+ * fairness. The default lower bound is 4MiB, but for zoned file
+ * systems we want to increase that both to reduce seeks, but also more
+ * importantly so that workloads that writes files in a multiple of the
+ * zone size do not get fragmented and require garbage collection when
+ * they shouldn't. Increase is to the zone size capped by the max
+ * extent len.
+ *
+ * Note that because s_min_writeback_pages is a superblock field, this
+ * value also get applied to non-zoned files on the data device if
+ * there are any. On typical zoned setup all data is on the RT device
+ * because using the more efficient sequential write required zones
+ * is the reason for using the zone allocator, and either the RT device
+ * and the (meta)data device are on the same block device, or the
+ * (meta)data device is on a fast SSD while the data on the RT device
+ * is on a SMR HDD. In any combination of the above cases enforcing
+ * the higher min_writeback_pages for non-RT inodes is either a noop
+ * or beneficial.
+ */
+ mp->m_super->s_min_writeback_pages =
+ XFS_FSB_TO_B(mp, min(zone_blocks, XFS_MAX_BMBT_EXTLEN)) >>
+ PAGE_SHIFT;
+
if (bdev_is_zoned(bt->bt_bdev)) {
error = blkdev_report_zones(bt->bt_bdev,
XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart),