From 845abeb1f06a8a44e21314460eeb14cddfca52cc Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Tue, 25 Mar 2025 09:10:49 +0000 Subject: [PATCH] xfs: add tunable threshold parameter for triggering zone GC Presently we start garbage collection late - when we start running out of free zones to backfill max_open_zones. This is a reasonable default as it minimizes write amplification. The longer we wait, the more blocks are invalidated and reclaim cost less in terms of blocks to relocate. Starting this late however introduces a risk of GC being outcompeted by user writes. If GC can't keep up, user writes will be forced to wait for free zones with high tail latencies as a result. This is not a problem under normal circumstances, but if fragmentation is bad and user write pressure is high (multiple full-throttle writers) we will "bottom out" of free zones. To mitigate this, introduce a zonegc_low_space tunable that lets the user specify a percentage of how much of the unused space that GC should keep available for writing. A high value will reclaim more of the space occupied by unused blocks, creating a larger buffer against write bursts. This comes at a cost as write amplification is increased. To illustrate this using a sample workload, setting zonegc_low_space to 60% avoids high (500ms) max latencies while increasing write amplification by 15%. Signed-off-by: Hans Holmberg Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- Documentation/admin-guide/xfs.rst | 21 ++++++++++++++++++++ fs/xfs/xfs_mount.h | 1 + fs/xfs/xfs_sysfs.c | 32 +++++++++++++++++++++++++++++++ fs/xfs/xfs_zone_alloc.c | 7 +++++++ fs/xfs/xfs_zone_gc.c | 16 ++++++++++++++-- 5 files changed, 75 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst index b67772cf36d6..7b0811d650f9 100644 --- a/Documentation/admin-guide/xfs.rst +++ b/Documentation/admin-guide/xfs.rst @@ -542,3 +542,24 @@ The interesting knobs for XFS workqueues are as follows: nice Relative priority of scheduling the threads. These are the same nice levels that can be applied to userspace processes. ============ =========== + +Zoned Filesystems +================= + +For zoned file systems, the following attributes are exposed in: + + /sys/fs/xfs//zoned/ + + max_open_zones (Min: 1 Default: Varies Max: UINTMAX) + This read-only attribute exposes the maximum number of open zones + available for data placement. The value is determined at mount time and + is limited by the capabilities of the backing zoned device, file system + size and the max_open_zones mount option. + + zonegc_low_space (Min: 0 Default: 0 Max: 100) + Define a percentage for how much of the unused space that GC should keep + available for writing. A high value will reclaim more of the space + occupied by unused blocks, creating a larger buffer against write + bursts at the cost of increased write amplification. Regardless + of this value, garbage collection will always aim to free a minimum + amount of blocks to keep max_open_zones open for data placement purposes. diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 799b84220ebb..e5192c12e7ac 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -229,6 +229,7 @@ typedef struct xfs_mount { bool m_finobt_nores; /* no per-AG finobt resv. */ bool m_update_sb; /* sb needs update in mount */ unsigned int m_max_open_zones; + unsigned int m_zonegc_low_space; /* * Bitsets of per-fs metadata that have been checked and/or are sick. diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index b7e82d85f043..7a5c5ef2db92 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -718,8 +718,40 @@ max_open_zones_show( } XFS_SYSFS_ATTR_RO(max_open_zones); +static ssize_t +zonegc_low_space_store( + struct kobject *kobj, + const char *buf, + size_t count) +{ + int ret; + unsigned int val; + + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; + + if (val > 100) + return -EINVAL; + + zoned_to_mp(kobj)->m_zonegc_low_space = val; + + return count; +} + +static ssize_t +zonegc_low_space_show( + struct kobject *kobj, + char *buf) +{ + return sysfs_emit(buf, "%u\n", + zoned_to_mp(kobj)->m_zonegc_low_space); +} +XFS_SYSFS_ATTR_RW(zonegc_low_space); + static struct attribute *xfs_zoned_attrs[] = { ATTR_LIST(max_open_zones), + ATTR_LIST(zonegc_low_space), NULL, }; ATTRIBUTE_GROUPS(xfs_zoned); diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 52af234936a2..d509e49b2aaa 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -1201,6 +1201,13 @@ xfs_mount_zones( xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, iz.available + iz.reclaimable); + /* + * The user may configure GC to free up a percentage of unused blocks. + * By default this is 0. GC will always trigger at the minimum level + * for keeping max_open_zones available for data placement. + */ + mp->m_zonegc_low_space = 0; + error = xfs_zone_gc_mount(mp); if (error) goto out_free_zone_info; diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index c5136ea9bb1d..8c541ca71872 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -162,18 +162,30 @@ struct xfs_zone_gc_data { /* * We aim to keep enough zones free in stock to fully use the open zone limit - * for data placement purposes. + * for data placement purposes. Additionally, the m_zonegc_low_space tunable + * can be set to make sure a fraction of the unused blocks are available for + * writing. */ bool xfs_zoned_need_gc( struct xfs_mount *mp) { + s64 available, free; + if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE)) return false; - if (xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE) < + + available = xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE); + + if (available < mp->m_groups[XG_TYPE_RTG].blocks * (mp->m_max_open_zones - XFS_OPEN_GC_ZONES)) return true; + + free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS); + if (available < mult_frac(free, mp->m_zonegc_low_space, 100)) + return true; + return false; } -- 2.25.1