| Message ID | 20250206064511.2323878-42-hch@lst.de (mailing list archive) |
|---|---|
| State | Not Applicable, archived |
| Headers | show |
| Series | [01/43] xfs: factor out a xfs_rt_check_size helper | expand |
On Thu, Feb 06, 2025 at 07:44:57AM +0100, Christoph Hellwig wrote: > From: Hans Holmberg <hans.holmberg@wdc.com> > > Add the per-zone life time hint and the used block distribution > for fully written zones, grouping reclaimable zones in fixed-percentage > buckets spanning 0..9%, 10..19% and full zones as 100% used as well as a > few statistics about the zone allocator and open and reclaimable zones > in /proc/*/mountstats. I'm kinda surprised you didn't export this via sysfs, but then remembered that Greg has strict rules against tabular data and whatnot. > This gives good insight into data fragmentation and data placement > success rate. I hope it's worth exporting a bunch of stringly-structured data. ;) Past me would've asked if we could just export some json and let userspace pick that up, but today me learned about the horrors of json and how it represents integers, stumbling over trailing commas, etc. Is any of this getting wired up into a zone-top tool? The /proc dump looks ok to me... Reviewed-by: "Darrick J. Wong" <djwong@kernel.org> --D > Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com> > Co-developed-by: Christoph Hellwig <hch@lst.de> > Signed-off-by: Christoph Hellwig <hch@lst.de> > --- > fs/xfs/Makefile | 1 + > fs/xfs/xfs_super.c | 4 ++ > fs/xfs/xfs_zone_alloc.h | 1 + > fs/xfs/xfs_zone_info.c | 105 ++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 111 insertions(+) > create mode 100644 fs/xfs/xfs_zone_info.c > > diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile > index e38838409271..5bf501cf8271 100644 > --- a/fs/xfs/Makefile > +++ b/fs/xfs/Makefile > @@ -140,6 +140,7 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ > xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o \ > xfs_zone_alloc.o \ > xfs_zone_gc.o \ > + xfs_zone_info.o \ > xfs_zone_space_resv.o > > xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o > diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c > index 134859a3719d..877332ffd84b 100644 > --- a/fs/xfs/xfs_super.c > +++ b/fs/xfs/xfs_super.c > @@ -1262,6 +1262,10 @@ xfs_fs_show_stats( > struct seq_file *m, > struct dentry *root) > { > + struct xfs_mount *mp = XFS_M(root->d_sb); > + > + if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT)) > + xfs_zoned_show_stats(m, mp); > return 0; > } > > diff --git a/fs/xfs/xfs_zone_alloc.h b/fs/xfs/xfs_zone_alloc.h > index 1269390bfcda..ecf39106704c 100644 > --- a/fs/xfs/xfs_zone_alloc.h > +++ b/fs/xfs/xfs_zone_alloc.h > @@ -44,6 +44,7 @@ void xfs_mark_rtg_boundary(struct iomap_ioend *ioend); > > uint64_t xfs_zoned_default_resblks(struct xfs_mount *mp, > enum xfs_free_counter ctr); > +void xfs_zoned_show_stats(struct seq_file *m, struct xfs_mount *mp); > > #ifdef CONFIG_XFS_RT > int xfs_mount_zones(struct xfs_mount *mp); > diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c > new file mode 100644 > index 000000000000..7ba0a5931c99 > --- /dev/null > +++ b/fs/xfs/xfs_zone_info.c > @@ -0,0 +1,105 @@ > +// SPDX-License-Identifier: GPL-2.0 > +/* > + * Copyright (c) 2023-2025 Christoph Hellwig. > + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. > + */ > +#include "xfs.h" > +#include "xfs_shared.h" > +#include "xfs_format.h" > +#include "xfs_trans_resv.h" > +#include "xfs_mount.h" > +#include "xfs_inode.h" > +#include "xfs_rtgroup.h" > +#include "xfs_zone_alloc.h" > +#include "xfs_zone_priv.h" > + > +static const char xfs_write_hint_shorthand[6][16] = { > + "NOT_SET", "NONE", "SHORT", "MEDIUM", "LONG", "EXTREME"}; > + > +static inline const char * > +xfs_write_hint_to_str( > + uint8_t write_hint) > +{ > + if (write_hint > WRITE_LIFE_EXTREME) > + return "UNKNOWN"; > + return xfs_write_hint_shorthand[write_hint]; > +} > + > +static void > +xfs_show_open_zone( > + struct seq_file *m, > + struct xfs_open_zone *oz) > +{ > + seq_printf(m, "\t zone %d, wp %u, written %u, used %u, hint %s\n", > + rtg_rgno(oz->oz_rtg), > + oz->oz_write_pointer, oz->oz_written, > + rtg_rmap(oz->oz_rtg)->i_used_blocks, > + xfs_write_hint_to_str(oz->oz_write_hint)); > +} > + > +static void > +xfs_show_full_zone_used_distribution( > + struct seq_file *m, > + struct xfs_mount *mp) > +{ > + struct xfs_zone_info *zi = mp->m_zone_info; > + unsigned int reclaimable = 0, full, i; > + > + spin_lock(&zi->zi_used_buckets_lock); > + for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) { > + unsigned int entries = zi->zi_used_bucket_entries[i]; > + > + seq_printf(m, "\t %2u..%2u%%: %u\n", > + i * (100 / XFS_ZONE_USED_BUCKETS), > + (i + 1) * (100 / XFS_ZONE_USED_BUCKETS) - 1, > + entries); > + reclaimable += entries; > + } > + spin_unlock(&zi->zi_used_buckets_lock); > + > + full = mp->m_sb.sb_rgcount; > + if (zi->zi_open_gc_zone) > + full--; > + full -= zi->zi_nr_open_zones; > + full -= atomic_read(&zi->zi_nr_free_zones); > + full -= reclaimable; > + > + seq_printf(m, "\t 100%%: %u\n", full); > +} > + > +void > +xfs_zoned_show_stats( > + struct seq_file *m, > + struct xfs_mount *mp) > +{ > + struct xfs_zone_info *zi = mp->m_zone_info; > + struct xfs_open_zone *oz; > + > + seq_puts(m, "\n"); > + > + seq_printf(m, "\tuser free RT blocks: %lld\n", > + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); > + seq_printf(m, "\treserved free RT blocks: %lld\n", > + mp->m_resblks[XC_FREE_RTEXTENTS].avail); > + seq_printf(m, "\tuser available RT blocks: %lld\n", > + xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE)); > + seq_printf(m, "\treserved available RT blocks: %lld\n", > + mp->m_resblks[XC_FREE_RTAVAILABLE].avail); > + seq_printf(m, "\tRT reservations required: %d\n", > + !list_empty_careful(&zi->zi_reclaim_reservations)); > + seq_printf(m, "\tRT GC required: %d\n", > + xfs_zoned_need_gc(mp)); > + > + seq_printf(m, "\tfree zones: %d\n", atomic_read(&zi->zi_nr_free_zones)); > + seq_puts(m, "\topen zones:\n"); > + spin_lock(&zi->zi_open_zones_lock); > + list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) > + xfs_show_open_zone(m, oz); > + if (zi->zi_open_gc_zone) { > + seq_puts(m, "\topen gc zone:\n"); > + xfs_show_open_zone(m, zi->zi_open_gc_zone); > + } > + spin_unlock(&zi->zi_open_zones_lock); > + seq_puts(m, "\tused blocks distribution (fully written zones):\n"); > + xfs_show_full_zone_used_distribution(m, mp); > +} > -- > 2.45.2 > >
On Thu, Feb 06, 2025 at 05:02:24PM -0800, Darrick J. Wong wrote: > I'm kinda surprised you didn't export this via sysfs, but then > remembered that Greg has strict rules against tabular data and whatnot. > > > This gives good insight into data fragmentation and data placement > > success rate. > > I hope it's worth exporting a bunch of stringly-structured data. ;) > > Past me would've asked if we could just export some json and let > userspace pick that up, but today me learned about the horrors of json > and how it represents integers, stumbling over trailing commas, etc. Yeah, this is really mostly used for human debugging at the moment. > Is any of this getting wired up into a zone-top tool? Heh, for that we'd actually need to commit to a stable format. But it does sound interesting. Combine with information from fsmap for the persistent space usage on disk.
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index e38838409271..5bf501cf8271 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -140,6 +140,7 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o \ xfs_zone_alloc.o \ xfs_zone_gc.o \ + xfs_zone_info.o \ xfs_zone_space_resv.o xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 134859a3719d..877332ffd84b 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1262,6 +1262,10 @@ xfs_fs_show_stats( struct seq_file *m, struct dentry *root) { + struct xfs_mount *mp = XFS_M(root->d_sb); + + if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT)) + xfs_zoned_show_stats(m, mp); return 0; } diff --git a/fs/xfs/xfs_zone_alloc.h b/fs/xfs/xfs_zone_alloc.h index 1269390bfcda..ecf39106704c 100644 --- a/fs/xfs/xfs_zone_alloc.h +++ b/fs/xfs/xfs_zone_alloc.h @@ -44,6 +44,7 @@ void xfs_mark_rtg_boundary(struct iomap_ioend *ioend); uint64_t xfs_zoned_default_resblks(struct xfs_mount *mp, enum xfs_free_counter ctr); +void xfs_zoned_show_stats(struct seq_file *m, struct xfs_mount *mp); #ifdef CONFIG_XFS_RT int xfs_mount_zones(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c new file mode 100644 index 000000000000..7ba0a5931c99 --- /dev/null +++ b/fs/xfs/xfs_zone_info.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Christoph Hellwig. + * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates. + */ +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_rtgroup.h" +#include "xfs_zone_alloc.h" +#include "xfs_zone_priv.h" + +static const char xfs_write_hint_shorthand[6][16] = { + "NOT_SET", "NONE", "SHORT", "MEDIUM", "LONG", "EXTREME"}; + +static inline const char * +xfs_write_hint_to_str( + uint8_t write_hint) +{ + if (write_hint > WRITE_LIFE_EXTREME) + return "UNKNOWN"; + return xfs_write_hint_shorthand[write_hint]; +} + +static void +xfs_show_open_zone( + struct seq_file *m, + struct xfs_open_zone *oz) +{ + seq_printf(m, "\t zone %d, wp %u, written %u, used %u, hint %s\n", + rtg_rgno(oz->oz_rtg), + oz->oz_write_pointer, oz->oz_written, + rtg_rmap(oz->oz_rtg)->i_used_blocks, + xfs_write_hint_to_str(oz->oz_write_hint)); +} + +static void +xfs_show_full_zone_used_distribution( + struct seq_file *m, + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + unsigned int reclaimable = 0, full, i; + + spin_lock(&zi->zi_used_buckets_lock); + for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) { + unsigned int entries = zi->zi_used_bucket_entries[i]; + + seq_printf(m, "\t %2u..%2u%%: %u\n", + i * (100 / XFS_ZONE_USED_BUCKETS), + (i + 1) * (100 / XFS_ZONE_USED_BUCKETS) - 1, + entries); + reclaimable += entries; + } + spin_unlock(&zi->zi_used_buckets_lock); + + full = mp->m_sb.sb_rgcount; + if (zi->zi_open_gc_zone) + full--; + full -= zi->zi_nr_open_zones; + full -= atomic_read(&zi->zi_nr_free_zones); + full -= reclaimable; + + seq_printf(m, "\t 100%%: %u\n", full); +} + +void +xfs_zoned_show_stats( + struct seq_file *m, + struct xfs_mount *mp) +{ + struct xfs_zone_info *zi = mp->m_zone_info; + struct xfs_open_zone *oz; + + seq_puts(m, "\n"); + + seq_printf(m, "\tuser free RT blocks: %lld\n", + xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS)); + seq_printf(m, "\treserved free RT blocks: %lld\n", + mp->m_resblks[XC_FREE_RTEXTENTS].avail); + seq_printf(m, "\tuser available RT blocks: %lld\n", + xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE)); + seq_printf(m, "\treserved available RT blocks: %lld\n", + mp->m_resblks[XC_FREE_RTAVAILABLE].avail); + seq_printf(m, "\tRT reservations required: %d\n", + !list_empty_careful(&zi->zi_reclaim_reservations)); + seq_printf(m, "\tRT GC required: %d\n", + xfs_zoned_need_gc(mp)); + + seq_printf(m, "\tfree zones: %d\n", atomic_read(&zi->zi_nr_free_zones)); + seq_puts(m, "\topen zones:\n"); + spin_lock(&zi->zi_open_zones_lock); + list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) + xfs_show_open_zone(m, oz); + if (zi->zi_open_gc_zone) { + seq_puts(m, "\topen gc zone:\n"); + xfs_show_open_zone(m, zi->zi_open_gc_zone); + } + spin_unlock(&zi->zi_open_zones_lock); + seq_puts(m, "\tused blocks distribution (fully written zones):\n"); + xfs_show_full_zone_used_distribution(m, mp); +}