@@ -4256,6 +4256,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
block_group->flags);
btrfs_lock_block_group(block_group,
ffe_ctl->delalloc);
+ ffe_ctl->hinted = true;
goto have_block_group;
}
} else if (block_group) {
@@ -4263,6 +4264,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
}
}
search:
+ trace_find_free_extent_search_loop(root, ffe_ctl);
ffe_ctl->have_caching_bg = false;
if (ffe_ctl->index == btrfs_bg_flags_to_raid_index(ffe_ctl->flags) ||
ffe_ctl->index == 0)
@@ -4272,6 +4274,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
&space_info->block_groups[ffe_ctl->index], list) {
struct btrfs_block_group *bg_ret;
+ ffe_ctl->hinted = false;
/* If the block group is read-only, we can skip it entirely. */
if (unlikely(block_group->ro)) {
if (ffe_ctl->for_treelog)
@@ -4313,6 +4316,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
}
have_block_group:
+ trace_find_free_extent_have_block_group(root, ffe_ctl, block_group);
ffe_ctl->cached = btrfs_block_group_done(block_group);
if (unlikely(!ffe_ctl->cached)) {
ffe_ctl->have_caching_bg = true;
@@ -75,6 +75,9 @@ struct find_free_extent_ctl {
/* Allocation policy */
enum btrfs_extent_allocation_policy policy;
+
+ /* Whether or not the allocator is currently following a hint */
+ bool hinted;
};
@@ -1268,6 +1268,79 @@ TRACE_EVENT(find_free_extent,
BTRFS_GROUP_FLAGS))
);
+TRACE_EVENT(find_free_extent_search_loop,
+
+ TP_PROTO(const struct btrfs_root *root,
+ const struct find_free_extent_ctl *ffe_ctl),
+
+ TP_ARGS(root, ffe_ctl),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, root_objectid )
+ __field( u64, num_bytes )
+ __field( u64, empty_size )
+ __field( u64, flags )
+ __field( u64, loop )
+ ),
+
+ TP_fast_assign_btrfs(root->fs_info,
+ __entry->root_objectid = root->root_key.objectid;
+ __entry->num_bytes = ffe_ctl->num_bytes;
+ __entry->empty_size = ffe_ctl->empty_size;
+ __entry->flags = ffe_ctl->flags;
+ __entry->loop = ffe_ctl->loop;
+ ),
+
+ TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s) loop=%llu",
+ show_root_type(__entry->root_objectid),
+ __entry->num_bytes, __entry->empty_size, __entry->flags,
+ __print_flags((unsigned long)__entry->flags, "|",
+ BTRFS_GROUP_FLAGS),
+ __entry->loop)
+);
+
+TRACE_EVENT(find_free_extent_have_block_group,
+
+ TP_PROTO(const struct btrfs_root *root,
+ const struct find_free_extent_ctl *ffe_ctl,
+ const struct btrfs_block_group *block_group),
+
+ TP_ARGS(root, ffe_ctl, block_group),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, root_objectid )
+ __field( u64, num_bytes )
+ __field( u64, empty_size )
+ __field( u64, flags )
+ __field( u64, loop )
+ __field( bool, hinted )
+ __field( u64, bg_start )
+ __field( u64, bg_flags )
+ ),
+
+ TP_fast_assign_btrfs(root->fs_info,
+ __entry->root_objectid = root->root_key.objectid;
+ __entry->num_bytes = ffe_ctl->num_bytes;
+ __entry->empty_size = ffe_ctl->empty_size;
+ __entry->flags = ffe_ctl->flags;
+ __entry->loop = ffe_ctl->loop;
+ __entry->hinted = ffe_ctl->hinted;
+ __entry->bg_start = block_group->start;
+ __entry->bg_flags = block_group->flags;
+ ),
+
+ TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s) "
+ "loop=%llu hinted=%d block_group=%llu bg_flags=%llu(%s)",
+ show_root_type(__entry->root_objectid),
+ __entry->num_bytes, __entry->empty_size, __entry->flags,
+ __print_flags((unsigned long)__entry->flags, "|",
+ BTRFS_GROUP_FLAGS),
+ __entry->loop, __entry->hinted,
+ __entry->bg_start, __entry->bg_flags,
+ __print_flags((unsigned long)__entry->bg_flags, "|",
+ BTRFS_GROUP_FLAGS))
+);
+
DECLARE_EVENT_CLASS(btrfs__reserve_extent,
TP_PROTO(const struct btrfs_block_group *block_group,
@@ -1280,6 +1353,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
__field( u64, flags )
__field( u64, start )
__field( u64, len )
+ __field( u64, loop )
+ __field( bool, hinted )
),
TP_fast_assign_btrfs(block_group->fs_info,
@@ -1287,15 +1362,17 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
__entry->flags = block_group->flags;
__entry->start = ffe_ctl->search_start;
__entry->len = ffe_ctl->num_bytes;
+ __entry->loop = ffe_ctl->loop;
+ __entry->hinted = ffe_ctl->hinted;
),
TP_printk_btrfs("root=%llu(%s) block_group=%llu flags=%llu(%s) "
- "start=%llu len=%llu",
+ "start=%llu len=%llu loop=%llu hinted=%d",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
__entry->bg_objectid,
__entry->flags, __print_flags((unsigned long)__entry->flags,
"|", BTRFS_GROUP_FLAGS),
- __entry->start, __entry->len)
+ __entry->start, __entry->len, __entry->loop, __entry->hinted)
);
DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent,
find_free_extent is a complicated function. It consists (at least) of: - a hint that jumps into the middle of a for loop macro - a middle loop trying every raid level - an outer loop ascending through ffe loop levels - complicated logic for skipping some of those ffe loop levels - multiple underlying in-bg allocators (zoned, cluster, no cluster) Which is all to say that more tracing is helpful for debugging its behavior. Add two new tracepoints: at the entrance to the block_groups loop (hit for every raid level and every ffe_ctl loop) and at the point we seriously consider a block_group for allocation. This way we can see the whole path through the algorithm, including hints, multiple loops, etc. Signed-off-by: Boris Burkov <boris@bur.io> --- fs/btrfs/extent-tree.c | 4 ++ fs/btrfs/extent-tree.h | 3 ++ include/trace/events/btrfs.h | 81 +++++++++++++++++++++++++++++++++++- 3 files changed, 86 insertions(+), 2 deletions(-)