tracing: Up the hist stacktrace size from 16 to 31
Steven Rostedt
maintainerPATCH 1/1 tracing: Up the hist stacktrace size from 16 to 31
From: Steven Rostedt <[email protected]>
Recording stacktraces is very useful, but the size of 16 deep is very restrictive. For example, in seeing where tasks schedule out in a non running state, the following can be used:
~# cd /sys/kernel/tracing
~# echo 'hist:keys=common_stacktrace:vals=hitcount if prev_state & 3' > events/sched/sched_switch/trigger ~# cat events/sched/sched_switch/hist
[..]
{ common_stacktrace:
__schedule+0xdc0/0x1860
schedule+0x27/0xd0
schedule_timeout+0xb5/0x100
wait_for_completion+0x8a/0x140
xfs_buf_iowait+0x20/0xd0 [xfs]
xfs_buf_read_map+0x103/0x250 [xfs]
xfs_trans_read_buf_map+0x161/0x310 [xfs]
xfs_btree_read_buf_block+0xa0/0x120 [xfs]
xfs_btree_lookup_get_block+0xa3/0x1e0 [xfs]
xfs_btree_lookup+0xea/0x530 [xfs]
xfs_alloc_fixup_trees+0x72/0x570 [xfs]
xfs_alloc_ag_vextent_size+0x67f/0x800 [xfs]
xfs_alloc_vextent_iterate_ags.constprop.0+0x52/0x230 [xfs]
xfs_alloc_vextent_start_ag+0x9d/0x1b0 [xfs]
xfs_bmap_btalloc+0x2af/0x680 [xfs]
xfs_bmapi_allocate+0xdb/0x2c0 [xfs]} hitcount: 1
[..]
The above stops at 16 functions where knowing more would be useful. As the allocated storage for stacks is the same for strings, and that size is 256 bytes, there is a lot of space not being used for stacktraces.
16 * 8 = 128
Up the size to 31 (it requires the last slot to be zero, so it can't be 32).
Also change the BUILD_BUG_ON() to allow the size of the stacktrace storage to be equal to the max size. It already accounts for the empty slot via a "+ 1":
BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX);
Change that from ">=" to just ">", as now they are equal.
--- kernel/trace/trace.h | 2 +- kernel/trace/trace_events_hist.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
kernel/trace/trace.h +1 -1
@@ -128,7 +128,7 @@ enum trace_type {#define FAULT_STRING "(fault)" -#define HIST_STACKTRACE_DEPTH 16 +#define HIST_STACKTRACE_DEPTH 31#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long))#define HIST_STACKTRACE_SKIP 5
kernel/trace/trace_events_hist.c +1 -1
@@ -3154,7 +3154,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,u64 var_val;/* Make sure stacktrace can fit in the string variable length */ -BUILD_BUG_ON ((HIST_STACKTRACE_DEPTH +1 ) *sizeof (long ) >=STR_VAR_LEN_MAX ); +BUILD_BUG_ON ((HIST_STACKTRACE_DEPTH +1 ) *sizeof (long ) >STR_VAR_LEN_MAX );for (i =0 , j = field_var_str_start; i < n_field_vars; i++) {struct field_var *field_var = field_vars[i];
Signature · 1 line
2.51.0
Steven Rostedt
maintainerQuoted 3 lines · On Fri, 23 Jan 2026 10:54:15 -0500 Steven Rostedt <[email protected]> wrote:
Also change the
BUILD_BUG_ON()to allow the size of the stacktrace storage to be equal to the max size. It already accounts for the empty slot via a "+ 1":
Correction. One slot is used to hold the number of elements in the stack.
-- Steve
Hi Steve,
Quoted 30 lines · Steven Rostedt
From: Steven Rostedt <[email protected]>
Recording stacktraces is very useful, but the size of 16 deep is very restrictive. For example, in seeing where tasks schedule out in a non running state, the following can be used:
~# cd
/sys/kernel/tracing
~# echo 'hist:keys=common_stacktrace:vals=hitcount ifprev_state& 3' > events/sched/sched_switch/trigger ~# cat events/sched/sched_switch/hist
[..]
{common_stacktrace:__schedule+0xdc0/0x1860 schedule+0x27/0xd0 schedule_timeout+0xb5/0x100 wait_for_completion+0x8a/0x140 xfs_buf_iowait+0x20/0xd0 [xfs] xfs_buf_read_map+0x103/0x250 [xfs] xfs_trans_read_buf_map+0x161/0x310 [xfs] xfs_btree_read_buf_block+0xa0/0x120 [xfs] xfs_btree_lookup_get_block+0xa3/0x1e0 [xfs] xfs_btree_lookup+0xea/0x530 [xfs] xfs_alloc_fixup_trees+0x72/0x570 [xfs] xfs_alloc_ag_vextent_size+0x67f/0x800 [xfs] xfs_alloc_vextent_iterate_ags.constprop.0+0x52/0x230 [xfs] xfs_alloc_vextent_start_ag+0x9d/0x1b0 [xfs] xfs_bmap_btalloc+0x2af/0x680 [xfs] xfs_bmapi_allocate+0xdb/0x2c0 [xfs]} hitcount: 1
[..]
Quoted 8 lines
The above stops at 16 functions where knowing more would be useful. As the allocated storage for stacks is the same for strings, and that size is 256 bytes, there is a lot of space not being used for stacktraces.
16 * 8 = 128
Up the size to 31 (it requires the last slot to be zero, so it can't be 32).
Yeah, it can't be 32 because of the extra slot needed for saving the number of elements. If the stacktrace doesn't take up the full 31 elements, it writes a 0 after the last one to mark the end; if it fills it up, the 0 isn't written since the size of the array is known.
Quoted 9 lines
Also change the
BUILD_BUG_ON()to allow the size of the stacktrace storage to be equal to the max size. It already accounts for the empty slot via a "+ 1":
BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX);Change that from ">=" to just ">", as now they are equal.
Signed-off-by Steven Rostedt (Google) <[email protected]>
The patch itself looks good to me, thanks!
Quoted 31 lines
---
kernel/trace/trace.h | 2 +-
kernel/trace/trace_events_hist.c | 2 +-2 files changed, 2 insertions(+), 2 deletions(-)kernel/trace/trace.h +0
-0@@ -128,7 +128,7 @@ enum trace_type {
#defineFAULT_STRING"(fault)"kernel/trace/trace.h +1
-1-#define HIST_STACKTRACE_DEPTH 16 +#define HIST_STACKTRACE_DEPTH 31#define
HIST_STACKTRACE_SIZE(HIST_STACKTRACE_DEPTH* sizeof(unsigned long))
#defineHIST_STACKTRACE_SKIP5kernel/trace/trace_events_hist.c +0
-0@@ -3154,7 +3154,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, u64 var_val;
/* Make sure stacktrace can fit in the string variable length */kernel/trace/trace_events_hist.c +1
-1-BUILD_BUG_ON ((HIST_STACKTRACE_DEPTH +1 ) *sizeof (long ) >=STR_VAR_LEN_MAX ); +BUILD_BUG_ON ((HIST_STACKTRACE_DEPTH +1 ) *sizeof (long ) >STR_VAR_LEN_MAX );
for (i = 0, j =field_var_str_start; i <n_field_vars; i++) { structfield_var*field_var= field_vars[i];