Report the task weight when dumping the task state during an error exit.
Moreover, adjust the output format to display dsq_vtime, slice, and
weight on the same line.

This can help identify whether certain tasks were excessively
prioritized or de-prioritized due to large niceness gaps.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 64967d28da7f..99179aa6f7dd 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5230,9 +5230,10 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 		  scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK,
 		  p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK,
 		  ops_state >> SCX_OPSS_QSEQ_SHIFT);
-	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu",
-		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf,
-		  p->scx.dsq_vtime, p->scx.slice);
+	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s",
+		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf);
+	dump_line(s, "      dsq_vtime=%llu slice=%llu weight=%u",
+		  p->scx.dsq_vtime, p->scx.slice, p->scx.weight);
 	dump_line(s, "      cpus=%*pb", cpumask_pr_args(p->cpus_ptr));
 
 	if (SCX_HAS_OP(dump_task)) {
-- 
2.48.1

On Wed, Jan 22, 2025 at 10:05:25AM +0100, Andrea Righi wrote:
> Report the task weight when dumping the task state during an error exit.
> Moreover, adjust the output format to display dsq_vtime, slice, and
> weight on the same line.
> 
> This can help identify whether certain tasks were excessively
> prioritized or de-prioritized due to large niceness gaps.
> 
> Signed-off-by: Andrea Righi <arighi@nvidia.com>

Applied to sched_ext/for-6.14-fixes.

Thanks.

-- 
tejun