Re: [PATCH iproute2-next v2] tc: fq_pie: add support for printing per-flow PIE statistics

[Stephen Hemminger <stephen@networkplumber.org>]

On Sun, 14 Jun 2026 18:37:29 +0530
"Hemendra M. Naik" <hemendranaik@gmail.com> wrote:

> 'tc -s class show' against an fq_pie qdisc now prints:
> 
>  prob           drop probability for the flow
>  delay          per-flow queue sojourn time (microseconds)
>  deficit        remaining DRR byte credits (signed integer)
>  avg_dq_rate    dequeue rate estimate in bytes/second
>              	(dq_rate_estimator mode only)
> 
> avg_dq_rate is formatted using tc_print_rate(), which converts the
> kernel's bytes/second value to a human-readable bits/second string
> (e.g. '3906Kbit'), consistent with how other tc schedulers display
> rate fields. Apply the same fix to tc/q_pie.c, where avg_dq_rate was
> also printed as a raw integer without a unit.
> 
> Update the UAPI header to mirror tc_fq_pie_cl_stats from the kernel.
> Fix the 'delay' field comment in struct tc_pie_xstats from "in ms" to
> "in microseconds" to match the kernel's
> PSCHED_TICKS2NS / NSEC_PER_USEC conversion.
> 
> Add a 'tc -s class show' example to tc-fq_pie(8) with dq_rate_estimator
> enabled, showing all per-flow fields (prob, delay, deficit, avg_dq_rate)
> across multiple flows. Update tc-pie(8) avg_dq_rate example from a raw
> integer to a formatted bits/second string.
> 
> The corresponding kernel patch can be viewed here:
> https://lore.kernel.org/netdev/20260614125000.6058-1-hemendranaik@gmail.com/
> 
> Signed-off-by: Hemendra M. Naik <hemendranaik@gmail.com>
> Signed-off-by: Vishal Kamath <vishy0777@gmail.com>
> Signed-off-by: Mohit P. Tahiliani <tahiliani@nitk.edu.in>

Minor feedback from AI review was:
Subject: Re: [PATCH iproute2-next v2] tc: fq_pie: add support for printing per-flow PIE statistics

On Sun, 14 Jun 2026, Hemendra M. Naik wrote:
> diff --git a/tc/q_fq_pie.c b/tc/q_fq_pie.c
> @@ -283,25 +285,43 @@ static int fq_pie_print_xstats(const struct qdisc_util *qu, FILE *f,
> +	if (st->type == TCA_FQ_PIE_XSTATS_CLASS) {
> +		print_float(PRINT_ANY, "prob", " prob %lg",
> +			    (double)st->class_stats.prob / (double)UINT64_MAX);
> +		print_uint(PRINT_JSON, "delay", NULL, st->class_stats.delay);
> +		print_string(PRINT_FP, NULL, " delay %s",
> +			     sprint_time(st->class_stats.delay, b1));
> +		print_int(PRINT_ANY, "deficit", " deficit %d",
> +			  st->class_stats.deficit);
> +
> +		if (st->class_stats.dq_rate_estimating) {
> +			tc_print_rate(PRINT_ANY, "avg_dq_rate", " avg_dq_rate %s",
> +				      st->class_stats.avg_dq_rate);
> +		}
> +	}
>  	print_nl();

The print_nl() at line 334 appears to be misplaced. It's outside both
conditional blocks, which means it will always print a newline regardless
of the statistics type being displayed. This could cause formatting issues:

- For TCA_FQ_PIE_XSTATS_CLASS, you'll get a newline after the class stats
- For qdisc stats, you'll get an extra newline after the memory_used field

The original code had print_nl() after the qdisc statistics. With the new
class statistics block, you likely need print_nl() inside each conditional
block to maintain proper formatting for each type.

Consider restructuring like this:
	if (!st->type || st->type == TCA_FQ_PIE_XSTATS_QDISC) {
		/* qdisc stats */
		...
		print_uint(PRINT_ANY, "memory_used", " memory_used %u",
			   st->memory_usage);
		print_nl();
	}

	if (st->type == TCA_FQ_PIE_XSTATS_CLASS) {
		/* class stats */
		...
		print_nl();
	}

Otherwise the patch looks good:
- Good use of print_* helpers throughout
- Proper handling of JSON vs text output modes
- The tc_print_rate() usage is correct and consistent
- Documentation updates in man pages are helpful