DPDK patches and discussions
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: dev@dpdk.org
Cc: Stephen Hemminger <stephen@networkplumber.org>,
	Cristian Dumitrescu <cristian.dumitrescu@intel.com>,
	Jasvinder Singh <jasvinder.singh@intel.com>,
	Wojciech Liguzinski <wojciechx.liguzinski@intel.com>
Subject: [PATCH v4 3/3] rte_pie: fix incorrect floating point math
Date: Wed, 25 May 2022 13:31:23 -0700	[thread overview]
Message-ID: <20220525203123.277180-4-stephen@networkplumber.org> (raw)
In-Reply-To: <20220525203123.277180-1-stephen@networkplumber.org>

The function rte_pie_drop was attempting to do a random probability
drop, but because of incorrect usage of fixed point divide
it would always return 1.

Change to use new rte_drand() instead.

Fixes: 44c730b0e379 ("sched: add PIE based congestion management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
 lib/sched/rte_pie.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/lib/sched/rte_pie.h b/lib/sched/rte_pie.h
index 3e2c1ef46721..528f2ea878e8 100644
--- a/lib/sched/rte_pie.h
+++ b/lib/sched/rte_pie.h
@@ -217,7 +217,6 @@ __rte_experimental
 _rte_pie_drop(const struct rte_pie_config *pie_cfg,
 	struct rte_pie *pie)
 {
-	uint64_t rand_value;
 	uint64_t qdelay = pie_cfg->qdelay_ref / 2;
 
 	/* PIE is active but the queue is not congested: return 0 */
@@ -240,9 +239,7 @@ _rte_pie_drop(const struct rte_pie_config *pie_cfg,
 	if (pie->accu_prob >= 8.5)
 		return 1;
 
-	rand_value = rte_rand()/RTE_RAND_MAX;
-
-	if ((double)rand_value < pie->drop_prob) {
+	if (rte_drand() < pie->drop_prob) {
 		pie->accu_prob = 0;
 		return 1;
 	}
-- 
2.35.1


  parent reply	other threads:[~2022-05-25 20:31 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-24 18:46 [RFT 0/2] pie: floating point fixes Stephen Hemminger
2022-05-24 18:46 ` [RFT 1/2] rte_pie: remove unnecessary floating point Stephen Hemminger
2022-05-24 18:46 ` [RFT 2/2] rte_pie: fix incorrect floating point math Stephen Hemminger
2022-05-24 19:31 ` [RFT 0/2] pie: floating point fixes Morten Brørup
2022-05-24 22:18 ` [RFT v2 0/3] pie: fix random number issues Stephen Hemminger
2022-05-24 22:18   ` [RFT v2 1/3] random: add rte_rand_float() Stephen Hemminger
2022-05-25 11:55     ` Ray Kinsella
2022-05-25 14:45     ` Mattias Rönnblom
2022-05-25 15:26       ` Morten Brørup
2022-05-25 15:45       ` Stephen Hemminger
2022-05-25 15:47       ` Stephen Hemminger
2022-05-24 22:18   ` [RFT v2 2/3] rte_pie: remove unnecessary floating point Stephen Hemminger
2022-05-24 22:18   ` [RFT v2 3/3] rte_pie: fix incorrect floating point math Stephen Hemminger
2022-05-25 17:12 ` [PATCH v3 0/3] introduce random floating point function Stephen Hemminger
2022-05-25 17:12   ` [PATCH v3 1/3] random: add rte_drand() funciton Stephen Hemminger
2022-05-25 17:12   ` [PATCH v3 2/3] rte_pie: remove unnecessary floating point Stephen Hemminger
2022-05-25 17:12   ` [PATCH v3 3/3] rte_pie: fix incorrect floating point math Stephen Hemminger
2022-05-25 20:31 ` [PATCH v4 0/3] introduce random floating point function Stephen Hemminger
2022-05-25 20:31   ` [PATCH v4 1/3] random: add rte_drand() function Stephen Hemminger
2022-05-26  9:56     ` Ray Kinsella
2022-05-26 13:20     ` Mattias Rönnblom
2022-05-26 15:25       ` Stephen Hemminger
2022-05-26 15:28       ` Stephen Hemminger
2022-05-26 20:19       ` Stephen Hemminger
2022-05-25 20:31   ` [PATCH v4 2/3] rte_pie: remove unnecessary floating point Stephen Hemminger
2022-05-25 20:31   ` Stephen Hemminger [this message]
2022-05-26  7:06   ` [PATCH v4 0/3] introduce random floating point function Morten Brørup
2022-05-26 20:26 ` [PATCH v5 " Stephen Hemminger
2022-05-26 20:26   ` [PATCH v5 1/3] random: add rte_drand() function Stephen Hemminger
2022-05-26 20:26   ` [PATCH v5 2/3] rte_pie: remove unnecessary floating point Stephen Hemminger
2022-05-30 11:50     ` Dumitrescu, Cristian
2022-06-21  8:18     ` Singh, Jasvinder
2022-05-26 20:26   ` [PATCH v5 3/3] rte_pie: fix incorrect floating point math Stephen Hemminger
2022-05-30 11:50     ` Dumitrescu, Cristian
2022-06-21  8:18     ` Singh, Jasvinder
2022-06-22  9:21   ` [PATCH v5 0/3] introduce random floating point function Thomas Monjalon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220525203123.277180-4-stephen@networkplumber.org \
    --to=stephen@networkplumber.org \
    --cc=cristian.dumitrescu@intel.com \
    --cc=dev@dpdk.org \
    --cc=jasvinder.singh@intel.com \
    --cc=wojciechx.liguzinski@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).