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>,
	Reshma Pattan <reshma.pattan@intel.com>
Subject: [PATCH v2 5/6] test: increase gap in pcapng test
Date: Mon, 29 Dec 2025 15:01:08 -0800	[thread overview]
Message-ID: <20251229230223.151874-6-stephen@networkplumber.org> (raw)
In-Reply-To: <20251229230223.151874-1-stephen@networkplumber.org>

Want to make sure that test takes long enough that 32 bit
counter wraps around.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
 app/test/test_pcapng.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/app/test/test_pcapng.c b/app/test/test_pcapng.c
index 5010355df5..73557eb2f1 100644
--- a/app/test/test_pcapng.c
+++ b/app/test/test_pcapng.c
@@ -27,7 +27,6 @@
 
 #define TOTAL_PACKETS	4096
 #define MAX_BURST	64
-#define MAX_GAP_US	100000
 #define DUMMY_MBUF_NUM	2
 
 static struct rte_mempool *mp;
@@ -175,7 +174,7 @@ test_setup(void)
 }
 
 static int
-fill_pcapng_file(rte_pcapng_t *pcapng, unsigned int num_packets)
+fill_pcapng_file(rte_pcapng_t *pcapng)
 {
 	struct dummy_mbuf mbfs;
 	struct rte_mbuf *orig;
@@ -193,7 +192,15 @@ fill_pcapng_file(rte_pcapng_t *pcapng, unsigned int num_packets)
 	mbuf1_prepare(&mbfs);
 	orig  = &mbfs.mb[0];
 
-	for (count = 0; count < num_packets; count += burst_size) {
+	/* How many microseconds does it take TSC to wrap around 32 bits */
+	const unsigned wrap_us
+		= (US_PER_S * (uint64_t)UINT32_MAX) / rte_get_tsc_hz();
+
+	/* Want overall test to take to wraparound at least twice. */
+	const unsigned int avg_gap = (2 * wrap_us)
+		/ (TOTAL_PACKETS / (MAX_BURST / 2));
+
+	for (count = 0; count < TOTAL_PACKETS; count += burst_size) {
 		struct rte_mbuf *clones[MAX_BURST];
 		unsigned int i;
 
@@ -229,8 +236,7 @@ fill_pcapng_file(rte_pcapng_t *pcapng, unsigned int num_packets)
 			return -1;
 		}
 
-		/* Leave a small gap between packets to test for time wrap */
-		usleep(rte_rand_max(MAX_GAP_US));
+		rte_delay_us_block(rte_rand_max(2 * avg_gap));
 	}
 
 	return count;
@@ -467,7 +473,7 @@ test_write_packets(void)
 		goto fail;
 	}
 
-	count = fill_pcapng_file(pcapng, TOTAL_PACKETS);
+	count = fill_pcapng_file(pcapng);
 	if (count < 0)
 		goto fail;
 
-- 
2.51.0


  parent reply	other threads:[~2025-12-29 23:02 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-26  5:12 [RFC] pcapng: improve performance of timestamping Stephen Hemminger
2025-12-29 23:01 ` [PATCH v2 0/6] pcapng: timestamping and comment fixes Stephen Hemminger
2025-12-29 23:01   ` [PATCH v2 1/6] pcapng: use alloca instead of fixed buffer Stephen Hemminger
2025-12-29 23:01   ` [PATCH v2 2/6] pcapng: add additional mbuf if space required on copy Stephen Hemminger
2025-12-29 23:01   ` [PATCH v2 3/6] test: add more tests for comments in pcapng Stephen Hemminger
2025-12-29 23:01   ` [PATCH v2 4/6] test: vary size of packets in pcapng test Stephen Hemminger
2025-12-29 23:01   ` Stephen Hemminger [this message]
2025-12-29 23:01   ` [PATCH v2 6/6] pcapng: improve performance of timestamping Stephen Hemminger

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=20251229230223.151874-6-stephen@networkplumber.org \
    --to=stephen@networkplumber.org \
    --cc=dev@dpdk.org \
    --cc=reshma.pattan@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).