DPDK patches and discussions
 help / color / mirror / Atom feed
From: Rasesh Mody <rasesh.mody@cavium.com>
To: dev@dpdk.org
Cc: Shahed Shaikh <shahed.shaikh@cavium.com>,
	ferruh.yigit@intel.com, Dept-EngDPDKDev@cavium.com,
	stable@dpdk.org
Subject: [dpdk-dev] [PATCH] net/qede: fix slow path completion timeout
Date: Wed, 23 May 2018 11:48:53 -0700	[thread overview]
Message-ID: <1527101333-16888-1-git-send-email-rasesh.mody@cavium.com> (raw)

From: Shahed Shaikh <shahed.shaikh@cavium.com>

In 100G mode, we poll firmware slow path completion for every 1 second,
which is not enough and may result in completion timeout if
driver misses that window.

Patch "eal: set affinity for control threads" exposed this issue since
alarm callback runs in control thread context.

Fix this issue by update polling period to 100ms.

Fixes: d651ee4919cd ("eal: set affinity for control threads")
Fixes: 2af14ca79c0a ("net/qede: support 100G")
Cc: stable@dpdk.org

Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
---
 drivers/net/qede/qede_ethdev.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/qede/qede_ethdev.c b/drivers/net/qede/qede_ethdev.c
index 30b6519..338ddc1 100644
--- a/drivers/net/qede/qede_ethdev.c
+++ b/drivers/net/qede/qede_ethdev.c
@@ -16,7 +16,7 @@
 int qede_logtype_driver;
 
 static const struct qed_eth_ops *qed_ops;
-static int64_t timer_period = 1;
+#define QEDE_SP_TIMER_PERIOD	10000 /* 100ms */
 
 /* VXLAN tunnel classification mapping */
 const struct _qede_udp_tunn_types {
@@ -1698,7 +1698,7 @@ static void qede_poll_sp_sb_cb(void *param)
 	qede_interrupt_action(ECORE_LEADING_HWFN(edev));
 	qede_interrupt_action(&edev->hwfns[1]);
 
-	rc = rte_eal_alarm_set(timer_period * US_PER_S,
+	rc = rte_eal_alarm_set(QEDE_SP_TIMER_PERIOD,
 			       qede_poll_sp_sb_cb,
 			       (void *)eth_dev);
 	if (rc != 0) {
@@ -3093,7 +3093,7 @@ static int qede_common_dev_init(struct rte_eth_dev *eth_dev, bool is_vf)
 	 * interrupt vector but we need one for each engine.
 	 */
 	if (ECORE_IS_CMT(edev) && IS_PF(edev)) {
-		rc = rte_eal_alarm_set(timer_period * US_PER_S,
+		rc = rte_eal_alarm_set(QEDE_SP_TIMER_PERIOD,
 				       qede_poll_sp_sb_cb,
 				       (void *)eth_dev);
 		if (rc != 0) {
-- 
1.7.10.3

             reply	other threads:[~2018-05-23 18:49 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-23 18:48 Rasesh Mody [this message]
2018-05-24 17:22 ` Ferruh Yigit
2018-05-24 18:02   ` Mody, Rasesh
2018-05-25  9:35     ` Ferruh Yigit

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=1527101333-16888-1-git-send-email-rasesh.mody@cavium.com \
    --to=rasesh.mody@cavium.com \
    --cc=Dept-EngDPDKDev@cavium.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=shahed.shaikh@cavium.com \
    --cc=stable@dpdk.org \
    /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).