From: bugzilla@dpdk.org
To: dev@dpdk.org
Subject: [dpdk-dev] [Bug 196] IXGBE Driver Tx Packet/Bytes counters Sent returns Zero even though link-partner received valid packets
Date: Tue, 29 Jan 2019 06:21:01 +0000 [thread overview]
Message-ID: <bug-196-3@http.bugs.dpdk.org/> (raw)
https://bugs.dpdk.org/show_bug.cgi?id=196
Bug ID: 196
Summary: IXGBE Driver Tx Packet/Bytes counters Sent returns
Zero even though link-partner received valid packets
Product: DPDK
Version: 18.08
Hardware: x86
OS: Linux
Status: CONFIRMED
Severity: major
Priority: Normal
Component: ethdev
Assignee: dev@dpdk.org
Reporter: madiwalar@hpe.com
Target Milestone: ---
Created attachment 28
--> https://bugs.dpdk.org/attachment.cgi?id=28&action=edit
IXGBE Stats Mismatch between Port 0 Tx and Port 1 Rx
We are using Denverton(Harisonville, C3000) Based SOC in the test we did.
We are observing Tx Packet/Bytes stats returns as Zero even though link-partner
received valid Packets/Bytes(stats). This behavior is random.
Test Scenario:
1. IXGBE driver in the DPDK is configured in SGMII Mode. We have total of four
ports. External Cat5e cable is connected back to back ports(i.e Port 0 is
connected to Port1 and Port 2 is connected to Port 3).
2. Testpmd application is used for the test. Where Packet fwd is configured as
flowgen(testpmd cmd: set fwd flowgen).
3. Packet stats were cleared prior to start of the traffic. Traffic test runs
for about 30 minutes
4. As IXGBE stats are Read on clear and Likely to rollover so we use 'show port
stats all' to read Hardware stats to DPDK hwstats periodically (Every 10
minutes, as we have seen counters are rolled over in 15 minutes in our SGMII
Mode configuration).
5. At about 30 minutes, we stop the traffic in testpmd and match counters
between ports manually.
Issue Observed:
1. Port 0 Tx Packet/Bytes counters reported as Zero(0) while Port
1(link-partner) Rx Packet/Bytes received valid frames and bytes.
2. Port 0 Rx Packet/Bytes Counters reported fine and were matching to the Port
1(link-partner) Tx Packet/Bytes.
3. With above observation it is fact that Port 0 actually transmitted the
packets that are captured in Port 1 Rx stats, But Port 0 Tx Stats are shown
always zero in the case.
Below is brief log of port 0 and port 1 stats.
testpmd> show port stats 0
######################## NIC statistics for port 0 ########################
RX-packets: 1877202080 RX-missed: 0 RX-bytes: 112632124800
RX-errors: 0
RX-nombuf: 0
TX-packets: 0 TX-errors: 0 TX-bytes: 0
Throughput (since last show)
Rx-pps: 0
Tx-pps: 0
############################################################################
testpmd> show port stats 1
######################## NIC statistics for port 1 ########################
RX-packets: 1877202080 RX-missed: 0 RX-bytes: 112632124800
RX-errors: 0
RX-nombuf: 0
TX-packets: 1877202080 TX-errors: 0 TX-bytes: 112632124800
Throughput (since last show)
Rx-pps: 0
Tx-pps: 0
############################################################################
testpmd>
Complete xtats for port 0 and port 1 is attached.
Regards,
Sadashiv Madiwalar
--
You are receiving this mail because:
You are the assignee for the bug.
reply other threads:[~2019-01-29 6:21 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=bug-196-3@http.bugs.dpdk.org/ \
--to=bugzilla@dpdk.org \
--cc=dev@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).