Bug 1762725

Summary:	[RFE] [openvswitch-2.12] Add visibility on netdev-dpdk tx drops in OVS
Product:	Red Hat Enterprise Linux Fast Datapath	Reporter:	Kevin Traynor <ktraynor>
Component:	openvswitch2.12	Assignee:	Kevin Traynor <ktraynor>
Status:	CLOSED ERRATA	QA Contact:	Jean-Tsung Hsiao <jhsiao>
Severity:	unspecified	Docs Contact:
Priority:	unspecified
Version:	FDP 19.G	CC:	cfontain, ctrautma, fbaudin, gmuthukr, jhsiao, kfida, qding, ralongi, vchundur
Target Milestone:	---
Target Release:	---
Hardware:	Unspecified
OS:	Unspecified
Whiteboard:
Fixed In Version:	openvswitch2.12-2.12.0-19.el7fdn.x86_64.rpm	Doc Type:	If docs needed, set a value
Doc Text:		Story Points:	---
Clone Of:
Clones:	1790841 (view as bug list)		Environment:
Last Closed:	2020-03-10 09:36:07 UTC	Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:
Bug Depends On:
Bug Blocks:	1790841

Description Kevin Traynor 2019-10-17 10:32:07 UTC

During TX in netdev-dpdk in OVS, there is a pkt drop counter but there are different reasons why that counter may be incremented:

- Drops due to egress policing
- Drops due to MTU exceeded
- Drops reported from the DPDK PMD Tx function

There is a proposed patch upstream [1] that adds the above as more fine grained custom stats for dpdk and vhost ports.

This Bz is to help with upstreaming of that patch and possible backport to downstream.

[1] https://mail.openvswitch.org/pipermail/ovs-dev/2019-September/362872.html

Comment 4 Jean-Tsung Hsiao 2020-02-05 19:36:05 UTC

Verified the RFE based on the validation nodes in commnent #1.

[root@localhost jhsiao]# cat testpmd.sh
testpmd -l 0,1,2,3,4 -w 0000:00:03.0 -w 0000:00:09.0 --socket-mem 4096 -- -i --nb-cores=4  --rxq=2 --txq=2 --rxd=10 --txd=1024
[root@localhost jhsiao]#

[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:tx_dropped
222079
[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:tx_dropped
222079
[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:tx_dropped
426161
[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:ovs_tx_failure_drops
2876063
[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:ovs_tx_failure_drops
3237435
[root@netqe7 jhsiao]# ovs-vsctl get Interface vhost0 statistics:ovs_tx_failure_drops
3237435
[root@netqe7 jhsiao]# ovs-vsctl set Interface dpdk0 ingress_policing_rate=368000
[root@netqe7 jhsiao]# ovs-vsctl get Interface dpdk0 statistics:ovs_rx_qos_drops
635919821
[root@netqe7 jhsiao]# ovs-vsctl get Interface dpdk0 statistics:ovs_rx_qos_drops
635919821
[root@netqe7 jhsiao]# ovs-vsctl get Interface dpdk0 statistics:ovs_rx_qos_drops
635919821
[root@netqe7 jhsiao]# ovs-vsctl get Interface dpdk0 statistics:ovs_rx_qos_drop

Comment 5 Jean-Tsung Hsiao 2020-02-05 19:38:36 UTC

[root@netqe7 jhsiao]# rpm -q openvswitch2.12
openvswitch2.12-2.12.0-21.el8fdp.x86_64
[root@netqe7 jhsiao]# uname -r
4.18.0-147.el8.x86_64
[root@netqe7 jhsiao]#

Comment 7 errata-xmlrpc 2020-03-10 09:36:07 UTC

Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.

For information on the advisory, and where to find the updated
files, follow the link below.

If the solution does not work for you, open a new bug report.

https://access.redhat.com/errata/RHBA-2020:0745