Difference between revisions of "CSIT/VPP-ubuntu-compare-1404to1604"
From fd.io
< CSIT
Mackonstan (Talk | contribs) |
Mackonstan (Talk | contribs) |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 4: | Line 4: | ||
** 1. Ubuntu 14.04 - vpp build 101, csit-vpp-perf-master-long #1076 | ** 1. Ubuntu 14.04 - vpp build 101, csit-vpp-perf-master-long #1076 | ||
** 2. Ubuntu 16.04 - vpp build 136, csit-vpp-perf-master-long #1080(onwards) | ** 2. Ubuntu 16.04 - vpp build 136, csit-vpp-perf-master-long #1080(onwards) | ||
| + | ** 3. Source data log files for above calcs available here: [https://wiki.fd.io/view/CSIT/long1076vs1080-ubuntu1404vs1604-analysis analysis], [https://wiki.fd.io/view/CSIT/long1076vs1080-ubuntu1404vs1604-thput-incr thput-increase], [https://wiki.fd.io/view/CSIT/long1076vs1080-ubuntu1404vs1604-thput-decr thput-decrease]. | ||
| − | * '''B. Increased | + | * '''B. Increased - all values for NIC2NIC, vpp 1worker unless noted:''' |
** 1. l2bd x520 6% | ** 1. l2bd x520 6% | ||
** 2. IPv4 x520 3% | ** 2. IPv4 x520 3% | ||
| Line 12: | Line 13: | ||
** 5. L2XC xl710 81% 2workers | ** 5. L2XC xl710 81% 2workers | ||
| − | * '''C. Decreased | + | * '''C. Decreased - all values for NIC2NIC, vpp 1worker:''' |
** 1. IPv6 x520 -5% | ** 1. IPv6 x520 -5% | ||
| − | + | * '''D. This is also reflected in NDR trending graphs generated by LF Jenkins jobs:''' | |
| − | + | ||
| − | * '''D. This is also reflected in NDR trending graphs | + | |
** 1. Ubuntu1404, vpp1609 release without fib2.0 patches: | ** 1. Ubuntu1404, vpp1609 release without fib2.0 patches: | ||
*** https://jenkins.fd.io/view/csit/job/csit-vpp-perf-1609-long/plot/RFC2544%3ANDR/ | *** https://jenkins.fd.io/view/csit/job/csit-vpp-perf-1609-long/plot/RFC2544%3ANDR/ | ||
** 2. Ubuntu1604, vpp master with fib2.0 patches: | ** 2. Ubuntu1604, vpp master with fib2.0 patches: | ||
*** https://jenkins.fd.io/view/csit/job/csit-vpp-perf-master-long/plot/RFC2544%3ANDR/ | *** https://jenkins.fd.io/view/csit/job/csit-vpp-perf-master-long/plot/RFC2544%3ANDR/ | ||
| − | + | ** 3. due to LF purged job history we only have vpp-1609 ("fib1.0") vs. vpp-master (fib2.0) trend graphs. | |
| − | trend graphs. | + | |
* '''E. Note that you can now see daily performance trending graphs for NDR and PDR for vpp master here:''' | * '''E. Note that you can now see daily performance trending graphs for NDR and PDR for vpp master here:''' | ||
| Line 31: | Line 29: | ||
*** https://jenkins.fd.io/view/csit/job/csit-vpp-verify-perf-master-nightly-all/plot/RFC2544%3APDR/ | *** https://jenkins.fd.io/view/csit/job/csit-vpp-verify-perf-master-nightly-all/plot/RFC2544%3APDR/ | ||
| − | * '''F. | + | * '''F. Few requests:''' |
| − | ** 1 | + | ** 1. Welcome any volunteers to help us catch any anomalies in perf trending. |
| − | + | ** 2. Pls send any suggestions and wishes for what you would like to see for performance tests and trending - csit-dev@lists.fd.io. | |
| − | ** | + | |
Latest revision as of 14:35, 1 November 2016
Summary of performance trending from FD.io testbeds after upgrading from Ubuntu14.04 Trusty to 16.04 Xenial:-
- A. Comparison based on:
- 1. Ubuntu 14.04 - vpp build 101, csit-vpp-perf-master-long #1076
- 2. Ubuntu 16.04 - vpp build 136, csit-vpp-perf-master-long #1080(onwards)
- 3. Source data log files for above calcs available here: analysis, thput-increase, thput-decrease.
- B. Increased - all values for NIC2NIC, vpp 1worker unless noted:
- 1. l2bd x520 6%
- 2. IPv4 x520 3%
- 3. L2XC x520 3..9% (untagged, dot1q, dot1ad)
- 4. L2XC xl710 3%
- 5. L2XC xl710 81% 2workers
- C. Decreased - all values for NIC2NIC, vpp 1worker:
- 1. IPv6 x520 -5%
- D. This is also reflected in NDR trending graphs generated by LF Jenkins jobs:
- 1. Ubuntu1404, vpp1609 release without fib2.0 patches:
- 2. Ubuntu1604, vpp master with fib2.0 patches:
- 3. due to LF purged job history we only have vpp-1609 ("fib1.0") vs. vpp-master (fib2.0) trend graphs.
- E. Note that you can now see daily performance trending graphs for NDR and PDR for vpp master here:
- 1. vpp master branch - RFC2544:NDR trending plot
- 2. vpp master branch - RFC2544:PDR trending plot
- F. Few requests:
- 1. Welcome any volunteers to help us catch any anomalies in perf trending.
- 2. Pls send any suggestions and wishes for what you would like to see for performance tests and trending - csit-dev@lists.fd.io.
