Difference between revisions of "CSIT/VPP-ubuntu-compare-1404to1604"
From fd.io
< CSIT
Mackonstan (Talk | contribs) |
Mackonstan (Talk | contribs) |
||
Line 6: | Line 6: | ||
** 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]. | ** 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 13: | 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 | + | * '''D. This is also reflected in NDR trending graphs generated by LF Jenkins jobs:''' |
** 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. | ||
Revision as of 14:31, 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. And few requests:
- 1. Welcome all comments!
- 2. Welcome any volunteers to help us catch any anomalies in perf trending.
- 3. Pls send any wishes for what you would like to see for performance tests and trending, to csit-dev@lists.fd.io.