From f35cc99d3ca298839f925605f0641489ab3e42fc Mon Sep 17 00:00:00 2001 From: Vratko Polak Date: Fri, 10 Jul 2020 12:10:01 +0200 Subject: RCA 2005: Update RCA files. + Current state. + Covers skx (also 3n) and clx. + Specific Jira sub-tasks, even for VPP progressions. - Only 2n-skx data for NDR. Change-Id: I56cf870aedc1319891b7188268ff6cf7bc744ff8 Signed-off-by: Vratko Polak (cherry picked from commit 713e795d22717f69edf298d9dc4a16859206335f) --- .../presentation/rca/rca-2n-clx-2t1c-pdr-rca1.yaml | 69 ++++++++++++++ .../presentation/rca/rca-2n-clx-2t1c-pdr-rca2.yaml | 29 ++++++ .../presentation/rca/rca-2n-skx-2t1c-ndr-rca1.yaml | 105 ++++++++++++++++----- .../presentation/rca/rca-2n-skx-2t1c-ndr-rca2.yaml | 64 +++++++------ .../presentation/rca/rca-2n-skx-2t1c-pdr-rca1.yaml | 99 ++++++++++++++----- .../presentation/rca/rca-2n-skx-2t1c-pdr-rca2.yaml | 60 ++++++------ .../presentation/rca/rca-3n-skx-2t1c-ndr-rca1.yaml | 25 ----- .../presentation/rca/rca-3n-skx-2t1c-ndr-rca2.yaml | 40 -------- .../presentation/rca/rca-3n-skx-2t1c-pdr-rca1.yaml | 82 +++++++++++----- .../presentation/rca/rca-3n-skx-2t1c-pdr-rca2.yaml | 56 ++++------- 10 files changed, 390 insertions(+), 239 deletions(-) create mode 100644 resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca1.yaml create mode 100644 resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca2.yaml delete mode 100644 resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca1.yaml delete mode 100644 resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca2.yaml diff --git a/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca1.yaml b/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca1.yaml new file mode 100644 index 0000000000..eda44b3b15 --- /dev/null +++ b/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca1.yaml @@ -0,0 +1,69 @@ +# CSIT progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +# CSIT regressions. +64b-2t1c-avf-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-avf-ethip4-ip4scale2m: 7 +64b-2t1c-avf-ethip4-ip4scale2m-rnd: 2 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 1 +64b-2t1c-avf-dot1q-l2xcbase: 3 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 7 +64b-2t1c-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-ethip4-ip4scale2m: 7 +64b-2t1c-ethip4-ip4scale2m-rnd: 2 + +# Multiline string, empty lines (or \n) are required, +# see https://yaml-multiline.info/ + +footnote: " + [1] DONE Regression in ACL tests. The cause is the CSIT part of + an API change, Gerrit 26112. Instead of failing, the misconfigured VPP + passes the test, albeit with reduced performance. [CSIT-1739] + + [2] DONE Regression in tests using random flows. + The cause is Gerrit 26456, unpinning random seed, needed to make TRex workers + generate different sequences of packets. [CSIT-1731] + + [3] DONE Regression in base dot1q-l2xcbase suites. The cause is Gerrit 25363, + which unified dot1q handling across various tests. + Previously, this one suite was different (only handling dot1q on one port). + + [5] OPEN Progression in performance of tests running VPP (l2xc) inside VM. + Due to relatively high stdev of results, bisecting has not found a cause yet. + [CSIT-1738] + + [7] POSTPONED Possible anomaly, but stdev of results is high. + Currently, the performance differences are considered to probably be just noise. + + [9] OPEN Progression in ip6 scale tests. Multiple candidate changes may have + affect code efficiency, but they have also caused the tests to fail + for a period of time. [CSIT-1735] + + [10] OPEN Progression in ip6 base tests with dot1q. [CSIT-1746] + + [11] OPEN Progression in memif tests, mainly in avf-eth-l2xcbase-eth-2memif-1dcr. + Not sure whether all memif tests are affected, nor what the cause is. + [CSIT-1744] + + [12] OPEN Progression in some l2bdscale tests. [CSIT-1745] + + [13] DONE Stateless ACL test have the same performance in 2005.0-4 as in + 2001.0-2, the difference shown here is just a consequence of API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [14] DONE Statefull ACL test have better performance in 2005.0-4 as in + 2001.0-2, but the difference shown here is inflated due to API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [15] OPEN Progression in nat44 test (not scale ones). [CSIT-1747] + + [17] OPEN Progression in some vhost tests (dpdk in VM). [CSIT-1749] +" diff --git a/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca2.yaml b/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca2.yaml new file mode 100644 index 0000000000..c6054fffd9 --- /dev/null +++ b/resources/tools/presentation/rca/rca-2n-clx-2t1c-pdr-rca2.yaml @@ -0,0 +1,29 @@ +# VPP progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-avf-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-avf-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-avf-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 13 +64b-2t1c-avf-ethip4udp-ip4base-nat44: 15 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 13 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-eth-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 +64b-2t1c-ethip4udp-ip4base-nat44: 15 +78b-2t1c-avf-dot1q-ip6base: 10 +78b-2t1c-avf-ethip6-ip6scale200k: 9 +78b-2t1c-avf-ethip6-ip6scale20k: 9 +78b-2t1c-avf-ethip6-ip6scale2m: 9 +78b-2t1c-ethip6-ip6scale200k: 9 +78b-2t1c-ethip6-ip6scale20k: 9 +78b-2t1c-ethip6-ip6scale2m: 9 +# VPP regressions. + +# Footnotes are in RCA1 file. diff --git a/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca1.yaml b/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca1.yaml index 6d450e9382..a2e3317480 100644 --- a/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca1.yaml +++ b/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca1.yaml @@ -1,25 +1,80 @@ -64b-2t1c-avf-dot1q-ip4base: 1 -64b-2t1c-avf-dot1q-l2bdbasemaclrn-gbp: 1 -64b-2t1c-avf-eth-l2patch: 2 -64b-2t1c-avf-eth-l2xcbase: 2 -64b-2t1c-avf-ethip4-ip4base: 1 -64b-2t1c-eth-l2patch: 2 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 4 -64b-2t1c-ethip4-ip4base: 1 -64b-2t1c-ethip4udp-ip4base-iacl50sf-10kflows: 1 -64b-2t1c-ethip4udp-ip4base-oacl50sl-10kflows: 1 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[1] DONE, Impact of upgrades: i) Skx ucode from 0x2000043 to - 0x2000065, ii) Linux kernel from 4.15.0-60 to 4.15.0-72 and iii) - SuperMicro motherboard BIOS from 3.0c to 3.2. - - [2] DONE, Applied fix of FVL NIC firmware 6.0.1 for increasing TRex - Mpps rate from 27 Mpps to 37 Mpps, [CSIT-1503], [TRex-519]. - - [3] DONE, Applied VPP PAPI fix to enable memif zero-copy, - [CSIT-1592], [VPP-1764]. - - [4] OPEN, Higher than before StDev of PDR throughput for VPP - vhost-user with VPP-inside-VM, under investigation, [CSIT-1699], - [CSIT-1704]. -" \ No newline at end of file +# CSIT progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 7 +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm: 7 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2patch: 7 +64b-2t1c-avf-eth-l2xcbase: 7 +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-eth-l2xcbase: 7 +64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +# CSIT regressions. +64b-2t1c-avf-dot1q-ip4base: 7 +64b-2t1c-avf-dot1q-l2xcbase: 7 +64b-2t1c-avf-eth-l2bdscale1mmaclrn: 7 +64b-2t1c-avf-ethip4-ip4scale200k: 7 +64b-2t1c-avf-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-avf-ethip4-ip4scale20k-rnd: 2 +64b-2t1c-avf-ethip4-ip4scale2m: 7 +64b-2t1c-avf-ethip4-ip4scale2m-rnd: 2 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-nat44: 7 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 1 +64b-2t1c-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-ethip4-ip4scale2m: 7 +64b-2t1c-ethip4-ip4scale2m-rnd: 2 +78b-2t1c-avf-ethip6-ip6scale20k: 7 +78b-2t1c-avf-ethip6-ip6base: 7 + +# Multiline string, empty lines (or \n) are required, +# see https://yaml-multiline.info/ + +footnote: " + [1] DONE Regression in ACL tests. The cause is the CSIT part of + an API change, Gerrit 26112. Instead of failing, the misconfigured VPP + passes the test, albeit with reduced performance. [CSIT-1739] + + [2] DONE Regression in tests using random flows. + The cause is Gerrit 26456, unpinning random seed, needed to make TRex workers + generate different sequences of packets. [CSIT-1731] + + [5] OPEN Progression in performance of tests running VPP (l2xc) inside VM. + Due to relatively high stdev of results, bisecting has not found a cause yet. + [CSIT-1738] + + [7] POSTPONED Possible anomaly, but stdev of results is high. + Currently, the performance differences are considered to probably be just noise. + + [8] OPEN Regressions in some tests with VPP in VM and using l2xcbase as vswitch. + The results have surprisingly small stdev, more investigation needed. + [CSIT-1741] + + [9] OPEN Progression in ip6 scale tests. Multiple candidate changes may have + affect code efficiency, but they have also caused the tests to fail + for a period of time. [CSIT-1735] + + [11] OPEN Progression in memif tests, mainly in avf-eth-l2xcbase-eth-2memif-1dcr. + Not sure whether all memif tests are affected, nor what the cause is. + [CSIT-1744] + + [12] OPEN Progression in some l2bdscale tests. [CSIT-1745] + + [13] DONE Stateless ACL test have the same performance in 2005.0-4 as in + 2001.0-2, the difference shown here is just a consequence of API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [14] DONE Statefull ACL test have better performance in 2005.0-4 as in + 2001.0-2, but the difference shown here is inflated due to API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [15] OPEN Progression in nat44 test (not scale ones). [CSIT-1747] + + [17] OPEN Progression in some vhost tests (dpdk in VM). [CSIT-1749] +" diff --git a/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca2.yaml b/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca2.yaml index 96a30ed074..2a20b5ea37 100644 --- a/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca2.yaml +++ b/resources/tools/presentation/rca/rca-2n-skx-2t1c-ndr-rca2.yaml @@ -1,35 +1,37 @@ -64b-2t1c-avf-dot1q-ip4base: 10 -64b-2t1c-avf-ethip4-ip4base: 10 +# VPP progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm: 7 +64b-2t1c-avf-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-avf-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 13 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 13 +78b-2t1c-avf-ethip6-ip6scale200k: 7 +78b-2t1c-avf-ethip6-ip6scale2m: 7 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-ethip4udp-ip4base-nat44: 15 +78b-2t1c-ethip6-ip6scale200k: 9 +78b-2t1c-ethip6-ip6scale20k: 9 +78b-2t1c-ethip6-ip6scale2m: 9 +# VPP regressions. +64b-2t1c-avf-dot1q-ip4base: 7 +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-avf-eth-l2bdbasemaclrn: 7 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-avf-eth-l2bdscale1mmaclrn: 7 +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 8 64b-2t1c-avf-ethip4-ip4scale200k: 7 -64b-2t1c-avf-ethip4-ip4scale20k: 7 +64b-2t1c-avf-ethip4-ip4scale200k-rnd: 7 64b-2t1c-avf-ethip4-ip4scale2m: 7 -64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-dot1q-l2xcbase: 5 -64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-avf-ethip4-ip4scale2m-rnd: 7 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm: 9 -64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 -64b-2t1c-ethip4udp-ip4base-nat44: 6 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[5] OPEN, dot1q-l2xcbase progression, retro-inspection of - weekly ndrpdr tests points to ge-22805, automated bisect script does - not work due to frequent API changes, [CSIT-1699], [CSIT-1705]. - [6] DONE, ip4base-nat44 regression, ge-23963 - (https://gerrit.fd.io/r/c/vpp/+/23963#message-044278e6_752c3327). - - [7] WIP, avf-ip4scale regression, CANDIDATE(S) before ge-22699, - [CSIT-1699], [CSIT-1706]. - - [8] OPEN, VPP vhost-user with VPP-inside-VM higher than before stdev - of PDR throughput, under investigation, [CSIT-1699], [CSIT-1704]. - - [9] WIP, vhost-user with testpmd-in-VM progression, CANDIDATE(S) - before 22277, [CSIT-1699], [CSIT-1707]. - - [10] WIP, avf-ip4base regression, CANDIDATE(S) range - ge-18361..ge-24505, [CSIT-1699], [CSIT-1708]. - - [11] DONE, memif regression, CANDIDATE(S) confirmed ge-23801. -" \ No newline at end of file +# Footnotes are in RCA1 file. diff --git a/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca1.yaml b/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca1.yaml index 6d450e9382..87d599ec3d 100644 --- a/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca1.yaml +++ b/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca1.yaml @@ -1,25 +1,74 @@ -64b-2t1c-avf-dot1q-ip4base: 1 -64b-2t1c-avf-dot1q-l2bdbasemaclrn-gbp: 1 -64b-2t1c-avf-eth-l2patch: 2 -64b-2t1c-avf-eth-l2xcbase: 2 -64b-2t1c-avf-ethip4-ip4base: 1 -64b-2t1c-eth-l2patch: 2 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 4 -64b-2t1c-ethip4-ip4base: 1 -64b-2t1c-ethip4udp-ip4base-iacl50sf-10kflows: 1 -64b-2t1c-ethip4udp-ip4base-oacl50sl-10kflows: 1 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[1] DONE, Impact of upgrades: i) Skx ucode from 0x2000043 to - 0x2000065, ii) Linux kernel from 4.15.0-60 to 4.15.0-72 and iii) - SuperMicro motherboard BIOS from 3.0c to 3.2. - - [2] DONE, Applied fix of FVL NIC firmware 6.0.1 for increasing TRex - Mpps rate from 27 Mpps to 37 Mpps, [CSIT-1503], [TRex-519]. - - [3] DONE, Applied VPP PAPI fix to enable memif zero-copy, - [CSIT-1592], [VPP-1764]. - - [4] OPEN, Higher than before StDev of PDR throughput for VPP - vhost-user with VPP-inside-VM, under investigation, [CSIT-1699], - [CSIT-1704]. -" \ No newline at end of file +# CSIT progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-dot1q-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2xcbase: 4 +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +# CSIT regressions. +64b-2t1c-avf-dot1q-l2xcbase: 3 +64b-2t1c-avf-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-avf-ethip4-ip4scale2m-rnd: 2 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 1 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 1 +64b-2t1c-ethip4-ip4scale200k-rnd: 2 +64b-2t1c-ethip4-ip4scale2m: 7 +64b-2t1c-ethip4-ip4scale2m-rnd: 2 + +# Multiline string, empty lines (or \n) are required, +# see https://yaml-multiline.info/ + +footnote: " + [1] DONE Regression in ACL tests. The cause is the CSIT part of + an API change, Gerrit 26112. Instead of failing, the misconfigured VPP + passes the test, albeit with reduced performance. [CSIT-1739] + + [2] DONE Regression in tests using random flows. + The cause is Gerrit 26456, unpinning random seed, needed to make TRex workers + generate different sequences of packets. [CSIT-1731] + + [3] DONE Regression in base dot1q-l2xcbase suites. The cause is Gerrit 25363, + which unified dot1q handling across various tests. + Previously, this one suite was different (only handling dot1q on one port). + + [4] OPEN Progression in one test. Bisect not started yet. [CSIT-1740] + + [5] OPEN Progression in performance of tests running VPP (l2xc) inside VM. + Due to relatively high stdev of results, bisecting has not found a cause yet. + [CSIT-1738] + + [7] POSTPONED Possible anomaly, but stdev of results is high. + Currently, the performance differences are considered to probably be just noise. + + [8] OPEN Regressions in some tests with VPP in VM and using l2xcbase as vswitch. + The results have surprisingly small stdev, more investigation needed. + [CSIT-1741] + + [9] OPEN Progression in ip6 scale tests. Multiple candidate changes may have + affect code efficiency, but they have also caused the tests to fail + for a period of time. [CSIT-1735] + + [11] OPEN Progression in memif tests, mainly in avf-eth-l2xcbase-eth-2memif-1dcr. + Not sure whether all memif tests are affected, nor what the cause is. + [CSIT-1744] + + [12] OPEN Progression in some l2bdscale tests. [CSIT-1745] + + [13] DONE Stateless ACL test have the same performance in 2005.0-4 as in + 2001.0-2, the difference shown here is just a consequence of API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [14] DONE Statefull ACL test have better performance in 2005.0-4 as in + 2001.0-2, but the difference shown here is inflated due to API change + having a performance impact when VPP version does not match CSIT version. + [CSIT-1739] + + [15] OPEN Progression in nat44 test (not scale ones). [CSIT-1747] + + [17] OPEN Progression in some vhost tests (dpdk in VM). [CSIT-1749] +" diff --git a/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca2.yaml b/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca2.yaml index 96a30ed074..32c8055d6b 100644 --- a/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca2.yaml +++ b/resources/tools/presentation/rca/rca-2n-skx-2t1c-pdr-rca2.yaml @@ -1,35 +1,31 @@ -64b-2t1c-avf-dot1q-ip4base: 10 -64b-2t1c-avf-ethip4-ip4base: 10 -64b-2t1c-avf-ethip4-ip4scale200k: 7 -64b-2t1c-avf-ethip4-ip4scale20k: 7 +# VPP progressions. +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-avf-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-avf-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-avf-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-iacl50sl-10kflows: 13 +64b-2t1c-avf-ethip4udp-ip4base-nat44: 15 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sf-10kflows: 14 +64b-2t1c-avf-ethip4udp-ip4base-oacl50sl-10kflows: 13 +64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-eth-l2bdscale10kmaclr: 12 +64b-2t1c-eth-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 +64b-2t1c-ethip4udp-ip4base-nat44: 15 +78b-2t1c-avf-ethip6-ip6scale200k: 9 +78b-2t1c-avf-ethip6-ip6scale2m: 9 +78b-2t1c-ethip6-ip6scale200k: 9 +78b-2t1c-ethip6-ip6scale2m: 9 +78b-2t1c-ethip6-ip6scale20k: 9 +78b-2t1c-avf-ethip6-ip6scale20k: 9 +# VPP regressions. 64b-2t1c-avf-ethip4-ip4scale2m: 7 -64b-2t1c-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-dot1q-l2xcbase: 5 -64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-eth-l2xcbase-eth-2memif-1dcr: 11 64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 8 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm: 9 -64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 -64b-2t1c-ethip4udp-ip4base-nat44: 6 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[5] OPEN, dot1q-l2xcbase progression, retro-inspection of - weekly ndrpdr tests points to ge-22805, automated bisect script does - not work due to frequent API changes, [CSIT-1699], [CSIT-1705]. - - [6] DONE, ip4base-nat44 regression, ge-23963 - (https://gerrit.fd.io/r/c/vpp/+/23963#message-044278e6_752c3327). - - [7] WIP, avf-ip4scale regression, CANDIDATE(S) before ge-22699, - [CSIT-1699], [CSIT-1706]. - - [8] OPEN, VPP vhost-user with VPP-inside-VM higher than before stdev - of PDR throughput, under investigation, [CSIT-1699], [CSIT-1704]. - - [9] WIP, vhost-user with testpmd-in-VM progression, CANDIDATE(S) - before 22277, [CSIT-1699], [CSIT-1707]. - - [10] WIP, avf-ip4base regression, CANDIDATE(S) range - ge-18361..ge-24505, [CSIT-1699], [CSIT-1708]. +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 8 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 - [11] DONE, memif regression, CANDIDATE(S) confirmed ge-23801. -" \ No newline at end of file +# Footnotes are in RCA1 file. diff --git a/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca1.yaml b/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca1.yaml deleted file mode 100644 index 6d450e9382..0000000000 --- a/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca1.yaml +++ /dev/null @@ -1,25 +0,0 @@ -64b-2t1c-avf-dot1q-ip4base: 1 -64b-2t1c-avf-dot1q-l2bdbasemaclrn-gbp: 1 -64b-2t1c-avf-eth-l2patch: 2 -64b-2t1c-avf-eth-l2xcbase: 2 -64b-2t1c-avf-ethip4-ip4base: 1 -64b-2t1c-eth-l2patch: 2 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 4 -64b-2t1c-ethip4-ip4base: 1 -64b-2t1c-ethip4udp-ip4base-iacl50sf-10kflows: 1 -64b-2t1c-ethip4udp-ip4base-oacl50sl-10kflows: 1 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[1] DONE, Impact of upgrades: i) Skx ucode from 0x2000043 to - 0x2000065, ii) Linux kernel from 4.15.0-60 to 4.15.0-72 and iii) - SuperMicro motherboard BIOS from 3.0c to 3.2. - - [2] DONE, Applied fix of FVL NIC firmware 6.0.1 for increasing TRex - Mpps rate from 27 Mpps to 37 Mpps, [CSIT-1503], [TRex-519]. - - [3] DONE, Applied VPP PAPI fix to enable memif zero-copy, - [CSIT-1592], [VPP-1764]. - - [4] OPEN, Higher than before StDev of PDR throughput for VPP - vhost-user with VPP-inside-VM, under investigation, [CSIT-1699], - [CSIT-1704]. -" \ No newline at end of file diff --git a/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca2.yaml b/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca2.yaml deleted file mode 100644 index e0598dee08..0000000000 --- a/resources/tools/presentation/rca/rca-3n-skx-2t1c-ndr-rca2.yaml +++ /dev/null @@ -1,40 +0,0 @@ -# TODO: Number only the real RCA2 causes. -64b-2t1c-eth-l2patch: 5 -64b-2t1c-eth-l2xcbase-eth-2memif-1dcr: 11 -64b-2t1c-eth-l2xcbase-eth-2memif-1lxc: 11 -64b-2t1c-eth-l2bdbasemaclrn-eth-2memif-1lxc: 11 -64b-2t1c-dot1q-l2xcbase: 5 -64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm: 9 -64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 -64b-2t1c-ethip4ipsec10000tnlsw-ip4base-int-aes256gcm: 12 -64b-2t1c-avf-ethip4-ip4base: 10 -64b-2t1c-avf-ethip4-ip4scale200k: 7 -64b-2t1c-avf-ethip4-ip4scale20k: 7 -64b-2t1c-avf-ethip4-ip4scale2m: 7 -64b-2t1c-ethip4udp-ip4base-nat44: 6 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[5] OPEN, dot1q-l2xcbase progression, retro-inspection of - weekly ndrpdr tests points to ge-22805, automated bisect script does - not work due to frequent API changes, [CSIT-1699], [CSIT-1705]. - - [6] DONE, ip4base-nat44 regression, ge-23963 - (https://gerrit.fd.io/r/c/vpp/+/23963#message-044278e6_752c3327). - - [7] WIP, avf-ip4scale regression, CANDIDATE(S) before ge-22699, - [CSIT-1699], [CSIT-1706]. - - [8] OPEN, VPP vhost-user with VPP-inside-VM higher than before stdev - of PDR throughput, under investigation, [CSIT-1699], [CSIT-1704]. - - [9] WIP, vhost-user with testpmd-in-VM progression, CANDIDATE(S) - before 22277, [CSIT-1699], [CSIT-1707]. - - [10] WIP, avf-ip4base regression, CANDIDATE(S) range - ge-18361..ge-24505, [CSIT-1699], [CSIT-1708]. - - [11] DONE, memif regression, CANDIDATE(S) confirmed ge-23801. - - [12] WIP, ipsec tnl sw scale regression, CANDIDATE(S) before - ge-23557, [CSIT-1699], [CSIT-xxxx]. -" diff --git a/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca1.yaml b/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca1.yaml index 6d450e9382..05f878e7fe 100644 --- a/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca1.yaml +++ b/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca1.yaml @@ -1,25 +1,57 @@ -64b-2t1c-avf-dot1q-ip4base: 1 -64b-2t1c-avf-dot1q-l2bdbasemaclrn-gbp: 1 -64b-2t1c-avf-eth-l2patch: 2 -64b-2t1c-avf-eth-l2xcbase: 2 -64b-2t1c-avf-ethip4-ip4base: 1 -64b-2t1c-eth-l2patch: 2 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 4 -64b-2t1c-ethip4-ip4base: 1 -64b-2t1c-ethip4udp-ip4base-iacl50sf-10kflows: 1 -64b-2t1c-ethip4udp-ip4base-oacl50sl-10kflows: 1 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[1] DONE, Impact of upgrades: i) Skx ucode from 0x2000043 to - 0x2000065, ii) Linux kernel from 4.15.0-60 to 4.15.0-72 and iii) - SuperMicro motherboard BIOS from 3.0c to 3.2. - - [2] DONE, Applied fix of FVL NIC firmware 6.0.1 for increasing TRex - Mpps rate from 27 Mpps to 37 Mpps, [CSIT-1503], [TRex-519]. - - [3] DONE, Applied VPP PAPI fix to enable memif zero-copy, - [CSIT-1592], [VPP-1764]. - - [4] OPEN, Higher than before StDev of PDR throughput for VPP - vhost-user with VPP-inside-VM, under investigation, [CSIT-1699], - [CSIT-1704]. -" \ No newline at end of file +# CSIT progressions. +64b-2t1c-avf-1lbvpplacp-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-avf-1lbvpplacp-dot1q-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 7 +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-eth-l2xcbase: 4 +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 5 +64b-2t1c-avf-ethip4-ip4base-eth-2vhostvr1024-1vm-vppip4: 5 +64b-2t1c-ethip4-ip4base-eth-2vhostvr1024-1vm: 7 +# CSIT regressions. +64b-2t1c-avf-eth-l2bdscale1mmaclrn: 7 +64b-2t1c-avf-ethip4-ip4scale2m: 7 +64b-2t1c-ethip4-ip4scale2m: 7 +imix-2t1c-avf-ethip4ipsec4tnlsw-ip4base-int-aes256gcm: 6 +imix-2t1c-avf-ethip4ipsec1000tnlsw-ip4base-int-aes256gcm: 6 +imix-2t1c-avf-ethip4ipsec10000tnlsw-ip4base-int-aes256gcm: 6 +imix-2t1c-ethip4ipsec10000tnlsw-ip4base-int-aes256gcm: 6 +imix-2t1c-ethip4ipsec4tnlsw-ip4base-int-aes256gcm: 6 + +# Multiline string, empty lines (or \n) are required, +# see https://yaml-multiline.info/ + +footnote: " + [4] OPEN Progression in one test. Bisect not started yet. [CSIT-1740] + + [5] OPEN Progression in performance of tests running VPP (l2xc) inside VM. + Due to relatively high stdev of results, bisecting has not found a cause yet. + [CSIT-1738] + + [6] OPEN Regression in CSIT, one specific test showing too small stdev + to be considered noise. Tentatively marking also other ipsec anomalies + with this, although their stdev are high enough to be explained + as maybe just noise. [CSIT-1742] + + [7] POSTPONED Possible anomaly, but stdev of results is high. + Currently, the performance differences are considered to probably be just noise. + + [8] OPEN Regressions in some tests with VPP in VM and using l2xcbase as vswitch. + The results have surprisingly small stdev, more investigation needed. + [CSIT-1741] + + [9] OPEN Progression in ip6 scale tests. Multiple candidate changes may have + affect code efficiency, but they have also caused the tests to fail + for a period of time. [CSIT-1735] + + [10] OPEN Progression in ip6 base tests with dot1q. [CSIT-1746] + + [11] OPEN Progression in memif tests, mainly in avf-eth-l2xcbase-eth-2memif-1dcr. + Not sure whether all memif tests are affected, nor what the cause is. + [CSIT-1744] + + [12] OPEN Progression in some l2bdscale tests. [CSIT-1745] + + [16] OPEN Progression in IPsec tests, only for aes128cbc-hmac512sha. [CSIT-1748] + + [17] OPEN Progression in some vhost tests (dpdk in VM). [CSIT-1749] +" diff --git a/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca2.yaml b/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca2.yaml index e0598dee08..25b4e65271 100644 --- a/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca2.yaml +++ b/resources/tools/presentation/rca/rca-3n-skx-2t1c-pdr-rca2.yaml @@ -1,40 +1,24 @@ -# TODO: Number only the real RCA2 causes. -64b-2t1c-eth-l2patch: 5 -64b-2t1c-eth-l2xcbase-eth-2memif-1dcr: 11 -64b-2t1c-eth-l2xcbase-eth-2memif-1lxc: 11 +# VPP progressions. +1518b-2t1c-avf-ethip4ipsec4tnlsw-ip4base-int-aes128cbc-hmac512sha: 16 +64b-2t1c-avf-eth-l2bdscale100kmaclrn: 12 +64b-2t1c-avf-eth-l2bdscale10kmaclrn: 12 +64b-2t1c-avf-eth-l2xcbase-eth-2memif-1dcr: 11 +64b-2t1c-avf-eth-l2xcbase-eth-2memif-1lxc: 11 +64b-2t1c-avf-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 +64b-2t1c-avf-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 +64b-2t1c-avf-ethip4-ip4base-eth-2vhostvr1024-1vm: 7 64b-2t1c-eth-l2bdbasemaclrn-eth-2memif-1lxc: 11 -64b-2t1c-dot1q-l2xcbase: 5 -64b-2t1c-dot1q-l2bdbasemaclrn-eth-2memif-1dcr: 11 -64b-2t1c-eth-l2xcbase-eth-2vhostvr1024-1vm: 9 +64b-2t1c-eth-l2bdbasemaclrn-eth-2vhostvr1024-1vm: 17 64b-2t1c-ethip4-ip4base-eth-2memif-1dcr: 11 -64b-2t1c-ethip4ipsec10000tnlsw-ip4base-int-aes256gcm: 12 -64b-2t1c-avf-ethip4-ip4base: 10 -64b-2t1c-avf-ethip4-ip4scale200k: 7 -64b-2t1c-avf-ethip4-ip4scale20k: 7 +64b-2t1c-ethip4-ip4base-eth-2vhostvr1024-1vm: 17 +78b-2t1c-avf-dot1q-ip6base: 10 +78b-2t1c-avf-ethip6-ip6scale200k: 9 +78b-2t1c-avf-ethip6-ip6scale20k: 9 +78b-2t1c-avf-ethip6-ip6scale2m: 9 +78b-2t1c-ethip6-ip6scale2m: 9 +imix-2t1c-avf-ethip4ipsec4tnlsw-ip4base-int-aes128cbc-hmac512sha: 16 +# VPP regressions. +64b-2t1c-avf-eth-l2xcbase-eth-2vhostvr1024-1vm-vppl2xc: 8 64b-2t1c-avf-ethip4-ip4scale2m: 7 -64b-2t1c-ethip4udp-ip4base-nat44: 6 -# Multiline string, empty lines (or \n) are required, see https://yaml-multiline.info/ -footnote: "[5] OPEN, dot1q-l2xcbase progression, retro-inspection of - weekly ndrpdr tests points to ge-22805, automated bisect script does - not work due to frequent API changes, [CSIT-1699], [CSIT-1705]. - [6] DONE, ip4base-nat44 regression, ge-23963 - (https://gerrit.fd.io/r/c/vpp/+/23963#message-044278e6_752c3327). - - [7] WIP, avf-ip4scale regression, CANDIDATE(S) before ge-22699, - [CSIT-1699], [CSIT-1706]. - - [8] OPEN, VPP vhost-user with VPP-inside-VM higher than before stdev - of PDR throughput, under investigation, [CSIT-1699], [CSIT-1704]. - - [9] WIP, vhost-user with testpmd-in-VM progression, CANDIDATE(S) - before 22277, [CSIT-1699], [CSIT-1707]. - - [10] WIP, avf-ip4base regression, CANDIDATE(S) range - ge-18361..ge-24505, [CSIT-1699], [CSIT-1708]. - - [11] DONE, memif regression, CANDIDATE(S) confirmed ge-23801. - - [12] WIP, ipsec tnl sw scale regression, CANDIDATE(S) before - ge-23557, [CSIT-1699], [CSIT-xxxx]. -" +# Footnotes are in RCA1 file. -- cgit 1.2.3-korg