aboutsummaryrefslogtreecommitdiffstats
path: root/docs/content/release_notes/current/vpp_performance.md
diff options
context:
space:
mode:
authorVratko Polak <vrpolak@cisco.com>2024-07-10 13:13:53 +0200
committerVratko Polak <vrpolak@cisco.com>2024-07-10 13:13:53 +0200
commit45e9ad6f66c77e750d1282883d0dc6b3053ba0ca (patch)
treef663aac3d0408a562f9f3e52c1ce2aa1e78e0570 /docs/content/release_notes/current/vpp_performance.md
parent09f9fb74865a0124262113a3fd63bfe03dfc9be2 (diff)
feat(report): Prepare 2406 known issues
- Few performance changes uncovered by edits to CSIT suites still need to be documented. Change-Id: I2573d4719141fb8792a2a59171784761a87a6303 Signed-off-by: Vratko Polak <vrpolak@cisco.com>
Diffstat (limited to 'docs/content/release_notes/current/vpp_performance.md')
-rw-r--r--docs/content/release_notes/current/vpp_performance.md79
1 files changed, 79 insertions, 0 deletions
diff --git a/docs/content/release_notes/current/vpp_performance.md b/docs/content/release_notes/current/vpp_performance.md
index ea569f547b..47ed1e5fce 100644
--- a/docs/content/release_notes/current/vpp_performance.md
+++ b/docs/content/release_notes/current/vpp_performance.md
@@ -28,6 +28,85 @@ weight: 1
3. PRESENTATION AND ANALYTICS LAYER
- Detailed views added to comparison tables.
+# Suspected issues
+
+Issues here are suspected to become known issues when confirmed by release runs.
+The suspicions come from trending and earlier runs (e.g. for RC2).
+This chapter should become empty before RCA is finished.
+
+## Suspected New
+
+Any issue listed here may have been present also in a previous release,
+but was not detected/recognized/reported enough back then.
+Also, issues previously thought fixed but now reopened are listed here.
+
+**#** | **JiraID** | **Issue Description**
+------|--------------------------------------------------|-----------------------------------------------------
+ 1 | [VPP-2118](https://jira.fd.io/browse/VPP-2118) | Performance decrease in tests involving SHA_256_128.
+
+## Suspected Previous
+
+Issues reported in previous releases which still affect the current results.
+
+**#** | **JiraID** | **Issue Description**
+------|--------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ 1 | [CSIT-1782](https://jira.fd.io/browse/CSIT-1782) | Multicore AVF tests are failing when trying to create interface. Frequency is reduced by CSIT workaround, but occasional failures do still happen.
+ 2 | [CSIT-1785](https://jira.fd.io/browse/CSIT-1785) | NAT44ED tests failing to establish all TCP sessions. At least for max scale, in allotted time (limited by session 500s timeout) due to worse slow path performance than previously measured and calibrated for. CSIT removed the max scale NAT tests to avoid this issue.
+ 3 | [CSIT-1795](https://jira.fd.io/browse/CSIT-1795) | Ocassionally not all DET44 sessions have been established: 4128767 != 4128768
+ 4 | [CSIT-1802](https://jira.fd.io/browse/CSIT-1802) | All testbeds: AF-XDP - NDR tests failing from time to time on small loss.
+ 5 | [CSIT-1804](https://jira.fd.io/browse/CSIT-1804) | 3n-tsh: NDR fails on ierrors.
+ 6 | [CSIT-1845](https://jira.fd.io/browse/CSIT-1845) | AVF 9000B any ndrpdr test may start failing due to packets not arriving in one or both directions.
+ 7 | [CSIT-1849](https://jira.fd.io/browse/CSIT-1849) | 2n-clx, 2n-icx: UDP 16m TPUT tests fail to create all sessions.
+ 8 | [CSIT-1881](https://jira.fd.io/browse/CSIT-1881) | 2n-icx: NFV density tests ocassionally breaks VPP which fails to start.
+ 9 | [CSIT-1886](https://jira.fd.io/browse/CSIT-1886) | 3n-icx: Wireguard tests with 100 and more tunnels are failing PDR criteria.
+ 10 | [CSIT-1892](https://jira.fd.io/browse/CSIT-1892) | 3n-alt: Unexpected two-band structure of ipsec and vxlan.
+ 11 | [CSIT-1896](https://jira.fd.io/browse/CSIT-1896) | Depending on topology, l3fwd avoids dut-dut link.
+ 12 | [CSIT-1901](https://jira.fd.io/browse/CSIT-1901) | 3n-icx: Negative ipackets on TB38 AVF 4c l2patch.
+ 13 | [CSIT-1904](https://jira.fd.io/browse/CSIT-1904) | DPDK 23.03 testpmd startup fails on some testbeds.
+ 14 | [CSIT-1906](https://jira.fd.io/browse/CSIT-1906) | Zero traffic with cx7 rdma. Testing migrated to mlx5-core on all Mellanox NICs.
+ 15 | [VPP-2077](https://jira.fd.io/browse/VPP-2077) | IP fragmentation: running_fragment_id is not thread safe. Causes reduced performance and failures in gtpu reassembly tests.
+ 16 | [CSIT-1914](https://jira.fd.io/browse/CSIT-1914) | TRex does not produce latency data on ICE NICs.
+ 17 | [CSIT-1915](https://jira.fd.io/browse/CSIT-1915) | The 2n-icx testbeds do not have the same performance.
+ 18 | [CSIT-1916](https://jira.fd.io/browse/CSIT-1916) | Poor CPU scaling on 2n-zn2 RDMA.
+ 19 | [CSIT-1917](https://jira.fd.io/browse/CSIT-1917) | TRex STL performance is unstable at high pps due to unsent packets.
+ 20 | [CSIT-1921](https://jira.fd.io/browse/CSIT-1921) | Two-band structure in SRv6, causes PDR failure in rare cases.
+ 21 | [CSIT-1922](https://jira.fd.io/browse/CSIT-1922) | 2n-tx2: AF_XDP MRR failures. On other testbeds MRR regressions and PDR failures.
+ 22 | [CSIT-1924](https://jira.fd.io/browse/CSIT-1924) | An l3fwd error in 200Ge2P1Cx7Veat-Mlx5 test with 9000B.
+ 23 | [CSIT-1935](https://jira.fd.io/browse/CSIT-1935) | Zero traffic reported in udpquic tests due to session close errors.
+ 24 | [CSIT-1936](https://jira.fd.io/browse/CSIT-1936) | TRex occasionally sees link down in L2 perf tests.
+ 25 | [CSIT-1937](https://jira.fd.io/browse/CSIT-1937) | Small but frequent loss in ASTF UDP on cx7 mlx5.
+ 26 | [CSIT-1938](https://jira.fd.io/browse/CSIT-1938) | 3n-alt: High scale ipsec policy tests may crash VPP.
+ 27 | [CSIT-1939](https://jira.fd.io/browse/CSIT-1939) | 3na-spr, 2n-zn2: VPP fails to start in first test cases.
+ 28 | [CSIT-1941](https://jira.fd.io/browse/CSIT-1941) | TRex may wrongly detect link bandwidth.
+ 29 | [CSIT-1942](https://jira.fd.io/browse/CSIT-1942) | 3nb-spr hoststack: Interface not up after first test.
+ 30 | [CSIT-1943](https://jira.fd.io/browse/CSIT-1943) | IMIX 4c tests may fail PDR due to ~10% loss.
+ 31 | [CSIT-1944](https://jira.fd.io/browse/CSIT-1944) | Memif LXC: unrecognized option '--no-validate'.
+ 32 | [VPP-2090](https://jira.fd.io/browse/VPP-2090) | MRR < PDR: DPDK plugin with MLX5 driver does not read full queue.
+ 33 | [VPP-2091](https://jira.fd.io/browse/VPP-2091) | Memif crashes with jumbo frames.
+ 34 | [CSIT-1946](https://jira.fd.io/browse/CSIT-1946) | Ipsec hwasync fails with large scale and multiple queues.
+ 35 | [CSIT-1947](https://jira.fd.io/browse/CSIT-1947) | VPP crash in udp nat avf 4c tests.
+ 36 | [CSIT-1948](https://jira.fd.io/browse/CSIT-1948) | NICs do not consistently distribute tunnels over RXQs depending on model or plugin.
+ 37 | [CSIT-1951](https://jira.fd.io/browse/CSIT-1951) | Combination of AVF and vhost drops all 9000B packets.
+ 38 | [CSIT-1954](https://jira.fd.io/browse/CSIT-1954) | 3n-icx: 9000B AVF ip6 tests show zero traffic in one direction due to no free tx slots.
+
+## Suspected Fixed
+
+Issues reported in previous releases which were fixed in this release:
+
+**#** | **JiraID** | **Issue Description**
+------|--------------------------------------------------|-------------------------------------------------------------
+ 1 | [CSIT-1950](https://jira.fd.io/browse/CSIT-1950) | 9000B tests with high encap overhead see fragmented packets.
+
+## Suspected Regressions
+
+Regressions visible in trending, but not confirmed in release results yet,
+or confirmed but cause not verified yet.
+
+**#** | **JiraID** | **Issue Description**
+------|--------------------------------------------------|----------------------------------------------------------------
+ 1 | [CSIT-1958](https://jira.fd.io/browse/CSIT-1958) | 3n-icx: investigate ipsec swasync regressions around 2024-04-20.
+ 2 | [CSIT-1959](https://jira.fd.io/browse/CSIT-1959) | Explain change in c6in performance.
+
# Known Issues
These are issues that cause test failures or otherwise limit usefulness of CSIT