[LU-19275] interop sanity-lnet test_205: Expected 2 resends found 0

• Type: Bug
• Resolution: Duplicate
• Priority: Medium
• Severity: 3
• Assignee: WC Triage
• Reporter: Maloo

Description

This issue was created by maloo for Andreas Dilger <[e-mail]>

This issue relates to the following test suite run with master client and b2_15/b2_16 server:
https://testing.whamcloud.com/test_sets/0cdab575-69ec-4488-9ebb-a5b10d949731

test_205 failed with the following error:

lnetctl ping 10.240.28.234@tcp
manage:
- ping: 
  errno: -5
  descr: ! 'failed to ping 10.240.28.234@tcp: Input/output error'
Pre resends: 2
Post resends: 2
Resends delta: 0
Pre local health: 3000
Post local health: 3000
Pre remote health: 2000
Post remote health: 1900
/usr/sbin/lnetctl peer set --health 1000 --all
/usr/sbin/lnetctl net set --health 1000 --all
/usr/sbin/lnetctl fault drop del -a
Check that 2 resends took place
Expected 2 resends found 0

Test session details:
clients: https://build.whamcloud.com/job/lustre-master/4645 - 4.18.0-553.58.1.el8_10.x86_64
servers: https://build.whamcloud.com/job/lustre-b2_15/107 - 4.18.0-553.53.1.el8_lustre.x86_64

This failed multiple times in interop testing on 2025-08-20 after recent patch landings, likely related to some of the LNet changes:

d3003b2a5a (origin/master, origin/HEAD, master) LU-16518 mdt: fix unused variable compiler warnings
41e415a1f5 LU-18925 build: 64k client do not use pgidx before defined
2fde141c02 LU-8066 obdclass: remove lprocfs release wrappers
83fa59b2d5 LU-19200 tests: Check routing/buffers/numa import
b3c718fb5f LU-18998 lnet: match size of LNet fault handling
74480d02be LU-19200 lnet: Support numa in jt_import
6686713670 LU-19200 lnet: Support buffers in jt_import
2ea6b6371c LU-19200 lnet: Support routing in jt_import
71f8fd5241 LU-10026 utils: reserve more values for compression
d9c50011bb LU-19126 lnet: Refactor jt_import netlink code
f6d68d194c LU-18359 mdd: Handle jobid strings with surrounding quotes
7fb531928d LU-15135 lnet: Add defines for state of routing
b1b3572581 LU-18207 ladvise: return -EOPNOTSUPP for unknown advice
3ccd941e2d LU-19080 compat: match kernel shrinker protocol
184b701104 LU-19246 tests: Error if FORCE_LARGE_NID=true w/o ipv6
7b82f368b4 LU-19237 llite: adopt i_version use to guard directory cache
fb6d4e95c7 LU-19237 ldiskfs: drop outdated i_version configure check
d71ebf9b03 LU-19229 ptlrpc: class_add_nids_to_uuid() allow many NIDs
ca6fdf7352 LU-19234 lst: Fix leak under emitter/parser delete (1)
dfb4416228 LU-19218 build: use common.postinst if it is available
7cd8af487a LU-19209 utils: ofd_access_log_reader usage mention log_size
f0a05f7c22 LU-19195 lnet: properly initialize LND tunables
ce7611a495 LU-19139 lnet: add accept_port_bulk module parameter
4c33ce3a86 LU-19158 ldiskfs: add trim statistics
8e9abba638 LU-19152 lnet: struct lnet_ioctl_config_ni too large for stack
84077945ce LU-19151 build: fortify memcpy dentry len
c419c500a7 LU-19141 build: convert some checks to parallel
ff5042c83b LU-18135 scripts: bad iproute rt_tables path
f26654ef23 LU-14459 tests: fix sanity/230p interop version check
b625dac234 LU-19095 mgc: notify MGS about LNet changes
08c1787f24 LU-18982 lov: Do not display lmm_stripe_offset for mdt file
e83eeb1bde LU-18436 tunefs: process to rebuild CONFIGS/mountdata file
4f2da48d57 LU-13814 clio: remove last DIO queue usage
ff25837496 LU-18877 build: handle aarch64 kernel-64k-devel
e354ba844d LU-17532 ptlrpc: LASSERT replaced by CERROR

VVVVVVV DO NOT REMOVE LINES BELOW, Added by Maloo for auto-association VVVVVVV
sanity-lnet test_205 - Expected 2 resends found 0

Issue Links

• is related to: LU-19309 Lnet interop crashes / lockups in master
• is related to: LU-17083 sanity-lnet test_205: Expected 2 resends found x