On Sun, Nov 8, 2020 at 7:02 AM Jakub Kicinski kuba@kernel.org wrote:
On Thu, 5 Nov 2020 18:50:51 +0800 Po-Hsu Lin wrote:
This test will treat all non-zero return codes as failures, it will make the pmtu.sh test script being marked as FAILED when some sub-test got skipped.
Improve the result processing by
- Only mark the whole test script as SKIP when all of the sub-tests were skipped
- If the sub-tests were either passed or skipped, the overall result will be PASS
- If any of them has failed, the overall result will be FAIL
- Treat other return codes (e.g. 127 for command not found) as FAIL
Signed-off-by: Po-Hsu Lin po-hsu.lin@canonical.com
Patch 1 looks like a cleanup while patch 2 is more of a fix, can we separate the two and apply the former to -next and latter to 5.10? They shouldn't conflict, right?
Hello Jakub,
Yes the first patch is just changing return code to $ksft_skip, the real fix is the second one. However the second patch was based on the first one, if we want to apply them separately we might need to change this $ksft_skip handling part in the second patch.
What should I do to deal with this? Resend the former for -next and rebase + resend the latter (plus the fix to remove case 1) for 5.10 without the former patch? Thanks!
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index fb53987..5c86fb1 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1652,7 +1652,23 @@ run_test() { return $ret ) ret=$?
[ $ret -ne 0 ] && exitcode=1
case $ret in0)all_skipped=false[ $exitcode=$ksft_skip ] && exitcode=0;;1)all_skipped=falseexitcode=1;;Does it make sense to remove this case? The handling is identical to the default case *).
Yes you're right, we can remove this part.
$ksft_skip)[ $all_skipped = true ] && exitcode=$ksft_skip;;*)all_skipped=falseexitcode=1;;esac return $ret} @@ -1786,6 +1802,7 @@ usage() { # exitcode=0 desc=0 +all_skipped=true
while getopts :ptv o do