On Mon, 9 Nov 2020 11:42:33 +0800 Po-Hsu Lin wrote:
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.
Ah, I misread the situation, ksft_skip is 4, not 2, so the patch is more than just refactoring.
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?
Let's apply both of the patches to net-next if that's fine with you. Indeed detangling them is may be more effort that it's worth.