On Tue, Nov 10, 2020 at 2:09 AM Jakub Kicinski kuba@kernel.org wrote:
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.
That would be great, but allow me to resend V2 to get rid of case 1 first. Thanks!