lkml.org 
[lkml]   [2020]   [Nov]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    Date
    SubjectRe: [PATCH 2/2] selftests: pmtu.sh: improve the test result processing
    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 in
    > > + 0)
    > > + all_skipped=false
    > > + [ $exitcode=$ksft_skip ] && exitcode=0
    > > + ;;
    > > + 1)
    > > + all_skipped=false
    > > + exitcode=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=false
    > > + exitcode=1
    > > + ;;
    > > + esac
    > >
    > > return $ret
    > > }
    > > @@ -1786,6 +1802,7 @@ usage() {
    > > #
    > > exitcode=0
    > > desc=0
    > > +all_skipped=true
    > >
    > > while getopts :ptv o
    > > do
    >

    \
     
     \ /
      Last update: 2020-11-09 04:43    [W:6.273 / U:0.048 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site