From 26d3d97f12db29dbad5bcdf7f698af0498c77e02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20K=C4=99pie=C5=84?= Date: Mon, 7 Aug 2023 11:26:58 +0200 Subject: [PATCH] Wait until fstrm_capture is ready The fstrm_capture utility is started in the background during the "dnstap" system test. Consequently, "rndc dnstap-reopen" and similar commands may be executed before fstrm_capture starts listening on the Unix domain socket it is configured to receive dnstap data on. This results in the dnstap data sent to that socket in the meantime to be lost; while the fstrm writer thread is able to recover from such a scenario within a couple of seconds (by reopening the configured dnstap destination itself), only one write attempt is made for data successfully queued to the writer thread, so dnstap frames can still be lost in the process. This may happen during the "dnstap" system test, leading to the dnstap output file being empty, which in turn causes the test to fail. Fix by waiting until fstrm_capture starts listening on the Unix domain socket it is configured to use before asking named to reopen the configured dnstap destination. Since various fstrm_capture versions log different messages when the listening socket is set up, wait for a common string that works for all fstrm_capture versions released to date. Add a few extra debug messages indicating test progress and make the test fail if the expected fstrm_capture log message is not generated within 10 seconds. --- bin/tests/system/dnstap/tests.sh | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bin/tests/system/dnstap/tests.sh b/bin/tests/system/dnstap/tests.sh index c6bad88475..42189e1486 100644 --- a/bin/tests/system/dnstap/tests.sh +++ b/bin/tests/system/dnstap/tests.sh @@ -78,9 +78,14 @@ mv ns1/dnstap.out ns1/dnstap.out.save mv ns2/dnstap.out ns2/dnstap.out.save if [ -n "$FSTRM_CAPTURE" ] ; then + ret=0 + echo_i "starting fstrm_capture" $FSTRM_CAPTURE -t protobuf:dnstap.Dnstap -u ns4/dnstap.out \ -w dnstap.out > fstrm_capture.out.1 2>&1 & fstrm_capture_pid=$! + wait_for_log 10 "socket path ns4/dnstap.out" fstrm_capture.out.1 || ret=1 + if [ $ret != 0 ]; then echo_i "failed"; fi + status=$((status + ret)) fi $RNDCCMD -s 10.53.0.1 dnstap-reopen | sed 's/^/ns1 /' | cat_i @@ -673,10 +678,14 @@ EOF mv dnstap.out dnstap.out.save + echo_i "restarting fstrm_capture" $FSTRM_CAPTURE -t protobuf:dnstap.Dnstap -u ns4/dnstap.out \ -w dnstap.out > fstrm_capture.out.2 2>&1 & fstrm_capture_pid=$! - sleep 1 + wait_for_log 10 "socket path ns4/dnstap.out" fstrm_capture.out.2 || { + echo_i "failed" + ret=1 + } $RNDCCMD -s 10.53.0.4 dnstap -reopen | sed 's/^/ns4 /' | cat_i $DIG $DIGOPTS @10.53.0.4 a.example > dig.out