From c012d6301d9828b65a8ec880bfe7ea4ad35d1349 Mon Sep 17 00:00:00 2001
From: Israel Fruchter <fruch@scylladb.com>
Date: Wed, 10 Jan 2024 21:59:42 +0200
Subject: [PATCH] fix(monitorstack): make it work when running hydara via
 podman

* podman now defaults to short-name-mode="enforcing", and the monitor stack
  doesn't able to pull images when working via socket,
  it doesn't have tty to offer which repository to alias it,
  setting short-name-mode="permissive" on ~/.config/containers/registries.conf
  alleviate this issue

* scylla-monitoring was using DOCKER_HOST inside it's start scripts, hence breaking
  our ability to use it to point to podman socket, a fix was subbmitted
  but until then we patch those out of the scripts so older collected monitoring
  data can be used

Ref: https://github.com/scylladb/scylla-monitoring/pull/2149
Fixes: #7080
---
 README.md                     |  5 +++++
 sdcm/monitorstack/__init__.py | 11 ++++++++---
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 5363e80e44..4dc0b800d1 100644
--- a/README.md
+++ b/README.md
@@ -30,6 +30,11 @@ export AWS_PROFILE=DeveloperAccessRole
 
 # Install hydra (docker holding all requirements for running SCT)
 sudo ./install-hydra.sh
+
+# if using podman, we need to disable enforcing of short name usage, without it monitoring stack won't run from withing hydra
+echo 'unqualified-search-registries = ["registry.fedoraproject.org", "registry.access.redhat.com", "docker.io", "quay.io"]
+short-name-mode="permissive"
+' > ~/.config/containers/registries.conf
 ```
 
 ### Run a test
diff --git a/sdcm/monitorstack/__init__.py b/sdcm/monitorstack/__init__.py
index 115d495185..4de6fcaf1f 100644
--- a/sdcm/monitorstack/__init__.py
+++ b/sdcm/monitorstack/__init__.py
@@ -416,8 +416,11 @@ def remove_sct_metrics(metric):
     prom_tmpl_file.write_text(yaml.safe_dump(templ_yaml))
 
     cmd = dedent("""cd {monitoring_dockers_dir};
+            # patch to make podman work for result that don't have https://github.com/scylladb/scylla-monitoring/pull/2149
+            sed -i 's/DOCKER_HOST/HOST_ADDRESS/' *.sh
+
             echo "" > UA.sh
-            ./start-all.sh \
+            bash -x ./start-all.sh \
             $(grep -q -- --no-renderer ./start-all.sh && echo "--no-renderer")  \
             $(grep -q -- --no-loki ./start-all.sh && echo "--no-loki")  \
             -g {graf_port} -m {alert_port} -p {prom_port} \
@@ -425,10 +428,12 @@ def remove_sct_metrics(metric):
             -d {monitoring_stack_data_dir} -v {scylla_version} \
             -b '-storage.tsdb.retention.time=100y' \
             -c 'GF_USERS_DEFAULT_THEME=dark'""".format(**locals()))
-    res = lr.run(cmd)
+    res = lr.run(cmd, ignore_status=True)
     if res.ok:
         LOGGER.info("Docker containers for monitoring stack are started")
-
+    else:
+        LOGGER.error("Failure to start monitoring stack: %s", res.stderr)
+        raise Exception("fail to start monitoring stack")
     return {"grafana_docker_port": graf_port,
             "alert_docker_port": alert_port,
             "prometheus_docker_port": prom_port}