From ef455a92838ee0e450d145fd597002632aceed54 Mon Sep 17 00:00:00 2001
From: Erwan Velu <erwan@redhat.com>
Date: Thu, 9 Mar 2017 14:37:25 +0100
Subject: [PATCH] docker: Adding docker_exec.sh

When debugging containers, it's always a pain understanding why a fault occured.
This is especially true since the last exec() call will make the container being stopped if the command fails.

This commit is about creating a trick to catch errors and preventing the container from dying.

This first implies adding some 'trap ERR' to catch errors but as per
docker environment, PID 1 received the SIGTERM when 'docker stop'
command occurs. So SIGTERM have to be forwarded to the exec'd process.

The current implementation is split in two parts:
- handling the ERR
- handling exec + SIGTERM

For the ERR, set_trap_err() does install the ERR trap and executes
trap_error() if triggered. This function is just displaying information
to the user and fall in sleep to keep the PID 1 alive for ever.

As the container is in sleep, it is possible to spawn a new bash in it
by using the 'docker exec' command. A special trick here, is that new
bash will reimport the 'env' context of PID 1 by loading a modified
~/.bashrc.

This file is also providing a override function of the built-in exec()
call. It does install the SIGTERM trap, spawn the desired command in
background and wait it to die before exiting with its return value.

The spawned process is not PID 1 so the SIGTERM trap will forward it to
the proper PID and then sucide itself with the appropriate return value.

The beauty of that is that sourcing docker_exec.sh is enough to get all
thoses features at once as this script is executing set_trap_err()
by default and overrides the exec() built-in function.

A typical usage looks like :

  if [ "$MY_DEBUG_CONDITION" = "what_ever_you_want" ]; then
    source docker_exec.sh
  fi

Note: I'm not really happy about the NOTRAP variable to disengage the
'trap ERR' but I didn't found a way to remove it from the SIGTERM trap
in an efficient way :/
---
 .../kraken/ubuntu/16.04/daemon/docker_exec.sh | 63 +++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 ceph-releases/kraken/ubuntu/16.04/daemon/docker_exec.sh

diff --git a/ceph-releases/kraken/ubuntu/16.04/daemon/docker_exec.sh b/ceph-releases/kraken/ubuntu/16.04/daemon/docker_exec.sh
new file mode 100644
index 000000000..d90023737
--- /dev/null
+++ b/ceph-releases/kraken/ubuntu/16.04/daemon/docker_exec.sh
@@ -0,0 +1,63 @@
+function set_trap_err {
+  # Let's propagate traps to all functions
+  set -E
+
+  # Let's call trap_error if we catch an ERR
+  trap 'trap_error' ERR
+}
+
+NOTRAP=
+function trap_error {
+  set +x
+  if [ -z "$NOTRAP" ]; then
+    echo "An issue occured and you asked me to stay alive."
+    echo "You can connect to me with: sudo docker exec -i -t $HOSTNAME /bin/bash"
+    echo "The current environment variables will be reloaded by this bash to be in a similar context."
+    echo "When debugging is over stop me with: pkill sleep"
+    echo "I'll sleep for 365 days waiting for you darling, bye bye"
+
+    # exporting current environement so the next bash will be in the same setup
+    for value in $(env); do
+      echo "export $value" >> /root/.bashrc
+    done
+
+    sleep 365d
+  else
+    # If NOTRAP is defined, we need to return true to avoid triggering an ERR
+    true
+  fi
+}
+
+child_for_exec=1
+function _term {
+  echo "Sending SIGTERM to PID $child_for_exec"
+
+  # Disabling the ERR trap before killing the process
+  # That's an expected failure so don't handle it
+  # Doing "trap ERR" or "trap - ERR" didn't worked :/
+  NOTRAP="yes"
+
+  kill -TERM "$child_for_exec" 2>/dev/null
+}
+
+function exec {
+  # This function overrides the built-in exec() call
+  # It starts the process in background to catch ERR but
+  # as per docker requirement, forward the SIGTERM to it.
+  trap _term SIGTERM
+
+  $@ &
+  child_for_exec=$!
+  echo "exec: PID $child_for_exec: spawning $@"
+  wait "$child_for_exec"
+  return_code=$?
+  echo "exec: PID $child_for_exec: exit $return_code"
+  exit $return_code
+}
+
+########
+# Main #
+########
+# Let's engage set_trap_err
+# and override the default exec() built-in
+set_trap_err