Zero downtime deployment with cord file
When replacing a container currently we:
1. Boot the new container
2. Wait for it to become healthy
3. Stop the old container
Traefik will send requests to the old container until it notices that it
is unhealthy. But it may have stopped serving requests before that point
which can result in errors.
To get round that the new boot process is:
1. Create a directory with a single file on the host
2. Boot the new container, mounting the cord file into /tmp and
including a check for the file in the docker healthcheck
3. Wait for it to become healthy
4. Delete the healthcheck file ("cut the cord") for the old container
5. Wait for it to become unhealthy and give Traefik a couple of seconds
to notice
6. Stop the old container
The extra steps ensure that Traefik stops sending requests before the
old container is shutdown.
This commit is contained in:
@@ -3,6 +3,7 @@ require "test_helper"
|
||||
class CommandsAppTest < ActiveSupport::TestCase
|
||||
setup do
|
||||
ENV["RAILS_MASTER_KEY"] = "456"
|
||||
Kamal::Configuration.any_instance.stubs(:run_id).returns("12345678901234567890123456789012")
|
||||
|
||||
@config = { service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ], env: { "secret" => [ "RAILS_MASTER_KEY" ] } }
|
||||
end
|
||||
@@ -13,13 +14,13 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
|
||||
test "run" do
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(curl -f http://localhost:3000/up || exit 1) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
test "run with hostname" do
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 --hostname myhost -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 --hostname myhost -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(curl -f http://localhost:3000/up || exit 1) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run(hostname: "myhost").join(" ")
|
||||
end
|
||||
|
||||
@@ -27,7 +28,7 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
@config[:volumes] = ["/local/path:/container/path" ]
|
||||
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(curl -f http://localhost:3000/up || exit 1) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
@@ -35,7 +36,7 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
@config[:healthcheck] = { "path" => "/healthz" }
|
||||
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/healthz || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(curl -f http://localhost:3000/healthz || exit 1) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
@@ -43,7 +44,7 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
@config[:healthcheck] = { "cmd" => "/bin/up" }
|
||||
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"/bin/up\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(/bin/up) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
@@ -51,7 +52,7 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
@config[:servers] = { "web" => { "hosts" => [ "1.1.1.1" ], "healthcheck" => { "cmd" => "/bin/healthy" } } }
|
||||
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"/bin/healthy\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(/bin/healthy) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
@@ -66,7 +67,7 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
@config[:logging] = { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => "3" } }
|
||||
|
||||
assert_equal \
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
"docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"(curl -f http://localhost:3000/up || exit 1) && (stat /tmp/kamal-cord/cord > /dev/null || exit 1)\" --health-interval \"1s\" --volume $(pwd)/.kamal/cords/app-web-12345678901234567890123456789012:/tmp/kamal-cord --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.run.join(" ")
|
||||
end
|
||||
|
||||
@@ -83,18 +84,6 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
new_command.start.join(" ")
|
||||
end
|
||||
|
||||
test "start_or_run" do
|
||||
assert_equal \
|
||||
"docker start app-web-999 || docker run --detach --restart unless-stopped --name app-web-999 -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.start_or_run.join(" ")
|
||||
end
|
||||
|
||||
test "start_or_run with hostname" do
|
||||
assert_equal \
|
||||
"docker start app-web-999 || docker run --detach --restart unless-stopped --name app-web-999 --hostname myhost -e KAMAL_CONTAINER_NAME=\"app-web-999\" --env-file .kamal/env/roles/app-web.env --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
|
||||
new_command.start_or_run(hostname: "myhost").join(" ")
|
||||
end
|
||||
|
||||
test "stop" do
|
||||
assert_equal \
|
||||
"docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker stop",
|
||||
@@ -342,6 +331,20 @@ class CommandsAppTest < ActiveSupport::TestCase
|
||||
assert_equal "rm -f .kamal/env/roles/app-web.env", new_command.remove_env_file.join(" ")
|
||||
end
|
||||
|
||||
test "cord" do
|
||||
assert_equal "docker inspect -f '{{ range .Mounts }}{{ .Source }} {{ .Destination }} {{ end }}' app-web-123 | awk '$2 == \"/tmp/kamal-cord\" {print $1}'", new_command.cord(version: 123).join(" ")
|
||||
end
|
||||
|
||||
test "tie cord" do
|
||||
assert_equal "mkdir -p . ; touch cordfile", new_command.tie_cord("cordfile").join(" ")
|
||||
assert_equal "mkdir -p corddir ; touch corddir/cordfile", new_command.tie_cord("corddir/cordfile").join(" ")
|
||||
assert_equal "mkdir -p /corddir ; touch /corddir/cordfile", new_command.tie_cord("/corddir/cordfile").join(" ")
|
||||
end
|
||||
|
||||
test "cut cord" do
|
||||
assert_equal "rm -r corddir", new_command.cut_cord("corddir").join(" ")
|
||||
end
|
||||
|
||||
private
|
||||
def new_command(role: "web")
|
||||
Kamal::Commands::App.new(Kamal::Configuration.new(@config, destination: @destination, version: "999"), role: role)
|
||||
|
||||
Reference in New Issue
Block a user