Files
neon/.github/ansible/deploy.yaml
Arthur Petukhovsky b067378d0d Measure cross-AZ traffic in safekeepers (#3806)
Create `safekeeper_pg_io_bytes_total` metric to track total amount of
bytes written/read in a postgres connections to safekeepers. This metric
has the following labels:
- `client_az` – availability zone of the connection initiator, or
`"unknown"`
- `sk_az` – availability zone of the safekeeper, or `"unknown"`
- `app_name` – `application_name` of the postgres client
- `dir` – data direction, either `"read"` or `"write"`
- `same_az` – `"true"`, `"false"` or `"unknown"`. Can be derived from
`client_az` and `sk_az`, exists purely for convenience.

This is implemented by passing availability zone in the connection
string, like this: `-c tenant_id=AAA timeline_id=BBB
availability-zone=AZ-1`.

Update ansible deployment scripts to add availability_zone argument
to safekeeper and pageserver in systemd service files.
2023-03-16 17:24:01 +03:00

212 lines
6.1 KiB
YAML

- name: Upload Neon binaries
hosts: storage
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: get latest version of Neon binaries
register: current_version_file
set_fact:
current_version: "{{ lookup('file', '.neon_current_version') | trim }}"
tags:
- pageserver
- safekeeper
- name: inform about versions
debug:
msg: "Version to deploy - {{ current_version }}"
tags:
- pageserver
- safekeeper
- name: upload and extract Neon binaries to /usr/local
ansible.builtin.unarchive:
owner: root
group: root
src: neon_install.tar.gz
dest: /usr/local
become: true
tags:
- pageserver
- safekeeper
- binaries
- putbinaries
- name: Deploy pageserver
hosts: pageservers
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: upload init script
when: console_mgmt_base_url is defined
ansible.builtin.template:
src: scripts/init_pageserver.sh
dest: /tmp/init_pageserver.sh
owner: root
group: root
mode: '0755'
become: true
tags:
- pageserver
- name: init pageserver
shell:
cmd: /tmp/init_pageserver.sh
args:
creates: "/storage/pageserver/data/tenants"
environment:
NEON_REPO_DIR: "/storage/pageserver/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
become: true
tags:
- pageserver
- name: read the existing remote pageserver config
ansible.builtin.slurp:
src: /storage/pageserver/data/pageserver.toml
register: _remote_ps_config
tags:
- pageserver
- name: parse the existing pageserver configuration
ansible.builtin.set_fact:
_existing_ps_config: "{{ _remote_ps_config['content'] | b64decode | sivel.toiletwater.from_toml }}"
tags:
- pageserver
- name: construct the final pageserver configuration dict
ansible.builtin.set_fact:
pageserver_config: "{{ pageserver_config_stub | combine({'id': _existing_ps_config.id }) }}"
tags:
- pageserver
- name: template the pageserver config
template:
src: templates/pageserver.toml.j2
dest: /storage/pageserver/data/pageserver.toml
become: true
tags:
- pageserver
# used in `pageserver.service` template
- name: learn current availability_zone
shell:
cmd: "curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone"
register: ec2_availability_zone
- set_fact:
ec2_availability_zone={{ ec2_availability_zone.stdout }}
- name: upload systemd service definition
ansible.builtin.template:
src: systemd/pageserver.service
dest: /etc/systemd/system/pageserver.service
owner: root
group: root
mode: '0644'
become: true
tags:
- pageserver
- name: start systemd service
ansible.builtin.systemd:
daemon_reload: yes
name: pageserver
enabled: yes
state: restarted
become: true
tags:
- pageserver
- name: post version to console
when: console_mgmt_base_url is defined
shell:
cmd: |
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
tags:
- pageserver
- name: Deploy safekeeper
hosts: safekeepers
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: upload init script
when: console_mgmt_base_url is defined
ansible.builtin.template:
src: scripts/init_safekeeper.sh
dest: /tmp/init_safekeeper.sh
owner: root
group: root
mode: '0755'
become: true
tags:
- safekeeper
- name: init safekeeper
shell:
cmd: /tmp/init_safekeeper.sh
args:
creates: "/storage/safekeeper/data/safekeeper.id"
environment:
NEON_REPO_DIR: "/storage/safekeeper/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
become: true
tags:
- safekeeper
# used in `safekeeper.service` template
- name: learn current availability_zone
shell:
cmd: "curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone"
register: ec2_availability_zone
- set_fact:
ec2_availability_zone={{ ec2_availability_zone.stdout }}
# in the future safekeepers should discover pageservers byself
# but currently use first pageserver that was discovered
- name: set first pageserver var for safekeepers
set_fact:
first_pageserver: "{{ hostvars[groups['pageservers'][0]]['inventory_hostname'] }}"
tags:
- safekeeper
- name: upload systemd service definition
ansible.builtin.template:
src: systemd/safekeeper.service
dest: /etc/systemd/system/safekeeper.service
owner: root
group: root
mode: '0644'
become: true
tags:
- safekeeper
- name: start systemd service
ansible.builtin.systemd:
daemon_reload: yes
name: safekeeper
enabled: yes
state: restarted
become: true
tags:
- safekeeper
- name: post version to console
when: console_mgmt_base_url is defined
shell:
cmd: |
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -H "Content-Type: application/json" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
tags:
- safekeeper