Make sk_collect_dumps also possible with teleport (#4739)

Co-authored-by: Arseny Sher <sher-ars@yandex.ru>

scripts/sk_collect_dumps/.gitignore

@@ -1,2 +1,4 @@
 result
 *.json
+hosts
+poetry.lock

scripts/sk_collect_dumps/ansible.cfg

@@ -0,0 +1,11 @@
+[defaults]
+host_key_checking = False
+inventory=./hosts
+remote_tmp=/tmp
+remote_user=developer
+callbacks_enabled = profile_tasks
+
+[ssh_connection]
+scp_if_ssh = True
+ssh_args = -F ./ssh.cfg
+pipelining = True

scripts/sk_collect_dumps/pyproject.toml

@@ -0,0 +1,16 @@
+[tool.poetry]
+name = "sk-collect-dumps"
+version = "0.1.0"
+description = ""
+authors = ["Arseny Sher <sher-ars@yandex.ru>"]
+readme = "README.md"
+packages = [{include = "sk_collect_dumps"}]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+ansible = "^9.1.0"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

scripts/sk_collect_dumps/readme.md

@@ -1,25 +1,43 @@
 # Collect /v1/debug_dump from all safekeeper nodes
 
-1. Run ansible playbooks to collect .json dumps from all safekeepers and store them in `./result` directory.
+3. Issue admin token (add/remove .stage from url for staging/prod and setting proper API key):
-2. Run `DB_CONNSTR=... ./upload.sh prod_feb30` to upload dumps to `prod_feb30` table in specified postgres database.
-
-## How to use ansible (staging)
-
 ```
-AWS_DEFAULT_PROFILE=dev ansible-playbook -i ../../.github/ansible/staging.us-east-2.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
+# staging:
+AUTH_TOKEN=$(curl https://console.stage.neon.tech/regions/console/api/v1/admin/issue_token -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer $NEON_STAGING_KEY" -X POST -d '{"ttl_seconds": 43200, "scope": "safekeeperdata"}' 2>/dev/null | jq --raw-output '.jwt')
+# prod:
+AUTH_TOKEN=$(curl https://console.neon.tech/regions/console/api/v1/admin/issue_token -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer $NEON_PROD_KEY" -X POST -d '{"ttl_seconds": 43200, "scope": "safekeeperdata"}' 2>/dev/null | jq --raw-output '.jwt')
+# check
+echo $AUTH_TOKEN
+```
+2. Run ansible playbooks to collect .json dumps from all safekeepers and store them in `./result` directory.
 
-AWS_DEFAULT_PROFILE=dev ansible-playbook -i ../../.github/ansible/staging.eu-west-1.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
+There are two ways to do that, with ssm or tsh. ssm:
+```
+# in aws repo, cd .github/ansible and run e.g. (adjusting profile and region in vars and limit):
+AWS_DEFAULT_PROFILE=dev ansible-playbook -i inventory_aws_ec2.yaml -i staging.us-east-2.vars.yaml -e @ssm_config -l 'safekeeper:&us_east_2' -e "auth_token=${AUTH_TOKEN}" ~/neon/neon/scripts/sk_collect_dumps/remote.yaml
+```
+It will put the results to .results directory *near the playbook*.
+
+tsh:
+
+Update the inventory, if needed, selecting .build/.tech and optionally region:
+```
+rm -f hosts && echo '[safekeeper]' >> hosts
+# staging:
+tsh ls | awk '{print $1}' | grep safekeeper | grep "neon.build" | grep us-east-2 >> hosts
+# prod:
+tsh ls | awk '{print $1}' | grep safekeeper | grep "neon.tech" | grep us-east-2 >> hosts
 ```
 
-## How to use ansible (prod)
+Test ansible connection:
-
 ```
-AWS_DEFAULT_PROFILE=prod ansible-playbook -i ../../.github/ansible/prod.us-west-2.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
+ansible all -m ping -v
-
-AWS_DEFAULT_PROFILE=prod ansible-playbook -i ../../.github/ansible/prod.us-east-2.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
-
-AWS_DEFAULT_PROFILE=prod ansible-playbook -i ../../.github/ansible/prod.eu-central-1.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
-
-AWS_DEFAULT_PROFILE=prod ansible-playbook -i ../../.github/ansible/prod.ap-southeast-1.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml
 ```
 
+Download the dumps:
+```
+mkdir -p result && rm -f result/*
+ansible-playbook -e "auth_token=${AUTH_TOKEN}" remote.yaml
+```
+
+3. Run `DB_CONNSTR=... ./upload.sh prod_feb30` to upload dumps to `prod_feb30` table in specified postgres database.

scripts/sk_collect_dumps/remote.yaml

@@ -1,18 +1,37 @@
 - name: Fetch state dumps from safekeepers
-  hosts: safekeepers
+  hosts: safekeeper
   gather_facts: False
-  remote_user: "{{ remote_user }}"
     
   tasks:
-    - name: Download file
+    - name: Dump file
       get_url:
         url: "http://{{ inventory_hostname }}:7676/v1/debug_dump?dump_all=true&dump_disk_content=false"
-        dest: "/tmp/{{ inventory_hostname }}.json"
+        dest: "/tmp/{{ inventory_hostname }}-dump.json"
+        headers:
+          Authorization: "Bearer {{ auth_token }}"
 
-    - name: Fetch file from remote hosts
+    - name: install rsync
+      ansible.builtin.apt:
+        name: rsync
+        update_cache: yes
+      become: yes
+      ignore_errors: true # it can be already installed and we don't always have sudo
+
+    - name: Fetch file from remote hosts (works only with ssm)
       fetch:
-        src: "/tmp/{{ inventory_hostname }}.json"
+        src: "/tmp/{{ inventory_hostname }}-dump.json"
-        dest: "./result/{{ inventory_hostname }}.json"
+        dest: "./result/{{ inventory_hostname }}-dump.json"
         flat: yes
         fail_on_missing: no
+      when: ansible_connection == "aws_ssm"
 
+    # xxx not sure how to make ansible 'synchronize' work with tsh
+    - name: Fetch file from remote hosts
+      shell: rsync -e 'tsh ssh' -azvP "developer@{{ inventory_hostname }}:/tmp/{{ inventory_hostname }}-dump.json"  "./result/{{ inventory_hostname }}-dump.json"
+      delegate_to: localhost
+      when: ansible_connection != "aws_ssm"
+
+    - name: remove remote dumps
+      ansible.builtin.file:
+        path: "/tmp/{{ inventory_hostname }}-dump.json"
+        state: absent

scripts/sk_collect_dumps/ssh.cfg

@@ -0,0 +1,13 @@
+# Begin generated Teleport configuration for teleport.aws.neon.tech by tsh
+
+# Common flags for all teleport.aws.neon.tech hosts
+Host *
+    HostKeyAlgorithms rsa-sha2-512-cert-v01@openssh.com,rsa-sha2-256-cert-v01@openssh.com,ssh-rsa-cert-v01@openssh.com
+
+# Flags for all teleport.aws.neon.tech hosts except the proxy
+Host * !teleport.aws.neon.tech
+    Port 3022
+    ProxyCommand "/usr/local/bin/tsh" proxy ssh --cluster=teleport.aws.neon.tech --proxy=teleport.aws.neon.tech:443 %r@%h:%p
+    User developer
+
+# End generated Teleport configuration

scripts/sk_collect_dumps/upload.sh

@@ -31,22 +31,22 @@ SELECT
   (data->>'tenant_id') AS tenant_id,
   (data->>'timeline_id') AS timeline_id,
   (data->'memory'->>'active')::bool AS active,
-  (data->'memory'->>'flush_lsn')::bigint AS flush_lsn,
+  (data->'memory'->>'flush_lsn')::pg_lsn AS flush_lsn,
-  (data->'memory'->'mem_state'->>'backup_lsn')::bigint AS backup_lsn,
+  (data->'memory'->'mem_state'->>'backup_lsn')::pg_lsn AS backup_lsn,
-  (data->'memory'->'mem_state'->>'commit_lsn')::bigint AS commit_lsn,
+  (data->'memory'->'mem_state'->>'commit_lsn')::pg_lsn AS commit_lsn,
-  (data->'memory'->'mem_state'->>'peer_horizon_lsn')::bigint AS peer_horizon_lsn,
+  (data->'memory'->'mem_state'->>'peer_horizon_lsn')::pg_lsn AS peer_horizon_lsn,
-  (data->'memory'->'mem_state'->>'remote_consistent_lsn')::bigint AS remote_consistent_lsn,
+  (data->'memory'->'mem_state'->>'remote_consistent_lsn')::pg_lsn AS remote_consistent_lsn,
-  (data->'memory'->>'write_lsn')::bigint AS write_lsn,
+  (data->'memory'->>'write_lsn')::pg_lsn AS write_lsn,
   (data->'memory'->>'num_computes')::bigint AS num_computes,
-  (data->'memory'->>'epoch_start_lsn')::bigint AS epoch_start_lsn,
+  (data->'memory'->>'epoch_start_lsn')::pg_lsn AS epoch_start_lsn,
   (data->'memory'->>'last_removed_segno')::bigint AS last_removed_segno,
   (data->'memory'->>'is_cancelled')::bool AS is_cancelled,
-  (data->'control_file'->>'backup_lsn')::bigint AS disk_backup_lsn,
+  (data->'control_file'->>'backup_lsn')::pg_lsn AS disk_backup_lsn,
-  (data->'control_file'->>'commit_lsn')::bigint AS disk_commit_lsn,
+  (data->'control_file'->>'commit_lsn')::pg_lsn AS disk_commit_lsn,
   (data->'control_file'->'acceptor_state'->>'term')::bigint AS disk_term,
-  (data->'control_file'->>'local_start_lsn')::bigint AS local_start_lsn,
+  (data->'control_file'->>'local_start_lsn')::pg_lsn AS local_start_lsn,
-  (data->'control_file'->>'peer_horizon_lsn')::bigint AS disk_peer_horizon_lsn,
+  (data->'control_file'->>'peer_horizon_lsn')::pg_lsn AS disk_peer_horizon_lsn,
-  (data->'control_file'->>'timeline_start_lsn')::bigint AS timeline_start_lsn,
+  (data->'control_file'->>'timeline_start_lsn')::pg_lsn AS timeline_start_lsn,
-  (data->'control_file'->>'remote_consistent_lsn')::bigint AS disk_remote_consistent_lsn
+  (data->'control_file'->>'remote_consistent_lsn')::pg_lsn AS disk_remote_consistent_lsn
 FROM tmp_json
 EOF