diff --git a/scripts/sk_collect_dumps/readme.md b/scripts/sk_collect_dumps/readme.md index 52b73e9495..3afeb778dd 100644 --- a/scripts/sk_collect_dumps/readme.md +++ b/scripts/sk_collect_dumps/readme.md @@ -1,25 +1,15 @@ # 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): +``` +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') +# check +echo $AUTH_TOKEN +``` +2. Run ansible playbooks to collect .json dumps from all safekeepers and store them in `./result` directory. +``` +# in aws repo, cd .github/ansible and run e.g. (ajusting profile and region in vars and limit): +AWS_DEFAULT_PROFILE=dev ansible-playbook -i inventory_aws_ec2.yaml -i staging.us-east-2.vars.yaml -e @ssm_config -l 'safekeeper:&us_east_2' -e "auth_token=${AUTH_TOKEN}" --check ~/neon/neon/scripts/sk_collect_dumps/remote.yaml +``` +It will put the results to .results directory *near the playbook*. 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 - -AWS_DEFAULT_PROFILE=dev ansible-playbook -i ../../.github/ansible/staging.eu-west-1.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml -``` - -## How to use ansible (prod) - -``` -AWS_DEFAULT_PROFILE=prod ansible-playbook -i ../../.github/ansible/prod.us-west-2.hosts.yaml -e @../../.github/ansible/ssm_config remote.yaml - -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 -``` - diff --git a/scripts/sk_collect_dumps/remote.yaml b/scripts/sk_collect_dumps/remote.yaml index 29ce83efde..2ea8d24f48 100644 --- a/scripts/sk_collect_dumps/remote.yaml +++ b/scripts/sk_collect_dumps/remote.yaml @@ -1,5 +1,5 @@ - name: Fetch state dumps from safekeepers - hosts: safekeepers + hosts: safekeeper gather_facts: False remote_user: "{{ remote_user }}" @@ -8,6 +8,8 @@ get_url: url: "http://{{ inventory_hostname }}:7676/v1/debug_dump?dump_all=true&dump_disk_content=false" dest: "/tmp/{{ inventory_hostname }}.json" + headers: + Authorization: "Bearer {{ auth_token }}" - name: Fetch file from remote hosts fetch: diff --git a/scripts/sk_collect_dumps/upload.sh b/scripts/sk_collect_dumps/upload.sh index 2e54ecba1c..5189883fcb 100755 --- a/scripts/sk_collect_dumps/upload.sh +++ b/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'->'mem_state'->>'backup_lsn')::bigint AS backup_lsn, - (data->'memory'->'mem_state'->>'commit_lsn')::bigint AS commit_lsn, - (data->'memory'->'mem_state'->>'peer_horizon_lsn')::bigint AS peer_horizon_lsn, - (data->'memory'->'mem_state'->>'remote_consistent_lsn')::bigint AS remote_consistent_lsn, - (data->'memory'->>'write_lsn')::bigint AS write_lsn, + (data->'memory'->>'flush_lsn')::pg_lsn AS flush_lsn, + (data->'memory'->'mem_state'->>'backup_lsn')::pg_lsn AS backup_lsn, + (data->'memory'->'mem_state'->>'commit_lsn')::pg_lsn AS commit_lsn, + (data->'memory'->'mem_state'->>'peer_horizon_lsn')::pg_lsn AS peer_horizon_lsn, + (data->'memory'->'mem_state'->>'remote_consistent_lsn')::pg_lsn AS remote_consistent_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'->>'commit_lsn')::bigint AS disk_commit_lsn, + (data->'control_file'->>'backup_lsn')::pg_lsn AS disk_backup_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'->>'peer_horizon_lsn')::bigint AS disk_peer_horizon_lsn, - (data->'control_file'->>'timeline_start_lsn')::bigint AS timeline_start_lsn, - (data->'control_file'->>'remote_consistent_lsn')::bigint AS disk_remote_consistent_lsn + (data->'control_file'->>'local_start_lsn')::pg_lsn AS local_start_lsn, + (data->'control_file'->>'peer_horizon_lsn')::pg_lsn AS disk_peer_horizon_lsn, + (data->'control_file'->>'timeline_start_lsn')::pg_lsn AS timeline_start_lsn, + (data->'control_file'->>'remote_consistent_lsn')::pg_lsn AS disk_remote_consistent_lsn FROM tmp_json EOF