Page MenuHomeSoftware Heritage

30-swh-schema.sql
No OneTemporary

30-swh-schema.sql

create table dbversion
(
version int primary key,
release timestamptz not null,
description text not null
);
comment on table dbversion is 'Schema update tracking';
insert into dbversion (version, release, description)
values (12, now(), 'Work In Progress');
create table task_type (
type text primary key,
description text not null,
backend_name text not null,
default_interval interval,
min_interval interval,
max_interval interval,
backoff_factor float,
max_queue_length bigint,
num_retries bigint,
retry_delay interval
);
comment on table task_type is 'Types of schedulable tasks';
comment on column task_type.type is 'Short identifier for the task type';
comment on column task_type.description is 'Human-readable task description';
comment on column task_type.backend_name is 'Name of the task in the job-running backend';
comment on column task_type.default_interval is 'Default interval for newly scheduled tasks';
comment on column task_type.min_interval is 'Minimum interval between two runs of a task';
comment on column task_type.max_interval is 'Maximum interval between two runs of a task';
comment on column task_type.backoff_factor is 'Adjustment factor for the backoff between two task runs';
comment on column task_type.max_queue_length is 'Maximum length of the queue for this type of tasks';
comment on column task_type.num_retries is 'Default number of retries on transient failures';
comment on column task_type.retry_delay is 'Retry delay for the task';
create type task_status as enum ('next_run_not_scheduled', 'next_run_scheduled', 'completed', 'disabled');
comment on type task_status is 'Status of a given task';
create type task_policy as enum ('recurring', 'oneshot');
comment on type task_policy is 'Recurrence policy of the given task';
create type task_priority as enum('high', 'normal', 'low');
comment on type task_priority is 'Priority of the given task';
create table priority_ratio(
id task_priority primary key,
ratio float not null
);
comment on table priority_ratio is 'Oneshot task''s reading ratio per priority';
comment on column priority_ratio.id is 'Task priority id';
comment on column priority_ratio.ratio is 'Percentage of tasks to read per priority';
insert into priority_ratio (id, ratio) values ('high', 0.5);
insert into priority_ratio (id, ratio) values ('normal', 0.3);
insert into priority_ratio (id, ratio) values ('low', 0.2);
create table task (
id bigserial primary key,
type text not null references task_type(type),
arguments jsonb not null,
next_run timestamptz not null,
current_interval interval,
status task_status not null,
policy task_policy not null default 'recurring',
retries_left bigint not null default 0,
priority task_priority references priority_ratio(id),
check (policy <> 'recurring' or current_interval is not null)
);
comment on table task is 'Schedule of recurring tasks';
comment on column task.arguments is 'Arguments passed to the underlying job scheduler. '
'Contains two keys, ''args'' (list) and ''kwargs'' (object).';
comment on column task.next_run is 'The next run of this task should be run on or after that time';
comment on column task.current_interval is 'The interval between two runs of this task, '
'taking into account the backoff factor';
comment on column task.policy is 'Whether the task is one-shot or recurring';
comment on column task.retries_left is 'The number of "short delay" retries of the task in case of '
'transient failure';
comment on column task.priority is 'Policy of the given task';
create type task_run_status as enum ('scheduled', 'started', 'eventful', 'uneventful', 'failed', 'permfailed', 'lost');
comment on type task_run_status is 'Status of a given task run';
create table task_run (
id bigserial primary key,
task bigint not null references task(id),
backend_id text,
scheduled timestamptz,
started timestamptz,
ended timestamptz,
metadata jsonb,
status task_run_status not null default 'scheduled'
);
comment on table task_run is 'History of task runs sent to the job-running backend';
comment on column task_run.backend_id is 'id of the task run in the job-running backend';
comment on column task_run.metadata is 'Useful metadata for the given task run. '
'For instance, the worker that took on the job, '
'or the logs for the run.';

File Metadata

Mime Type
text/plain
Expires
Fri, Jul 4, 12:22 PM (2 w, 3 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3443473

Event Timeline