Files
cloudron-box/src/locks.js
T
Girish Ramakrishnan bb392207ea remove global lock
Currently, the update/apptask/fullbackup/platformstart take a
global lock and cannot run in parallel. This causes situations
where when a user tries to trigger an apptask, it says "waiting for
backup to finish..." etc

The solution is to let them run in parallel. We need a lock at the
app level as app operations running in parallel would be bad (tm).
In addition, the update task needs a lock just for the update part.
We also need multi-process locks. Running tasks as processes is core
to our "kill" strategy.

Various inter process locks were explored:

* node's IPC mechanism with process.send(). But this only works for direct node.js
children. taskworker is run via sudo and the IPC does not work.

* File lock using O_EXCL. Basic ideas to create lock files. While file creation
can be done atomically, it becomes complicated to clean up lock files when
the tasks crash. We need a way to know what locks were held by the crashing task.
flock and friends are not built-into node.js

* sqlite/redis were options but introduce additional deps

* Settled on MySQL based locking. Initial plan was to have row locks
or table locks. Each row is a kind of lock. While implementing, it was found that
we need many types of locks (and not just update lock and app locks). For example,
we need locks for each task type, so that only one task type is active at a time.

* Instead of rows, we can just lock table and have a json blob in it. This hit a road
block that LOCK TABLE is per session and our db layer cannot handle this easily! i.e
when issing two db.query() it might use two different connections from the pool. We have to
expose the connection, release connection etc.

* Next idea was atomic blob update of the blob checking if old blob was same. This approach,
was finally refined into a version field.

Phew!
2024-12-07 20:41:22 +01:00

120 lines
4.3 KiB
JavaScript

'use strict';
exports = module.exports = {
setTaskId,
acquire,
wait,
release,
releaseAll,
releaseByTaskId,
TYPE_APP_PREFIX: 'app_',
TYPE_UPDATE: 'update',
TYPE_UPDATE_TASK: 'update_task',
TYPE_BACKUP_TASK: 'backup_task'
};
const assert = require('assert'),
BoxError = require('./boxerror.js'),
database = require('./database.js'),
debug = require('debug')('box:locks'),
promiseRetry = require('./promise-retry.js');
let gTaskId = null;
function setTaskId(taskId) {
assert.strictEqual(typeof taskId, 'string');
gTaskId = taskId;
}
async function read() {
const result = await database.query('SELECT version, dataJson FROM locks');
return { version: result[0].version, data: JSON.parse(result[0].dataJson) };
}
async function write(value) {
assert.strictEqual(typeof value.version, 'number');
assert.strictEqual(typeof value.data, 'object');
const result = await database.query('UPDATE locks SET dataJson=?, version=version+1 WHERE id=? AND version=?', [ JSON.stringify(value.data), 'platform', value.version ]);
if (result.affectedRows !== 1) throw new BoxError(BoxError.CONFLICT, 'Someone updated before we did');
debug(`write: current locks: ${JSON.stringify(value.data)}`);
}
function canAcquire(data, type) {
assert.strictEqual(typeof data, 'object');
assert.strictEqual(typeof type, 'string');
if (type === exports.TYPE_UPDATE) {
if (Object.keys(data).some(k => k.startsWith('app-'))) return new BoxError(BoxError.BAD_STATE, 'One or more apptasks are active');
} else if (type.startsWith(exports.TYPE_APP_PREFIX)) {
if (exports.TYPE_UPDATE in data) return new BoxError(BoxError.BAD_STATE, 'Update is active');
} else if (type === exports.TYPE_BACKUP_TASK) {
if (exports.TYPE_UPDATE_TASK in data) return new BoxError(BoxError.BAD_STATE, 'Update task is active');
} else if (type === exports.TYPE_UPDATE_TASK) {
if (exports.TYPE_BACKUP_TASK in data) return new BoxError(BoxError.BAD_STATE, 'Backup task is active');
}
return null;
}
async function acquire(type) {
assert.strictEqual(typeof type, 'string');
await promiseRetry({ times: Number.MAX_SAFE_INTEGER, interval: 100, debug, retry: (error) => error.reason === BoxError.CONFLICT }, async () => {
const { version, data } = await read();
if (type in data) throw new BoxError(BoxError.BAD_STATE, `Locked by ${data[type]}`);
const error = canAcquire(data, type);
if (error) throw error;
data[type] = gTaskId;
await write({ version, data });
debug(`acquire: ${type}`);
});
}
async function wait(type) {
assert.strictEqual(typeof type, 'string');
await promiseRetry({ times: Number.MAX_SAFE_INTEGER, interval: 10000, debug }, async () => await acquire(type));
}
async function release(type) {
assert.strictEqual(typeof type, 'string');
await promiseRetry({ times: Number.MAX_SAFE_INTEGER, interval: 100, debug, retry: (error) => error.reason === BoxError.CONFLICT }, async () => {
const { version, data } = await read();
if (!(type in data)) throw new BoxError(BoxError.BAD_STATE, `Lock ${type} was never acquired`);
if (data[type] !== gTaskId) throw new BoxError(BoxError.BAD_STATE, `Task ${gTaskId} attempted to release lock ${type} acquired by ${data[type]}`);
delete data[type];
await write({ version, data });
debug(`release: ${type}`);
});
}
async function releaseAll() {
await database.query('DELETE FROM locks');
await database.query('INSERT INTO locks (id, dataJson) VALUES (?, ?)', [ 'platform', JSON.stringify({}) ]);
debug('releaseAll: all locks released');
}
async function releaseByTaskId(taskId) {
assert.strictEqual(typeof taskId, 'string');
await promiseRetry({ times: Number.MAX_SAFE_INTEGER, interval: 100, debug, retry: (error) => error.reason === BoxError.CONFLICT }, async () => {
const { version, data } = await read();
for (const type of Object.keys(data)) {
if (data[type] === taskId) {
debug(`releaseByTaskId: task ${taskId} forgot to unlock ${type}`);
delete data[type];
}
}
await write({ version, data });
debug(`releaseByTaskId: ${taskId}`);
});
}