Should any test fail, Playwright will discard entire worker process along with the browsers used and will start a new one. That way failing tests can't affect healthy ones.
You can control the maximum number of parallel worker processes via [command line](./test-cli.md) or in the [configuration file](./test-configuration.md).
Each worker process is assigned a unique sequential index that is accessible through the [`workerInfo`](./test-advanced.md#workerinfo) object. Since each worker is a process, there also is a process-wide environment variable `process.env.TEST_WORKER_INDEX` that has the same value.
Playwright Test can shard a test suite, so that it can be executed on multiple machines. For that, pass `--shard=x/y` to the command line. For example, to split the suite into three shards, each running one third of the tests: