kalugin66/windmill
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor default non-cloud-hosted timeout

Browse Source
This commit is contained in:
Ruben Fiszel
2023-08-20 16:30:31 +02:00
parent 580c4cf6ae
commit 1def1d3c66
3 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -339,7 +339,8 @@ it being synced automatically everyday.
| METRICS_ADDR | None | (ee only) The socket addr at which to expose Prometheus metrics at the /metrics path. Set to "true" to expose it on port 8001 | All |
| JSON_FMT | false | Output the logs in json format instead of logfmt | All |
| BASE_URL | http://localhost:8000 | The base url that is exposed publicly to access your instance | Server |
| TIMEOUT | 300 | The maximum time of execution of a script. When reached, the job is failed as having timedout. | Worker |
| TIMEOUT | 60 _ 60 _ 24 \* 7 (1 week) | The maximum time of execution of a script. When reached, the job is failed as having timedout. |
| SCRIPT_TOKEN_EXPIRY | 900 | The default duration period of the ephemeral-token generated at the beginning of a script | Worker |
| ZOMBIE_JOB_TIMEOUT | 30 | The timeout after which a job is considered to be zombie if the worker did not send pings about processing the job (every server check for zombie jobs every 30s) | Server |
| RESTART_ZOMBIE_JOBS | true | If true then a zombie job is restarted (in-place with the same uuid and some logs), if false the zombie job is failed | Server |
| SLEEP_QUEUE | 50 | The number of ms to sleep in between the last check for new jobs in the DB. It is multiplied by NUM_WORKERS such that in average, for one worker instance, there is one pull every SLEEP_QUEUE ms. | Worker |

4
backend/src/monitor.rs
View File

@@ -10,7 +10,7 @@ use windmill_common::{
METRICS_ENABLED,
};
use windmill_worker::{
create_token_for_owner, handle_job_error, AuthedClient, SESSION_TOKEN_EXPIRY,
create_token_for_owner, handle_job_error, AuthedClient, SCRIPT_TOKEN_EXPIRY,
};
lazy_static::lazy_static! {
@@ -116,7 +116,7 @@ async fn handle_zombie_jobs<R: rsmq_async::RsmqConnection + Send + Sync + Clone>
&job.workspace_id,
&job.permissioned_as,
"ephemeral-zombie-jobs",
*SESSION_TOKEN_EXPIRY,
*SCRIPT_TOKEN_EXPIRY,
&job.email,
)
.await

12
backend/windmill-worker/src/worker.rs
View File

@@ -77,7 +77,7 @@ pub async fn create_token_for_owner_in_bg(db: &Pool<Postgres>, job: &QueuedJob)
&job.workspace_id,
&job.permissioned_as,
"ephemeral-script",
*SESSION_TOKEN_EXPIRY,
*SCRIPT_TOKEN_EXPIRY,
&job.email,
)
.await.expect("could not create job token");
@@ -148,7 +148,8 @@ const NUM_SECS_PING: u64 = 5;
const INCLUDE_DEPS_PY_SH_CONTENT: &str = include_str!("../nsjail/download_deps.py.sh");
pub const DEFAULT_TIMEOUT: u64 = 900;
pub const DEFAULT_CLOUD_TIMEOUT: u64 = 900;
pub const DEFAULT_SELFHOSTED_TIMEOUT: u64 = 604800; // 7 days
pub const DEFAULT_SLEEP_QUEUE: u64 = 50;
// only 1 native job so that we don't have to worry about concurrency issues on non dedicated native jobs workers
@@ -217,11 +218,14 @@ lazy_static::lazy_static! {
static ref TIMEOUT: u64 = std::env::var("TIMEOUT")
.ok()
.and_then(|x| x.parse::<u64>().ok())
.unwrap_or(DEFAULT_TIMEOUT);
.unwrap_or_else(|| if *CLOUD_HOSTED { DEFAULT_CLOUD_TIMEOUT } else { DEFAULT_SELFHOSTED_TIMEOUT });
pub static ref TIMEOUT_DURATION: Duration = Duration::from_secs(*TIMEOUT);
pub static ref SESSION_TOKEN_EXPIRY: i32 = (*TIMEOUT as i32) * 2;
pub static ref SCRIPT_TOKEN_EXPIRY: i32 = std::env::var("SCRIPT_TOKEN_EXPIRY")
.ok()
.and_then(|x| x.parse::<i32>().ok())
.unwrap_or(900);
pub static ref GLOBAL_CACHE_INTERVAL: u64 = std::env::var("GLOBAL_CACHE_INTERVAL")
.ok()