Skip to content

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Doc: random-delay-multiplier (#1062)

Kilian Lieret5b816dd0d706
diff --git a/docs/usage/batch_mode.md b/docs/usage/batch_mode.md
index 0cca72c3..de4d4df1 100644
--- a/docs/usage/batch_mode.md
+++ b/docs/usage/batch_mode.md
@@ -79,6 +79,11 @@ You'll see output that looks like this (only with 3 workers instead of 30):
!!! tip "All command line options"
See [`RunBatchConfig`](../reference/run_batch_config.md/#sweagent.run.run_batch.RunBatchConfig) for an overview of all options.
+When starting a lot of parallel instances with the docker backend, it might happen that you see some bottleneck effects
+(e.g., when running on a platform with few CPUs, you might see some timeouts because there's not enough CPUs to handle the startup of all containers in time).
+In this case, please set `--random_delay_multiplier` to e.g., 1. This means that every worker will wait a random time between `0s` and `1s * #workers` before starting,
+thereby easing CPU pressure. Default is 0.3.
+
## Loading instances from a file
```bash
diff --git a/sweagent/run/run_batch.py b/sweagent/run/run_batch.py
index 6f9684ec..2b04cc7c 100644
--- a/sweagent/run/run_batch.py
+++ b/sweagent/run/run_batch.py
@@ -89,7 +89,8 @@ class RunBatchConfig(BaseSettings, cli_implicit_flags=False):
random_delay_multiplier: float = 0.3
"""We will wait for a random amount of time between 0 and `random_delay_multiplier`
times the number of workers at the start of each instance. This is to avoid any
- potential race conditions.
+ potential race condition or issues with bottlenecks, e.g., when running on a platform
+ with few CPUs that cannot handle the startup of all containers in time.
"""
progress_bar: bool = True
"""Whether to show a progress bar. Progress bar is never shown for human models.