Struct WorkloadConfig 

pub struct WorkloadConfig {
    pub dataset_path: Option<String>,
    pub arrival_pattern: String,
    pub arrival_rate: f64,
    pub input_len_dist: LengthDistribution,
    pub output_len_dist: LengthDistribution,
    pub num_requests: Option<usize>,
    pub num_concurrent_users: Option<usize>,
    pub duration_secs: Option<f64>,
    pub seed: u64,
}

Fields

dataset_path: Option<String>

Path to dataset file (JSONL in OpenAI batch API format) If provided, dataset mode is used instead of synthetic workload

arrival_pattern: String

Arrival pattern: “poisson”, “uniform”, “burst”, “fixed_rate”, “closed_loop”, “batched”

arrival_rate: f64

Mean arrival rate (requests per second) Not used for “closed_loop” or “batched” patterns

input_len_dist: LengthDistribution

Input sequence length distribution (ignored in dataset mode)

output_len_dist: LengthDistribution

Output sequence length distribution (ignored in dataset mode)

num_requests: Option<usize>

Total number of requests to simulate (None = run until duration)

num_concurrent_users: Option<usize>

Number of concurrent users for closed-loop pattern Each user immediately sends a new request when their previous one completes

duration_secs: Option<f64>

Simulation duration in seconds (None = run until num_requests)

seed: u64

Random seed for reproducibility

Trait Implementations

impl Clone for WorkloadConfig

fn clone(&self) -> WorkloadConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for WorkloadConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for WorkloadConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.