pub struct StorageOptions {
pub backend: StorageBackendConfig,
pub bloom_false_positive_rate: Option<f64>,
pub cache_mib: Option<u64>,
pub compression: StorageCompression,
pub min_step_storage_bytes: Option<u64>,
pub min_storage_bytes: Option<u64>,
}Expand description
Storage configuration for a pipeline.
JSON schema
{
"description": "Storage configuration for a pipeline.",
"type": "object",
"properties": {
"backend": {
"default": {
"name": "default"
},
"allOf": [
{
"$ref": "#/components/schemas/StorageBackendConfig"
}
]
},
"bloom_false_positive_rate": {
"description": "False-positive rate for Bloom filters on batches on storage, as a\nfraction f, where 0 < f < 1.\n\nThe false-positive rate trades off between the amount of memory used by\nBloom filters and how frequently storage needs to be searched for keys\nthat are not actually present. Typical false-positive rates and their\ncorresponding memory costs are:\n\n- 0.1: 4.8 bits per key\n- 0.01: 9.6 bits per key\n- 0.001: 14.4 bits per key\n- 0.0001: 19.2 bits per key (default)\n\nValues outside the valid range, such as 0.0, disable Bloom filters.",
"type": [
"number",
"null"
],
"format": "double"
},
"cache_mib": {
"description": "The maximum size of the in-memory storage cache, in MiB.\n\nIf set, the specified cache size is spread across all the foreground and\nbackground threads. If unset, each foreground or background thread cache\nis limited to 256 MiB.",
"type": [
"integer",
"null"
],
"minimum": 0.0
},
"compression": {
"default": "default",
"allOf": [
{
"$ref": "#/components/schemas/StorageCompression"
}
]
},
"min_step_storage_bytes": {
"description": "For a batch of data passed through the pipeline during a single step,\nthe minimum estimated number of bytes to write it to storage.\n\nThis is provided for debugging and fine-tuning and should ordinarily be\nleft unset. A value of 0 will write even empty batches to storage, and\nnonzero values provide a threshold. `usize::MAX`, the default,\neffectively disables storage for such batches. If it is set to another\nvalue, it should ordinarily be greater than or equal to\n`min_storage_bytes`.",
"type": [
"integer",
"null"
],
"minimum": 0.0
},
"min_storage_bytes": {
"description": "For a batch of data maintained as part of a persistent index during a\npipeline run, the minimum estimated number of bytes to write it to\nstorage.\n\nThis is provided for debugging and fine-tuning and should ordinarily be\nleft unset.\n\nA value of 0 will write even empty batches to storage, and nonzero\nvalues provide a threshold. `usize::MAX` would effectively disable\nstorage for such batches. The default is 10,048,576 (10 MiB).",
"type": [
"integer",
"null"
],
"minimum": 0.0
}
}
}Fields§
§backend: StorageBackendConfig§bloom_false_positive_rate: Option<f64>False-positive rate for Bloom filters on batches on storage, as a fraction f, where 0 < f < 1.
The false-positive rate trades off between the amount of memory used by Bloom filters and how frequently storage needs to be searched for keys that are not actually present. Typical false-positive rates and their corresponding memory costs are:
- 0.1: 4.8 bits per key
- 0.01: 9.6 bits per key
- 0.001: 14.4 bits per key
- 0.0001: 19.2 bits per key (default)
Values outside the valid range, such as 0.0, disable Bloom filters.
cache_mib: Option<u64>The maximum size of the in-memory storage cache, in MiB.
If set, the specified cache size is spread across all the foreground and background threads. If unset, each foreground or background thread cache is limited to 256 MiB.
compression: StorageCompression§min_step_storage_bytes: Option<u64>For a batch of data passed through the pipeline during a single step, the minimum estimated number of bytes to write it to storage.
This is provided for debugging and fine-tuning and should ordinarily be
left unset. A value of 0 will write even empty batches to storage, and
nonzero values provide a threshold. usize::MAX, the default,
effectively disables storage for such batches. If it is set to another
value, it should ordinarily be greater than or equal to
min_storage_bytes.
min_storage_bytes: Option<u64>For a batch of data maintained as part of a persistent index during a pipeline run, the minimum estimated number of bytes to write it to storage.
This is provided for debugging and fine-tuning and should ordinarily be left unset.
A value of 0 will write even empty batches to storage, and nonzero
values provide a threshold. usize::MAX would effectively disable
storage for such batches. The default is 10,048,576 (10 MiB).
Implementations§
Source§impl StorageOptions
impl StorageOptions
pub fn builder() -> StorageOptions
Trait Implementations§
Source§impl Clone for StorageOptions
impl Clone for StorageOptions
Source§fn clone(&self) -> StorageOptions
fn clone(&self) -> StorageOptions
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read more