tensorflow::serving::AspiredVersionsManager::Options

#include <aspired_versions_manager.h>

Config options and pluggable objects that will be used by the AspiredVersionsManager.

Summary

Public attributes

aspired_version_policy
std::unique_ptr< AspiredVersionPolicy >
The AspiredVersionPolicy to use for the manager. Must be non-null.
env = Env::Default()
Env *
The environment to use for starting threads in the thread-pool or for sleeping.
flush_filesystem_caches = false
bool
load_retry_interval_micros = 1LL * 60 * 1000 * 1000
int64
The interval, in microseconds, between each servable load retry.
manage_state_interval_micros = 100 * 1000
int64
The periodicity, in microseconds, of the thread which manages the state of the servables.
max_num_load_retries = 5
uint32
Maximum number of times we retry loading a servable, after the first failure, before we give up.
num_load_threads = 0
uint32
The number of threads in the thread-pool used to load servables.
num_unload_threads = 0
uint32
The number of threads in the thread-pool used to unload servables.
pre_load_hook
PreLoadHook
Callback to be called just before a servable is to be loaded.
resource_tracker
std::unique_ptr< ResourceTracker >
The resource tracker to use while managing servable resources.
servable_event_bus = nullptr
EventBus< ServableState > *
EventBus to publish servable state changes.

Public attributes

aspired_version_policy

std::unique_ptr< AspiredVersionPolicy > tensorflow::serving::AspiredVersionsManager::Options::aspired_version_policy

The AspiredVersionPolicy to use for the manager. Must be non-null.

env

Env * tensorflow::serving::AspiredVersionsManager::Options::env = Env::Default()

The environment to use for starting threads in the thread-pool or for sleeping.

flush_filesystem_caches

bool tensorflow::serving::AspiredVersionsManager::Options::flush_filesystem_caches = false

load_retry_interval_micros

int64 tensorflow::serving::AspiredVersionsManager::Options::load_retry_interval_micros = 1LL * 60 * 1000 * 1000

The interval, in microseconds, between each servable load retry.

If set negative, we don't wait. Default: 1 minute.

manage_state_interval_micros

int64 tensorflow::serving::AspiredVersionsManager::Options::manage_state_interval_micros = 100 * 1000

The periodicity, in microseconds, of the thread which manages the state of the servables.

Default: 100 milliseconds. If this is set less than or equal to 0, we don't run this thread at all.

max_num_load_retries

uint32 tensorflow::serving::AspiredVersionsManager::Options::max_num_load_retries = 5

Maximum number of times we retry loading a servable, after the first failure, before we give up.

num_load_threads

uint32 tensorflow::serving::AspiredVersionsManager::Options::num_load_threads = 0

The number of threads in the thread-pool used to load servables.

If set as 0, we don't use a thread-pool, and servable loads are performed serially in the manager's main work loop.

num_unload_threads

uint32 tensorflow::serving::AspiredVersionsManager::Options::num_unload_threads = 0

The number of threads in the thread-pool used to unload servables.

If set as 0, we don't use a thread-pool, and servable unloads are performed serially in the manager's main work loop.

pre_load_hook

PreLoadHook tensorflow::serving::AspiredVersionsManager::Options::pre_load_hook

Callback to be called just before a servable is to be loaded.

This will called on the same manager load thread which starts the load.

resource_tracker

std::unique_ptr< ResourceTracker > tensorflow::serving::AspiredVersionsManager::Options::resource_tracker

The resource tracker to use while managing servable resources.

Optional. If left as nullptr, we do not validate servable resource usage.

servable_event_bus

EventBus< ServableState > * tensorflow::serving::AspiredVersionsManager::Options::servable_event_bus = nullptr

EventBus to publish servable state changes.

This is optional, if unset, we don't publish.