execution: fold in dependency aware caching / Fix --cache-none with loops/lazy etc (Resubmit) (#10440)
* execution: fold in dependency aware caching This makes --cache-none compatiable with lazy and expanded subgraphs. Currently the --cache-none option is powered by the DependencyAwareCache. The cache attempts to maintain a parallel copy of the execution list data structure, however it is only setup once at the start of execution and does not get meaninigful updates to the execution list. This causes multiple problems when --cache-none is used with lazy and expanded subgraphs as the DAC does not accurately update its copy of the execution data structure. DAC has an attempt to handle subgraphs ensure_subcache however this does not accurately connect to nodes outside the subgraph. The current semantics of DAC are to free a node ASAP after the dependent nodes are executed. This means that if a subgraph refs such a node it will be requed and re-executed by the execution_list but DAC wont see it in its to-free lists anymore and leak memory. Rather than try and cover all the cases where the execution list changes from inside the cache, move the while problem to the executor which maintains an always up-to-date copy of the wanted data-structure. The executor now has a fast-moving run-local cache of its own. Each _to node has its own mini cache, and the cache is unconditionally primed at the time of add_strong_link. add_strong_link is called for all of static workflows, lazy links and expanded subgraphs so its the singular source of truth for output dependendencies. In the case of a cache-hit, the executor cache will hold the non-none value (it will respect updates if they happen somehow as well). In the case of a cache-miss, the executor caches a None and will wait for a notification to update the value when the node completes. When a node completes execution, it simply releases its mini-cache and in turn its strong refs on its direct anscestor outputs, allowing for ASAP freeing (same as the DependencyAwareCache but a little more automatic). This now allows for re-implementation of --cache-none with no cache at all. The dependency aware cache was also observing the dependency sematics for the objects and UI cache which is not accurate (this entire logic was always outputs specific). This also prepares for more complex caching strategies (such as RAM pressure based caching), where a cache can implement any freeing strategy completely independently of the DepedancyAwareness requirement. * main: re-implement --cache-none as no cache at all The execution list now tracks the dependency aware caching more correctly that the DependancyAwareCache. Change it to a cache that does nothing. * test_execution: add --cache-none to the test suite --cache-none is now expected to work universally. Run it through the full unit test suite. Propagate the server parameterization for whether or not the server is capabale of caching, so that the minority of tests that specifically check for cache hits can if else. Hard assert NOT caching in the else to give some coverage of --cache-none expected behaviour to not acutally cache.
This commit is contained in:
rattus
GitHub
@@ -265,6 +265,26 @@ class HierarchicalCache(BasicCache):
|
||||
assert cache is not None
|
||||
return await cache._ensure_subcache(node_id, children_ids)
|
||||
|
||||
class NullCache:
|
||||
|
||||
async def set_prompt(self, dynprompt, node_ids, is_changed_cache):
|
||||
pass
|
||||
|
||||
def all_node_ids(self):
|
||||
return []
|
||||
|
||||
def clean_unused(self):
|
||||
pass
|
||||
|
||||
def get(self, node_id):
|
||||
return None
|
||||
|
||||
def set(self, node_id, value):
|
||||
pass
|
||||
|
||||
async def ensure_subcache_for(self, node_id, children_ids):
|
||||
return self
|
||||
|
||||
class LRUCache(BasicCache):
|
||||
def __init__(self, key_class, max_size=100):
|
||||
super().__init__(key_class)
|
||||
@@ -316,157 +336,3 @@ class LRUCache(BasicCache):
|
||||
self._mark_used(child_id)
|
||||
self.children[cache_key].append(self.cache_key_set.get_data_key(child_id))
|
||||
return self
|
||||
|
||||
|
||||
class DependencyAwareCache(BasicCache):
|
||||
"""
|
||||
A cache implementation that tracks dependencies between nodes and manages
|
||||
their execution and caching accordingly. It extends the BasicCache class.
|
||||
Nodes are removed from this cache once all of their descendants have been
|
||||
executed.
|
||||
"""
|
||||
|
||||
def __init__(self, key_class):
|
||||
"""
|
||||
Initialize the DependencyAwareCache.
|
||||
|
||||
Args:
|
||||
key_class: The class used for generating cache keys.
|
||||
"""
|
||||
super().__init__(key_class)
|
||||
self.descendants = {} # Maps node_id -> set of descendant node_ids
|
||||
self.ancestors = {} # Maps node_id -> set of ancestor node_ids
|
||||
self.executed_nodes = set() # Tracks nodes that have been executed
|
||||
|
||||
async def set_prompt(self, dynprompt, node_ids, is_changed_cache):
|
||||
"""
|
||||
Clear the entire cache and rebuild the dependency graph.
|
||||
|
||||
Args:
|
||||
dynprompt: The dynamic prompt object containing node information.
|
||||
node_ids: List of node IDs to initialize the cache for.
|
||||
is_changed_cache: Flag indicating if the cache has changed.
|
||||
"""
|
||||
# Clear all existing cache data
|
||||
self.cache.clear()
|
||||
self.subcaches.clear()
|
||||
self.descendants.clear()
|
||||
self.ancestors.clear()
|
||||
self.executed_nodes.clear()
|
||||
|
||||
# Call the parent method to initialize the cache with the new prompt
|
||||
await super().set_prompt(dynprompt, node_ids, is_changed_cache)
|
||||
|
||||
# Rebuild the dependency graph
|
||||
self._build_dependency_graph(dynprompt, node_ids)
|
||||
|
||||
def _build_dependency_graph(self, dynprompt, node_ids):
|
||||
"""
|
||||
Build the dependency graph for all nodes.
|
||||
|
||||
Args:
|
||||
dynprompt: The dynamic prompt object containing node information.
|
||||
node_ids: List of node IDs to build the graph for.
|
||||
"""
|
||||
self.descendants.clear()
|
||||
self.ancestors.clear()
|
||||
for node_id in node_ids:
|
||||
self.descendants[node_id] = set()
|
||||
self.ancestors[node_id] = set()
|
||||
|
||||
for node_id in node_ids:
|
||||
inputs = dynprompt.get_node(node_id)["inputs"]
|
||||
for input_data in inputs.values():
|
||||
if is_link(input_data): # Check if the input is a link to another node
|
||||
ancestor_id = input_data[0]
|
||||
self.descendants[ancestor_id].add(node_id)
|
||||
self.ancestors[node_id].add(ancestor_id)
|
||||
|
||||
def set(self, node_id, value):
|
||||
"""
|
||||
Mark a node as executed and store its value in the cache.
|
||||
|
||||
Args:
|
||||
node_id: The ID of the node to store.
|
||||
value: The value to store for the node.
|
||||
"""
|
||||
self._set_immediate(node_id, value)
|
||||
self.executed_nodes.add(node_id)
|
||||
self._cleanup_ancestors(node_id)
|
||||
|
||||
def get(self, node_id):
|
||||
"""
|
||||
Retrieve the cached value for a node.
|
||||
|
||||
Args:
|
||||
node_id: The ID of the node to retrieve.
|
||||
|
||||
Returns:
|
||||
The cached value for the node.
|
||||
"""
|
||||
return self._get_immediate(node_id)
|
||||
|
||||
async def ensure_subcache_for(self, node_id, children_ids):
|
||||
"""
|
||||
Ensure a subcache exists for a node and update dependencies.
|
||||
|
||||
Args:
|
||||
node_id: The ID of the parent node.
|
||||
children_ids: List of child node IDs to associate with the parent node.
|
||||
|
||||
Returns:
|
||||
The subcache object for the node.
|
||||
"""
|
||||
subcache = await super()._ensure_subcache(node_id, children_ids)
|
||||
for child_id in children_ids:
|
||||
self.descendants[node_id].add(child_id)
|
||||
self.ancestors[child_id].add(node_id)
|
||||
return subcache
|
||||
|
||||
def _cleanup_ancestors(self, node_id):
|
||||
"""
|
||||
Check if ancestors of a node can be removed from the cache.
|
||||
|
||||
Args:
|
||||
node_id: The ID of the node whose ancestors are to be checked.
|
||||
"""
|
||||
for ancestor_id in self.ancestors.get(node_id, []):
|
||||
if ancestor_id in self.executed_nodes:
|
||||
# Remove ancestor if all its descendants have been executed
|
||||
if all(descendant in self.executed_nodes for descendant in self.descendants[ancestor_id]):
|
||||
self._remove_node(ancestor_id)
|
||||
|
||||
def _remove_node(self, node_id):
|
||||
"""
|
||||
Remove a node from the cache.
|
||||
|
||||
Args:
|
||||
node_id: The ID of the node to remove.
|
||||
"""
|
||||
cache_key = self.cache_key_set.get_data_key(node_id)
|
||||
if cache_key in self.cache:
|
||||
del self.cache[cache_key]
|
||||
subcache_key = self.cache_key_set.get_subcache_key(node_id)
|
||||
if subcache_key in self.subcaches:
|
||||
del self.subcaches[subcache_key]
|
||||
|
||||
def clean_unused(self):
|
||||
"""
|
||||
Clean up unused nodes. This is a no-op for this cache implementation.
|
||||
"""
|
||||
pass
|
||||
|
||||
def recursive_debug_dump(self):
|
||||
"""
|
||||
Dump the cache and dependency graph for debugging.
|
||||
|
||||
Returns:
|
||||
A list containing the cache state and dependency graph.
|
||||
"""
|
||||
result = super().recursive_debug_dump()
|
||||
result.append({
|
||||
"descendants": self.descendants,
|
||||
"ancestors": self.ancestors,
|
||||
"executed_nodes": list(self.executed_nodes),
|
||||
})
|
||||
return result
|
||||
|
||||
Reference in New Issue
Block a user