Enable configuration of local store size limits

src/python/pants/engine/internals/native_engine.pyi

@@ -99,13 +99,13 @@ def scheduler_create(
     tasks: PyTasks,
     types: PyTypes,
     build_root: str,
-    local_store_dir: str,
     local_execution_root_dir: str,
     named_caches_dir: str,
     ca_certs_path: str | None,
     ignore_patterns: Sequence[str],
     use_gitignore: bool,
     remoting_options: PyRemotingOptions,
+    local_store_options: PyLocalStoreOptions,
     exec_strategy_opts: PyExecutionStrategyOptions,
 ) -> PyScheduler: ...
 def scheduler_execute(
@@ -183,6 +183,9 @@ class PyNailgunClient:
 class PyRemotingOptions:
     def __init__(self, **kwargs: Any) -> None: ...
 
+class PyLocalStoreOptions:
+    def __init__(self, **kwargs: Any) -> None: ...
+
 class PyScheduler:
     pass
 

src/python/pants/engine/internals/scheduler.py

@@ -37,6 +37,7 @@
     PyExecutionRequest,
     PyExecutionStrategyOptions,
     PyExecutor,
+    PyLocalStoreOptions,
     PyRemotingOptions,
     PyScheduler,
     PySession,
@@ -56,7 +57,11 @@
 )
 from pants.engine.rules import Rule, RuleIndex, TaskRule
 from pants.engine.unions import UnionMembership, union
-from pants.option.global_options import ExecutionOptions
+from pants.option.global_options import (
+    LOCAL_STORE_LEASE_TIME_SECS,
+    ExecutionOptions,
+    LocalStoreOptions,
+)
 from pants.util.contextutil import temporary_file_path
 from pants.util.logging import LogLevel
 from pants.util.strutil import pluralize
@@ -100,13 +105,13 @@ def __init__(
         ignore_patterns: List[str],
         use_gitignore: bool,
         build_root: str,
-        local_store_dir: str,
         local_execution_root_dir: str,
         named_caches_dir: str,
         ca_certs_path: Optional[str],
         rules: Iterable[Rule],
         union_membership: UnionMembership,
         execution_options: ExecutionOptions,
+        local_store_options: LocalStoreOptions,
         executor: PyExecutor,
         include_trace_on_error: bool = True,
         visualize_to_dir: Optional[str] = None,
@@ -116,13 +121,13 @@ def __init__(
         :param ignore_patterns: A list of gitignore-style file patterns for pants to ignore.
         :param use_gitignore: If set, pay attention to .gitignore files.
         :param build_root: The build root as a string.
-        :param local_store_dir: The directory to use for storing the engine's LMDB store in.
         :param local_execution_root_dir: The directory to use for local execution sandboxes.
         :param named_caches_dir: The directory to use as the root for named mutable caches.
         :param ca_certs_path: Path to pem file for custom CA, if needed.
         :param rules: A set of Rules which is used to compute values in the graph.
         :param union_membership: All the registered and normalized union rules.
         :param execution_options: Execution options for (remote) processes.
+        :param local_store_options: Options for the engine's LMDB store(s).
         :param include_trace_on_error: Include the trace through the graph upon encountering errors.
         :param validate_reachability: True to assert that all rules in an otherwise successfully
           constructed rule graph are reachable: if a graph cannot be successfully constructed, it
@@ -176,6 +181,13 @@ def __init__(
             execution_headers=tuple(execution_options.remote_execution_headers.items()),
             execution_overall_deadline_secs=execution_options.remote_execution_overall_deadline_secs,
         )
+        py_local_store_options = PyLocalStoreOptions(
+            store_dir=local_store_options.store_dir,
+            process_cache_max_size_bytes=local_store_options.processes_max_size_bytes,
+            files_max_size_bytes=local_store_options.files_max_size_bytes,
+            directories_max_size_bytes=local_store_options.directories_max_size_bytes,
+            lease_time_millis=LOCAL_STORE_LEASE_TIME_SECS * 1000,
+        )
         exec_stategy_opts = PyExecutionStrategyOptions(
             local_parallelism=execution_options.process_execution_local_parallelism,
             remote_parallelism=execution_options.process_execution_remote_parallelism,
@@ -190,13 +202,13 @@ def __init__(
             tasks,
             types,
             build_root,
-            local_store_dir,
             local_execution_root_dir,
             named_caches_dir,
             ca_certs_path,
             ignore_patterns,
             use_gitignore,
             remoting_options,
+            py_local_store_options,
             exec_stategy_opts,
         )
 

src/python/pants/engine/internals/scheduler_test_base.py

@@ -6,7 +6,7 @@
 from pants.engine.internals.native_engine import PyExecutor
 from pants.engine.internals.scheduler import Scheduler, SchedulerSession
 from pants.engine.unions import UnionMembership
-from pants.option.global_options import DEFAULT_EXECUTION_OPTIONS
+from pants.option.global_options import DEFAULT_EXECUTION_OPTIONS, DEFAULT_LOCAL_STORE_OPTIONS
 from pants.util.contextutil import temporary_file_path
 from pants.util.dirutil import safe_mkdtemp, safe_rmtree
 
@@ -35,21 +35,20 @@ def mk_scheduler(
         build_root = os.path.join(work_dir, "build_root")
         os.makedirs(build_root)
 
-        local_store_dir = os.path.realpath(safe_mkdtemp())
         local_execution_root_dir = os.path.realpath(safe_mkdtemp())
         named_caches_dir = os.path.realpath(safe_mkdtemp())
         scheduler = Scheduler(
             ignore_patterns=[],
             use_gitignore=False,
             build_root=build_root,
-            local_store_dir=local_store_dir,
             local_execution_root_dir=local_execution_root_dir,
             named_caches_dir=named_caches_dir,
             ca_certs_path=None,
             rules=rules,
             union_membership=UnionMembership({}),
             executor=self._executor,
             execution_options=DEFAULT_EXECUTION_OPTIONS,
+            local_store_options=DEFAULT_LOCAL_STORE_OPTIONS,
             include_trace_on_error=include_trace_on_error,
         )
         return scheduler.new_session(

src/python/pants/engine/rules_test.py

@@ -30,7 +30,7 @@
     rule,
 )
 from pants.engine.unions import UnionMembership
-from pants.option.global_options import DEFAULT_EXECUTION_OPTIONS
+from pants.option.global_options import DEFAULT_EXECUTION_OPTIONS, DEFAULT_LOCAL_STORE_OPTIONS
 from pants.testutil.rule_runner import MockGet, run_rule_with_mocks
 from pants.util.enums import match
 from pants.util.logging import LogLevel
@@ -44,14 +44,14 @@ def create_scheduler(rules, validate=True):
         ignore_patterns=[],
         use_gitignore=False,
         build_root=str(Path.cwd()),
-        local_store_dir="./.pants.d/lmdb_store",
         local_execution_root_dir="./.pants.d",
         named_caches_dir="./.pants.d/named_caches",
         ca_certs_path=None,
         rules=rules,
         union_membership=UnionMembership({}),
         executor=_EXECUTOR,
         execution_options=DEFAULT_EXECUTION_OPTIONS,
+        local_store_options=DEFAULT_LOCAL_STORE_OPTIONS,
         validate_reachability=validate,
     )
 

src/python/pants/init/engine_initializer.py

@@ -30,7 +30,12 @@
 from pants.engine.target import RegisteredTargetTypes
 from pants.engine.unions import UnionMembership
 from pants.init import specs_calculator
-from pants.option.global_options import DEFAULT_EXECUTION_OPTIONS, ExecutionOptions, GlobalOptions
+from pants.option.global_options import (
+    DEFAULT_EXECUTION_OPTIONS,
+    ExecutionOptions,
+    GlobalOptions,
+    LocalStoreOptions,
+)
 from pants.option.options_bootstrapper import OptionsBootstrapper
 from pants.option.subsystem import Subsystem
 from pants.util.ordered_set import FrozenOrderedSet
@@ -175,13 +180,14 @@ def setup_graph(
         assert bootstrap_options is not None
         executor = executor or GlobalOptions.create_py_executor(bootstrap_options)
         execution_options = ExecutionOptions.from_options(options, env, local_only=local_only)
+        local_store_options = LocalStoreOptions.from_options(bootstrap_options)
         return EngineInitializer.setup_graph_extended(
             build_configuration,
             execution_options,
             executor=executor,
             pants_ignore_patterns=GlobalOptions.compute_pants_ignore(build_root, bootstrap_options),
             use_gitignore=bootstrap_options.pants_ignore_use_gitignore,
-            local_store_dir=bootstrap_options.local_store_dir,
+            local_store_options=local_store_options,
             local_execution_root_dir=bootstrap_options.local_execution_root_dir,
             named_caches_dir=bootstrap_options.named_caches_dir,
             ca_certs_path=bootstrap_options.ca_certs_path,
@@ -198,7 +204,7 @@ def setup_graph_extended(
         executor: PyExecutor,
         pants_ignore_patterns: List[str],
         use_gitignore: bool,
-        local_store_dir: str,
+        local_store_options: LocalStoreOptions,
         local_execution_root_dir: str,
         named_caches_dir: str,
         ca_certs_path: Optional[str] = None,
@@ -280,14 +286,14 @@ def ensure_optional_absolute_path(v: Optional[str]) -> Optional[str]:
             ignore_patterns=pants_ignore_patterns,
             use_gitignore=use_gitignore,
             build_root=build_root,
-            local_store_dir=ensure_absolute_path(local_store_dir),
             local_execution_root_dir=ensure_absolute_path(local_execution_root_dir),
             named_caches_dir=ensure_absolute_path(named_caches_dir),
             ca_certs_path=ensure_optional_absolute_path(ca_certs_path),
             rules=rules,
             union_membership=union_membership,
             executor=executor,
             execution_options=execution_options,
+            local_store_options=local_store_options,
             include_trace_on_error=include_trace_on_error,
             visualize_to_dir=native_engine_visualize_to,
         )

src/python/pants/option/global_options.py

@@ -251,11 +251,59 @@ def from_options(
         )
 
 
+@dataclass(frozen=True)
+class LocalStoreOptions:
+    """A collection of all options related to the local store.
+
+    TODO: These options should move to a Subsystem once we add support for "bootstrap" Subsystems (ie,
+    allowing Subsystems to be consumed before the Scheduler has been created).
+    """
+
+    store_dir: str
+    processes_max_size_bytes: int
+    files_max_size_bytes: int
+    directories_max_size_bytes: int
+
+    def target_total_size_bytes(self) -> int:
+        """Returns the target total size of all of the stores.
+
+        The `max_size` values are caps on the total size of each store: the "target" size
+        is the size that garbage collection will attempt to shrink the stores to each time
+        it runs.
+
+        NB: This value is not currently configurable, but that could be desirable in the future.
+        """
+        max_total_size_bytes = (
+            self.processes_max_size_bytes
+            + self.files_max_size_bytes
+            + self.directories_max_size_bytes
+        )
+        return max_total_size_bytes // 10
+
+    @classmethod
+    def from_options(cls, options: OptionValueContainer) -> LocalStoreOptions:
+        return cls(
+            store_dir=Path(options.local_store_dir).resolve().as_posix(),
+            processes_max_size_bytes=options.local_store_processes_max_size_bytes,
+            files_max_size_bytes=options.local_store_files_max_size_bytes,
+            directories_max_size_bytes=options.local_store_directories_max_size_bytes,
+        )
+
+
 _CPU_COUNT = (
     len(os.sched_getaffinity(0)) if hasattr(os, "sched_getaffinity") else os.cpu_count()
 ) or 2
 
 
+# The time that leases are acquired for in the local store. Configured on the Python side
+# in order to ease interaction with the StoreGCService, which needs to be aware of its value.
+LOCAL_STORE_LEASE_TIME_SECS = 2 * 60 * 60
+
+
+MEGABYTES = 1000000
+GIGABYTES = 1000 * MEGABYTES
+
+
 DEFAULT_EXECUTION_OPTIONS = ExecutionOptions(
     # Remote execution strategy.
     remote_execution=False,
@@ -285,6 +333,13 @@ def from_options(
     remote_execution_overall_deadline_secs=60 * 60,  # one hour
 )
 
+DEFAULT_LOCAL_STORE_OPTIONS = LocalStoreOptions(
+    store_dir=os.path.join(get_pants_cachedir(), "lmdb_store"),
+    processes_max_size_bytes=(4 * GIGABYTES),
+    files_max_size_bytes=(128 * GIGABYTES),
+    directories_max_size_bytes=(4 * GIGABYTES),
+)
+
 
 class GlobalOptions(Subsystem):
     options_scope = GLOBAL_SCOPE
@@ -701,12 +756,13 @@ def register_bootstrap_options(cls, register):
             ),
         )
 
+        local_store_dir_flag = "--local-store-dir"
         cache_instructions = (
             "The path may be absolute or relative. If the directory is within the build root, be "
             "sure to include it in `--pants-ignore`."
         )
         register(
-            "--local-store-dir",
+            local_store_dir_flag,
             advanced=True,
             help=(
                 f"Directory to use for the local file store, which stores the results of "
@@ -715,7 +771,46 @@ def register_bootstrap_options(cls, register):
             # This default is also hard-coded into the engine's rust code in
             # fs::Store::default_path so that tools using a Store outside of pants
             # are likely to be able to use the same storage location.
-            default=os.path.join(get_pants_cachedir(), "lmdb_store"),
+            default=DEFAULT_LOCAL_STORE_OPTIONS.store_dir,
+        )
+        register(
+            "--local-store-processes-max-size-bytes",
+            type=int,
+            advanced=True,
+            help=(
+                "The maximum size in bytes of the local store containing process cache entries. "
+                f"Stored below `{local_store_dir_flag}`."
+            ),
+            default=DEFAULT_LOCAL_STORE_OPTIONS.processes_max_size_bytes,
+        )
+        register(
+            "--local-store-files-max-size-bytes",
+            type=int,
+            advanced=True,
+            help=(
+                "The maximum size in bytes of the local store containing files. "
+                f"Stored below `{local_store_dir_flag}`."
+                "\n\n"
+                "NB: This size value bounds the total size of all files, but (due to sharding of the "
+                "store on disk) it also bounds the per-file size to (VALUE / 16)."
+                "\n\n"
+                "This value doesn't reflect space allocated on disk, or RAM allocated (it "
+                "may be reflected in VIRT but not RSS). However, the default is lower than you "
+                "might otherwise choose because macOS creates core dumps that include MMAP'd "
+                "pages, and setting this too high might cause core dumps to use an unreasonable "
+                "amount of disk if they are enabled."
+            ),
+            default=DEFAULT_LOCAL_STORE_OPTIONS.files_max_size_bytes,
+        )
+        register(
+            "--local-store-directories-max-size-bytes",
+            type=int,
+            advanced=True,
+            help=(
+                "The maximum size in bytes of the local store containing directories. "
+                f"Stored below `{local_store_dir_flag}`."
+            ),
+            default=DEFAULT_LOCAL_STORE_OPTIONS.directories_max_size_bytes,
         )
         register(
             "--named-caches-dir",

src/python/pants/pantsd/pants_daemon.py

@@ -21,7 +21,7 @@
 from pants.init.engine_initializer import GraphScheduler
 from pants.init.logging import initialize_stdio, pants_log_path
 from pants.init.util import init_workdir
-from pants.option.global_options import GlobalOptions
+from pants.option.global_options import GlobalOptions, LocalStoreOptions
 from pants.option.option_value_container import OptionValueContainer
 from pants.option.options import Options
 from pants.option.options_bootstrapper import OptionsBootstrapper
@@ -102,7 +102,10 @@ def _setup_services(
             max_memory_usage_in_bytes=bootstrap_options.pantsd_max_memory_usage,
         )
 
-        store_gc_service = StoreGCService(graph_scheduler.scheduler)
+        store_gc_service = StoreGCService(
+            graph_scheduler.scheduler,
+            local_store_options=LocalStoreOptions.from_options(bootstrap_options),
+        )
         return PantsServices(services=(scheduler_service, store_gc_service))
 
     def __init__(