Merge branch 'main' into nslookup-v1

Author: dhirupandey

docs/caches.rst

@@ -0,0 +1,126 @@
+..
+   Copyright (c) 2022, 2024, Oracle and/or its affiliates.
+   Licensed under the Universal Permissive License v 1.0 as shown at
+   https://oss.oracle.com/licenses/upl.
+
+Caches
+======
+
+Once a Session has been obtained, it is now possible to begin working with
+`NamedMap` and/or `NamedCache` instances.  This is done by calling either
+`Session.get_map(name: str, cache_options: Optional[CacheOptions] = None)` or
+`Session.get_cache(name: str, cache_options: Optional[CacheOptions] = None)`.
+The `name` argument is the logical name for this cache.  The optional `cache_options`
+argument accepts a `CacheOptions` to configure the default time-to-live (ttl)
+for entries placed in the cache as well as allowing the configuration of near
+caching (discussed later in this section).
+
+Here are some examples:
+
+.. code-block:: python
+
+  # obtain NamedCache 'person'
+  cache: NamedCache[int, Person] = await session.get_cache("person")
+
+.. code-block:: python
+
+  # obtain NamedCache 'person' with a default ttl of 2000 millis
+  # any entry inserted into this cache, unless overridden by a put call
+  # with a custom ttl, will have a default ttl of 2000
+  options: CacheOptions = CacheOptions(2000)
+  cache: NamedCache[int, Person] = await session.get_cache("person", options)
+
+Near Caches
+===========
+
+Near caches are a local cache within the `NamedMap` or `NamedCache`
+that will store entries as they are obtained from the remote cache.  By doing
+so, it is possible to reduce the number of remote calls made to the Coherence
+cluster by returning the locally cached value.  This local cache also
+ensures updates made to, or removal of, an entry are properly
+reflected thus ensuring stale data isn't mistakenly returned.
+
+.. note::
+  Near caching will only work with Coherence CE `24.09` or later.  Attempting
+  to use near caching features with older versions will have no effect.
+
+A near cache is configured via `NearCacheOptions` which provides several
+options for controlling how entries will be cached locally.
+
+    - `ttl` - configures the time-to-live of locally cached entries (this has no
+      impact on entries stored within Coherence).  If not specified, or the
+      `ttl` is `0`, entries in the near cache will not expire
+    - `high_units` - configures the max number of entries that may be locally
+       cached.  Once the number of locally cached entries exceeds the configured
+       value, the cache will be pruned down (least recently used entries first)
+       to a target size based on the configured `prune_factor`
+       (defaults to `0.80` meaning the prune operation would retain 80% of
+       the entries)
+    - `high_units_memory` - configures the maximum memory size, in bytes, the
+       locally cached entries may use.  If total memory exceeds the configured
+       value, the cache will be pruned down (least recently used entries first)
+       to a target size based on the configured `prune_factor` (defaults to
+       `0.80` meaning the prune operation would retain 80% the cache memory)
+    - `prune_factor` - configures the target near cache size after exceeding
+       either `high_units` or `high_units_memory` high-water marks
+
+.. note::
+  `high_units` and `high_units_memory` are mutually exclusive
+
+Examples of configuring near caching:
+
+.. code-block:: python
+
+  # obtain NamedCache 'person' and configure near caching with a local
+  # ttl of 20_000 millis
+  near_options: NearCacheOptions = NearCacheOptions(20_000)
+  cache_options: CacheOptions = CacheOptions(near_cache_options=near_options)
+  cache: NamedCache[int, Person] = await session.get_cache("person", options)
+
+
+.. code-block:: python
+
+  # obtain NamedCache 'person' and configure near caching with a max
+  # number of entries of 1_000 and when pruned, it will be reduced
+  # to 20%
+  near_options: NearCacheOptions = NearCacheOptions(high_units=1_000, prune_factor=0.20)
+  cache_options: CacheOptions = CacheOptions(near_cache_options=near_options)
+  cache: NamedCache[int, Person] = await session.get_cache("person", options)
+
+To verify the effectiveness of a near cache, several statistics are monitored
+and may be obtained from the `CacheStats` instance returned by the
+`near_cache_stats` property of the `NamedMap` or `NamedCache`
+
+The following statistics are available (the statistic name given is the same
+property name on the `CacheStats` instance)
+
+    - hits - the number of times an entry was found in the near cache
+    - misses - the number of times an entry was not found in the near cache
+    - misses_duration - The accumulated time, in millis, spent for a cache miss
+      (i.e., having to make a remote call and update the local cache)
+    - hit_rate - the ratio of hits to misses
+    - puts - the total number of puts that have been made against the near cache
+    - gets - the total number of gets that have been made against the near cache
+    - prunes - the number of times the cache was pruned due to exceeding the
+      configured `high_units` or `high_units_memory` high-water marks
+    - expires - the number of times the near cache's expiry logic expired entries
+    - num_pruned - the total number of entries that were removed due to exceeding the
+      configured `high_units` or `high_units_memory` high-water marks
+    - num_expired - the total number of entries that were removed due to
+      expiration
+    - prunes_duration - the accumulated time, in millis, spent pruning
+      the near cache
+    - expires_duration - the accumulated time, in millis, removing
+      expired entries from the near cache
+    - size - the total number of entries currently held by the near cache
+    - bytes - the total bytes the near cache entries consume
+
+.. note::
+  The `near_cache_stats` option will return `None` if near caching isn't
+  configured or available
+
+The following example demonstrates the value that near caching can provide:
+
+.. literalinclude:: ../examples/near_caching.py
+    :language: python
+    :linenos:

docs/index.rst

@@ -9,6 +9,7 @@
 
    installation
    sessions
+   caches
    basics
    querying
    aggregation

docs/sessions.rst

@@ -1,5 +1,5 @@
 ..
-   Copyright (c) 2022, 2023, Oracle and/or its affiliates.
+   Copyright (c) 2022, 2024, Oracle and/or its affiliates.
    Licensed under the Universal Permissive License v 1.0 as shown at
    https://oss.oracle.com/licenses/upl.
 
@@ -37,7 +37,7 @@ The currently supported arguments foe `Options` are:
     import asyncio
 
        # create a new Session to the Coherence server
-        session: Session = Session(None)
+        session: Session = await Session.create()
 
 This is the simplest invocation which assumes the following defaults:
     - `address` is `localhost:1408`
@@ -55,7 +55,7 @@ and pass it to the constructor of the `Session`:
        # create a new Session to the Coherence server
         addr: str = 'example.com:4444'
         opt: Options = Options(addr, default_scope, default_request_timeout, default_format)
-        session: Session = Session(opt)
+        session: Session = await Session.create(opt)
 
 It's also possible to control the default address the session will bind to by providing
 an address via the `COHERENCE_SERVER_ADDRESS` environment variable.  The format of the value would

examples/near_caching.py

@@ -0,0 +1,94 @@
+# Copyright (c) 2024, Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at
+# https://oss.oracle.com/licenses/upl.
+
+import asyncio
+import time
+from functools import reduce
+
+from coherence import CacheOptions, CacheStats, NamedCache, NearCacheOptions, Session
+
+
+async def do_run() -> None:
+    session: Session = await Session.create()
+
+    # obtain the basic cache and configure near caching with
+    # all defaults; meaning no expiry or pruning
+    cache_remote: NamedCache[str, str] = await session.get_cache("remote")
+    cache_near: NamedCache[str, str] = await session.get_cache(
+        "near", CacheOptions(near_cache_options=NearCacheOptions(ttl=0))
+    )
+
+    await cache_remote.clear()
+    await cache_near.clear()
+    stats: CacheStats = cache_near.near_cache_stats
+
+    # these knobs control:
+    #  - how many current tasks to run
+    #  - how many entries will be inserted and queried
+    #  - how many times the calls will be invoked
+    task_count: int = 25
+    num_entries: int = 1_000
+    iterations: int = 4
+
+    # seed data to populate the cache
+    cache_seed: dict[str, str] = {str(x): str(x) for x in range(num_entries)}
+    cache_seed_keys: set[str] = {key for key in cache_seed.keys()}
+    print()
+
+    # task calling get_all() for 1_000 keys
+    async def get_all_task(task_cache: NamedCache[str, str]) -> int:
+        begin = time.time_ns()
+
+        for _ in range(iterations):
+            async for _ in await task_cache.get_all(cache_seed_keys):
+                continue
+
+        return (time.time_ns() - begin) // 1_000_000
+
+    await cache_remote.put_all(cache_seed)
+    await cache_near.put_all(cache_seed)
+
+    print("Run without near caching ...")
+    begin_outer: int = time.time_ns()
+    results: list[int] = await asyncio.gather(*[get_all_task(cache_remote) for _ in range(task_count)])
+    end_outer: int = time.time_ns()
+    total_time = end_outer - begin_outer
+    task_time = reduce(lambda first, second: first + second, results)
+
+    # Example output
+    # Run without near caching ...
+    # [remote] 25 tasks completed!
+    # [remote] Total time: 4246ms
+    # [remote] Tasks completion average: 3755.6
+
+    print(f"[remote] {task_count} tasks completed!")
+    print(f"[remote] Total time: {total_time // 1_000_000}ms")
+    print(f"[remote] Tasks completion average: {task_time / task_count}")
+
+    print()
+    print("Run with near caching ...")
+    begin_outer = time.time_ns()
+    results = await asyncio.gather(*[get_all_task(cache_near) for _ in range(task_count)])
+    end_outer = time.time_ns()
+    total_time = end_outer - begin_outer
+    task_time = reduce(lambda first, second: first + second, results)
+
+    # Run with near caching ...
+    # [near] 25 tasks completed!
+    # [near] Total time: 122ms
+    # [near] Tasks completion average: 113.96
+    # [near] Near cache statistics: CacheStats(puts=1000, gets=100000, hits=99000,
+    #     misses=1000, misses-duration=73ms, hit-rate=0.99, prunes=0,
+    #     num-pruned=0, prunes-duration=0ms, size=1000, expires=0,
+    #     num-expired=0, expires-duration=0ms, memory-bytes=681464)
+
+    print(f"[near] {task_count} tasks completed!")
+    print(f"[near] Total time: {total_time // 1_000_000}ms")
+    print(f"[near] Tasks completion average: {task_time / task_count}")
+    print(f"[near] Near cache statistics: {stats}")
+
+    await session.close()
+
+
+asyncio.run(do_run())

pyproject.toml

@@ -23,10 +23,10 @@ classifiers = [
 [tool.poetry.dependencies]
 python = "^3.9"
 protobuf = "5.29.2"
-grpcio = "1.68.1"
+grpcio = "1.69.0"
 grpcio-tools = "1.68.1"
 jsonpickle = ">=3.0,<4.1"
-pymitter = ">=0.4,<0.6"
+pymitter = ">=0.4,<1.1"
 typing-extensions = ">=4.11,<4.13"
 types-protobuf = "5.29.1.20241207"
 pympler = "1.1"
@@ -37,7 +37,7 @@ pytest-asyncio = "~0.25"
 pytest-cov = "~6.0"
 pytest-unordered = "~0.6"
 pre-commit = "~4.0"
-Sphinx = "~7.1"
+Sphinx = "~7.4"
 sphinx-rtd-theme = "~3.0"
 sphinxcontrib-napoleon = "~0.7"
 m2r = "~0.3"