p2pstore 0.1.7.dev1__tar.gz

p2pstore-0.1.7.dev1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1.  Definitions.
+
+    "License" shall mean the terms and conditions for use, reproduction,
+    and distribution as defined by Sections 1 through 9 of this document.
+
+    "Licensor" shall mean the copyright owner or entity authorized by
+    the copyright owner that is granting the License.
+
+    "Legal Entity" shall mean the union of the acting entity and all
+    other entities that control, are controlled by, or are under common
+    control with that entity. For the purposes of this definition,
+    "control" means (i) the power, direct or indirect, to cause the
+    direction or management of such entity, whether by contract or
+    otherwise, or (ii) ownership of fifty percent (50%) or more of the
+    outstanding shares, or (iii) beneficial ownership of such entity.
+
+    "You" (or "Your") shall mean an individual or Legal Entity
+    exercising permissions granted by this License.
+
+    "Source" form shall mean the preferred form for making modifications,
+    including but not limited to software source code, documentation
+    source, and configuration files.
+
+    "Object" form shall mean any form resulting from mechanical
+    transformation or translation of a Source form, including but
+    not limited to compiled object code, generated documentation,
+    and conversions to other media types.
+
+    "Work" shall mean the work of authorship, whether in Source or
+    Object form, made available under the License, as indicated by a
+    copyright notice that is included in or attached to the work
+    (an example is provided in the Appendix below).
+
+    "Derivative Works" shall mean any work, whether in Source or Object
+    form, that is based on (or derived from) the Work and for which the
+    editorial revisions, annotations, elaborations, or other modifications
+    represent, as a whole, an original work of authorship. For the purposes
+    of this License, Derivative Works shall not include works that remain
+    separable from, or merely link (or bind by name) to the interfaces of,
+    the Work and Derivative Works thereof.
+
+    "Contribution" shall mean any work of authorship, including
+    the original version of the Work and any modifications or additions
+    to that Work or Derivative Works thereof, that is intentionally
+    submitted to Licensor for inclusion in the Work by the copyright owner
+    or by an individual or Legal Entity authorized to submit on behalf of
+    the copyright owner. For the purposes of this definition, "submitted"
+    means any form of electronic, verbal, or written communication sent
+    to the Licensor or its representatives, including but not limited to
+    communication on electronic mailing lists, source code control systems,
+    and issue tracking systems that are managed by, or on behalf of, the
+    Licensor for the purpose of discussing and improving the Work, but
+    excluding communication that is conspicuously marked or otherwise
+    designated in writing by the copyright owner as "Not a Contribution."
+
+    "Contributor" shall mean Licensor and any individual or Legal Entity
+    on behalf of whom a Contribution has been received by Licensor and
+    subsequently incorporated within the Work.
+
+2.  Grant of Copyright License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    copyright license to reproduce, prepare Derivative Works of,
+    publicly display, publicly perform, sublicense, and distribute the
+    Work and such Derivative Works in Source or Object form.
+
+3.  Grant of Patent License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    (except as stated in this section) patent license to make, have made,
+    use, offer to sell, sell, import, and otherwise transfer the Work,
+    where such license applies only to those patent claims licensable
+    by such Contributor that are necessarily infringed by their
+    Contribution(s) alone or by combination of their Contribution(s)
+    with the Work to which such Contribution(s) was submitted. If You
+    institute patent litigation against any entity (including a
+    cross-claim or counterclaim in a lawsuit) alleging that the Work
+    or a Contribution incorporated within the Work constitutes direct
+    or contributory patent infringement, then any patent licenses
+    granted to You under this License for that Work shall terminate
+    as of the date such litigation is filed.
+
+4.  Redistribution. You may reproduce and distribute copies of the
+    Work or Derivative Works thereof in any medium, with or without
+    modifications, and in Source or Object form, provided that You
+    meet the following conditions:
+
+    (a) You must give any other recipients of the Work or
+    Derivative Works a copy of this License; and
+
+    (b) You must cause any modified files to carry prominent notices
+    stating that You changed the files; and
+
+    (c) You must retain, in the Source form of any Derivative Works
+    that You distribute, all copyright, patent, trademark, and
+    attribution notices from the Source form of the Work,
+    excluding those notices that do not pertain to any part of
+    the Derivative Works; and
+
+    (d) If the Work includes a "NOTICE" text file as part of its
+    distribution, then any Derivative Works that You distribute must
+    include a readable copy of the attribution notices contained
+    within such NOTICE file, excluding those notices that do not
+    pertain to any part of the Derivative Works, in at least one
+    of the following places: within a NOTICE text file distributed
+    as part of the Derivative Works; within the Source form or
+    documentation, if provided along with the Derivative Works; or,
+    within a display generated by the Derivative Works, if and
+    wherever such third-party notices normally appear. The contents
+    of the NOTICE file are for informational purposes only and
+    do not modify the License. You may add Your own attribution
+    notices within Derivative Works that You distribute, alongside
+    or as an addendum to the NOTICE text from the Work, provided
+    that such additional attribution notices cannot be construed
+    as modifying the License.
+
+    You may add Your own copyright statement to Your modifications and
+    may provide additional or different license terms and conditions
+    for use, reproduction, or distribution of Your modifications, or
+    for any such Derivative Works as a whole, provided Your use,
+    reproduction, and distribution of the Work otherwise complies with
+    the conditions stated in this License.
+
+5.  Submission of Contributions. Unless You explicitly state otherwise,
+    any Contribution intentionally submitted for inclusion in the Work
+    by You to the Licensor shall be under the terms and conditions of
+    this License, without any additional terms or conditions.
+    Notwithstanding the above, nothing herein shall supersede or modify
+    the terms of any separate license agreement you may have executed
+    with Licensor regarding such Contributions.
+
+6.  Trademarks. This License does not grant permission to use the trade
+    names, trademarks, service marks, or product names of the Licensor,
+    except as required for reasonable and customary use in describing the
+    origin of the Work and reproducing the content of the NOTICE file.
+
+7.  Disclaimer of Warranty. Unless required by applicable law or
+    agreed to in writing, Licensor provides the Work (and each
+    Contributor provides its Contributions) on an "AS IS" BASIS,
+    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+    implied, including, without limitation, any warranties or conditions
+    of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+    PARTICULAR PURPOSE. You are solely responsible for determining the
+    appropriateness of using or redistributing the Work and assume any
+    risks associated with Your exercise of permissions under this License.
+
+8.  Limitation of Liability. In no event and under no legal theory,
+    whether in tort (including negligence), contract, or otherwise,
+    unless required by applicable law (such as deliberate and grossly
+    negligent acts) or agreed to in writing, shall any Contributor be
+    liable to You for damages, including any direct, indirect, special,
+    incidental, or consequential damages of any character arising as a
+    result of this License or out of the use or inability to use the
+    Work (including but not limited to damages for loss of goodwill,
+    work stoppage, computer failure or malfunction, or any and all
+    other commercial damages or losses), even if such Contributor
+    has been advised of the possibility of such damages.
+
+9.  Accepting Warranty or Additional Liability. While redistributing
+    the Work or Derivative Works thereof, You may choose to offer,
+    and charge a fee for, acceptance of support, warranty, indemnity,
+    or other liability obligations and/or rights consistent with this
+    License. However, in accepting such obligations, You may act only
+    on Your own behalf and on Your sole responsibility, not on behalf
+    of any other Contributor, and only if You agree to indemnify,
+    defend, and hold each Contributor harmless for any liability
+    incurred by, or claims asserted against, such Contributor by reason
+    of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+Copyright 2025 Paddle
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

p2pstore-0.1.7.dev1/MANIFEST.in

@@ -0,0 +1,10 @@
+include README.md
+include LICENSE
+include pyproject.toml
+recursive-include src/p2pstore *.py
+recursive-include src/p2pstore *.pyi
+global-exclude __pycache__
+global-exclude *.py[cod]
+prune src/p2pstore/benchmark
+prune src/p2pstore/examples
+prune tests

p2pstore-0.1.7.dev1/PKG-INFO

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: p2pstore
+Version: 0.1.7.dev1
+Summary: P2P Store - 基于 RDMA 的高性能分布式数据传输系统
+Author: Paddle
+License-Expression: Apache-2.0
+Keywords: p2p,rdma,distributed,tensor,transfer
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: System :: Distributed Computing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: safetensors>=0.3.0
+Requires-Dist: mooncake-transfer-engine==0.3.7
+Requires-Dist: protobuf==3.20.3
+Requires-Dist: etcd3==0.12.0
+Provides-Extra: paddle
+Requires-Dist: paddlepaddle>=2.5.0; extra == "paddle"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.20.0; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Provides-Extra: benchmark
+Requires-Dist: paddlepaddle-gpu>=2.5.0; extra == "benchmark"
+Dynamic: license-file
+
+# P2P Store - 分布式 P2P 数据存储系统
+
+## 项目概述
+
+P2P Store 是一个基于 RDMA 的高性能分布式数据传输系统，支持 Tensor、文件、字节数据的点对点传输。
+
+### 核心概念
+
+- **P2PClient**: 客户端，用于 put/get/list/delete 数据
+- **P2PServer**: 服务端，元数据服务器 (MetadataServer)
+- **P2PConfig**: 统一配置类，Server 和 Client 共用
+- **Transport**: 传输层，负责实际的数据传输，支持 RDMA 和 TCP 协议
+
+## 安装指南
+
+### 安装步骤
+
+1. 依赖 RDMA 库
+
+```bash
+apt install -y rdma-core libibverbs1 libmlx5-1 libibverbs-dev
+```
+
+2. 安装 mooncake-transfer-engine
+
+```bash
+pip install mooncake-transfer-engine==0.3.7
+
+# 其他环境已有的依赖
+# numpy>=1.20.0
+# pyzmq>=22.0.0
+# safetensors
+# paddlepaddle-gpu
+```
+
+## 快速开始
+
+### 1. 启动 Metaserver
+
+```bash
+# 直接运行 (使用默认配置: zmq://127.0.0.1:5765,127.0.0.1:5766)
+python examples/start_metaserver.py
+```
+
+### 2. 启动 Put 节点
+
+```bash
+# 直接运行 (默认: 5 个 1MB 的 test_data_{i} key)
+python examples/test_put.py
+```
+
+### 3. 启动 Get 节点
+
+在其他节点启动示例脚本获取数据:
+
+```bash
+python examples/benchmark_get.py
+```
+
+## 示例脚本
+
+`examples/` 目录提供了多个示例脚本，**所有脚本都支持直接运行（使用默认参数）**:
+
+| 脚本                   | 作用                 | 默认配置                                |
+| ---------------------- | -------------------- | --------------------------------------- |
+| `start_metaserver.py`  | 启动 Metadata Server | `zmq://{POD_0_IP}:5765,{POD_0_IP}:5766` |
+| `test_put.py`          | 写入测试数据         | 5 个 1MB 数据, key 前缀 `test_data`     |
+| `test_delete.py`       | 删除数据             | 删除 `test_data` 前缀的 key             |
+| `test_delete_batch.py` | 批量删除数据         | 删除 `test_data` 前缀的 key             |
+| `test_list_files.py`   | 列出所有已注册数据   | -                                       |
+| `test_clear.py`        | 清空所有数据         | -                                       |
+| `benchmark_put.py`     | PUT 性能测试         | 10MB × 10 个 key (`bench_test_key_{i}`) |
+| `benchmark_get.py`     | GET 性能测试         | 拉取 10 个 `bench_test_key_{i}`, 1 轮   |
+
+### 使用示例
+
+#### 直接运行（使用默认参数）
+
+```bash
+# 1. 启动 Metaserver (默认监听 127.0.0.1:5765,5766)
+python examples/start_metaserver.py
+
+# 2. 写入测试数据 (默认: 5 个 1MB, key 前缀 test_data)
+python examples/test_put.py
+
+# 3. 查看已注册数据
+python examples/test_list_files.py
+
+# 4. 删除数据 (默认删除 test_data 前缀的 key)
+python examples/test_delete.py
+
+# 5. 批量删除 (默认删除 test_data 前缀的 key)
+python examples/test_delete_batch.py
+
+# 6. 清空所有数据
+python examples/test_clear.py
+```
+
+#### 自定义参数
+
+```bash
+# 写入 10 个 50MB 数据，key 前缀为 my_data
+python examples/test_put.py --size_mb 50 --count 10 --key-prefix my_data
+
+# 删除指定前缀的 key
+python examples/test_delete_batch.py --key-prefix my_data
+
+# 删除指定的多个 key
+python examples/test_delete_batch.py --keys key1,key2,key3
+
+# 指定 Metaserver 地址
+python examples/test_put.py --metadata-server zmq://10.0.0.1:5765,10.0.0.1:5766
+```
+
+## 配置说明
+
+P2P Store 使用 `P2PConfig` 类进行配置管理，Server 和 Client 共用同一配置类:
+
+| 配置项          | 描述                                                      | 默认值               |
+| --------------- | --------------------------------------------------------- | -------------------- |
+| metadata_server | Metaserver 地址，格式: `zmq://ip:sync_port,ip:coord_port` | 必填                 |
+| local_host      | 本地地址 (ip)                                             | 从 `POD_IP` 环境变量 |
+| protocol        | 传输协议 (rdma/tcp)                                       | `"rdma"`             |
+| device          | RDMA 设备列表                                             | 自动探测             |
+| max_retries     | 最大重试次数                                              | `10`                 |
+| retry_interval  | 重试间隔 (秒)                                             | `3`                  |
+
+### 配置示例
+
+```python
+from p2pstore import P2PConfig
+
+# ZMQ 模式
+config = P2PConfig(
+    metadata_server="zmq://10.0.0.1:5765,10.0.0.1:5766",
+    protocol="rdma",
+    device="mlx5_2,mlx5_3,mlx5_4,mlx5_5"
+)
+```
+
+## Client API
+
+### 初始化 Client
+
+```python
+from p2pstore import P2PClient, P2PConfig
+
+# 创建配置
+config = P2PConfig(
+    metadata_server="zmq://10.0.0.1:5765,10.0.0.1:5766",
+    protocol="rdma",
+    device="mlx5_2,mlx5_3,mlx5_4,mlx5_5"
+)
+
+# 初始化客户端
+client = P2PClient(config)
+```
+
+### 注册数据 (put)
+
+```python
+import paddle
+import numpy as np
+
+# 创建示例数据
+tensor = paddle.to_tensor(np.random.randn(128, 128), dtype="float32")
+
+# 注册数据，指定 key (如果 key 已存在，会先删除旧数据再写入)
+await client.put("my_tensor", tensor)
+```
+
+### 获取数据 (get)
+
+```python
+# 获取数据
+tensor = await client.get("my_tensor")
+
+# 保存到文件
+await client.get("my_tensor", output_path="/path/to/save.bin")
+```
+
+### 删除数据 (delete)
+
+```python
+# 删除指定 key 的数据 (可删除任意节点注册的数据)
+await client.delete("my_tensor")
+
+# 批量删除
+results = await client.delete_batch(["key1", "key2", "key3"])
+```
+
+### 清除所有数据 (clear)
+
+```python
+# 清除所有已注册的数据
+result = await client.clear()
+# result: {"success": bool, "cleared": int, "failed": list[str]}
+```
+
+### 列出数据 (list)
+
+```python
+# 列出所有已注册的数据
+files = client.list()
+print(f"已注册的数据: {list(files.keys())}")
+```
+
+### 检查数据是否存在 (exists)
+
+```python
+# 检查指定 key 是否存在
+exists = await client.exists("my_tensor")
+```
+
+## 环境变量
+
+| 变量名     | 作用                         | 默认值      |
+| ---------- | ---------------------------- | ----------- |
+| `POD_0_IP` | Metaserver 所在节点 IP       | `127.0.0.1` |
+| `POD_IP`   | 本地节点 IP (用于 RDMA 绑定) | `127.0.0.1` |
+
+所有脚本默认从 `POD_0_IP` 环境变量拼装 Metaserver 地址（格式：`zmq://{POD_0_IP}:5765,{POD_0_IP}:5766`）。
+
+## Benchmark 脚本
+
+`benchmark/` 目录提供了多种性能基准测试，方便验证 RDMA 传输链路。**所有脚本的参数都有默认值，可直接运行**。
+
+### 脚本列表
+
+| 脚本                          | 作用                                                      | 关键指标                             |
+| ----------------------------- | --------------------------------------------------------- | ------------------------------------ |
+| `benchmark_put.py`            | 单客户端顺序 PUT，生成指定数量的 `bench_test_key_{i}`     | 吞吐量、Avg/P50/P95/P99 Latency      |
+| `benchmark_get.py`            | 单客户端顺序 GET，拉取 PUT 端生成的 `bench_test_key_{i}`  | 吞吐量、Avg/P50/P99 Latency          |
+| `benchmark_put_size_sweep.py` | 按不同数据大小生成 Key，格式 `{prefix}_{size}mb_{index}`  | 各尺寸吞吐、Avg/P95/P99、失败次数    |
+| `benchmark_get_size_sweep.py` | 适配 PUT sweep，按目标尺寸列表逐一测试 GET                | 各尺寸吞吐、Avg/P95/P99、失败次数    |
+| `benchmark_get_concurrent.py` | 启动 N 个独立 Client 并发拉取同一批 Key，评估链路饱和吞吐 | 总吞吐、QPS、Avg/P50/P95/P99 Latency |
+
+### 使用示例
+
+#### 基础 PUT/GET 测试
+
+```bash
+# PUT 端：写入 16 个 10MB 的 Key (默认 key 为 bench_test_key_{i})
+python benchmark/benchmark_put.py --size_mb 10 --count 16
+
+# GET 端：拉取 PUT 端写入的数据，循环拉取 3 轮 (count 需与 PUT 端一致)
+python benchmark/benchmark_get.py --count 16 --rounds 3
+```
+
+#### 多尺寸 Size Sweep 测试
+
+```bash
+# PUT 端：使用默认值 (10MB × 8 个 key)
+python benchmark/benchmark_put_size_sweep.py
+
+# PUT 端：按 1MB/10MB/50MB 三个尺寸生成数据
+python benchmark/benchmark_put_size_sweep.py \
+    --size_mb 1,10,50 --keys-per-size 8 --key-prefix bench_size_sweep
+
+# GET 端：拉取对应尺寸的数据，循环 3 轮
+python benchmark/benchmark_get_size_sweep.py \
+    --size_mb 1,10,50 --keys-per-size 8 --rounds 3 --key-prefix bench_size_sweep
+```
+
+#### 并发 GET 测试
+
+```bash
+# 先启动 PUT 端生成数据 (默认值: 10MB × 8 key, prefix=bench_size_sweep)
+python benchmark/benchmark_put_size_sweep.py
+# 或自定义 PUT 参数
+python benchmark/benchmark_put_size_sweep.py --size_mb 10 --keys-per-size 8 --key-prefix bench_size_sweep
+
+# 启动并发 GET (默认值: 4 并发, 10MB × 8 key, 5 轮, prefix=bench_size_sweep)
+python benchmark/benchmark_get_concurrent.py
+
+# 自定义参数: 8 个客户端并发 GET，循环 5 轮
+python benchmark/benchmark_get_concurrent.py \
+    --size_mb 10 --keys-per-size 8 --concurrency 8 --rounds 5
+```