kvcache-ai/Mooncake

Fork

You've already forked Mooncake

mirror of https://github.com/kvcache-ai/Mooncake.git synced 2026-11-05 01:17:55 +00:00

Code Issues 368 Projects Packages Wiki Activity

[PR #1330] [MERGED] [TENT] fix a bug in memory registration and add TENT support to the example #2165

New issue

Closed

opened 2026-10-29 21:33:17 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-29 21:33:17 +00:00

Owner

Copy link

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/Mooncake/pull/1330
Author: @staryxchen
Created: 1/5/2026
Status: ✅ Merged
Merged: 1/6/2026
Merged by: @alogfans

Base: main ← Head: fix/tent

📝 Commits (4)

6c835cc fix(register-memory): correct function call and add metadata sync
55eebe9 feat(example): add TENT backend support and refactor common utilities
3946735 refactor(example): simplify protocol handling and improve signal management
ec31e7c style: reformat comment line length in transfer engine

📊 Changes

4 files changed (+357 additions, -154 deletions)

View changed files

📝 mooncake-transfer-engine/example/CMakeLists.txt (+4 -0)
📝 mooncake-transfer-engine/example/transfer_engine_bench.cpp (+342 -145)
📝 mooncake-transfer-engine/tent/src/runtime/transfer_engine_impl.cpp (+10 -8)
📝 mooncake-transfer-engine/tent/src/transfer_engine.cpp (+1 -1)

📄 Description

Description

This PR adds TENT backend support to the transfer engine benchmark and fixes a critical bug in memory registration that prevented remote peers from discovering newly registered buffers.

Changes

Bug Fix: Memory Registration Metadata Sync

Problem: When calling registerLocalMemory(void* addr, size_t size, Permission permission) with a single buffer, the registered memory was not visible to remote peers because the local segment metadata was not synchronized to the metadata server.

Root Cause:

In transfer_engine.cpp, the single-buffer overload incorrectly called itself recursively instead of delegating to the implementation.
In transfer_engine_impl.cpp, the single-buffer overload did not trigger metadata synchronization after registration.

Fix:

Corrected TransferEngine::registerLocalMemory to properly delegate to impl_->registerLocalMemory
Added metadata_->segmentManager().synchronizeLocal() call after successful buffer registration to ensure remote peers can discover the new buffers

Feature: TENT Backend Support in Benchmark

Added --backend flag to select between classic and tent backends
Refactored common buffer allocation/deallocation logic into shared helper functions
Added TENT-specific initiator and target implementations under tent_backend namespace
Updated CMakeLists.txt to conditionally link TENT library when USE_TENT is enabled

Type of Change

Types
- Bug fix
- New feature
  - Transfer Engine
  - Mooncake Store
  - Mooncake EP
  - Integration
  - P2P Store
  - Python Wheel
- Breaking change
- CI/CD
- Documentation update
- Other

How Has This Been Tested?

Testing

Verified that registered memory buffers are now visible to remote peers when using TENT backend
Tested both initiator and target modes with the new backend selection

Checklist

I have performed a self-review of my own code.
I have updated the documentation.
I have added tests to prove my changes are effective.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/kvcache-ai/Mooncake/pull/1330 **Author:** [@staryxchen](https://github.com/staryxchen) **Created:** 1/5/2026 **Status:** ✅ Merged **Merged:** 1/6/2026 **Merged by:** [@alogfans](https://github.com/alogfans) **Base:** `main` ← **Head:** `fix/tent` --- ### 📝 Commits (4) - [`6c835cc`](https://github.com/kvcache-ai/Mooncake/commit/6c835cc9d7696a3e89a848c24ae51614f38653ef) fix(register-memory): correct function call and add metadata sync - [`55eebe9`](https://github.com/kvcache-ai/Mooncake/commit/55eebe9be8f5d6ce99a666e21429d3b577d0fa0c) feat(example): add TENT backend support and refactor common utilities - [`3946735`](https://github.com/kvcache-ai/Mooncake/commit/39467354ccf05a59e4d0a897bda9b2a878a53e08) refactor(example): simplify protocol handling and improve signal management - [`ec31e7c`](https://github.com/kvcache-ai/Mooncake/commit/ec31e7c66e78f0a2ed163b85432a8e27efa92f86) style: reformat comment line length in transfer engine ### 📊 Changes **4 files changed** (+357 additions, -154 deletions) <details> <summary>View changed files</summary> 📝 `mooncake-transfer-engine/example/CMakeLists.txt` (+4 -0) 📝 `mooncake-transfer-engine/example/transfer_engine_bench.cpp` (+342 -145) 📝 `mooncake-transfer-engine/tent/src/runtime/transfer_engine_impl.cpp` (+10 -8) 📝 `mooncake-transfer-engine/tent/src/transfer_engine.cpp` (+1 -1) </details> ### 📄 Description ## Description This PR adds TENT backend support to the transfer engine benchmark and fixes a critical bug in memory registration that prevented remote peers from discovering newly registered buffers. ## Changes ### Bug Fix: Memory Registration Metadata Sync **Problem**: When calling `registerLocalMemory(void* addr, size_t size, Permission permission)` with a single buffer, the registered memory was not visible to remote peers because the local segment metadata was not synchronized to the metadata server. **Root Cause**: 1. In `transfer_engine.cpp`, the single-buffer overload incorrectly called itself recursively instead of delegating to the implementation. 2. In `transfer_engine_impl.cpp`, the single-buffer overload did not trigger metadata synchronization after registration. **Fix**: - Corrected `TransferEngine::registerLocalMemory` to properly delegate to `impl_->registerLocalMemory` - Added `metadata_->segmentManager().synchronizeLocal()` call after successful buffer registration to ensure remote peers can discover the new buffers ### Feature: TENT Backend Support in Benchmark - Added `--backend` flag to select between `classic` and `tent` backends - Refactored common buffer allocation/deallocation logic into shared helper functions - Added TENT-specific initiator and target implementations under `tent_backend` namespace - Updated CMakeLists.txt to conditionally link TENT library when `USE_TENT` is enabled ## Type of Change * Types - [x] Bug fix - [x] New feature - [x] Transfer Engine - [ ] Mooncake Store - [ ] Mooncake EP - [ ] Integration - [ ] P2P Store - [ ] Python Wheel - [ ] Breaking change - [ ] CI/CD - [ ] Documentation update - [ ] Other ## How Has This Been Tested? ## Testing - Verified that registered memory buffers are now visible to remote peers when using TENT backend - Tested both initiator and target modes with the new backend selection ## Checklist - [x] I have performed a self-review of my own code. - [x] I have updated the documentation. - [x] I have added tests to prove my changes are effective. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-29 21:33:17 +00:00

closed this issue
added the
pull-request
label

No Branch/Tag specified

main

te-coro

staryxchen-tent-capability-research

feature/musa-ep-jit

zxpdemonio/fix-tent-bootstrap-admission

add-store-rs-tone-tests

scatter-rdma-completion-pr2

P2P-Mooncake-Store

release/v0.3.14

feat/tent-rdma-adaptive-adapter

fix/ep-local-counter-gpu-scope

codex/kvcs-oplog-eviction

give-me-a-star

cruz/mooncake-kvcs-lowlevel-pr1-20261008

ylt-handshake-limits

ci/rocm-e2e-tent

sima/docs-pypi-downloads

fix-ci/hicache-mooncake-metadata-loopback

sima/cuda-driver-loading

sima/ci-performance-gate

fix/tent-rdma-unknown-topology-rail-pairing

ci/tent-e2e-dual-job

mc-patch-1

codex/p2p-merge-prerequisites

sima/store-hca-numa-placement

codex/p2p-merge-cli

codex/p2p-merge-ipv6

copilot/fix-ctests-job-failure

czh/pg-device-collectives-pr6

dependabot/cargo/mooncake-store-rs/pyo3-0.29.0

czh/pg-device-collectives-pr5

codex/segment-pool-master-cutover

sima/nightly-ci-recovery

ci/tent-params

stmatengss-patch-1

dependabot/cargo/mooncake-store-rs/rand-0.8.8

dependabot/cargo/mooncake-store-rs/opentelemetry_sdk-0.32.1

dependabot/cargo/mooncake-store-rs/xxhash-rust-0.8.16

codex/migrate-store-rest-service

fix/tone-wheel-arch-selection

czh/pg-device-collectives-pr4

czh/pg-device-collectives-pr3

ketong/fix_moe_tc

copilot/fix-test-wheel-ubuntu-job

fix/ci-wheel-torch-pg-pin

codex/migrate-structured-object-storage

codex/migrate-allocator-python

codex/migrate-vllm-python

codex/migrate-shared-segment

ci/fix_sgl_eval_install

codex/segment-pool-nof-placement-cleanup

feat/pip-native-release

copilot/bugfix-ha-standby-promotion

copilot/mooncake-store-transport-settings

copilot/fix-tensor-support-issues

copilot/optimize-rl-direction

copilot/mooncake-storeagentic-workflow

copilot/fix-client-reconnect-timeout

copilot/mooncake-error-debugging

copilot/mooncake-ipv6-support

feat/nccl-host-python-api

dependabot/go_modules/mooncake-p2p-store/src/p2pstore/google.golang.org/grpc-1.82.1

copilot/migrate-and-move-operations

copilot/migrate-and-move-operations-again

refactor/centralize-env-vars

idhanani/mooncake-retain-groups

copilot/codeownerreviewer

copilot/give-feedback-on-issue-2123

copilot/create-issue-rfc

copilot/break-cuda-monopoly-logic

copilot/compare-cudamemcpy-cu12-cu13

copilot/report-ci-error-issue

copilot/research-commit-history-analysis

copilot/explain-mooncake-store-service

copilot/analyze-project-functionality

copilot/sub-pr-1680

copilot/review-pr-1680

copilot/sub-pr-1597

copilot/fix-github-actions-job-failure

copilot/move-test-sglang-integration-job

v0.3.14

v0.3.14-pre-4

v0.3.14-pre-3

v0.3.14-pre-2

v0.3.14-pre

v0.3.14-rc1

v0.3.13.post1

v0.3.13-rc2

v0.3.13-rc1

v0.3.13

v0.3.12.post1

v0.3.12

v0.3.11-rc1

v0.3.11.post1

v0.3.11

v0.3.10.post2

v0.3.10.post1

v0.3.10

v0.3.9

v0.3.8.post1

v0.3.8

v0.3.7.post2

v0.3.7.post1

v0.3.7

v0.3.6.post1

v0.3.6

v0.3.5

v0.3.4.post2

v0.3.4.post1

v0.3.4

v0.3.3.post2

v0.3.3.post1

v0.3.3

v0.3.2.post1

v0.3.2

v0.3.1

v0.3.0

v0.3.0-beta

v0.3.0-alpha

v0.2.0

Labels

Clear labels

Mirrored from GitHub Pull Request

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

kvcache-ai/Mooncake#2165

Reference in a new issue

Repository

kvcache-ai/Mooncake

Title

Body

No description provided.

Delete branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?

Rows
Columns