[model-gateway] Replace PolicyRegistry RwLock with DashMap for lock-free policy lookups#15361
Merged
[model-gateway] Replace PolicyRegistry RwLock with DashMap for lock-free policy lookups#15361
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
/gemini review |
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
The PolicyRegistry was using Arc<RwLock<HashMap<...>>> which required acquiring a std::sync::RwLock on every get_policy() call - this happens on every single request during worker selection. Changed model_policies and model_worker_counts to use DashMap: - get_policy() is now lock-free (sharded concurrent HashMap) - on_worker_added/removed use DashMap's efficient entry API - Eliminates lock contention on the hot path Kept RwLock for prefill/decode policies since they're set once at startup and only used in PD mode (less frequent access pattern).
64e432d to
3cbae89
Compare
Collaborator
Author
|
/gemini review |
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Liwansi
added a commit
to iforgetmyname/sglang
that referenced
this pull request
Dec 19, 2025
…n3_pp * 'main' of https://github.com/sgl-project/sglang: (74 commits) [bug fix][pp] fix inconsistent latency between tp (sgl-project#15379) Fix warp illegal instruction in kimi k2 thinking PCG (sgl-project#15306) Fix gpt-oss yarn with `truncate` argument (sgl-project#14270) Monkey patch deepseek-ocr's `v_head_dim` (sgl-project#15384) [model-gateway] Replace PolicyRegistry RwLock with DashMap for lock-free policy lookups (sgl-project#15361) [PP] Fix dynamic chunking strategy for PP (sgl-project#15372) Fix issue: ENABLE_BELOW_SM90 cannot be enabled on aarch64 CPU (sgl-project#12967) Split test_piecewise_cuda_graph.py to optimize CI resource usage (sgl-project#15290) unified management of environment variables for vlm cuda ipc transport (sgl-project#14501) Mistral Large 3 NVFP4 TRTLLM MoE support (sgl-project#15049) fix: adjust time for test_epd_disaggregation.py (sgl-project#15354) Add doc for qwen3 next (sgl-project#15337) feat: DeepSeek-V3.2 Streaming tool call output (sgl-project#15278) Feature/trtllm mha workspace size configurable sgl-project#15089 (sgl-project#15131) [VLM] Support cos sin cache for Qwen3-VL & GLM-4.1V (sgl-project#15205) [Deepseek V3.2] Support Overlap Spec + NSA (sgl-project#15307) Add request-level timestamp for when prefill finishes (sgl-project#14860) [CI] Migrate LoRA tests to test/registered/lora/ (sgl-project#15176) Reserve more memory for DeepSeekOCR model and adjust server start timeout for DeepGEMM to reduce flakiness (sgl-project#15277) Fix condition check for require_gathered_buffer (sgl-project#15328) ...
Prozac614
pushed a commit
to Prozac614/sglang
that referenced
this pull request
Dec 23, 2025
…ree policy lookups (sgl-project#15361)
jiaming1130
pushed a commit
to zhuyijie88/sglang
that referenced
this pull request
Dec 25, 2025
…ree policy lookups (sgl-project#15361)
YChange01
pushed a commit
to YChange01/sglang
that referenced
this pull request
Jan 13, 2026
…ree policy lookups (sgl-project#15361)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The PolicyRegistry was using Arc<RwLock<HashMap<...>>> which required acquiring a std::sync::RwLock on every get_policy() call - this happens on every single request during worker selection.
Changed model_policies and model_worker_counts to use DashMap:
Kept RwLock for prefill/decode policies since they're set once at startup and only used in PD mode (less frequent access pattern).
Checklist