Add Power-of-Two-Choices Peak-EWMA load balancer (p2c)

[rajvarun77]

What problem does this PR solve?

Issue Number: resolve #3340

Problem Summary: brpc has no Power-of-Two-Choices load balancer — the most widely deployed tail-latency-aware policy (Envoy LEAST_REQUEST, Finagle/linkerd Peak-EWMA). A single degraded backend keeps receiving 25% of rr traffic until humans intervene; la's averaging window reacts slower than one observation.

What is changed and the side effects?

Changed: New p2c policy (src/brpc/policy/p2c_ewma_load_balancer.{h,cpp}): each selection samples two random servers (p2c:choices=N widens; evaluates all when N ≥ cluster size, with random tie-breaking to avoid herding) and routes to the lower peak_ewma_latency_us * (inflight + 1) / weight. Latency spikes replace the average immediately; recovery decays over tau_ms (default 10s); failures are punished with at least the RPC timeout. Uses only existing hooks (SelectServer/Feedback, DoublyBufferedData membership like rr); per-node stats are stable pointers shared by both buffers as in la. Registered in global.cpp; 10 unit tests; p2c docs in docs/{cn,en}/client.md.

Benchmark (rpc_press, 4 echo backends, slow = +5ms bthread_usleep, qps=4000, 15s, 50 threads, 3 reps averaged, zero errors; p99/p999 µs):

scenario	la	p2c (best-of-2)	p2c:choices=4	rr
all healthy	450 / 1042	418 / 768	435 / 1136	567 / 12833
1 slow of 4	384 / 771	2451 / 6460	399 / 545	6440 / 6511
2 slow of 4	1045 / 2709	6458 / 6779	4284 / 6486	6474 / 6542

Slow-node traffic share (1 slow of 4): rr 25%, p2c 1.3%, p2c:choices=4 0.6%, la 0.0% — consistent with the numbers on #3340.

Side effects:

• Performance effects: none on existing policies; p2c selection is O(1) (two score evaluations).
• Breaking backward compatibility: no.

---

Check List:

• Compiles in CMake/Bazel/Makefile (sources and tests are picked up by the existing globs); brpc_p2c_ewma_load_balancer_unittest passes 10/10 and brpc_load_balancer_unittest passes 16/16.

cc @chenBright (thanks for the green light on #3340!) @zyearn

🤖 Generated with Claude Code

[Copilot]

Pull request overview

This PR adds a new client-side load balancing policy, p2c (Power-of-Two-Choices with Peak-EWMA latency scoring), to improve tail latency by quickly shifting traffic away from slow or failing backends using per-node peak-sensitive EWMA latency and in-flight request tracking.

Changes:

• Introduces P2CEwmaLoadBalancer implementing P2C sampling with Peak-EWMA latency scoring and in-flight bias.
• Registers the new balancer under the name p2c in global load balancer extensions.
• Adds unit tests and updates user-facing documentation and tooling help text to describe/enable p2c.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
tools/rpc_press/rpc_press.cpp	Adds p2c to the -lb_policy help text.
test/brpc_p2c_ewma_load_balancer_unittest.cpp	Adds unit tests covering selection behavior, weights, errors, exclusions, and concurrent churn.
src/brpc/policy/p2c_ewma_load_balancer.h	Declares the new P2CEwmaLoadBalancer and its per-node stats/membership structures.
src/brpc/policy/p2c_ewma_load_balancer.cpp	Implements P2C selection, Peak-EWMA scoring/decay, and feedback updates.
src/brpc/global.cpp	Registers p2c in the global load balancer registry.
docs/en/client.md	Documents the p2c policy and its parameters.
docs/cn/rpc_press.md	Updates rpc_press documentation to list p2c as a supported -lb_policy.
docs/cn/client.md	Adds Chinese documentation for the p2c policy and its parameters.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.