feat(gateway): add retry_on_refused for pymsg MsgClient (v0.6.1)
- Add MsgConnectionRefusedException to distinguish ECONNREFUSED from other connection errors; openConnection() now throws it when connect() returns ECONNREFUSED. - MsgClient::call() adds retry_on_refused/retry_interval parameters (defaults false/1.0s), matching Python pymsg.MsgClient.call(retry_on_refused=True). - Retry loop: only retries on ECONNREFUSED; other exceptions (timeout, connection reset, business errors) propagate immediately. Throttled logging: first failure prints immediately, subsequent logs every 5 seconds. - DbC::call_msg() enables retry_on_refused=true (db is a hard dependency; gateway blocks waiting for db on startup instead of crashing). - LogC::_send() explicitly passes retry_on_refused=false (fail-safe; never block the background log thread when db is unavailable). - captcha/smtp auxiliary services keep default retry_on_refused=false (fail-fast; blocking in request threads would exhaust the thread pool). - Update README with pymsg protocol documentation, downstream retry strategy table, and v0.6.1 changelog entry.
This commit is contained in:
qing committed
1 parent
b30ce1424b
commit
7d6ba6de93
5 files changed
+121
-32
No files matched your search
+14
-12
@@ -25,18 +25,20 @@ namespace qing {
|
||||
}
|
||||
|
||||
// 新版 pymsg 接口：通过 MsgClient（TCP 长度前缀帧协议）调用 dbv2。
|
||||
// 自动添加 _route = "execute"，返回 dbv2 pymsg 完整 JSON 响应
|
||||
// {"success":..., "data":[...]}。
|
||||
// 响应格式与 call_http 兼容，调用方可直接替换。
|
||||
static json::value call_msg(const json::value& params,
|
||||
double timeout = DEFAULT_TIMEOUT) {
|
||||
json::value jv_route = params;
|
||||
jv_route.as_object()["_route"] = "execute";
|
||||
pmc::net::MsgClient client("127.0.0.1", 8005, "gateway");
|
||||
std::string resp = client.call(
|
||||
json::serialize(jv_route), timeout);
|
||||
return json::parse(resp);
|
||||
}
|
||||
// 自动添加 _route = "execute"，返回 dbv2 pymsg 完整 JSON 响应
|
||||
// {"success":..., "data":[...]}。
|
||||
// 响应格式与 call_http 兼容，调用方可直接替换。
|
||||
// db 是强依赖，启用 retry_on_refused：db 未启动时阻塞等待，避免启动顺序问题。
|
||||
static json::value call_msg(const json::value& params,
|
||||
double timeout = DEFAULT_TIMEOUT) {
|
||||
json::value jv_route = params;
|
||||
jv_route.as_object()["_route"] = "execute";
|
||||
pmc::net::MsgClient client("127.0.0.1", 8005, "gateway");
|
||||
std::string resp = client.call(
|
||||
json::serialize(jv_route), timeout,
|
||||
/*retry_on_refused=*/true);
|
||||
return json::parse(resp);
|
||||
}
|
||||
|
||||
private:
|
||||
static constexpr const char* _DBURL = "http://127.0.0.1:8005/execute";
|
||||
|
||||
@@ -196,7 +196,8 @@ private:
|
||||
payload["values"] = std::move(values);
|
||||
|
||||
const std::string resp = client.call(
|
||||
json::serialize(payload), _TIMEOUT);
|
||||
json::serialize(payload), _TIMEOUT,
|
||||
/*retry_on_refused=*/false); // 日志是 fail-safe，db 不可用时静默丢弃，绝不阻塞重试
|
||||
auto obj = json::parse(resp).as_object();
|
||||
if (!obj.at("success").as_bool()) {
|
||||
std::string err = "unknown";
|
||||
|
||||
+75
-16
@@ -17,11 +17,14 @@
|
||||
*/
|
||||
|
||||
#include <cerrno>
|
||||
#include <chrono>
|
||||
#include <cstdint>
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <functional>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <thread>
|
||||
#include <vector>
|
||||
|
||||
#include <arpa/inet.h>
|
||||
@@ -59,6 +62,13 @@ public:
|
||||
explicit MsgConnectionException(const std::string &msg) : MsgException(msg) {}
|
||||
};
|
||||
|
||||
/// 目标服务未启动（connect 返回 ECONNREFUSED），用于 retry_on_refused 重试机制
|
||||
class MsgConnectionRefusedException : public MsgConnectionException {
|
||||
public:
|
||||
explicit MsgConnectionRefusedException(const std::string &msg)
|
||||
: MsgConnectionException(msg) {}
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
// Low-level protocol: 4-byte big-endian length prefix + UTF-8 payload
|
||||
// ============================================================================
|
||||
@@ -155,10 +165,14 @@ inline int openConnection(const std::string& addr, int port, double timeout) {
|
||||
|
||||
if (::connect(fd, reinterpret_cast<struct sockaddr *>(&serv_addr),
|
||||
sizeof(serv_addr)) < 0) {
|
||||
int saved_errno = errno;
|
||||
::close(fd);
|
||||
throw MsgConnectionException(
|
||||
"could not connect to " + addr + ":" + std::to_string(port) +
|
||||
" - " + ::strerror(errno));
|
||||
std::string err_msg = "could not connect to " + addr + ":" +
|
||||
std::to_string(port) + " - " + ::strerror(saved_errno);
|
||||
if (saved_errno == ECONNREFUSED) {
|
||||
throw MsgConnectionRefusedException(err_msg);
|
||||
}
|
||||
throw MsgConnectionException(err_msg);
|
||||
}
|
||||
|
||||
return fd;
|
||||
@@ -242,19 +256,64 @@ public:
|
||||
///
|
||||
/// 不会给消息添加 ``name:`` 前缀（适用于 RPC/API 调用）。
|
||||
///
|
||||
/// @param msg 要发送的原始字符串。
|
||||
/// @param timeout 超时秒数，默认 10.0。
|
||||
/// @returns 服务器返回的字符串。
|
||||
std::string call(const std::string &msg, double timeout = 10.0) {
|
||||
int fd = detail::openConnection(_addr, _port, timeout);
|
||||
try {
|
||||
pmsg_send(fd, msg);
|
||||
std::string resp = pmsg_recv(fd);
|
||||
::close(fd);
|
||||
return resp;
|
||||
} catch (...) {
|
||||
::close(fd);
|
||||
throw;
|
||||
/// @param msg 要发送的原始字符串。
|
||||
/// @param timeout 超时秒数，默认 10.0。
|
||||
/// @param retry_on_refused 目标服务未启动（ECONNREFUSED）时是否阻塞重试，
|
||||
/// 直到连接成功。适用于启动顺序不确定的服务发现场景。
|
||||
/// 默认 false（连接拒绝立即抛异常）。
|
||||
/// @param retry_interval 重试间隔秒数，默认 1.0。
|
||||
/// @returns 服务器返回的字符串。
|
||||
std::string call(const std::string &msg, double timeout = 10.0,
|
||||
bool retry_on_refused = false,
|
||||
double retry_interval = 1.0) {
|
||||
if (!retry_on_refused) {
|
||||
// 快速路径：不重试，直接执行一次，保持原有行为
|
||||
int fd = detail::openConnection(_addr, _port, timeout);
|
||||
try {
|
||||
pmsg_send(fd, msg);
|
||||
std::string resp = pmsg_recv(fd);
|
||||
::close(fd);
|
||||
return resp;
|
||||
} catch (...) {
|
||||
::close(fd);
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
// 重试路径：仅对 ECONNREFUSED 重试，其他错误立即抛出
|
||||
constexpr double kLogEvery = 5.0; // 重试期间打印等待提示的间隔（秒）
|
||||
int attempt = 0;
|
||||
auto last_log = std::chrono::steady_clock::now() -
|
||||
std::chrono::duration_cast<std::chrono::steady_clock::duration>(
|
||||
std::chrono::duration<double>(kLogEvery));
|
||||
|
||||
while (true) {
|
||||
try {
|
||||
int fd = detail::openConnection(_addr, _port, timeout);
|
||||
try {
|
||||
pmsg_send(fd, msg);
|
||||
std::string resp = pmsg_recv(fd);
|
||||
::close(fd);
|
||||
return resp;
|
||||
} catch (...) {
|
||||
::close(fd);
|
||||
throw;
|
||||
}
|
||||
} catch (const MsgConnectionRefusedException &) {
|
||||
++attempt;
|
||||
auto now = std::chrono::steady_clock::now();
|
||||
double elapsed = std::chrono::duration<double>(now - last_log).count();
|
||||
if (elapsed >= kLogEvery || attempt == 1) {
|
||||
std::fprintf(stderr,
|
||||
"[pymsg] 等待服务 %s:%d 就绪... (已重试 %d 次)\n",
|
||||
_addr.c_str(), _port, attempt);
|
||||
std::fflush(stderr);
|
||||
last_log = now;
|
||||
}
|
||||
std::this_thread::sleep_for(
|
||||
std::chrono::duration<double>(retry_interval));
|
||||
}
|
||||
// 其他异常（MsgTimeoutException、普通MsgConnectionException等）不捕获，直接向上抛出
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user