core: add tools/bench (throughput/load/alloc-check) and record the M7 baseline
Three subcommands in one binary, driving vdm::Engine directly (docs/04 §8): - throughput: a single download against a fast local origin (support/local_server.hpp, busybox httpd), reporting Mbps/CPU%/RSS. Gates on --require-mbps/--max-cpu-pct only when passed, so the ctest smoke registration stays a correctness check, not a hardware-dependent perf gate -- the real 1-Gbit-link sign-off is a manual/CI job (see the file's header comment). - load: N concurrent tasks against tools/testserver's `throttled` mode (support/testserver_client.hpp), reporting peak RSS via getrusage(). Paced externally rather than through the engine's own rate::RateLimiter or busybox: the limiter's pause/resume path allocates on every throttle event (would contaminate alloc-check's measurement) and under heavy segment contention was found to starve individual tasks indefinitely (see docs/adr/0016, added here); busybox couldn't sustain the DoD's ~160 concurrent connections (20 tasks * default_segments=8) reliably. The ctest registration runs at reduced concurrency under sanitizer presets -- see the CMakeLists.txt comment and the ADR's postscript. - alloc-check: operator new/delete overridden process-wide, sampling the allocation count across a steady mid-transfer window against a paced tools/testserver origin. Caught a real bug in the same change (see the http_client.cpp commit) and, by dropping its Engine mid-download to end cleanly, also surfaced the quiesce() use-after-free (see that commit). core/docs/m7-baseline.md records actual measured numbers against the M1/M7 DoD lines, including where they don't clear yet (RSS ~70 MB vs a 60 MB target; throughput/CPU only measured on loopback, no 1 Gbit link available here) rather than rounding them away. docs/adr/0016 documents a rate::RateLimiter fairness gap found building the load subcommand: a single shared TokenBucket under heavy segment contention has no fairness ordering across its peek/commit race and can starve a waiter well past what its configured rate implies. Filed as a follow-up (it's a core/src/rate design question, not a tools/bench one) rather than fixed here, along with a related TSan-only load-test straggler that could not be root-caused in this environment. Co-Authored-By: Claude Sonnet 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Q3QrF7rCt21bkAjt9BCDFQ
This commit is contained in:
Claude Sonnet 5
@@ -0,0 +1,126 @@
|
||||
// tools/bench/support/testserver_client.hpp — spawn tools/testserver for benches that need
|
||||
// a genuinely paced, external source (alloc-check's steady-state sampling window).
|
||||
//
|
||||
// LocalServer (busybox httpd) is right for the throughput/load numbers -- it's fast and
|
||||
// honest, closer to "a real origin". But that speed is exactly wrong for alloc-check: at
|
||||
// this server's loopback throughput a modest file transfers in well under the sampling
|
||||
// window, leaving nothing to sample mid-transfer. Rather than pace the transfer with the
|
||||
// engine's own rate::RateLimiter (whose curl-write-callback pause/resume path allocates a
|
||||
// timer node + std::function per throttle event -- exactly the kind of cost alloc-check
|
||||
// exists to catch, so using it to build the fixture would contaminate the measurement),
|
||||
// pace it *externally*: tools/testserver's `throttled` mode sleeps between chunks
|
||||
// server-side, so curl's write callback fires already spaced out and the engine never
|
||||
// takes the pause/resume path at all.
|
||||
//
|
||||
// Linux-only (fork/exec/pipe/kill), same shape as core/tests/net/testserver_fixture.hpp
|
||||
// (which this mirrors rather than includes -- that header lives under core/tests and pulls
|
||||
// in VDM_TESTSERVER_PY via core/tests/CMakeLists.txt's own injection; tools/bench gets its
|
||||
// own so the two test trees stay independently buildable).
|
||||
|
||||
#ifndef VDM_BENCH_TESTSERVER_CLIENT_HPP
|
||||
#define VDM_BENCH_TESTSERVER_CLIENT_HPP
|
||||
|
||||
#include <fcntl.h>
|
||||
#include <signal.h>
|
||||
#include <sys/wait.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include <cerrno>
|
||||
#include <chrono>
|
||||
#include <cstdlib>
|
||||
#include <string>
|
||||
#include <thread>
|
||||
|
||||
#ifndef VDM_TESTSERVER_PY
|
||||
#define VDM_TESTSERVER_PY ""
|
||||
#endif
|
||||
|
||||
namespace vdm::bench {
|
||||
|
||||
class TestServerProc {
|
||||
public:
|
||||
// `throttle_bps` sets the `throttled` mode's rate (testserver's own default is 1
|
||||
// MiB/s, generally too slow to keep a ctest's TIMEOUT happy at a size big enough to
|
||||
// span a sampling window -- callers pacing a specific --size/--window-s pair should
|
||||
// pass one sized to match, same arithmetic cmd_load uses for its own rate limit).
|
||||
explicit TestServerProc(std::uint64_t throttle_bps = 0) {
|
||||
const char *script = VDM_TESTSERVER_PY;
|
||||
if (!script || !*script || ::access(script, R_OK) != 0)
|
||||
return;
|
||||
|
||||
int pipefd[2];
|
||||
if (::pipe(pipefd) != 0)
|
||||
return;
|
||||
|
||||
pid_ = ::fork();
|
||||
if (pid_ < 0) {
|
||||
::close(pipefd[0]);
|
||||
::close(pipefd[1]);
|
||||
pid_ = -1;
|
||||
return;
|
||||
}
|
||||
if (pid_ == 0) {
|
||||
::dup2(pipefd[1], STDOUT_FILENO);
|
||||
::close(pipefd[0]);
|
||||
::close(pipefd[1]);
|
||||
int devnull = ::open("/dev/null", O_WRONLY);
|
||||
if (devnull >= 0)
|
||||
::dup2(devnull, STDERR_FILENO);
|
||||
std::string bps_str = std::to_string(throttle_bps ? throttle_bps : 1048576ull);
|
||||
::execlp("python3", "python3", script, "--port", "0", "--seed", "7",
|
||||
"--throttle-bps", bps_str.c_str(), static_cast<char *>(nullptr));
|
||||
::_exit(127);
|
||||
}
|
||||
::close(pipefd[1]);
|
||||
|
||||
std::string line;
|
||||
char c = 0;
|
||||
auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(10);
|
||||
while (std::chrono::steady_clock::now() < deadline) {
|
||||
ssize_t r = ::read(pipefd[0], &c, 1);
|
||||
if (r == 1) {
|
||||
if (c == '\n')
|
||||
break;
|
||||
line += c;
|
||||
} else if (r == 0) {
|
||||
break;
|
||||
} else if (errno != EINTR) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
::close(pipefd[0]);
|
||||
if (!line.empty())
|
||||
port_ = std::atoi(line.c_str());
|
||||
std::this_thread::sleep_for(std::chrono::milliseconds(150));
|
||||
}
|
||||
|
||||
~TestServerProc() {
|
||||
if (pid_ > 0) {
|
||||
::kill(pid_, SIGTERM);
|
||||
int status = 0;
|
||||
for (int i = 0; i < 50; ++i) {
|
||||
if (::waitpid(pid_, &status, WNOHANG) == pid_)
|
||||
return;
|
||||
std::this_thread::sleep_for(std::chrono::milliseconds(20));
|
||||
}
|
||||
::kill(pid_, SIGKILL);
|
||||
::waitpid(pid_, &status, 0);
|
||||
}
|
||||
}
|
||||
|
||||
TestServerProc(const TestServerProc &) = delete;
|
||||
TestServerProc &operator=(const TestServerProc &) = delete;
|
||||
|
||||
[[nodiscard]] bool available() const { return port_ > 0; }
|
||||
[[nodiscard]] std::string url(const std::string &path) const {
|
||||
return "http://127.0.0.1:" + std::to_string(port_) + path;
|
||||
}
|
||||
|
||||
private:
|
||||
pid_t pid_ = -1;
|
||||
int port_ = 0;
|
||||
};
|
||||
|
||||
} // namespace vdm::bench
|
||||
|
||||
#endif // VDM_BENCH_TESTSERVER_CLIENT_HPP
|
||||
Reference in New Issue
Block a user