Skip to content

branch-4.1: [fix](be) Report stream load size limits in MiB #66224 #66351

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
github-actions wants to merge 1 commit into
base: branch-4.1
Choose a base branch
from
+97 −13
Open

branch-4.1: [fix](be) Report stream load size limits in MiB #66224 #66351

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions be/src/service/http/action/http_stream.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,8 @@ using namespace ErrorCode;

namespace {

constexpr size_t MEBIBYTE = 1024 * 1024;

bool is_compressed_file_scan(const TPipelineFragmentParams& params) {
if (!params.__isset.file_scan_params) {
return false;
Expand Down Expand Up @@ -231,7 +233,8 @@ Status HttpStreamAction::_on_header(HttpRequest* http_req, std::shared_ptr<Strea
// TODO(zs) : need Need to request an FE to obtain information such as format
// check content length
ctx->body_bytes = 0;
size_t csv_max_body_bytes = config::streaming_load_max_mb * 1024 * 1024;
const auto csv_max_body_mb = config::streaming_load_max_mb;
size_t csv_max_body_bytes = csv_max_body_mb * MEBIBYTE;
if (!http_req->header(HttpHeaders::CONTENT_LENGTH).empty()) {
try {
ctx->body_bytes = std::stol(http_req->header(HttpHeaders::CONTENT_LENGTH));
Expand All @@ -243,9 +246,11 @@ Status HttpStreamAction::_on_header(HttpRequest* http_req, std::shared_ptr<Strea
if (ctx->body_bytes > csv_max_body_bytes) {
LOG(WARNING) << "body exceed max size." << ctx->brief();
return Status::Error<ErrorCode::EXCEEDED_LIMIT>(
"body size {} exceed BE's conf `streaming_load_max_mb` {}. increase it if you "
"are sure this load is reasonable",
ctx->body_bytes, csv_max_body_bytes);
"body size {} bytes ({:.2f} MiB) exceeds the limit of {} bytes ({} MiB) set "
"by BE config `streaming_load_max_mb`. Increase it if you are sure this load "
"is reasonable",
ctx->body_bytes, static_cast<double>(ctx->body_bytes) / MEBIBYTE,
csv_max_body_bytes, csv_max_body_mb);
}
}

Expand Down
23 changes: 15 additions & 8 deletions be/src/service/http/action/stream_load.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,7 @@ bvar::LatencyRecorder g_stream_load_commit_and_publish_latency_ms("stream_load",
"commit_and_publish_ms");

static constexpr size_t MIN_CHUNK_SIZE = 64 * 1024;
static constexpr size_t MEBIBYTE = 1024 * 1024;
static const std::string CHUNK = "chunked";
static const std::string OFF_MODE = "off_mode";
static const std::string SYNC_MODE = "sync_mode";
Expand Down Expand Up @@ -290,8 +291,10 @@ Status StreamLoadAction::_on_header(HttpRequest* http_req, std::shared_ptr<Strea

// check content length
ctx->body_bytes = 0;
size_t csv_max_body_bytes = config::streaming_load_max_mb * 1024 * 1024;
size_t json_max_body_bytes = config::streaming_load_json_max_mb * 1024 * 1024;
const auto csv_max_body_mb = config::streaming_load_max_mb;
size_t csv_max_body_bytes = csv_max_body_mb * MEBIBYTE;
const auto json_max_body_mb = config::streaming_load_json_max_mb;
size_t json_max_body_bytes = json_max_body_mb * MEBIBYTE;
bool read_json_by_line = false;
if (!http_req->header(HTTP_READ_JSON_BY_LINE).empty()) {
if (iequal(http_req->header(HTTP_READ_JSON_BY_LINE), "true")) {
Expand All @@ -309,17 +312,21 @@ Status StreamLoadAction::_on_header(HttpRequest* http_req, std::shared_ptr<Strea
if ((ctx->format == TFileFormatType::FORMAT_JSON) &&
(ctx->body_bytes > json_max_body_bytes) && !read_json_by_line) {
return Status::Error<ErrorCode::EXCEEDED_LIMIT>(
"json body size {} exceed BE's conf `streaming_load_json_max_mb` {}. increase "
"it if you are sure this load is reasonable",
ctx->body_bytes, json_max_body_bytes);
"json body size {} bytes ({:.2f} MiB) exceeds the limit of {} bytes ({} MiB) "
"set by BE's conf streaming_load_json_max_mb. Increase it if you are sure "
"this load is reasonable",
ctx->body_bytes, static_cast<double>(ctx->body_bytes) / MEBIBYTE,
json_max_body_bytes, json_max_body_mb);
}
// csv max body size
else if (ctx->body_bytes > csv_max_body_bytes) {
LOG(WARNING) << "body exceed max size." << ctx->brief();
return Status::Error<ErrorCode::EXCEEDED_LIMIT>(
"body size {} exceed BE's conf `streaming_load_max_mb` {}. increase it if you "
"are sure this load is reasonable",
ctx->body_bytes, csv_max_body_bytes);
"body size {} bytes ({:.2f} MiB) exceeds the limit of {} bytes ({} MiB) set "
"by BE's conf streaming_load_max_mb. Increase it if you are sure this load is "
"reasonable",
ctx->body_bytes, static_cast<double>(ctx->body_bytes) / MEBIBYTE,
csv_max_body_bytes, csv_max_body_mb);
}
} else {
#ifndef BE_TEST
Expand Down
74 changes: 73 additions & 1 deletion be/test/service/http/stream_load_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,9 @@
#include "event2/http_struct.h"
#include "evhttp.h"
#include "load/group_commit/wal/wal_manager.h"
#include "load/stream_load/stream_load_context.h"
#include "runtime/exec_env.h"
#include "service/http/action/http_stream.h"
#include "service/http/ev_http_server.h"
#include "service/http/http_channel.h"
#include "service/http/http_common.h"
Expand All @@ -37,6 +39,7 @@
#include "service/http/http_headers.h"
#include "service/http/http_request.h"
#include "service/http/utils.h"
#include "util/defer_op.h"

namespace doris {

Expand Down Expand Up @@ -123,4 +126,73 @@ TEST_F(StreamLoadTest, TestHeader) {
evhttp_request_free(evhttp_req);
}
}
} // namespace doris

TEST_F(StreamLoadTest, JsonBodySizeLimitPlusOneErrorIncludesExactBytes) {
const auto original_json_max_mb = config::streaming_load_json_max_mb;
Defer restore_json_max_mb {
[original_json_max_mb] { config::streaming_load_json_max_mb = original_json_max_mb; }};
config::streaming_load_json_max_mb = 100;

auto* evhttp_req = evhttp_request_new(nullptr, nullptr);
HttpRequest req(evhttp_req);
req.set_header(HttpHeaders::AUTHORIZATION, "Basic cm9vdDo=");
req.set_header(HTTP_FORMAT_KEY, "json");
req.set_header(HttpHeaders::CONTENT_LENGTH, "104857601");

StreamLoadAction action(nullptr);
auto ctx = std::make_shared<StreamLoadContext>(nullptr);
auto status = action._on_header(&req, ctx);

EXPECT_TRUE(status.is<ErrorCode::EXCEEDED_LIMIT>());
EXPECT_EQ(status.to_string_no_stack(),
"[E-217]json body size 104857601 bytes (100.00 MiB) exceeds the limit of 104857600 "
"bytes (100 MiB) set by BE's conf streaming_load_json_max_mb. Increase it if you "
"are sure this load is reasonable");
evhttp_request_free(evhttp_req);
}

TEST_F(StreamLoadTest, CsvBodySizeLimitPlusOneErrorIncludesExactBytes) {
const auto original_max_mb = config::streaming_load_max_mb;
Defer restore_max_mb {[original_max_mb] { config::streaming_load_max_mb = original_max_mb; }};
config::streaming_load_max_mb = 100;

auto* evhttp_req = evhttp_request_new(nullptr, nullptr);
HttpRequest req(evhttp_req);
req.set_header(HttpHeaders::AUTHORIZATION, "Basic cm9vdDo=");
req.set_header(HTTP_FORMAT_KEY, "csv");
req.set_header(HttpHeaders::CONTENT_LENGTH, "104857601");

StreamLoadAction action(nullptr);
auto ctx = std::make_shared<StreamLoadContext>(nullptr);
auto status = action._on_header(&req, ctx);

EXPECT_TRUE(status.is<ErrorCode::EXCEEDED_LIMIT>());
EXPECT_EQ(status.to_string_no_stack(),
"[E-217]body size 104857601 bytes (100.00 MiB) exceeds the limit of 104857600 bytes "
"(100 MiB) set by BE's conf streaming_load_max_mb. Increase it if you are sure this "
"load is reasonable");
evhttp_request_free(evhttp_req);
}

TEST_F(StreamLoadTest, HttpStreamBodySizeLimitPlusOneErrorIncludesExactBytes) {
const auto original_max_mb = config::streaming_load_max_mb;
Defer restore_max_mb {[original_max_mb] { config::streaming_load_max_mb = original_max_mb; }};
config::streaming_load_max_mb = 100;

auto* evhttp_req = evhttp_request_new(nullptr, nullptr);
HttpRequest req(evhttp_req);
req.set_header(HttpHeaders::AUTHORIZATION, "Basic cm9vdDo=");
req.set_header(HttpHeaders::CONTENT_LENGTH, "104857601");

HttpStreamAction action(nullptr);
auto ctx = std::make_shared<StreamLoadContext>(nullptr);
auto status = action._on_header(&req, ctx);

EXPECT_TRUE(status.is<ErrorCode::EXCEEDED_LIMIT>());
EXPECT_EQ(status.to_string_no_stack(),
"[E-217]body size 104857601 bytes (100.00 MiB) exceeds the limit of 104857600 bytes "
"(100 MiB) set by BE config `streaming_load_max_mb`. Increase it if you are sure "
"this load is reasonable");
evhttp_request_free(evhttp_req);
}
} // namespace doris
Loading