From ed37c8175abdfd98ce2b3c4e6e2e74615c341c82 Mon Sep 17 00:00:00 2001 From: hui lai <1353307710@qq.com> Date: Fri, 6 Sep 2024 00:37:59 +0800 Subject: [PATCH] [fix](multi table) do not use strlen to calculate the length of msg (#40367) Meet code dump when using single stream multi table load: ``` SUMMARY: AddressSanitizer: heap-buffer-overflow /root/doris/be/src/io/fs/multi_table_pipe.cpp:99:22 in doris::io::MultiTablePipe::dispatch(std::__cxx11::basic_string, std::allocator> const&, char const*, unsigned long, doris::Status (doris::io::KafkaConsumerPipe::*)(char const*, unsigned long)) ``` 1. It is hard to guaranteed that msg is a C-style string ending in '\0' character. If not, it may cause the core dump to access memory out of bounds. 2. It is not need to calculate the length of msg twice. Therefore, deleting the logic that using strlen to calculate the length of msg. --- be/src/io/fs/multi_table_pipe.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/be/src/io/fs/multi_table_pipe.cpp b/be/src/io/fs/multi_table_pipe.cpp index 357abee9d0fdb1..70ad64a81ce7cb 100644 --- a/be/src/io/fs/multi_table_pipe.cpp +++ b/be/src/io/fs/multi_table_pipe.cpp @@ -96,7 +96,7 @@ std::string MultiTablePipe::parse_dst_table(const char* data, size_t size) { Status MultiTablePipe::dispatch(const std::string& table, const char* data, size_t size, AppendFunc cb) { - if (size == 0 || strlen(data) == 0) { + if (size == 0) { LOG(WARNING) << "empty data for table: " << table << ", ctx: " << _ctx->brief(); return Status::InternalError("empty data"); }