yanglimingcn commented on code in PR #2942:
URL: https://github.com/apache/brpc/pull/2942#discussion_r2032674185
##########
src/butil/iobuf.cpp:
##########
@@ -1371,6 +1371,50 @@ IOBuf::Area IOBuf::reserve(size_t count) {
return result;
}
+IOBuf::Area IOBuf::reserve_aligned(size_t n, size_t alignment) {
+ bool is_power_two = alignment > 0 && (alignment & (alignment - 1));
+ if (is_power_two != 0) {
+ LOG(ERROR) << "Invalid alignment, must power of two";
+ return INVALID_AREA;
+ }
+ size_t count = (n + alignment - 1) & ~(alignment - 1);
+ IOBuf::Area result = INVALID_AREA;
+ size_t total_nc = 0;
+ while (total_nc < count) { // excluded count == 0
+ IOBuf::Block* b = iobuf::share_tls_block();
+ if (BAIDU_UNLIKELY(!b)) {
+ return INVALID_AREA;
+ }
+ const size_t remainder =
Review Comment:
> 一般只是需要长度为n的连续内存块起始地址对齐，需要每个block都是对齐的吗？
系统调用类似writev这种，都是支持一个数组的，iobuf里面的block在写文件的时候也是writev的，所以就自然能匹配上了。
rdma这种内存，内存分配也都在rdma内部就做完了而且适配了iobuf，它内存管理也都是按照不同大小的块组成的。
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: dev-unsubscr...@brpc.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@brpc.apache.org
For additional commands, e-mail: dev-h...@brpc.apache.org
