- 博客(8)
- 收藏
- 关注
转载 linux kernel 2.6.35中RFS特性详解
本文链接地址: linux kernel 2.6.35中RFS特性详解前面我介绍过google对内核协议栈的patch,RPS,它主要是为了软中断的负载均衡,这次继续来介绍google 的对RPS的增强path RFS(receive flow steering),RPS是把软中断map到对应cpu,而这个时候还会有另外的性能影响,那就是如果应用程序所在的cpu和软中断处理的cpu不是
2015-03-31 15:20:52 627
原创 TCP receive_queue prequeue backlog
接收到数据包时struct sock *sk 可能被进程下上文或者中断上下文占用:1、如果被进程上下文使占用时,软中断暂时拿不到锁,所以数据只能暂存在后备队列中(backlog),当进程上下文逻辑处理完成后会回调tcp_v4_do_rcv处理backlog队列作为补偿,具体看tcp_sendmsg 函数 release_sock的实现。2、如果sk被软中断占用时,那么数据可能被放置到rec
2015-03-31 09:46:32 1533 1
原创 两个单链表合并
#include #include typedef struct listchain{ int value; struct listchain *next;}List;List *malloc_list(void){ List *node = NULL; if((node=(List *)malloc(sizeof(struct listchai
2015-03-09 16:32:42 483
原创 linux tcp SACK分析(一)
why should SACK be designed ? TCP may experience poor performance when multiple packets are lost from one window of data. With the limited information available from cumulative acknowledgments
2015-03-08 10:39:06 2343
原创 C 语言 类型强制转换问题
C语言编程经常存在计算时隐藏类型转换问题,下面是转换规则: 高 double ←← float ↑ ↑ ↑ long ↑ ↑ ↑ unsigned ↑
2015-03-04 17:02:44 485
原创 Blind Data Injection Attack
TCP has historically been considered to be protected against spoofedoff-path packet injection attacks by relying on the fact that it is difficult to guess the 4-tuple (the source and destination IP
2015-03-04 08:57:22 1311
原创 Linux Per-CPU Data
Linux Per-CPU DataReasons for Using Per-CPU DataThere are a couple benefits to using per-CPU data. The first is the reduction inlocking requirements(减少locking的使用需求). Depending on thesemantics by
2015-03-01 21:44:22 842
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人