1[](https://travis-ci.org/F-Stack/f-stack) 2 3# F-Stack 4 5 6## Introduction 7 8With the rapid development of Network Interface Cards the poor performance of data packet processing with the Linux kernel has become the bottleneck in modern network systems. Yet, the increasing demands of the Internet's growth demand a higher performant network processing solution. Kernel bypass has emerged to catch more and more attention. There are various similar technologies such as: DPDK, NETMAP and PF_RING. The main idea of kernel bypass is that Linux is only used to deal with control flow; all data streams are processed in user space. Therefore, kernel bypass can avoid performance bottlenecks caused by kernel packet copying, thread scheduling, system calls, and interrupts. Furthermore, kernel bypass can achieve higher performance with multi-optimizing methods. Within various techniques, DPDK has been widely used because of it's more thorough isolation from kernel scheduling and active community support. 9 10[F-Stack](http://www.f-stack.org/?from=github) is an open source high performant network framework based on DPDK with the following characteristics: 11 121. Ultra high network performance which the network card can achieve under full load: 10 million concurrent connections, 5 million RPS, 1 million CPS. 132. Transplant FreeBSD 11.01 user space stack, which provides a complete stack function, and cut a great amount of irrelevant features. This greatly enhances network performance. 143. Support Nginx, Redis, and other mature applications. Services can easily use F-Stack. 154. Easy to extend with multi-process architecture. 165. Provides micro thread interface. Various applications with stateful applications can easily use F-Stack to get high performance without processing complex asynchronous logic. 176. Provide an Epoll/Kqueue interface that allow many kinds of applications to easily use F-Stack. 18 19## History 20 21To deal with the increasingly severe DDoS attacks the authorized DNS server of Tencent Cloud DNSPod switched from Gigabit Ethernet to 10-Gigabit at the end of 2012. We faced several options: one is to continue to use the original network stack in the Linux kernel, another is to use kernel bypass techniques. After several rounds of investigation; we finally chose to develop our next generation of DNS server based on DPDK. The reason is DPDK provides ultra-high performance and can be seamlessly extended to 40G, or even 100G NIC, in the future. 22 23After several months of development and testing, DKDNS, high-performance DNS server based on DPDK officially released in October 2013. It's capable of achieving up to 11 million QPS with a single 10GE port and 18.2 million QPS with two 10GE ports. And then we developed a user-space TCP/IP stack called F-Stack that can process 0.6 million RPS with a single 10GE port. 24 25With the fast growth of Tencent Cloud more and more of our services needed higher network access performance. Meanwhile, F-Stack was continuing to improve, being driven by our business growth, and, ultimately developed into a general network access framework. But our initial TCP/IP stack couldn't meet the needs of these services. Continuing to develop and maintain a complete high performance network stack would have been too expensive. After evaluating several plans; we finally determined to port FreeBSD's (11.0 stable) TCP/IP stack into F-Stack. Not only does this allow us to stop reinventing the wheel, we can take advantage of the the improvements the FreeBSD community will bring in the future. Thanks to [libplebnet](https://gitorious.org/freebsd/kmm-sandbox/commit/fa8a11970bc0ed092692736f175925766bebf6af?p=freebsd:kmm-sandbox.git;a=tree;f=lib/libplebnet;h=ae446dba0b4f8593b69b339ea667e12d5b709cfb;hb=refs/heads/work/svn_trunk_libplebnet) and [libuinet](https://github.com/pkelsey/libuinet) this work became a lot easier. 26 27With the rapid development of all kinds of applications, in order to help different APPs quick and easily use F-Stack, F-Stack has integrated Nginx, Redis and other commonly used APPs, and a micro thread framework, and provides a standard Epoll/Kqueue interface. 28 29Currently, besides authorized DNS server of DNSPod, there are various products in Tencent Cloud has used the F-Stack, such as HttpDNS (D+), COS access module, CDN access module, etc.. 30 31## Quick Start 32 33 # clone F-Stack 34 mkdir -p /data/f-stack 35 git clone https://github.com/F-Stack/f-stack.git /data/f-stack 36 37 # Install libnuma-dev 38 yum install numactl-devel # on Centos 39 #sudo apt-get install libnuma-dev # on Ubuntu 40 41 cd f-stack 42 # Compile DPDK 43 cd dpdk/usertools 44 ./dpdk-setup.sh # compile with x86_64-native-linuxapp-gcc 45 46 # Set hugepage 47 # single-node system 48 echo 1024 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages 49 50 # or NUMA 51 echo 1024 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages 52 echo 1024 > /sys/devices/system/node/node1/hugepages/hugepages-2048kB/nr_hugepages 53 54 # Using Hugepage with the DPDK 55 mkdir /mnt/huge 56 mount -t hugetlbfs nodev /mnt/huge 57 58 # Close ASLR; it is necessary in multiple process 59 echo 0 > /proc/sys/kernel/randomize_va_space 60 61 # Install python for running DPDK python scripts 62 sudo apt install python # On ubuntu 63 64 # Offload NIC 65 modprobe uio 66 insmod /data/f-stack/dpdk/x86_64-native-linuxapp-gcc/kmod/igb_uio.ko 67 insmod /data/f-stack/dpdk/x86_64-native-linuxapp-gcc/kmod/rte_kni.ko carrier=on # carrier=on is necessary, otherwise need to be up `veth0` via `echo 1 > /sys/class/net/veth0/carrier` 68 python dpdk-devbind.py --status 69 ifconfig eth0 down 70 python dpdk-devbind.py --bind=igb_uio eth0 # assuming that use 10GE NIC and eth0 71 72 # Install DPDK 73 cd ../x86_64-native-linuxapp-gcc 74 make install 75 76 # On Ubuntu, use gawk instead of the default mawk. 77 #sudo apt-get install gawk # or execute `sudo update-alternatives --config awk` to choose gawk. 78 79 # Install dependencies for F-Stack 80 sudo apt install gcc make libssl-dev # On ubuntu 81 82 # Compile F-Stack 83 export FF_PATH=/data/f-stack 84 export FF_DPDK=/data/f-stack/dpdk/x86_64-native-linuxapp-gcc 85 cd ../../lib/ 86 make 87 88 # Install F-STACK 89 # libfstack.a will be installed to /usr/local/lib 90 # ff_*.h will be installed to /usr/local/include 91 # start.sh will be installed to /usr/local/bin/ff_start 92 # config.ini will be installed to /etc/f-stack.conf 93 make install 94 95#### Nginx 96 97 cd app/nginx-1.16.1 98 bash ./configure --prefix=/usr/local/nginx_fstack --with-ff_module 99 make 100 make install 101 cd ../.. 102 /usr/local/nginx_fstack/sbin/nginx 103 104for more details, see [nginx guide](https://github.com/F-Stack/f-stack/blob/master/doc/F-Stack_Nginx_APP_Guide.md). 105 106#### Redis 107 108 cd app/redis-5.0.5/ 109 make 110 make install 111 112 If KNI is enabled in the configuration file, you should create a virtual NIC after F-Stack started, and set the ipaddr, netmask, mac addr, route table, etc. These addrs must be same with F-Stack. 113 114 If you don't have another management port, you should execute a script like this. 115 116 /usr/local/nginx_fstack/sbin/nginx 117 sleep 10 118 ifconfig veth0 <ipaddr> netmask <netmask> broadcast <broadcast> hw ether <mac addr> 119 route add -net 0.0.0.0 gw <gateway> dev veth0 120 echo 1 > /sys/class/net/veth0/carrier # if `carrier=on` not set while `insmod rte_kni.ko` 121 # route add -net ... # other route rules 122 123## Binary Release 124 125We provide a f-stack-binary-release package that you can use F-Stack directly without compiling. For more details, see [Binary_Release_Quick_Start](https://github.com/F-Stack/f-stack/blob/master/doc/F-Stack_Binary_Release_Quick_Start.md). 126 127## Nginx Testing Result 128 129Test environment 130 131 NIC:Intel Corporation Ethernet Controller XL710 for 40GbE QSFP+ 132 CPU:Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz(NUMA) 133 Memory：128G 134 OS:CentOS Linux release 7.2 (Final) 135 Kernel：3.10.104-1-tlinux2-0041.tl2 136 137Nginx uses linux kernel's default config, all soft interrupts are working in the first CPU core. 138 139Nginx si means modify the smp_affinity of every IRQ, so that the decision to service an interrupt with a particular CPU is made at the hardware level, with no intervention from the kernel. 140 141Nginx Reuseport means enable "reuseport" in `nginx.conf`. 142 143Nginx_FStack's 600 cache bytes' body was returned directly in nginx.conf. 144 145All of these test cases use CPUs' physical cores. 146 147 148CPS (Connection:close, Small data packet) test result 149 150 151CPS_Reuseport (Connection:close, Small data packet) test result, This test case runs in a different test environment 152 153 154RPS (Connection:Keep-Alive, Small data packet) test data 155 156 157Bandwidth (Connection:Keep-Alive, 3.7k bytes data packet) test data 158 159 160## Licenses 161See [LICENSE](LICENSE) 162 163## Join us 164 165Tencent Cloud F-Stack team developed F-Stack which is a general network framework based on DPDK and provides ultra high network performance. We are here looking for more and more talented people with great passion on technology to join us. You would have the chance to work with brightest minds on this planet and help Tencent cloud and F-stack continuously evolve. Send us your resume or refer your friend to us if you are interested in joining us. 166 167Open Positions: Software engineer(C/C++), Web developer, IOS/Android developer, Product Manager, Operating Manager, etc. 168Contact: Please send your resume to [us](mailto:[email protected]) 169
){kind=link}
