我无法处理多个同时活动的连接。对于1,000个活动连接,网络I / O达到大约1 Gb / s,但在将活动连接数增加一倍后,网络I / O会下降一半。在这两种情况下,每秒处理的请求都非常低,并且使用浏览器测试每个站点至少在30秒内加载。 CPU和RAM很难使用,它必须是配置问题。
问题是: 如何通过大量活动连接实现高网络I / O并每秒处理大量请求
当前的nginx配置:
user www-data;
worker_processes 4;
pid /run/nginx.pid;
worker_rlimit_nofile 40000;
events {
use epoll;
worker_connections 5000;
multi_accept on;
}
http {
sendfile on;
tcp_nopush on;
tcp_nodelay on;
keepalive_timeout 30;
keepalive_requests 1000;
client_body_timeout 10;
send_timeout 2;
types_hash_max_size 2048;
server_tokens off;
proxy_cache_path /data/nginx/cache levels=1:2 keys_zone=STATIC:10m inactive=24h max_size=1g;
aio threads=default;
default_type application/octet-stream;
resolver 8.8.8.8;
access_log off;
error_log /var/log/nginx/error.log;
gzip on;
gzip_min_length 5000;
gzip_types text/plain text/css application/json application/x-javascript text/xml application/xml application/xml+rss text/javascript;
gzip_disable "msie6";
client_header_buffer_size 5k;
open_file_cache max=10000 inactive=30s;
open_file_cache_valid 60s;
open_file_cache_min_uses 2;
open_file_cache_errors on;
server {
listen 80 default_server;
server_name proxy;
server_tokens off;
error_log /var/log/nginx/proxy-error.log;
error_page 502 /50x.html;
location = /50x.html {
root /etc/nginx/custom_error_pages;
internal;
}
keepalive_timeout 10;
proxy_set_header Host $host;
proxy_http_version 1.1;
proxy_set_header Connection "";
proxy_set_header Accept-Encoding "";
proxy_set_header X-REALIP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_buffering off;
proxy_intercept_errors off;
proxy_max_temp_file_size 0;
proxy_buffer_size 5m;
proxy_buffers 100 10m;
proxy_connect_timeout 600;
proxy_send_timeout 600;
proxy_read_timeout 600;
send_timeout 600;
location / {
proxy_pass $scheme://$http_host$request_uri;
proxy_cache STATIC;
proxy_cache_valid 200 1d;
proxy_cache_use_stale error timeout invalid_header updating http_500 http_502 http_503 http_504;
}
}
}
当前的sysctl.conf:
# Increase size of file handles and inode cache
fs.file-max = 2097152
# Do less swapping
vm.swappiness = 10
vm.dirty_ratio = 60
vm.dirty_background_ratio = 2
### GENERAL NETWORK SECURITY OPTIONS ###
# Number of times SYNACKs for passive TCP connection.
net.ipv4.tcp_synack_retries = 2
# Allowed local port range
net.ipv4.ip_local_port_range = 2000 65535
# Protect Against TCP Time-Wait
net.ipv4.tcp_rfc1337 = 1
# Decrease the time default value for tcp_fin_timeout connection
net.ipv4.tcp_fin_timeout = 15
# Decrease the time default value for connections to keep alive
net.ipv4.tcp_keepalive_time = 300
net.ipv4.tcp_keepalive_probes = 5
net.ipv4.tcp_keepalive_intvl = 15
### TUNING NETWORK PERFORMANCE ###
# Default Socket Receive Buffer
net.core.rmem_default = 31457280
# Maximum Socket Receive Buffer
net.core.rmem_max = 12582912
# Default Socket Send Buffer
net.core.wmem_default = 31457280
# Maximum Socket Send Buffer
net.core.wmem_max = 12582912
# Increase number of incoming connections
net.core.somaxconn = 65536
# Increase number of incoming connections backlog
net.core.netdev_max_backlog = 65536
# Increase the maximum amount of option memory buffers
net.core.optmem_max = 25165824
# Increase the maximum total buffer-space allocatable
# This is measured in units of pages (4096 bytes)
net.ipv4.tcp_mem = 65536 131072 662144
net.ipv4.udp_mem = 65536 131072 662144
# Increase the read-buffer space allocatable
net.ipv4.tcp_rmem = 8192 87380 16777216
net.ipv4.udp_rmem_min = 16384
# Increase the write-buffer-space allocatable
net.ipv4.tcp_wmem = 8192 65536 16777216
net.ipv4.udp_wmem_min = 16384
# Increase the tcp-time-wait buckets pool size to prevent simple DOS attacks
net.ipv4.tcp_max_tw_buckets = 1440000
net.ipv4.tcp_tw_recycle = 1
net.ipv4.tcp_tw_reuse = 1
Current limits.conf:
* soft nofile 65536
* hard nofile 65536
硬件信息:8GB RAM,4个核心,Ubuntu
其他信息: 我通过代理向3个不同大小的文件1mb,2mb和5mb
发送请求