ubuntu server performance monitor

Server high performance program disk I/O Linux IoSystem Architecture I.Device--------Factors Affecting disk Performance The speed of the hard disk affects the overall performance of the hard disk. Generally, the higher the speed, the better the performance. Hard

tutorial, which is basically very old. When we use Ubuntu, we usually use the software package manager of the system to install the software, and seldom compile and install the software by ourselves. However, we recommend that you use an earlier version for independent/usr,/opt,/usr/local, instead of re-compiling the software when reinstalling the system. However, for most common users, this suggestion is usually meaningless.5./var: System Log Record

Anywhere (v6)139/tcp ALLOW Anywhere (v6)445/tcp ALLOW Anywhere (v6)8080/tcp ALLOW Anywhere (v6)3306 ALLOW Anywhere (v6)Devadm @ devserver :~ $ 3) Local Connection to configure the user and user database Devadm @ devserver :~ $ Mysql-h 127.0.0.1-u root-pEnter password:Welcome to the MySQL monitor. Commands end with; or \ g.Your MySQL connection id is 43Server version: 5.1.58-1Ubuntu1 (Ubuntu)

For systems running on-line, current database performance monitoring typically monitors the following points:(1) Whether there is obstruction (Blocking);(2) whether there is waiting (waiting), blocking is the lock (locks) waiting;(3) Whether the running time is too long (long running);(4) Whether there is a deadlock (Deadlock);Sys.dm_exec_query_stats and so on, and so on some statistical information, usually not as the real-time alarm content, but in

on the size of the data.resolves a memory fragmentation problem , but creates a waste of memory ( such as 100bytes of data to be stored in a block of )tuning : adjusting the block size of a group based on data sizedata deletion aspects of MemcachedU Memcached does not really delete data , does not monitor expired data , but checks for expiration at get , This technique is called lazy ( lazy )U LRU overwrites the least recently used dataMemcached 's

services in Ubuntu require memory, CPU, and disk space. disabling or deleting unnecessary services can improve the overall system performance and reduce the attack surface. Run the following command to check which services are running in the current system: Sudo initctl list | grep running You can use the following command to disable services that are not needed: Sudo update-rc.d-f service name remove

Ubuntu under Zabbix Server monitoring tool deploymentAn installationInstall Apache, Mysql, PHP, Zabbixsudo apt-get updatesudo apt-get install apache2 mysql-server libapache2-mod-php5 php5-gd php5-mysql php5-common zabbix-server-mysql zabbix- frontend-phpTwo service-side configuration2.1 Configuring database connections

installation, the installation steps are as follows:TAR-XZVF rpc.rstatd-4.0.1.tar.gzCD RPC.RSTATD-4.0.1/./configure-Configuration Actionsmake-to compileMake install-start InstallationRpc.rstatd-starting the RSTATD process"Rpcinfo-p" command to see if the current system has started the RSTATD daemonAppears as followsProgram Version Protocol port100000 2 TCP 111 Portmapper100000 2 UDP 111 Portmapper100024 1 UDP 669 status100024 1 TCP 672 status100001 5 UDP 718 RSTATD100001 3 UDP 718 RSTATD100001

Performance testing, we have two parts of the attention point1 service itself: Concurrency response time QPS2 Server Resource Usage: CPU memory I/O disk, etc.JMeter Plugins plug-in can realize the "two" monitoring, the specific operation steps are as follows (the main record of my practice process):Description: My jmeter version is 2.13Download Plugin1 visit URL http://jmeter-plugins.org/downloads/all/, dow

, non-blocking IO. Stability is strong, but the overhead of the context switch grows rapidly with HTTP request increments. 2> a kernel-level thread that handles a single connection, non-blocking IO, multi-process multithreaded hybrid approach. The problem with Context switch still exists.In theory, more concurrent connections can be supported. 3> a process handles multiple connections, non-blocking IO. (Epoll, Kqueue) lighttpd, Nginx. Strong concurrency perf