solaris 10 performance monitoring

added nDo not add nnTcpdump-nn-c 10-w 1.cap only catch 10 packets and save to 1.cap file, 1.cap is not cat'sIf you want to view 1.cap to use the commandTcpdump-r/tmp/1.capTshark needs to be installedRemember this command, check the network card capture specific information, you can clearly see what time there is what IP visited the site, access to the site of what linksTshark-n-T a-r http.request-t fields-

) = 0 Application available memory/system physical memory Monitoring tools Vmstat $ Vmstat 1 Procs ----------- memory ---------- --- swap -- ----- io ---- system -- ----- cpu ------ r b swpd free buff cache si so bi bo in cs us sy id wa st0 3 252696 2432 268 7148 3604 2368 3608 2372 288 288 0 0 21 78 10 2 253484 2216 228 7104 5368 2976 5372 3036 930 519 0 0 0 100 00 1 259252 2616 128 6148 19784 18712 1

Linux performance monitoring software (Perf, PAPI) Installation tutorial, perfpapi Perf Perf is a built-in Linux kernel performance tool. The installation process is as follows: 1. Download a Linux kernel source code and decompress it into tools/perf. 2. Open the terminal and install make make install. 3. After installation, you can run the perf program in this

main cache mode: Buffer Cache and Page cache. The former is for the disk block read and write, the latter for the file inode read and write. These caches can effectively shorten the time for I/O system calls (such as read,write,getdents). Remember that the memory is for use, not to take a look. Unlike windows, no matter how much of your real physical memory, he will have to take the hard disk swap files to read. This is why Windows often prompts for a lack of virtual space. You think, how borin

period, kernel time (%) (system/total) *100%iowait in internal time period, HDD io wait time (%) (iowait/total) *100%IRQ in internal time period, hard interrupt time (%) (irq/total) *100%soft in internal time period, soft interrupt time (%) (softirq/total) *100%idle in internal time period, the CPU is removed from waiting for the disk IO operation for any reason idle time idle time (%) (idle/total) *100The calculation formula is as follows:Total_cur=user+system+nice+idle+iowait+irq+softirqtotal

The basic functions of the top command and ps command are the same, displaying the current process of the system and other conditions. However, the top command is a dynamic display process, that is, you can press the key to continuously refresh the current state. Such? The front-end executes this command, and it will exclusively occupy the front-end until the user terminates the program. More accurately, the top command provides real-time monitoring o

# Vi/etc/yum.repos.d/dag.repo[Dag]Name=dag RPM Repository for Red Hat Enterprise Linuxbaseurl=http://apt.sw.be/redhat/el$releasever/en/$basearch/dagGpgcheck=1Gpgkey=http://dag.wieers.com/rpm/packages/rpm-gpg-key.dag.txtEnabled=1Once done, the direct Yum installation is as follows:#yum Install RRDtoolcan be installed successfully.Installing Python-rrdtool1.yum install-y GCC2.Yum Install Rrdtool-python3.yum Install Python-psutilRequirements: verifying ddttool as the network

occupied by the process. SHR identifies the memory and library size that can be shared with other processes. 8. Performance monitoring sar command The sar-u output shows CPU information. -U option is the default option of sar. This output shows CPU usage in percentage CPU CPU ID % User Duration of running a process in user mode % Nice Time taken to run a normal process % System Duration of running a proce

This article mainly introduces the linux performance monitoring tool. For more information, see 1. uptime This command intuitively shows the average load of the server in the past 15 minutes, 5 minutes, and 1 minute 2.Vmstat Output vmstat information every 2 seconds, 10 times in total. Category Procs Swap Io System Cpu

= (qcahce_hits/(qcache_hits + qcache_inserts) * 100%; Mysql> show status like 'qcache % ';(6) Number of table cache statusesMysql> show status like 'open % '; (7) thread cache hit rateThread_cache_hits = (1-threads_created/connections) * 100% Mysql> show status like 'thread % '; Mysql> show status like 'connections '; (8) Lock statusMysql> show status like '% lock % '; (9) replication latencyMysql> show slave status (10) TMP Table Status (temporary t

context switching, resulting in less time for the CPU to do serious work, and the CPU not being fully utilized, is undesirable.5) Information about the CPU is: (CPU)US: CPU utilization in the user state during the specified time interval.SY: CPU utilization in the kernel mentality at the specified time interval.ID: The CPU idle time ratio during the specified time interval.WA: The CPU is idle for I/O during the specified time interval.Vmstat can be used to determine whether the work of a system

displayed, and each item can be consulted. Need to observe the value of the ID (idle), generally speaking, he should be close to 100%, indicating that the system is rarely used resourcesLines Fourth and fifth: represents the current use of physical memory and virtual memory (MEM/SWAP).after line sixth: This is where the state is displayed when the command is entered in the top program. The picture below the top is the resource situation used by each process.By default, only the more important P

?" Enable all warning options unless there is an excellent reason for not doing so. 10. lint At first, lint was used to check unportable code in C language, but now it is not just a portability check program, you can also check out the features in the code that are portable and fully compliant with the syntax but are likely to be incorrect. Lint has many versions. in Linux, splint can be used for installation through apt-get. Integrated debugging: gd

-sz Avgqu-sz await SVCTM%UTILSDA0.00 12862.00 80.00 1464.00 1424.00 63416.00 83.99 121.29 87.37 0.65 100.00DEVICE:RRQM/s wrqm/s r/sW/s rkb/s wkb/s avgrq-sz Avgqu-sz await SVCTM%UTILSDA0.00 0.00 857.00 10.00 12512.00 1972.00 33.41 11.65 14.53 1.15 100.00Iostat-d-K 1 10$ iostat-d-K1 TenLinux2.6. +-358. el6.x86_64 (Vnode1) February 25, 2015 _x86_64_ ( -CPU) Device:tps Kb_read/s kb_wrtn/s Kb_read kb_wrtnsda270.40 4306.84

memory shared by other processes. Res identifies the amount of memory that this process is actually consuming. The SHR identifies the memory and library sizes that can be shared with other processes. 8, performance monitoring SAR command Sar-u output displays CPU information. The-u option is the default option for SAR. This output shows the CPU usage as a percentage Cpu CPU number %user The tim

0.000.000.0044.60 0.009.14419.82 1.6336.460.361.62dm-1 0.000.000.00 0.000.000.00 0.000.000.000.000.00For the example output above, we can obtain the following information:Write about 30M data (wkb/s value) to disk per second91 IO operations per second (R/S+W/S), with write as the principalAverage per IO request waits 120.57 milliseconds, processing time is 6.33 millisecondsIn the queue of IO requests waiting to be processed, there are an average of 11.79 requests residingThere is also a connect

0.000.000.00 0.000.000.000.000.00For the example output above, we can obtain the following information:Write about 30M data (wkb/s value) to disk per second91 IO operations per second (R/S+W/S), with write as the principalAverage per IO request waits 120.57 milliseconds, processing time is 6.33 millisecondsIn the queue of IO requests waiting to be processed, there are an average of 11.79 requests residingThere is also a connection between the above values, and we can calculate other values by s

0.000.000.0044.60 0.009.14419.82 1.6336.460.361.62dm-1 0.000.000.00 0.000.000.00 0.000.000.000.000.00For the example output above, we can obtain the following information:Write about 30M data (wkb/s value) to disk per second91 IO operations per second (R/S+W/S), with write as the principalAverage per IO request waits 120.57 milliseconds, processing time is 6.33 millisecondsIn the queue of IO requests waiting to be processed, there are an average of 11.79 requests residingThere is also a connect

]} 'LISTEN 3Established 3 Tcpdump Install Yum install-y tcpdumpGrab Bag tool: tcpdumpUsage: TCPDUMP-NNThe first n indicates the IP display, and if you do not add N, the host name will be displayed.Listening for specified NICTcpdump-nn-i eth0[Email protected] ~]# tcpdump-nn-i eth0Listening on the specified portListening to the web port[[email protected] ~]# TCPDUMP-NN Port 80Monitor NIC Eth0 Port 80[Email protected] ~]# tcpdump-nn-i eth0 Port 80Do not listen on port 22Tcpdump-nn-i E

, the string is constantly refreshed, which is the flow of data transfer process and data packets, focusing on the third and fourth columns that represents which ip+ port is connected to which ip+ Port . Ctrl + C exits the program.The tcpdump also has the- C and- w options,-c Specifies the number of catches, and-W saves the crawl results to the specified path [Email protected] ~]# tcpdump-nn-i ens33-c 10-w/home/ask/documentation/ Besides