identify the unix processes performing high disk i/o reads and writes


 
Thread Tools Search this Thread
Top Forums Shell Programming and Scripting identify the unix processes performing high disk i/o reads and writes
# 1  
Old 01-09-2009
identify the unix processes performing high disk i/o reads and writes

I would like to write shell/perl script which identifies the top unix processes that are performing high disk I/O's [read and write] or/and writes

If any one knows the solution please help me?

-Swamy

Last edited by jim mcnamara; 01-09-2009 at 11:58 PM.. Reason: Closed - duplicate post
Login or Register to Ask a Question

Previous Thread | Next Thread

10 More Discussions You Might Find Interesting

1. Linux

Dealing with a really high amount of reads merged

I'm trying to performance tune the I/O of my web server, which is at 41.1% reads merged (If my math is correct), which seems a tad high to just be going along with the defaults. Will modifying read_ahead_kb affect the value of "reads merged" in diskstats? If not, what's a good way of tracking... (2 Replies)
Discussion started by: thmnetwork
2 Replies

2. AIX

How to Identify long running unix processes

Hi All, Need an urgent help, I have a requirement to find long running unix processes.. I have tried the below commands, but not succeed. I need to arrange the unix processess in an order of elapsed time (high to low) that runs in a system. For Eg: Consider we have 3 processes, Pid 1 pid 2... (5 Replies)
Discussion started by: mohamedirfan
5 Replies

3. Shell Programming and Scripting

Help with script that reads and writes java console Minecraft

Hi I am looking for an easy way to lock game mode (0) for everyone included op on a Minecraft server. It can be a script that every time a player changes game to 1 the script changes back to 0. What the player writes is visible in the java console. I am not good at script programming and my... (0 Replies)
Discussion started by: MyMorris
0 Replies

4. UNIX for Dummies Questions & Answers

Difference between buffered disk reads and cached reads?

I was analyzing the Disk read using hdparm utility. This is what i got as a result. # hdparm -t /dev/sda /dev/sda: Timing buffered disk reads: 108 MB in 3.04 seconds = 35.51 MB/sec # hdparm -T /dev/sda /dev/sda: Timing cached reads: 3496 MB in 1.99 seconds = 1756.56 MB/sec... (1 Reply)
Discussion started by: pinga123
1 Replies

5. Shell Programming and Scripting

Identify high values "ÿ" in a text file using Unix command

I have high values (such as ÿÿÿÿ) in a text file contained in an Unix AIX server. I need to identify all the records which are having these high values and also get the position/column number in the record structure if possible. Is there any Unix command by which this can be done to : 1.... (5 Replies)
Discussion started by: devina
5 Replies

6. AIX

Script to identify high CPU usage processes

Hi Guys, I need to write a script capable of identifying when a high cpu utilitzation process. It sounds simple but we are on a AIX 5.3 environment with Virtual CPU's (VP's) and logical CPU's. Please any ideas or tips would be highly appreciated. Thanks. Harby. (6 Replies)
Discussion started by: arizah
6 Replies

7. Filesystems, Disks and Memory

Life span of HDD - maximum reads/writes etc

Hi All I was wondering how the copying of vast amounts of data affected the overall lifespan of an HDD. In my example, I'm copying approx 120GB (250,000) of files, once per hour from disk to another. Is this likely to have a detrimental effect on the disk in terms of reads/writes etc? ... (2 Replies)
Discussion started by: huskie69
2 Replies

8. Filesystems, Disks and Memory

Does vmstat -d give a count of actual physical writes/reads done to/from hard disk?

Hi, I am trying to find the reliability of 'vmstat -d' for showing the actual physical writes on sectors on hard disk. Can anyone please tell me if the numbers in the "sectors" field under "read" or "write" headers show a count of the actual write commands sent to disk from the low level... (2 Replies)
Discussion started by: jake24
2 Replies

9. UNIX for Advanced & Expert Users

identify the unix process performing high disk i/o reads and writes

Guys, Is there any UNIX command that captures the 'Unix process which is performing high disk I/O reads and writes'. can you help me in this? -Swamy (6 Replies)
Discussion started by: avsswamy
6 Replies

10. Shell Programming and Scripting

sh script that reads/writes based upon contents of a file

Hi everyone, Ive got a quick question about the feasibility and any suggestions for a shell script. I can use sh or ksh, doesnt matter. Basically, Ive got an output file from a db2 command that looks like so: SCHEMA NAME CARD LEAF ELEAF LVLS ISIZE NDEL KEYS F4 F5 ... (3 Replies)
Discussion started by: rdudejr
3 Replies
Login or Register to Ask a Question
acctdisk(8)						      System Manager's Manual						       acctdisk(8)

NAME
acctdisk, acctdusg - Perform disk-usage accounting SYNOPSIS
acctdisk acctdusg [-u file] [-p file] FLAGS
Searches file as the alternate file for login names and numbers, instead of searching /etc/passwd. Writes records of file names for which it does not charge into file. DESCRIPTION
Normally the acctdisk and acctdusg commands are called from the dodisk shell procedure to do disk-usage accounting. The dodisk shell proce- dure is invoked when the cron daemon executes commands in the /usr/spool/cron/crontabs/[filename] file. In the usual case, the output of the diskusg command is the redirected input to the acctdisk command. When a more thorough, but slower, version of disk accounting is needed, specify the -o flag with the dodisk command. This is not normally done in the /usr/spool/cron/crontabs/[filename] file. When the -o flag is used, the acctdusg command replaces the diskusg command. acctdisk Normally, the acctdisk command reads a temporary output file produced by the diskusg or the acctdusg command from standard input, converts each record into a total disk-accounting record, and writes it to standard output. These records are merged with other accounting records with the acctmerg command to produce a daily accounting report. acctdusg The acctdusg command is called when the -o flag is used with the dodisk command. This produces a more thorough, but slower, version of disk-accounting records. Otherwise, the dodisk shell procedure invokes the diskusg command. The acctdusg command reads a list of files from standard input (usually piped from a find / -print command), computes the number of disk blocks (including indirect blocks) allocated to each file divided by the number of hard links then writes an individual record for each user to standard output. To find the user who is charged for the file, compare each file pathname with the login directories of the users. The user who has the longest pathname component match is charged for the file. Therefore, the relevant information for charging users is not ownership of a file but the directory where it is stored. The acctdusg command searches the /etc/passwd file, or the alternate password file specified with the -p flag, for login names, numbers and login directories. Each output record has the following format: uid login #blocks EXAMPLES
To start normal disk-accounting procedures, add a line similar to the following to the /usr/spool/cron/crontabs/[filename] file: 0 2 * * 4 /usr/sbin/acct/dodisk The foregoing example is a typical, periodically invoked command that the cron daemon reads and executes. The period is expressed by a 6-field entry having the format: mm hh daymon monyr wkday cmd. For any field requiring digits, numbers are integers. These six fields have the following significance: Purpose Time variable that has the value 0 through 59 expressing minutes past the hour. Time variable for the hour of the day in 24-hour clock notation. Time variable for the day of the month. Time variable for month of the year. Time variable for the day or days of the week, where 0 is Sunday and inclusive days are separated with a hyphen (-). Command the cron daemon must execute. Whenever you write any of the time variables described in the foregoing table, an unspecified value must be noted with an * (aster- isk) to define an empty field. In the foregoing example, the dodisk shell procedure runs at 02:00 hours (2) every Thursday (4). The dodisk shell procedure calls the acctdusg command to redirect its input to a temporary file and then calls the acctdisk shell procedure to redirect disk-usage records from the temporary file as input to a /var/adm/acct/nite/[filename] file as output. The file stored in the /var/adm/acct/nite subdirectory is a permanent binary record of disk usage for the specified period. To initiate a slower, more thorough disk-accounting procedure, add a line similar to the following to the /usr/spool/cron/crontabs/[filename] file. 0 2 * * 0-4 /usr/sbin/acct/dodisk -o The dodisk shell procedure calls the acctdusg command and the acctdisk command to write disk-usage records to the /var/adm/acct/nite/[filename] file just as in the previous example. The dodisk procedure runs at 2 a.m. every day (0-6) including Sunday. FILES
Specifies the command path. Specifies the command path. User database file. The active login/logout database file. Accounting header files that define formats for writing accounting files. RELATED INFORMATION
Commands: acct(8), acctmerg(8), cron(8), diskusg(8), dodisk(8), runacct(8) Functions: acct(2) delim off acctdisk(8)