Sponsored Content
Top Forums UNIX for Advanced & Expert Users What process is writing to disk? Post 302252411 by otheus on Wednesday 29th of October 2008 11:01:57 AM
Old 10-29-2008
Ah crap... From collectl - Process Monitoring
Quote:
Process I/O monitoring is limited to kernels that have that capability enabled and that didn't even appear before 2.6.22. If you don't see the file /proc/self/io, your kernel was not built with process I/O accounting enabled and you need to get one that has the following enabled: CONFIG_TASKSTATS, CONFIG_TASK_XACCT and CONFIG_TASK_IO_ACCOUNTING.
We're running 2.6.18.
 

10 More Discussions You Might Find Interesting

1. UNIX for Dummies Questions & Answers

Writing file to disk takes time

Hi All, I am working on a Solaris machine. When i use a particular software to generate some files, the log shows around 0 to 3 secs for generating each file. But the same when i see on the disk it shows double the time difference between two file generation. For example if file A takes 0 secs... (7 Replies)
Discussion started by: nileshkarania
7 Replies

2. UNIX for Advanced & Expert Users

disk i/o per process

Dear All, We are using AIX 5.2 with IBM pseries servers. I want to check disk io for a running process. Please if anybody can help me. Thanks. Aqeel Anwar (1 Reply)
Discussion started by: aqeelcu@hotmail
1 Replies

3. AIX

disk i/o per process on aix 5.2

hi, i am working on aix 5.2, i want to check disk i/o for any running process. please if anybody can help me. thanks Aqeel Anwar (1 Reply)
Discussion started by: system-admin
1 Replies

4. Shell Programming and Scripting

Which Process is writing this Log file!!

Hello , Well I have some /tmp files which are growing very quickly..Can anyone suggest me a way to find which process is logging into this file :confused: ? Thanks very much in Advance!! Mohammed (2 Replies)
Discussion started by: Mohammed
2 Replies

5. UNIX for Dummies Questions & Answers

Which process is doing all the writing

Hi We are running an IBM P570 with AIX and Unidata. The disk monitor in nmon is showing that one of our logical volumes is hitting 100% most of the time, and that 98% of it is write. I am trying to identify the top processes in terms of disk IO, obviously particularly write so that we... (4 Replies)
Discussion started by: idwalton72
4 Replies

6. Linux

How to follow up disk mirroring process?

Hi, The OS is SuSE Enterprise 11 and the system is HP WS460c G6 Blade with hardware disk array RAID 1 mirror. One disk was just replaced and the disk mirroring process is on its way. My question is how to follow up / monitor the disk mirroring process? I know hpacucli can do the job, but there... (0 Replies)
Discussion started by: aixlover
0 Replies

7. UNIX for Dummies Questions & Answers

Writing a loop to process multiple input files by a shell script

I have multiple input files that I want to manipulate using a shell script. The files are called 250.1 through 250.1000 but I only want the script to manipulate 250.300 through 250.1000. Before I was using the following script to manipulate the text files: for i in 250.*; do || awk... (4 Replies)
Discussion started by: evelibertine
4 Replies

8. Ubuntu

Reading disk usage per process

Hi, I am using iostat and /proc/<pid>/status to determine the disk usage per process. I have a question regarding buffer cache. When I am reading a 10MB file, the counters I get show that <5MB of the file is read. Do the counters in iostat and /proc/<pid> reflect the amount of data that is... (2 Replies)
Discussion started by: fidelity
2 Replies

9. Emergency UNIX and Linux Support

How to find which process using, while getting High Disk I/O?

In Our Production server I/O was very high, I Recived mail that Disk I/O was high, is it possible how to find which process Used this much I/O ? Iam Using Ubuntu server 12.04. Linux 3.9.3-x86_64-server33 (Li473-1200) 07/23/2014 _x86_64_ (8 CPU) 12:05:01 AM DEV ... (5 Replies)
Discussion started by: babinlonston
5 Replies

10. Open Source

Help with writing Shell Script to automate process using multiple commands

Hello! Need help to write a Linux script that can be run from windows using command/Cygwin/any other way. I am new to scripting, actually i am trying to automate server health check like free disk space, memory along with few services status, if any services is not running then start services ,... (7 Replies)
Discussion started by: Sayed Ibrahim
7 Replies
ACCT(5) 						     Linux Programmer's Manual							   ACCT(5)

NAME
acct - process accounting file SYNOPSIS
#include <sys/acct.h> DESCRIPTION
If the kernel is built with the process accounting option enabled (CONFIG_BSD_PROCESS_ACCT), then calling acct(2) starts process account- ing, for example: acct("/var/log/pacct"); When process accounting is enabled, the kernel writes a record to the accounting file as each process on the system terminates. This record contains information about the terminated process, and is defined in <sys/acct.h> as follows: #define ACCT_COMM 16 typedef u_int16_t comp_t; struct acct { char ac_flag; /* Accounting flags */ u_int16_t ac_uid; /* Accounting user ID */ u_int16_t ac_gid; /* Accounting group ID */ u_int16_t ac_tty; /* Controlling terminal */ u_int32_t ac_btime; /* Process creation time (seconds since the Epoch) */ comp_t ac_utime; /* User CPU time */ comp_t ac_stime; /* System CPU time */ comp_t ac_etime; /* Elapsed time */ comp_t ac_mem; /* Average memory usage (kB) */ comp_t ac_io; /* Characters transferred (unused) */ comp_t ac_rw; /* Blocks read or written (unused) */ comp_t ac_minflt; /* Minor page faults */ comp_t ac_majflt; /* Major page faults */ comp_t ac_swaps; /* Number of swaps (unused) */ u_int32_t ac_exitcode; /* Process termination status (see wait(2)) */ char ac_comm[ACCT_COMM+1]; /* Command name (basename of last executed command; null-terminated) */ char ac_pad[X]; /* padding bytes */ }; enum { /* Bits that may be set in ac_flag field */ AFORK = 0x01, /* Has executed fork, but no exec */ ASU = 0x02, /* Used superuser privileges */ ACORE = 0x08, /* Dumped core */ AXSIG = 0x10 /* Killed by a signal */ }; The comp_t data type is a floating-point value consisting of a 3-bit, base-8 exponent, and a 13-bit mantissa. A value, c, of this type can be converted to a (long) integer as follows: v = (c & 0x1fff) << (((c >> 13) & 0x7) * 3); The ac_utime, ac_stime, and ac_etime fields measure time in "clock ticks"; divide these values by sysconf(_SC_CLK_TCK) to convert them to seconds. Version 3 Accounting File Format Since kernel 2.6.8, an optional alternative version of the accounting file can be produced if the CONFIG_BSD_PROCESS_ACCT_V3 option is set when building the kernel. With this option is set, the records written to the accounting file contain additional fields, and the width of c_uid and ac_gid fields is widened from 16 to 32 bits (in line with the increased size of UID and GIDs in Linux 2.4 and later). The records are defined as follows: struct acct_v3 { char ac_flag; /* Flags */ char ac_version; /* Always set to ACCT_VERSION (3) */ u_int16_t ac_tty; /* Controlling terminal */ u_int32_t ac_exitcode; /* Process termination status */ u_int32_t ac_uid; /* Real user ID */ u_int32_t ac_gid; /* Real group ID */ u_int32_t ac_pid; /* Process ID */ u_int32_t ac_ppid; /* Parent process ID */ u_int32_t ac_btime; /* Process creation time */ float ac_etime; /* Elapsed time */ comp_t ac_utime; /* User CPU time */ comp_t ac_stime; /* System time */ comp_t ac_mem; /* Average memory usage (kB) */ comp_t ac_io; /* Characters transferred (unused) */ comp_t ac_rw; /* Blocks read or written (unused) */ comp_t ac_minflt; /* Minor page faults */ comp_t ac_majflt; /* Major page faults */ comp_t ac_swaps; /* Number of swaps (unused) */ char ac_comm[ACCT_COMM]; /* Command name */ }; VERSIONS
The acct_v3 structure is defined in glibc since version 2.6. CONFORMING TO
Process accounting originated on BSD. Although it is present on most systems, it is not standardized, and the details vary somewhat between systems. NOTES
Records in the accounting file are ordered by termination time of the process. In kernels up to and including 2.6.9, a separate accounting record is written for each thread created using the NPTL threading library; since Linux 2.6.10, a single accounting record is written for the entire process on termination of the last thread in the process. The proc/sys/kernel/acct file, described in proc(5), defines settings that control the behavior of process accounting when disk space runs low. SEE ALSO
lastcomm(1), acct(2), accton(8), sa(8) COLOPHON
This page is part of release 3.25 of the Linux man-pages project. A description of the project, and information about reporting bugs, can be found at http://www.kernel.org/doc/man-pages/. Linux 2008-06-15 ACCT(5)
All times are GMT -4. The time now is 05:34 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy