Linux Certif

Toute la documentation sur la certification Linux LPI

collectl-data

DATA FIELDS

CPU Summary

USER...WAIT

percentage of time spent in CPU states, averaged over all CPUs.

INTR

Interrupts per second.

CTXSW

Context switches per second.

PROC

Process creations per second.

RUNQ

Number of processes in the run queue.

RUN

Number of processes in the run state.

AVG1,5,15

Load average over the last 1,5 and 15 minutes.

Single CPUs

USER...WAIT

percentage of time spent in CPU states for individual CPUs

Disk Summary

There are currently 3 places that collectl can gather disk performance data from. Fortunately you don't really have to worry about it unless you really care. In the 2.4 kernel, the most detailed disk data is stored in /proc/partitions and that is indeed where collectl tries to get it from. However, some older kernels may not have been configured to provide this data in which case collectl will grab less detailed data from /proc/stat. In the 2.6 kernel, performance data havbe been moved from /proc/partitions to /proc/diskstats and so it is gathered from there.

In any event, regardless of where the data comes from it is all presented in the same format. This means some fields may be 0 (2.4 kernels and /proc/stat), but it is expected few systems will fall into this category.

Reads

Read operations per second

R-Merged

Read operations merged per second when queued. Depending on the queue size, the amount of data merged may be recorded multiple seconds before that data is ultimately read. These statistics are not available in older kernels which only record disk statistics in /proc/stat.

R-KBytes

Kilobytes read per second

Writes

Writes per second

W-Merged

Write operations merged per second when queued. Depending on the queue size, the amount of data merged may be recorded multiple seconds before that data is ultimately written. These statistics are not available in older kernels which only record disk statistics in /proc/stat.

WriteKB

Kilobytes written per second

Single Disks

Name

The name of the disk

Read/Write Ops,Merged,KBytes

These are the `standard` counts of the number of operations, merged operations and KB transfered. Note that these, as well as the remainder of the counters are either expressed as a rate/second or a rate/interval, the latter is the `n` option is selected.

Average Request

Average I/O size (in KB) of requests queued

Average Queue Length

Average number of requests queued

Average Wait

Average wait time for I/O requests

Average SvcTim

Average service time for I/O requests

Percent Util

Percentage of CPU during which I/O requests were issued

Inodes/Filesystem

DCache Unusd

Number of unused entries in directory cache

OpenFiles Hndles

Number of open file handles

% Max

Percentage of maximum available file handles

OpenFiles Inode

Number of user inode handles

SBlock Hndls

Number of allocated Super Blocks handlers

% Max

Percentage of maximum allowed

DQuot Entry

Number of allocated Disk Quota Entries

% Max

Percentage of maximum allowed

Memory

Tot

Total physical memory

Used

Used physical memory. This does not include memory used by the kernel itself.

Free

Free physical memory

Buff

Amount of physical memory used for buffers by the kernel.

Cached

Amount of physical memory used to cache data by the kernel.

Total

Total Swap

Used

Used Swap

Free

Free Swap

Inactive

Inactive pages. On ealier kernels this number is the sum of the clean, dirty and laundry pages.

Pages/Sec In

Total number of pages read by block devices

Pages/Sec Out

Total number of pages written by block devices

Network Summary

The entries for error counts are actually the total of several types of errors. To get individual error counts, you must report details on individual interfaces in plot format.

InPck

Incoming packet rate

InErr

Incoming error rate

OutPck

Outgoing packet rate

OutErr

Outgoing error rate

Mult

Outgoing multicast packet rate

ICmp

Incoming compressed packets

OCmp

Outgoing compressed packets

IKB

Incoming kilibytes

OKB

Outgoing kilobytes

Single Network Interfaces

Same as summary, only by individual

Error information by specific error types is only available in plot format. Specific transmission errors are categorized by errors, dropped, fifo, collisions and carrier. Receive errors are broken out for errors, dropped, fifo and fragments.

TCP/IP Statistics

PureAcks

Count of ACKs that only contain acks (ie no data)

HPAcks

Loss

Count of packets TCP thinks have been lost coming in

FTrans

Fast Retransmissions

Slabs (both detail and summary)

Name

Name of cache is displayed when reporting details

Objects InUse

Count of objects that are currently in use.

Objects Bytes

Size of the objects.

Objects Alloc

Total number of objects that have been allocated but not necessarily in use.

Objects Bytes

Size of allocated objects.

Slab Allocations InUse

Number of slabs that have at least one active object in them.

Slab Allocations Bytes

Size of slabs.

Slab Allocations Total

Total number of slabs that have been allocated.

Slab Allocations Bytes

Size of slabs.

Caches InUse

Not all caches are actully in use. This included only those with non-zero counts.

Caches Total

This is the count of all caches, whether currently in use or not.

Partition Summary

Read/Write Ops

Number of I/O operations

Read/Write Merge

I/O Requests merged per second

Read/Write KB

KBs transferred per second

Single Partitions (all times in msec)

This data is identical that for 2.6 kernel disks. As of the 2.6 kernel this information can only be found there.

Sockets

Used

Tcp Inuse

Tcp Orphan

Tcp Tw

Tcp Alloc

Tcp Mem

Udp Inuse

Raw Inuse

Frag Inuse

Frag Mem

Lustre MDS Data

Close

Getattr

Reint

Reintegrated Operation. These include create, unlink, rename, link and setattr.

Sync

Processes

PID

Pid of the process

User

Name of user which this process is running under. In playback mode on a different machine, use -oP to direct collectl to use the password file named in collectl.conf (default is /etc/passwd) to lookup the corresponding username. Otherwise the UID will be reported instead.

PR

Process priority

PPID

PID of this process`s parent

S

Process State: S - Sleeping, D - Uninterruptable Sleep, R - Running, Z - Zombie or T - Stopped/Traced

VSZ

This is the amount of VS memory used by this process.

RSS

This is the amount of RSS memory used by this process.

SysT

The amount of System Time this process used during this interval

UsrT

The amount of User Time this process used during this interval

Pct

Percentage of the current interval taken up by this task (the User and System time are used for this calculation)

AccuTime

Total accumulated System and User time since the process began execution

MajF

Major Page Faults per second

MinF

Minor Page Faults per second

Command

Command that is running. Patch and command line options are NOT included

AUTHOR

Copyright 2003-2007 Hewlett-Packard Development Company, LP collectl may be copied only under the terms of either the Artistic License or the GNU General Public License, which may be found in the source kit