UNIX Commands to get Disk Performance

What are some UNIX and Linux commands and switches to get detailed disk related performance. Are storage is VMAX. We have Solaris 9/10, AIX 5.3 and up, HP-UX 11.31 and Red Hat Linux 5. We need as much info on performance as possible. Are UNIX admin runs the iostat command.

However, he asked us what switches should he use? I know that does not make any sense but he did ask that question.
Rhiaanon44Asked:
Who is Participating?
 
Joseph GanSystem AdminCommented:
iostat -c dispaly only cpu statistics
iostat -d display only disk I/O statistics
iostat -n display only network statistics
iostat -m display I/O data on MB/second
iostat -t display timestamp information
iostat -x display extended status etc....
0
 
Kerem ERSOYPresidentCommented:
Hi,

As far as I understand you ahve your systems and you ahve your storage which are attached to your storage through either a HBA and Fiber Fabric "switches" or NAS through Ethernet "Switches". This is why he asks you about what switches to use.

If you can send some more details about your Switch and system configuration I can tell you some advice based on this knowledge.

But let me tell you something about storage systems. Storage devices can show some graphics about the throughput.  Generally some detailed measurements such as iops value per channel or RAID array are generally available if you have purchased a separate license from your storage vendor. So IT might be good if you could contact with your storage vendor and ask for these information and licensing status.

Cheers,
K.

0
Free Tool: Path Explorer

An intuitive utility to help find the CSS path to UI elements on a webpage. These paths are used frequently in a variety of front-end development and QA automation tasks.

One of a set of tools we're offering as a way of saying thank you for being a part of the community.

 
TomuniqueCommented:
He does not mean switches as in hardware.

Parameters to a command are sometimes referred to as switches.

for AIX, have him try iostat  -Dl  {interval}
(that's capital D, little "el")

Tom
0
 
Rhiaanon44Author Commented:
Hi guys. Thanks so much for clearing up the confusion with "switches." =)   KeremE the the storage performance team uses EMC's Symmetrix Performance Analyzer. Those guys want to know what command is used in Linux to something like c3tt1d4s2 instead of sd1. All this info they want along with performance related info. I am not sure why they need this info.

They are using RAID 6 if that matters at all for commands to use for drive performance. All fibre attached and Cisco 9148 switches.
0
 
AnacreoCommented:
On Solaris perhaps you're looking for:

iostat -xn:

# iostat -xn
                    extended device statistics
    r/s    w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device
    2.2    2.2   66.8   53.2  0.0  0.3    6.3   57.5   3   8 md/d0
    0.9    0.9   52.4   52.4  0.0  0.0    2.7   27.5   0   5 md/d1
    0.8    0.8   52.1   52.5  0.0  0.1    0.0   31.6   0   5 md/d3
    0.8    0.8   51.8   51.8  0.0  0.0    0.0   30.3   0   5 md/d5
    2.3    2.3  144.9  144.8  0.0  0.1    0.0   15.4   0   7 md/d6
    1.0    1.9   25.5   35.9  0.0  0.0    0.0   15.9   0   3 md/d10
    0.3    0.6   17.7   35.1  0.0  0.0    0.0   18.8   0   2 md/d11
    0.3    0.5   17.4   35.2  0.0  0.0    0.0   25.4   0   2 md/d13
    0.3    0.5   17.3   34.5  0.0  0.0    0.0   24.0   0   2 md/d15
    0.8    1.5   48.3   96.6  0.0  0.0    0.0   12.5   0   3 md/d16
    1.2    1.7   41.4   18.7  0.0  0.2    0.0   79.7   0   5 md/d20
    0.6    0.4   35.1   18.0  0.0  0.0    0.0   34.6   0   3 md/d21
    0.6    0.3   34.8   18.0  0.0  0.0    0.0   37.7   0   3 md/d23
    0.5    0.3   34.9   17.4  0.0  0.0    0.0   36.6   0   3 md/d25
    1.6    0.8   97.7   48.8  0.0  0.0    0.0   18.2   0   4 md/d26
    4.4    3.8  241.9  120.1  0.0  0.4    0.2   52.3   0  11 c1t1d0
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    1.3   0   0 c0t0d0
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c4t2d0
    2.7    5.2  127.2  237.3  0.0  0.1    0.0   17.1   0   5 c1t0d0
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t2d0
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t3d1
   17.0    6.4  925.1  298.9  0.0  0.4    0.0   15.9   0   5 c3t3d0
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t2d5
    0.1    0.4    0.4  264.7  0.0  0.0    0.0   11.4   0   0 c3t2d4
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c4t2d1
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t2d1
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t2d2
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c3t2d3
    0.0    0.0    0.0    0.0  0.0  0.0    0.0    0.0   0   0 c4t2d2

Open in new window


For doing this across a bunch of systems it may be easier to setup something like SolarWinds, Nagios or Cacti to gather all the information via SNMP which has standardized interfaces.
0
Question has a verified solution.

Are you are experiencing a similar issue? Get a personalized answer when you ask a related question.

Have a better answer? Share it in a comment.

All Courses

From novice to tech pro — start learning today.