Solaris Performance Monitoring & Tuning - iostat , vmstat & netstat

 

Introduction to iostat , vmstat and netstat  This document is primarily written with reference to solaris performance monitoring and tuning but these tools are available in other unix variants also with slight syntax difference.  iostat , vmstat and netstat are three most commonly used tools  for performance monitoring . These comes built in with the operating system and are easy to use .iostat stands for input output statistics and reports statistics for i/o devices such as disk drives . vmstat  gives  the statistics for virtual Memory and netstat gives the network statstics . Following paragraphs describes these tools and their usage for performance monitoring  and  if you need more information there are some very good solaris performance monitoring books available at www.besttechbooks.com. Table of content : 1. Iostat Syntax example Result and Solutions  2. vmstat syntax example Result and Solutions  3. netstat  syntax  example  Result and Solutions 4. Next Steps Input Output statistics (  iostat )  iostat   reports terminal and disk  I/O  activity and  CPU utilization.  The first line of output is for the  time period  since boot  &  each subsequent line is for  the  prior  interval . Kernel maintains  a number of counters to keep track of  the  values. iostat's activity class options default  to  tdc  (terminal,  disk, and CPU). If any other option/s are specified,  this  default is completely overridden i.e.  iostat -d will report only statistics about the disks. syntax: Basic synctax is iostat  <options>   interval  count option - let you specify the device for which information is needed like disk , cpu or terminal. (-d , -c , -t  or -tdc ) .  x options gives the extended statistics . interval -  is time period in seconds between two samples . iostat  4  will give data at each 4 seconds interval. count  - is the  number of times the data is needed .  iostat 4 5   will give data at 4 seconds interval   5 times

Example

$ iostat -xtc 5 2 extended disk statistics tty cpu disk r/s w/s Kr/s Kw/s wait actv svc_t %w %b tin tout us sy wt id sd0 2.6 3.0 20.7 22.7 0.1 0.2 59.2 6 19 0 84 3 85 11 0 sd1 4.2 1.0 33.5 8.0 0.0 0.2 47.2 2 23 sd2 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0 0 sd3 10.2 1.6 51.4 12.8 0.1 0.3 31.2 3 31 The fields have the following meanings: disk name of the disk r/s reads per second w/s writes per second Kr/s kilobytes read per second Kw/s kilobytes written per second wait average number of transactions waiting for service (Q length) actv average number of transactions actively being serviced (removed from the queue but not yet completed) %w percent of time there are transactions waiting for service (queue non-empty) %b percent of time the disk is busy (transactions in progress)

Results and Solutions:

The values to look from the iostat output  are:

• Reads/writes  per second (r/s , w/s)
• Percentage busy (%b)
• Service time (svc_t)

If a disk shows consistently high reads/writes along with , the percentage busy (%b) of the disks is greater than 5 percent, and the average service time  (svc_t) is greater than 30 milliseconds, then  one of the following action needs to be taken

1.)Tune the application to use disk i/o more efficiently  by modifying the disk queries and using available cache facilities of application servers .

2.) Spread the file system of the disk on to two or more disk  using disk striping feature of volume manager /disksuite  etc.

3.) Increase the system parameter values for  inode cache  , ufs_ninode ,  which is  Number of inodes to be held in memory. Inodes are cached globally (for UFS), not on a per-file system basis 

4.) Move the file system to another faster disk /controller  or replace existing disk/controller to a faster      one.

---

Virtual Memory Statistics ( vmstat )

vmstat -  vmstat reports virtual memory statistics of   process, virtual memory, disk, trap, and CPU activity.

 On multicpu systems , vmstat averages the number of CPUs  into  the  output. For per-process statistics .Without options, vmstat displays a one-line summary  of  the  virtual memory activity since the system was booted.

 syntax:

Basic synctax is vmstat  <options>   interval  count

option - let you specify the type of information needed such as paging  -p , cache   -c ,.interrupt -i  etc.

if no option is specified  information about   process , memory , paging , disk ,interrupts & cpu  is displayed  .

interval  - is time period in seconds between two samples . vmstat   4  will give data at each 4 seconds interval.

count  - is the number of times the data is needed . vmstat 4   5   will give data at 4 seconds interval   5              times.

 Example

     The following command displays a summary of what the  system
     is doing every five seconds.

     example% vmstat 5

procs memory page disk faults cpu r b w swap free re mf pi p fr de sr s0 s1 s2 s3 in sy cs us sy id 0 0 0 11456 4120 1 41 19 1 3 0 2 0 4 0 0 48 112 130 4 14 82 0 0 1 10132 4280 0 4 44 0 0 0 0 0 23 0 0 211 230 144 3 35 62 0 0 1 10132 4616 0 0 20 0 0 0 0 0 19 0 0 150 172 146 3 33 64 0 0 1 10132 5292 0 0 9 0 0 0 0 0 21 0 0 165 105 130 1 21 78

 The fields of vmstat's display are
      procs 
             r     in run queue
             b     blocked for resources I/O, paging etc.
            w     swapped

      memory (in Kbytes)
              swap -  amount  of  swap   space   currently   available                
              free   - size of the free list 

      page ( in units per second).
           re    page reclaims -  see  -S  option  for  how  this field is modified.
           mf    minor faults -  see  -S  option  for  how    this field is modified.
           pi    kilobytes paged in
           po    kilobytes paged out
           fr    kilobytes freed
           de    anticipated short-term memory shortfall (Kbytes)
           sr    pages scanned by clock algorithm

      disk  ( operations per second )            There are  slots for up to four disks, labeled with a single letter and number.            The letter indicates  the  type  of  disk  (s = SCSI, i = IPI, etc) . The number is             the logical unit number.

      faults
            in    (non clock) device interrupts
           sy    system calls
           cs    CPU context switches

      cpu  -   breakdown of percentage usage of CPU  time.  On multiprocessors  this is an a                 verage across all processors.
           us    user time
           sy    system time
           id    idle time
 

Results and Solutions:

A.   CPU issues:

Following columns has to be watched to determine if there is any cpu issue

1. Processes in the run queue (procs r)
2. User time (cpu us)
3. System time (cpu sy)
4. Idle time (cpu id)

procs cpu r b w us sy id 0 0 0 4 14 82 0 0 1 3 35 62 0 0 1 3 33 64 0 0 1 1 21 78

Problem symptoms: 1.) If the number of processes in run queue ( procs r) are consistently greater than the number of CPUs on the system it will slow down system as there are more processes then available CPUs . 2.) if  this number is more than four times the number of available CPUs in the system then system is facing shortage of cpu power and will greatly slow down the processess on the system. 3.) If  the idle time ( cpu id) is consistently 0 and if the system time ( cpu sy) is double the user time ( cpu us)  system is facing shortage of CPU resources.

 

Resolution : Resolution to these kind of issues involves tuning of application procedures  to make efficient use of cpu  and as a last resort increasing the cpu power or adding more cpu to the system.       B.   Memory Issues: Memory bottlenecks are determined by the scan rate ( sr) . The scan rate is the pages scanned by the clock algorithm per second. If the scan rate ( sr) is continuously over 200 pages per second then there is a memory shortage.   Resolution : 1. Tune the applications & servers to make  efficient use of memory and cache. 2. Increase system memory . 3. Implement priority paging in s  in pre solaris 8 versions by adding line "set priority paging=1" in      /etc/system. Remove this line if upgrading from Solaris 7 to 8 & retaining old /etc/system file.

---

Network Statistics (netstat)

netstat displays the  contents  of  various  network-related  data structures in  depending on the options selected.

Syntax :

netstat  <option/s>

multiple options can be given at one time.

Options

 -a - displays the state of all sockets.
 -r - shows the system routing tables
 -i - gives statistics on a per-interface basis.
-m - displays information from the network memory buffers. On Solaris, this shows statistics          forSTREAMS
 -p [proto] - retrieves statistics for the specified protocol
  -s - shows per-protocol statistics. (some implementations allow -ss to remove fileds with a value of 0 (zero) from the display.)
 -D - display the status of DHCP configured interfaces. 
-n do not lookup hostnames, display only IP addresses. -d (with -i) displays dropped packets per interface. -I [interface] retrieve information about only the specified interface. -v be verbose

interval  -   number for continuous display of statictics.

Example :

$netstat -rn Routing Table: IPv4   Destination           Gateway               Flags  Ref   Use   Interface -------------------- -------------------- ----- ----- ------ --------- 192.168.1.0         192.168.1.11           U        1   1444      le0 224.0.0.0             192.168.1.11           U        1   0            le0 default                  192.168.1.1           UG       1   68276   127.0.0.1             127.0.0.1               UH       1  10497     lo0

This shows the output on a Solaris machine who's IP address is 192.168.1.11 with a default router at 192.168.1.1

Results and Solutions:

A.) Network availability

The command as above is mostly useful in troubleshooting network accessibility issues . When  outside network is not accessible from a machine check the following

1. if the default router ip  address is correct

2.  you can ping it from your machine.

3. If router address is incorrect  it can be changed  with route add  commnad . See man route  for more info .

route command examples:
$route add default <hostname> $ route add 192.0.2.32  <gateway_name>

If the router address is correct but still you can't ping it  there may be some  network cable /hub/switch problem  and you have to try and eliminate the faulty component .

B.) Network Response

$ netstat -i

Name	Mtu	Net/Dest	Address	Ipkts	Ierrs	Opkts	Oerrs	Collis	Queue
lo0	8232	loopback	localhost	77814	0	77814	0	0	0
hme0	1500	server1	server1	10658566	3	4832511	0	279257	0

This option is used to diagnose the network problems when  the connectivity is there but  it is slow in response .

Values to look at:

• Collisions (Collis)
• Output packets (Opkts)
• Input errors (Ierrs)
• Input packets (Ipkts)

The above values will give information to workout

i.  Network collision rate as follows :

Network collision rate = Output collision counts / Output packets

 Network-wide collision rate greater than 10 percent  will indicate

•  Overloaded network,
•  Poorly configured network,
•  Hardware problems. 

ii.  Input packet error rate as follows :

 Input Packet Error Rate = Ierrs / Ipkts.

If the input error rate is high (over 0.25 percent), the host is dropping packets. Hub/switch cables etc needs to be checked for potential problems.

C.  Network socket &  TCP Cconnection state

Netstat gives important   information about network socket and tcp state . This is very useful in
finding out the open , closed and  waiting network tcp connection .

Network states returned by  netstat are following :

     CLOSED               ----  Closed.  The socket  is  not  being used.
     LISTEN                 ----  Listening for incoming connections.
     SYN_SENT           ----  Actively trying to  establish  connection.
     SYN_RECEIVED  ---- Initial synchronization of the connection under way.
     ESTABLISHED     ----  Connection has been established.
     CLOSE_WAIT      ----  Remote shut down; waiting  for  the socket to close.
     FIN_WAIT_1        ----  Socket closed; shutting  down  connection.
     CLOSING             ----  Closed,   then   remote   shutdown; awaiting acknowledgement.
     LAST_ACK          ----   Remote  shut  down,  then   closed ;awaiting acknowledgement.
     FIN_WAIT_2        ----  Socket closed; waiting for shutdown from remote.
     TIME_WAIT         ----  Wait after close for  remote  shutdown retransmission.
        Example:
 #netstat -a

Local Address Remote Address Swind   Send-Q Rwind Recv-Q State  *.* *.* 0 0 24576 0 IDLE *.22 *.* 0 0 24576 0 LISTEN *.22 *.* 0 0 24576 0 LISTEN *.* *.* 0 0 24576 0 IDLE *.32771 *.* 0 0 24576 0 LISTEN *.4045 *.* 0 0 24576 0 LISTEN *.25 *.* 0 0 24576 0 LISTEN *.5987 *.* 0 0 24576 0 LISTEN *.898 *.* 0 0 24576 0 LISTEN *.32772 *.* 0 0 24576 0 LISTEN *.32775