Interstage Shunsaku Data Manager Troubleshooting - Microsoft(R) Windows(R) 2000/ Microsoft(R) Windows Server(TM) 2003 - - UNIX -

3.7.3 Performance Information (Linux)

This section explains how to collect the performance information necessary when investigate a performance problem in Linux platform.

• CPU Use Status
• Network Load Status
• Memory Use Status
• I/O Status
• Process Information

CPU Use Status

Execute the mpstat command to monitor the CPU use status.

Install the sysstat package if the mpstat command does not exist.

If there are multiple CPUs in one machine, refer to the following example:

mpstat -P ALL [execution time interval (sec.)]  [number of execution]

Remark: The execution will not stop if the number of execution is omitted.

If the machine has only one CPU, refer to the following example:

mpstat [execution time interval (sec.)]  [number of execution]

Remark: The execution will not stop if the number of execution is omitted.

Display Sample

xx:xx:xx CPU   %user   %nice %system   %idle    intr/s
xx:xx:xx all    0.00    0.00    0.50   99.50    103.98

Remark: CPU use rate =%user+%system

Network Load Status

Refer to the file similar to /proc/net/dev to monitor the network load status.

view /proc/net/dev

This will provide the number of sent packets, the number of errors and collisions, and other basic statistic.

The format is as follows:

Inter-|   Receive                                                |  Transmit
 face |bytes   packets errs drop fifo frame compressed multicast |bytes   packets errs drop fifo colls carrier compressed
   lo: 2776770 11307   0    0    0    0          0         0      2776770 11307   0    0    0     0     0         0 
 eth0: 1215645 2751    0    0    0    0          0         0      1782404 4324    0    0    0    427    0         0

Receive/packets:Number of received packets
Receive/errs: Number of received packets that have errors
Transmit/packets:Number of sent packets
Transmit/errs:Number of sent packets that have errors
Transmit/colls:Number of packets that have a collision

Memory Use Status

Execute the vmstat command to monitor the memory use status.

The amount of memory for swap-in (reading the swap-out data into physical memory) and swap-out (writing the physical memory data into the hard disk) can be examined.

vmstat [execution time interval (sec.)]  [number of execution]

Remark: The execution will not stop if the number of execution is omitted.

Display sample

procs               memory    swap     io   system         cpu
 r b w  swpd  free  buff  cache  si  so  bi  bo  in   cs  us  sy  id
 1 0 0 22016 36076  2140  80676   9  21  96  63 156  583  35  2   63

si:The amount of memory for swap-in in 1 second (kilobytes)
so:The amount of memory for swap-out in 1 second (kilobytes)

I/O Status

Execute the iostat command to monitor the I/O status if the disk in the director server.

Install the sysstat package if the .iostat command does not exist.

iostat -x [execution time interval (sec.)]  [number of execution]

Display Sample

avg-cpu:  %user   %nice    %sys   %idle
           0.01    0.00    0.01   99.98
Device:    rrqm/s  wrqm/s   r/s   w/s  rsec/s  wsec/s  rkB/s   wkB/s  avgrq-sz  avgqu-sz  await  svctm  %util
/dev/sda     0.01   0.18   0.03  0.12    0.30    2.45   0.15    1.23     18.20      0.09  59.50   0.99   0.02
/dev/sda1    0.00   0.00   0.00  0.00    0.00    0.00   0.00    0.00     12.21      0.00  55.11  32.70   0.00

Process Information

Execute the ps command to monitor the operating status of the process.

ps -elfy

Display Sample

S      UID   PID  PPID   C PRI NI   RSS     SZ    WCHAN    STIME TTY         TIME CMD
S     root 21715 21714   0  59 20 20328  23296        ? 16:35:55 ?           0:00 shunddmn
shunsys shundir1 60432
S     root 21706 21705   0  58 20 20336  23304        ? 16:35:55 ?           0:00 shunddmn
shunsys shundir2 60432

Remark: RSS: the actual amount of memory use in the process