• kolik CPU/RAM zere jaky proces se zjisti snadno, napriklad vypisem top
• monitorovani IO je zlozitejsi a dost casto zpomaluje system nejvic

• existuji programy:
  • iotop
  • atop
  • pidstat
  • dstat (–topio, –topbio)
  • vmstat (-d)
  • iostat
  • iozone
  • sar

• využívá hodnoty ze sar
• příklad statistik

iostat -d 2
Linux 2.6.18-194.3.1.el5 (nejaky.stroj.nekde.cz)        09/05/2014

Device:            tps   Blk_read/s   Blk_wrtn/s   Blk_read   Blk_wrtn
sda             558.07       236.28     20370.08 1604053205 138289873008
sda1              0.07         0.00         0.36      33698    2429406
sda2              0.00         0.00         0.00        621          0
sda3              2.51         1.59        37.58   10783682  255133504
sda4            555.50       234.68     20332.15 1593234484 138032310098

Device:            tps   Blk_read/s   Blk_wrtn/s   Blk_read   Blk_wrtn
sda               0.50         0.00        12.00          0         24
sda1              0.00         0.00         0.00          0          0
sda2              0.00         0.00         0.00          0          0
sda3              0.00         0.00         0.00          0          0
sda4              0.50         0.00        12.00          0         24

...

• první statistika je myslím průmer za celý den, další výpisy odpovídají už zadanému časovému období

• ukládá statistiky dlouhodobě (období lze specifikovat)
• příklad:

# sar -b
Linux 2.6.18-194.3.1.el5 (nejakej.stroj.nekde.cz)  09/05/2014

12:00:01 AM       tps      rtps      wtps   bread/s   bwrtn/s
12:10:01 AM    843.15      7.64    835.51    173.54  27131.75
12:20:01 AM   1512.20     15.58   1496.62    255.28  33938.05
12:30:01 AM   1210.95     11.62   1199.33    183.09  29124.69
12:40:01 AM   1069.91      9.31   1060.60    186.96  27125.52
12:50:01 AM   1060.24      9.94   1050.30    157.10  25954.69
01:00:01 AM   1013.24      7.39   1005.85    113.41  27263.05
01:10:01 AM    891.21      7.74    883.47    122.58  25108.18
01:20:01 AM    838.14      7.02    831.12    169.31  25711.26
..

• výpis obsahuje průměry za 10 minut. Sloupec bread/bwrtn udává, kolik bloků bylo přečteno/zapsáno. Bloky jsou typicky velikosti 4k. Lze ověřit přes tune2fs

tune2fs -l /dev/sda4 | grep "Block size"
Block size:               4096

Here’s how you use it. First, get it:

wget http://aspersa.googlecode.com/svn/trunk/iodump

Then turn on kernel messages about I/O:

echo 1 > /proc/sys/vm/block_dump

This makes the kernel start writing messages about every I/O operation that takes place. Now all you have to do is get those messages and feed them into my script:

while true; do sleep 1; dmesg -c; done | perl iodump

Wait a little while, then cancel the script. The results should look something like the following:

root@kanga:~# while true; do sleep 1; dmesg -c; done | perl iodump
^C# Caught SIGINT.
TASK                   PID      TOTAL       READ      WRITE      DIRTY DEVICES
firefox               4450       4538        251       4287          0 sda4, sda3
kjournald             2100        551          0        551          0 sda4
firefox              28452        185        185          0          0 sda4
kjournald              782         59          0         59          0 sda3
pdflush                 31         30          0         30          0 sda4, sda3
syslogd               2485          2          0          2          0 sda3
firefox              28414          2          2          0          0 sda4, sda3
firefox              28413          1          1          0          0 sda4
firefox              28410          1          1          0          0 sda4
firefox              28307          1          1          0          0 sda4
firefox              28451          1          1          0          0 sda4

I deliberately generated a bunch of I/O by deleting my Firefox history and cache.

Do dmseq se zapisuje neco jako….

firefox(4450): WRITE block 25058328 on sda4
firefox(4450): WRITE block 25058336 on sda4
firefox(4450): WRITE block 25059104 on sda4

A quick way is to look at the /proc/[PID]/io file.

Example:

$ cat /proc/1944/io
read_bytes: 17961091072
write_bytes: 8192000
cancelled_write_bytes: 32768

#!/bin/bash

while [ 1 ]
do

  #CPIDS=`pgrep cache`
  CPIDS=`ls /proc/ | grep "[0-9]"`

  i=0
  for P in $CPIDS
  do
    STATA[i]=`cat /proc/$P/io 2>/dev/null | grep "^write_bytes:" | cut -d " " -f 2`
    i=$((i+1))
  done
 
  sleep 1
 
  i=0
  for P in $CPIDS
  do
    STATB[i]=`cat /proc/$P/io 2>/dev/null | grep "^write_bytes:" | cut -d " " -f 2`
    i=$((i+1))
  done
 
  i=0
  for P in $CPIDS
  do
    [[ ${STATB[$i]} -gt 0 ]] && [[ ${STATA[$i]} -gt 0 ]] && DIFF=$(( ${STATB[$i]} - ${STATA[$i]}  )) || DIFF=0
    [[ $DIFF -gt 0 ]] && {
      DIFF=$((DIFF/1024))
      echo "PID $P: $DIFF kB/s (${STATB[$i]} - ${STATA[$i]})"
    }
    i=$((i+1))
  done
 
  echo "---" 

done

   wa -- iowait (Amount of time the CPU has been waiting for I/O to complete)

• procesy ve stavu D

PROCESS STATE CODES
 D uninterruptible sleep (usually IO)
 R running or runnable (on run queue)
 S interruptible sleep (waiting for an event to complete)
 T stopped, either by a job control signal or because it is being traced.
 W paging (not valid since the 2.6.xx kernel)
 X dead (should never be seen)
 Z defunct ("zombie") process, terminated but not reaped by its parent.

• vypis procesu ve stavu D

 for x in `seq 1 1 10`; do ps -eo state,pid,cmd | grep "^D"; echo "----"; sleep 5; done

• zdroj (http://bencane.com/2012/08/06/troubleshooting-high-io-wait-in-linux)