LinuxQuestions.org
Visit Jeremy's Blog.
Go Back   LinuxQuestions.org > Forums > Linux Forums > Linux - Newbie
User Name
Password
Linux - Newbie This Linux forum is for members that are new to Linux.
Just starting out and have a question? If it is not in the man pages or the how-to's this is the place!

Notices


Reply
  Search this Thread
Old 09-21-2009, 02:49 PM   #1
EnderX
Member
 
Registered: Nov 2006
Posts: 66

Rep: Reputation: 15
What are some possible sources of slowdown on SuSE boxes?


The company I work for maintains a set of boxes running SuSE 9.3 and SuSE 11 (as 9.3 boxes go bad, they're replaced with clones of the original 11 box) for one of our customers. With the exception of the main server and my own test and development boxes, these are all at remote locations. With the exception of the 9.3/11 division, the boxes should have the same setup; only database data should have any differences, as some is specific to each location.

I recently received an email stating that at one remote site, everything was behaving slowly - that is, on all client machines at this particular location, all programs designed to point at the major database on the system were extremely sluggish in retrieving data. (Yes, I recognize that 'everything' isn't exactly an accurate term here.)

I have tried to look inside the server in question (a 9.3 box), comparing its condition to another 9.3 box at a site where we have not received any reports of slowdown.

First, I'm not personally experiencing any slowdown while I'm inside the shell (via PuTTY). Second, I'm not seeing anything on top (with -i flag), even though one of the CPUs listed in the output across the top of the screen is showing a near 100% usage at all times. Third, the biggest difference I found in a ps ax run against both systems was that the slow one had ksoftirqd and kirqd listed in the ps ax output, alongside two processes labeled 'migration/N', where N was either 0 or 1.

Given that the programs are all intended to hit a postgresql database, I'm also trying to check into possible sources of slowdown there. I'd thought at first the ksoftirqd might have something to do with it, but everything I've seen online for that possibility indicates that it would be going crazy in top, and the process listings there are showing nothing; they don't even appear when the -i flag is run.

Current contents of top:
Code:
top - 13:46:32 up 1 day, 11:15,  2 users,  load average: 0.00, 0.00, 0.00
Tasks: 100 total,   1 running,  99 sleeping,   0 stopped,   0 zombie
Cpu(s):  0.2% us,  0.2% sy,  0.0% ni, 99.7% id,  0.0% wa,  0.0% hi,  0.0% si
Mem:   1025200k total,  1007876k used,    17324k free,   126516k buffers
Swap:  1020088k total,       40k used,  1020048k free,   736944k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
    1 root      16   0   680  248  216 S  0.0  0.0   0:00.75 init
    2 root      RT   0     0    0    0 S  0.0  0.0   0:00.07 migration/0
    3 root      34  19     0    0    0 S  0.0  0.0   0:00.00 ksoftirqd/0
    4 root      RT   0     0    0    0 S  0.0  0.0   0:00.07 migration/1
    5 root      34  19     0    0    0 S  0.0  0.0   0:00.00 ksoftirqd/1
    6 root      10  -5     0    0    0 S  0.0  0.0   0:00.00 events/0
    7 root      10  -5     0    0    0 S  0.0  0.0   0:00.00 events/1
    8 root      10  -5     0    0    0 S  0.0  0.0   0:00.01 khelper
   13 root      10  -5     0    0    0 S  0.0  0.0   0:00.00 kthread
   24 root      12  -5     0    0    0 S  0.0  0.0   0:00.00 kacpid
  122 root      10  -5     0    0    0 S  0.0  0.0   0:07.93 kblockd/0
  123 root      10  -5     0    0    0 S  0.0  0.0   0:00.13 kblockd/1
  168 root      15   0     0    0    0 S  0.0  0.0   0:18.38 kswapd0
  169 root      11  -5     0    0    0 S  0.0  0.0   0:00.00 aio/0
  170 root      11  -5     0    0    0 S  0.0  0.0   0:00.00 aio/1
  772 root      15   0     0    0    0 S  0.0  0.0   0:00.02 kseriod
  867 root      15   0     0    0    0 S  0.0  0.0   0:00.00 kirqd
 1006 root      11  -5     0    0    0 S  0.0  0.0   0:00.00 ata/0
 1007 root      10  -5     0    0    0 S  0.0  0.0   0:00.00 ata/1
 1014 root      19   0     0    0    0 S  0.0  0.0   0:00.00 scsi_eh_0
 1015 root      20   0     0    0    0 S  0.0  0.0   0:00.00 scsi_eh_1
 1130 root      10  -5     0    0    0 S  0.0  0.0   0:00.20 reiserfs/0
 1131 root      10  -5     0    0    0 S  0.0  0.0   0:00.09 reiserfs/1
 2247 root      12  -4  1472  604  408 S  0.0  0.1   0:00.22 udevd
 3043 root      15   0     0    0    0 S  0.0  0.0   0:00.00 khubd
 3281 root      11  -5     0    0    0 S  0.0  0.0   0:00.00 hda_codec/0
 3282 root      10  -5     0    0    0 S  0.0  0.0   0:00.00 hda_codec/1
 4262 root      15  -2  1460  440  312 S  0.0  0.0   0:00.00 hwscand
 5060 root      16   0  1528  624  520 S  0.0  0.1   0:00.08 syslogd
 5144 root      16   0  1604  596  400 S  0.0  0.1   0:00.00 klogd
 5343 messageb  15   0  3356 1488 1272 S  0.0  0.1   0:00.00 dbus-daemon-1
 5719 root      16   0  1920  528  460 S  0.0  0.1   0:00.00 resmgrd
 5796 ldap      18   0  6108 2884 2144 S  0.0  0.3   0:00.00 slapd
 5827 postgres  16   0 16760 2856 2468 S  0.0  0.3   0:03.70 postmaster
 5906 postgres  15   0 16744  10m  10m S  0.0  1.1   0:00.12 postmaster
 5907 postgres  16   0  7548 2908 1516 S  0.0  0.3   0:00.66 postmaster
 5908 postgres  15   0  6688 2052 1524 S  0.0  0.2   0:00.55 postmaster
 6045 nobody    18   0  1508  476  396 S  0.0  0.0   0:00.00 portmap
 6136 root      19   0  2444 1148  928 S  0.0  0.1   0:00.00 mysqld_safe
 6144 root      15   0  5856 1976 1540 S  0.0  0.2   0:04.59 nmbd
 6158 root      16   0  4600 1968 1592 S  0.0  0.2   0:00.30 sshd
 6253 nobody    16   0  2048 1076  712 S  0.0  0.1   0:00.00 mdnsd
 6274 root      16   0  2732  740  620 S  0.0  0.1   0:00.00 kdm
 6279 root      15   0 29212  19m 2072 S  0.0  2.0   0:12.02 X
 6280 root      17   0  3068 1140  912 S  0.0  0.1   0:00.00 kdm
Aside from my attempts to follow up the possibility of a postgresql explanation for the slowdown, what are some possible things I might want to look for/ask the end users to look for?
 
Old 09-21-2009, 07:26 PM   #2
chrism01
LQ Guru
 
Registered: Aug 2004
Location: Sydney
Distribution: Centos 6.9, Centos 7.3
Posts: 17,417

Rep: Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397Reputation: 2397
If they are complaining about sluggish data retrieval, ask if its only or mostly DB related jobs that are slow. could be the DB needs a vacuum or other kind of tidy up? No more room on db partition? Check the db logs? Try a few db queries your self from the cmd line and tail -f /var/log/messages and/or any other relevant log eg Pg's log.
NB I'm not a PG guy, but have worked with other DBs.
 
  


Reply


Thread Tools Search this Thread
Search this Thread:

Advanced Search

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off



Similar Threads
Thread Thread Starter Forum Replies Last Post
3 Ubuntu boxes with Samba - One finds all XP shares - Two UltraSparc64 boxes do not mwx Linux - Server 1 01-28-2009 07:03 AM
sudden internet slowdown when using suse, but not xp ungua SUSE / openSUSE 10 01-30-2007 11:39 AM
suse modprobe ndiswrapper slowdown aminics SUSE / openSUSE 0 07-18-2006 09:57 AM
SuSE 9.3 'fam' causes slowdown & lockups vinbob Linux - Newbie 2 06-06-2005 08:00 PM

LinuxQuestions.org > Forums > Linux Forums > Linux - Newbie

All times are GMT -5. The time now is 02:26 AM.

Main Menu
Advertisement
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
Facebook: linuxquestions Google+: linuxquestions
Open Source Consulting | Domain Registration