Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!


Dedicated Server slow downs.
New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

Dedicated Server slow downs.

HuntersPadHuntersPad Member
edited January 2015 in Help

So I have a Dedicated Server with about 400 or so gigabytes, which is downloadable on a plain html directory listing, which is uploadable only by me. Then I have another site with about 300Gb or so which is a upload/downloader script. Xfilesharing.

I just keep getting extreme slow downs, Ive had to move my plain Wordpress sites off to another shared host due to this, And usually a reboot of the server will resolve the issue for a little while.

My server is in France through Oneprovider which gets it from Online.net I`m thinking either Disk I/O or its the script causing issues or something is not configed properly, I never had this on a VPS I had last year (before August)

Spec: CPU: Intel Xeon X3450 2.66Ghz + IPMI
RAM: 8GB
Hard drive(s): 2x 1TB HW RAID 0
Bandwidth: 1Gbps.

I also use NodeQuery and get these several times a day:
Average: 11.15 6.95 3.63

System Load: 87%
Ram Usage: 27%
Disk Usage: 43%

index.cgi 4% 18.65 MB user (1)
sw-collectd 0.3% 3.49 MB root (1)
mysqld 0.1% 195.37 MB mysql (1)
sw-engine 0.1% 34.71 MB root (1)
php-cgi 0.1% 14.33 MB hyelton (1)
/usr/sbin/httpd 0% 781.98 MB apache (22)
drwebd.real 0% 501.43 MB drweb (2)
/usr/sbin/httpd 0% 43.82 MB root (1)

But also this morning System load was only about 5% total but pages took about 1 min to load.

Thanks :)

Comments

  • The next time you see it's slow, try to get output from these following things:

    1. vmstat -S M 1 10
    2. ps fauxww
    3. netstat -plant

    Using that you should be able to get a pretty good idea what's going on.

  • MunMun Member

    Sounds like IO wait is killing you.

  • @tehmaggot, Correction, it should be vnstat ;)

  • jlayjlay Member
    edited January 2015

    @Nomad said:
    tehmaggot, Correction, it should be vnstat ;)

    Throw that in the mix too! :p More information at this stage can't hurt :D

  • yusufg90yusufg90 Member
    edited February 2015

    mate we have a good fast one check us out

  • HuntersPadHuntersPad Member
    edited February 2015

    @yusufg90 said:
    mate we have a good fast one check us out

    Seriously ? Did you even read the post? Even if I was looking for a new provider I`m sure you dont offer 2TB of storage and truely unmetered bw.. for 40TB a month.

  • @hyelton Hire sysadmin. Stop thinking you can ask any question on forums.

  • @Profforg said:
    hyelton Hire sysadmin. Stop thinking you can ask any question on forums.

    With what money??! I provide a FREE service to people with Phone dev. I`m not paying someone for prob something simple going on..

  • @tehmaggot said:
    The next time you see it's slow, try to get output from these following things:

    1. vmstat -S M 1 10
    2. ps fauxww
    3. netstat -plant

    Using that you should be able to get a pretty good idea what's going on.

    I got this for the first one:

  • LeeLee Veteran

    @Profforg said:
    hyelton Hire sysadmin. Stop thinking you can ask any question on forums.

    That's what the help section is for, not sure we have any rules about type of question.

    Thanked by 1HuntersPad
  • W1V_Lee said: That's what the help section is for, not sure we have any rules about type of question.

    This type of question can not be solved on forums. Need deep overview with SSH. However he may be lucky to find some sysadmin which is a telepath and will fix his slowdown with power of mind. But this chance is little :)

  • @hyelton said:

    Oh wow. Your I/O wait is really high. Your system is spending around half the time sitting around waiting for the disk.

    There's something that's hitting the disk hard. Mostly lots of "reads" from the disk (in the "io" column, under "bi"). Disk writes were spiking a bit too, under "bo".

    Thanked by 1HuntersPad
  • Its the XFilesharing script

  • @tehmaggot said:
    There's something that's hitting the disk hard. Mostly lots of "reads" from the disk (in the "io" column, under "bi"). Disk writes were spiking a bit too, under "bo".

    Thank you, any suggestions? Also this was just after about 18gb uploaded but it was sort of slow before. I'm also running Plesk

  • @aggressivenetworks said:
    Its the XFilesharing script

    I wish I could find something lighter. I just need something where they click a download link and they see an ad and they have to enter a catch code and click download. I'd hope I could finding something like that for a directory listing script

  • @hyelton said:
    Thank you, any suggestions? Also this was just after about 18gb uploaded but it was sort of slow before. I'm also running Plesk

    The output from either "iotop" or "ps fauxww" would at least give you an idea of what process is doing it.

    Thanked by 1HuntersPad
  • I did PS fauxww but there was so much stuff

  • jlayjlay Member
    edited February 2015

    Yea, it's really noisy but there's lot of good info in there.

    Do you see any processes with "D" in the "STAT" column? If so, that mean's they're in a kind of sleep state that usually means they're waiting for I/O. The process name is in the "COMMAND" column, along with the arguments passed to the process.

    The "iotop" one would be a lot more helpful, but it's not installed by default I think.

  • @tehmaggot said:
    Yea, it's really noisy but there's lot of good info in there.

    Do you see any processes with "D" in the "STAT" column? If so, that mean's they're in a kind of sleep state that usually means they're waiting for I/O. The process name is in the "COMMAND" column, along with the arguments passed to the process.

    The "iotop" one would be a lot more helpful, but it's not installed by default I think.

    I think I only seen 1 that had D under STAT.

    I seen this though :

    root 553 0.0 0.0 209648 2028 ? Ss Jan27 0:03 /usr/bin/abrt-w atch-log -F BUG: WARNING: at WARNING: CPU: INFO: possible recursive locking dete cted ernel BUG at list_del corruption list_add corruption do_IRQ: stack overflow : ear stack overflow (cur: eneral protection fault nable to handle kernel ouble fault: RTNL: assertion failed eek! page_mapcount(page) went negative! adness at NETDEV WATCHDOG ysctl table check failed : nobody cared IRQ handler type mismatc h Machine Check Exception: Machine check events logged divide error: bounds: cop rocessor segment overrun: invalid TSS: segment not present: invalid opcode: alig nment check: stack segment: fpu exception: simd exception: iret exception: /var/

Sign In or Register to comment.