Howdy, Stranger!

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


When is it okay to complain about disk I/O?
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.

When is it okay to complain about disk I/O?

KairusKairus Member
edited October 2011 in General

I'm curious when you guys think it's okay to complain about slow disk I/O? Especially on a low end box.

For instance, I have a 190MB $15/year box from AlienVPS, and it performs okay, I don't really host much on it, a website that's unused now, and a mumble VOIP server for around 15 people. I'm a performance junkie, so every so often, especially with VPSes considering how many companies oversell, I like to check my servers to make sure everything's at an acceptable level.

dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 106.66 s, 10.1 MB/s
ioping -c 10 /
4096 bytes from / (simfs /vz/private/3992): request=1 time=0.2 ms
4096 bytes from / (simfs /vz/private/3992): request=2 time=657.9 ms
4096 bytes from / (simfs /vz/private/3992): request=3 time=14.9 ms
4096 bytes from / (simfs /vz/private/3992): request=4 time=25.8 ms
4096 bytes from / (simfs /vz/private/3992): request=5 time=0.3 ms
4096 bytes from / (simfs /vz/private/3992): request=6 time=5.0 ms
4096 bytes from / (simfs /vz/private/3992): request=7 time=29.4 ms
4096 bytes from / (simfs /vz/private/3992): request=8 time=13.3 ms
4096 bytes from / (simfs /vz/private/3992): request=9 time=16.3 ms
4096 bytes from / (simfs /vz/private/3992): request=10 time=15.6 ms

--- / (simfs /vz/private/3992) ioping statistics ---
10 requests completed in 9780.5 ms, 13 iops, 0.1 mb/s
min/avg/max/mdev = 0.2/77.9/657.9/193.6 ms

So, would you open a ticket regarding this? It's only a $15/year server, should I just expect this level of performance?

What about on a 2GB/$7/mo server (can't resist, I love minecraft), would you open a ticket about:

ioping -c 10 /
4096 bytes from / (simfs /dev/simfs): request=1 time=129.1 ms
4096 bytes from / (simfs /dev/simfs): request=2 time=493.2 ms
4096 bytes from / (simfs /dev/simfs): request=3 time=172.4 ms
4096 bytes from / (simfs /dev/simfs): request=4 time=118.4 ms
4096 bytes from / (simfs /dev/simfs): request=5 time=334.7 ms
4096 bytes from / (simfs /dev/simfs): request=6 time=21.7 ms
4096 bytes from / (simfs /dev/simfs): request=7 time=191.9 ms
4096 bytes from / (simfs /dev/simfs): request=8 time=82.6 ms
4096 bytes from / (simfs /dev/simfs): request=9 time=288.4 ms
4096 bytes from / (simfs /dev/simfs): request=10 time=105.4 ms

--- / ioping statistics ---
10 requests completed in 10949.7 ms
min/avg/max/mdev = 21.7/193.8/493.2/133.6 ms
«13

Comments

  • Turn the screws to these providers for overselling the IO so drasticly

  • My $30/year is much better:

    dd if=/dev/zero of=test bs=16k count=64k conv=fdatasync
    65536+0 records in
    65536+0 records out
    1073741824 bytes (1.1 GB) copied, 8.22325 seconds, 131 MB/s
    
    4096 bytes from . (ext3 /dev/root): request=1 time=0.3 ms
    4096 bytes from . (ext3 /dev/root): request=2 time=0.8 ms
    4096 bytes from . (ext3 /dev/root): request=3 time=1.0 ms
    4096 bytes from . (ext3 /dev/root): request=4 time=0.9 ms
    4096 bytes from . (ext3 /dev/root): request=5 time=1.4 ms
    4096 bytes from . (ext3 /dev/root): request=6 time=0.8 ms
    4096 bytes from . (ext3 /dev/root): request=7 time=0.7 ms
    4096 bytes from . (ext3 /dev/root): request=8 time=0.3 ms
    4096 bytes from . (ext3 /dev/root): request=9 time=2.3 ms
    4096 bytes from . (ext3 /dev/root): request=10 time=0.7 ms
    
    --- . (ext3 /dev/root) ioping statistics ---
    10 requests completed in 9027.4 ms, 1072 iops, 4.2 mb/s
    min/avg/max/mdev = 0.3/0.9/2.3/0.5 ms
  • not really, for $15 it's good, you shouldn't compain at all.

  • rds100rds100 Member
    edited October 2011

    I think for the price you are paying this performance is to be expected. I am not saying it is good, just that it is expected. Which doesn't mean you can't whine about it, but you should whine mostly to yourself anyway.

  • For me, and LEA would agree with me on this (if he is reading this) that at least 25MB/sec should be there even though you are not going to extensively need IO

  • rds100 said: I think for the price you are paying this performance is to be expected.

    How can you say that when a number of $15/yr providers make that 10MB/sec look like it is standing still. I call double standards

  • InfinityInfinity Member, Host Rep
    dd if=/dev/zero of=test bs=16k count=64k conv=fdatasync
    65536+0 records in
    65536+0 records out
    1073741824 bytes (1.1 GB) copied, 14.7817 seconds, 72.6 MB/s
    
    ioping /
    4096 bytes from / (simfs /dev/simfs): request=1 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=2 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=3 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=4 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=5 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=6 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=7 time=0.2 ms
    4096 bytes from / (simfs /dev/simfs): request=8 time=0.2 ms
    
    --- / (simfs /dev/simfs) ioping statistics ---
    8 requests completed in 7034.3 ms, 5155 iops, 20.1 mb/s
    min/avg/max/mdev = 0.2/0.2/0.2/0.0 ms
    

    From a $0 per month OVZ VPS from Hostigation thanks to dmmcintyre3 :) Beat that.

  • @miTgiB i had about the same disk IO with that $15/year provider you have in mind for several months in a row (i have a 15/year on node28). They managed to fix it though, after the move to the new data center. So yes, this disk IO is to be expected. Only a very few providers know how to provide good service at this price level. It is not for everyone.

  • I would be concerned if I/O is slower than 130MB/s, and will complain if below 100MB/s.

  • Anything above 50 MB/s is okay.

  • If I get at least 50MB/s I think its ok, the main problem its that many providers dont accept the result from DD as a valid benchmark.

    For example on my qualityservers vps (uk node) Im lucky if i get past 14MB/s most of the time its in the 9MB/s.

  • drmikedrmike Member
    edited October 2011

    We've had providers who have said that ~10MB/sec is fine....

  • InfinityInfinity Member, Host Rep
    edited October 2011

    My QualityServers VPS got max 500kb/s the last time(s) I checked..

  • @Infinity but how does that make you feel?

  • InfinityInfinity Member, Host Rep
    edited October 2011

    drmike said: @Infinity but how does that make you feel?

    Confused to say the least.

    EDIT: Done a few more tests, and to do more at different times of day but so far it seems they have bumped up to around 12MB/s. I just need to do an ioping now.

    Damn, I suspect something is wrong with glibc:

     /lib/ld-linux.so.2: bad ELF interpreter: No such file or directory
  • Google shows a couple of threads where 32 and 64 bit software has been mixed.

    You're not doing that, are you?

  • I complain if the IO is under 50 MB/s.

  • fanfan Veteran

    maxexcloo said: I complain if the IO is under 50 MB/s.

    If I am you, I'll be complaining everyday. Actually for a lowendbox, anything > 20mb/s (some providers utilize raid 1 instead of 10 for a small and less dense node) is just fine, but this is already the lowest acceptable value.

  • maxexcloo said: I complain if the IO is under 50 MB/s.

    I had a VPS on a node when the host was testing Xen (basically an empty node), and the dd result was around 50 MB/s.

  • 10 mb/s is not really good, try it at different times, if 10 mb/s is minimum you're getting (and not maximum) then this is not a problem imo.

  • Asim said: For me, and LEA would agree with me on this...

    Speak for yourself :)

    I am actually happy with a consistent 20MB/sec, but as it has been mentioned that DD test is flawed. It's just better to have consistent IO latency than having 200MB/sec one day, and then 5MB/sec the day after.

  • Anything above 40MB/sec is stable.

    @danielfeng
    Seriously? I think you need to get out of the budget VPS range then.. Single SATA drives rarely even get above 100MB/sec

  • danielfengdanielfeng Member
    edited October 2011

    VMport said: Anything above 40MB/sec is stable.

    @danielfeng Seriously? I think you need to get out of the budget VPS range then.. Single SATA drives rarely even get above 100MB/sec

    I think budget means more work on stability, security and maintenance, but not necessarily on disk/network performance. Why does budget VPS have to use single SATA drive? RAID10 can also be used on budget VPS.

    Look at my tests on 3 VPS. 2 OVZ and 1 KVM:

    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB) copied, 7.65535 s, 140 MB/s

    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB) copied, 7.20065 s, 149 MB/s

    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB) copied, 6.98297 s, 154 MB/s

    They are all budget VPS.

    PS: ~40MB/s usually means (sort of) overselling. Agree?

  • danielfeng said: PS: ~40MB/s usually means (sort of) overselling. Agree?

    It depends on the disk setup. My development box gets around 35MB/s all the time, and it's real hardware. High latency on disk reads is a bigger issue than low write speeds.

  • DD Write tests are not really an accurate way to test the I/O as a whole, IOPing is a much better test of average performance. And yes RAID10 is used on budget VPS and so it should be.. but that does not mean that the tests should show to be above 100MB/sec.

    Afterall there is not really that much you could run that would require a write speed that high anyway.

    However if speeds are showing anything under 40MB/s its pretty safe to assume its heavily used.

    Thanked by 1Infinity
  • yomeroyomero Member
    edited October 2011

    So, this is a crap @VMport ???

    4096 bytes from . (simfs /dev/simfs): request=1 time=0.5 ms
    4096 bytes from . (simfs /dev/simfs): request=2 time=151.0 ms
    4096 bytes from . (simfs /dev/simfs): request=3 time=12.0 ms
    4096 bytes from . (simfs /dev/simfs): request=4 time=12.9 ms
    4096 bytes from . (simfs /dev/simfs): request=5 time=22.2 ms
    4096 bytes from . (simfs /dev/simfs): request=6 time=25.9 ms
    4096 bytes from . (simfs /dev/simfs): request=7 time=33.7 ms
    4096 bytes from . (simfs /dev/simfs): request=8 time=375.8 ms
    4096 bytes from . (simfs /dev/simfs): request=9 time=227.9 ms
    4096 bytes from . (simfs /dev/simfs): request=10 time=383.3 ms
    
    --- . (simfs /dev/simfs) ioping statistics ---
    10 requests completed in 10255.7 ms, 8 iops, 0.0 mb/s
    min/avg/max/mdev = 0.5/124.5/383.3/145.1 ms
    

    From a known 2GB provider...

    I am still thinking on using it.. or not

  • @yomero very bad, should be below 0.5ms most of the time.

  • Anyone know if this is good or bad?

    7 requests completed in 6108.5 ms, 8986 iops, 35.1 mb/s
    min/avg/max/mdev = 0.1/0.1/0.1/0.0 ms

  • KairusKairus Member
    edited October 2011

    justinb said: Anyone know if this is good or bad?

    7 requests completed in 6108.5 ms, 8986 iops, 35.1 mb/s min/avg/max/mdev = 0.1/0.1/0.1/0.0 ms

    8986 iops is amazing, min/max latency is 0.1, can't get better than that. Is that on an SSD?

  • You are just a presumptuous ¬_¬

Sign In or Register to comment.