Howdy, Stranger!

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

Sign In Register

Quick Links


Categories

In this Discussion

› › Did some benchmarks, thought id share
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.

Did some benchmarks, thought id share

ronaldgrnronaldgrn Member
edited September 2014 in Reviews

Was bored between flights and was looking for a shove-all-low-traffic-sites-here (<1000 visits a day) box so did a few benchmarks on some low end servers... heres what I got

became a surprisingly difficult decision

Which would you choose
  1. ??27 votes
    1. Vultr 2GB
      11.11%
    2. Vultr 1GB
      11.11%
    3. Ramnode
      62.96%
    4. RootNerds
      14.81%

Comments

  • GoodHostingGoodHosting Member

    None of these benchmarks quantitative of anything...

    Here's some related pornography:

    [root@xxxxx ~]# ioping -c1 / -s 4M
4.0 MiB from / (ext4 /dev/sda1): request=1 time=1.1 ms

--- / (ext4 /dev/sda1) ioping statistics ---
1 requests completed in 1.1 ms, 936 iops, 3.7 GiB/s
min/avg/max/mdev = 1.1 ms / 1.1 ms / 1.1 ms / 0 us

    [root@xxxxx ~]# ioping -c1 / -s 4k
4.0 KiB from / (ext4 /dev/sda1): request=1 time=11 us

--- / (ext4 /dev/sda1) ioping statistics ---
1 requests completed in 45 us, 90.9 k iops, 355.1 MiB/s
min/avg/max/mdev = 11 us / 11 us / 11 us / 0 us
  • ronaldgrnronaldgrn Member

    in general no... but considering I used the exact same method (serverbear) on each... In that closed group you can compare against one another

  • GoodHostingGoodHosting Member

    @ronaldgrn said:
    in general no... but considering I used the exact same method (serverbear) on each... In that closed group you can compare against one another

    Maaaybe, but when in an shared environment; "benchmarking" results are especially invalid.

    Let alone that "benchmarks" are never actually a stick towards the actual service performance.

    --

    What matters most is "Does this server run the program I need it to, as fast as I need it to?"

  • FrankZFrankZ Veteran
    edited September 2014

    @GoodHosting - You are so right with

    What matters most is "Does this server run the program I need it to, as fast as I need it to?"

    I think this is what the OP is trying to find out.. please tell us the best way to know?

  • linuxthefishlinuxthefish Member

    Get the one with the highest results in dd test, all other benchmarks are useless anyway!

    Thanked by 1sc754
  • ronaldgrnronaldgrn Member

    @linuxthefish said:
    Get the one with the highest results in dd test, all other benchmarks are useless anyway!

    Thanks... thought about that.. but was conflicted between I/O with RamNode and he 3gb of ram on RootNerds...

  • Shoaib_AShoaib_A Member

    @ronaldgrn said:
    Thanks... thought about that.. but was conflicted between I/O with RamNode and he 3gb of ram on RootNerds...

    Remember DD test results should be 10 GB/s atleast otherwise the VPS is useless & will carry out the tasks slower than .....

    Thanked by 1sc754
  • ronaldgrnronaldgrn Member

    as @GoodHosting rightly said you can't use pure numbers for the tests... so im just comparing those with each other... if you had to choose one of those for a server getting < 5000 hits a day.. which would be your choice (performance + price wise)

  • Shoaib_AShoaib_A Member

    @ronaldgrn said:
    as GoodHosting rightly said you can't use pure numbers for the tests... so im just comparing those with each other... if you had to choose one of those for a server getting < 5000 hits a day.. which would be your choice (performance + price wise)

    All of the servers that you mentioned would serve your purpose but just to feel more secure you may go with RamNode who have been consistently ranked # 1 in last 3 quarterly top provider polls here on LET.

  • hostnoobhostnoob Member
    edited September 2014

    Vultr 2GB gives you 4GB RAM? Also Vultr's 1GB plan is $7

    But then I would still go for either the 1GB Vultr or Ramnode, and if you're willing to pay a little extra, then Ramnode gives you more everything than Vultr 1GB

  • DalCompDalComp Member

    @ronaldgrn said:
    as GoodHosting rightly said you can't use pure numbers for the tests... so im just comparing those with each other... if you had to choose one of those for a server getting < 5000 hits a day.. which would be your choice (performance + price wise)

    If it's a heavy database website, go for the high I/O. If it's a gallery website, bandwidth and/or network speed and/or disk space is important. If it's gonna need more CPU power, go with the provider who is more tolerant to high server load. And other ifs...

  • ronaldgrnronaldgrn Member
    edited September 2014

    @hostnoob said:
    Vultr 2GB gives you 4GB RAM? Also Vultr's 1GB plan is $7

    But then I would still go for either the 1GB Vultr or Ramnode, and if you're willing to pay a little extra, then Ramnode gives you more everything than Vultr 1GB

    forgot to mention.. for vultr both have the double ram promo...
    Rootnerds has that previous promo they did on lowendtalk
    and Ramnode... well.. thats just their standard pricing

  • edanedan Member

    @ronaldgrn said:

    (<1000 visits a day)

    @ronaldgrn said:
    for vultr both have the double ram promo

    performance + price wise? than Vultr.

  • BrianHarrisonBrianHarrison Member, Patron Provider

    @DalComp said:
    If it's a heavy database website, go for the high I/O.

    High I/O on random reads and writes.

Sign In or Register to comment.