Howdy, Stranger!

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


DigitalOcean (4 cores/8 GB) vs RunAbove XL3 (4 cores / 16 GB) vs Vultr (4 cores / 8 GB)
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.

DigitalOcean (4 cores/8 GB) vs RunAbove XL3 (4 cores / 16 GB) vs Vultr (4 cores / 8 GB)

GulfGulf Member
edited August 2015 in Reviews

I need to process some data, what would you choose?

DigitalOcean (4 cores/8 GB) $ 80 / mo

RunAbove XL3 (4 cores / 16 GB) $72/mo

Vultr (4 cores / 8 GB) 64$


Just installed 4 cores DO droplet

DigitalOcean vs RunAbove XL3 vs Vultr
  1. DigitalOcean vs RunAbove XL3 vs Vultr79 votes
    1. DigitalOcean
      29.11%
    2. RunAbove
      31.65%
    3. Vultr
      39.24%
«13

Comments

  • Do a geekbench. No one can say for sure because each provider utilize different CPUs and based on chance, one might be better than the other.

    Thanked by 1Gulf
  • perennateperennate Member, Host Rep
    edited August 2015

    AWS gives 36 cores of E5-2666 v3 processors at $1.763/hour on the c4.8xlarge.

    Thanked by 2Gulf vimalware
  • GulfGulf Member

    @perennate said:
    AWS gives 36 cores of E5-2666 v3 processors at $1.763/hour on the c4.8xlarge.

    Is it about 1000$ per month? :(

  • Gulf said: Is it about 1000$ per month? :(

    If you want to do monthly it's cheaper to buy a dedicated.

    Thanked by 1Gulf
  • GulfGulf Member

    @black said:
    If you want to do monthly it's cheaper to buy a dedicated.

    I need something to process data and then kill the server. For example, within 1-10 days.
    AWS c4.8xlarge will cost 43$ daily, not bad.

  • Run Geekbench on each and post the results. There are other options but I need to see the performance you are looking for first.

    Thanked by 1Gulf
  • desperanddesperand Member
    edited August 2015

    Vultr perfomance very good for me. Much faster & more parrots i can get from different CPU tests. (if compare with DO & RunAbove)

    Thanked by 3Gulf sin Rapta
  • BG32BG32 Member

    Vultr simply because you can kill it if you don't want/like

  • yea, dear topicstart, take a look for this, this is much better then any cloud provider, there you will use clear not shared dedicated resources.

    Thanked by 1Gulf
  • perennateperennate Member, Host Rep

    There's also this for dedicated server -- https://www.incero.com/instant

  • sinsin Member

    @desperand said:
    Vultr perfomance very good for me. Much faster & more parrots i can get from different CPU tests. (if compare with DO & RunAbove)

    Yup, I get amazing performance from VULTR instances with the 3.6GHz cores

  • GulfGulf Member

    @desperand said:
    yea, dear topicstart, take a look for this, this is much better then any cloud provider, there you will use clear not shared dedicated resources.

    Great deal, will bookmark it. One downside - no delivery time information.

  • eva2000eva2000 Veteran
    edited August 2015

    Unfortunately, Vultr 3.6Ghz cores aren't the common cpus used now, Vultr is 2.4Ghz unless you use Vultr Dedicated Cloud series.

    Benchmarks I did below will help @Gulf decide

    If you don't care about virtualisation used, Wable's OpenVZ New York location some servers have Xeon E5-2643v3 @ 3.4Ghz. Mine do

    processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 63 model name : Intel(R) Xeon(R) CPU E5-2643 v3 @ 3.40GHz stepping : 2 microcode : 43 cpu MHz : 3400.289 cache size : 20480 KB physical id : 0 siblings : 12 core id : 1 cpu cores : 6 apicid : 2 initial apicid : 2 fpu : yes fpu_exception : yes cpuid level : 15 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf cpuid_faulting pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer xsave avx f16c rdrand lahf_lm abm ida arat epb pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase bmi1 avx2 smep bmi2 erms invpcid xsaveopt bogomips : 6800.57 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:

  • @eva2000 - Did you run any Geekbench benchmarks?

  • When talking about the GHz of a cpu.. Don't forget https://en.wikipedia.org/wiki/Megahertz_myth

    Thanked by 1perennate
  • LeeLee Veteran

    DO for me has become more and more unstable over time, certainly in the UK at least. Becoming so regular that performance is great one minute and next it it slow and randomly disconnects, loads through roof etc..

  • eva2000eva2000 Veteran
    edited August 2015

    MarkTurner said: Did you run any Geekbench benchmarks?

    nah solely just my centminmodbench.sh script at http://bench.centminmod.com - I'm concerned more about real world performance as it relates to my usage for servers and big part of that is SPDY SSL https based sites etc :)

  • The newer xeons have AES-NI instructions that can pump out close to 500MB/sec aes-128 in openssl bench,without spiking cpu.

    I think you'd be fine with any modern E5/E3.

    Somebody correct me if I'm mistaken.

  • eva2000eva2000 Veteran
    edited August 2015

    vimalware said: The newer xeons have AES-NI instructions that can pump out close to 500MB/sec aes-128 in openssl bench,without spiking cpu.

    I think you'd be fine with any modern E5/E3.

    Somebody correct me if I'm mistaken.

    yup and with AES-NI Xeon v3 > v2 > v1

  • FredQcFredQc Member
    edited August 2015

    @MarkTurner - Incero NYC

    sysbench --num-threads=2 --test=cpu --cpu-max-prime=25000 run

    E5-2670 v2 @ 2.50GHz

    execution time (avg/stddev): 23.1779/0.00

    E5-2643 v3 @ 3.40GHz

    execution time (avg/stddev): 16.0713/0.00

  • jarjar Patron Provider, Top Host, Veteran

    @Lee said:
    DO for me has become more and more unstable over time, certainly in the UK at least. Becoming so regular that performance is great one minute and next it it slow and randomly disconnects, loads through roof etc..

    :(

    Let me know if you wanna follow up on that.

  • sinsin Member
    edited August 2015

    eva2000 said: Unfortunately, Vultr 3.6Ghz cores aren't the common cpus used now, Vultr is 2.4Ghz unless you use Vultr Dedicated Cloud series.

    They're actually still pretty common (depending on what location you're using), I get 3.6GHz cores all time and I deploy daily - if you end up with a 2.4GHz core just redeploy.

  • BG32BG32 Member

    @sin said:
    They're actually still pretty common (depending on what location you're using), I get 3.6GHz cores all time and I deploy daily - if you end up with a 2.4GHz core just redeploy.

    what location? i suspect it depends on your plan price too they wouldnt throw the 3.6 to <$20 plans

  • sinsin Member
    edited August 2015

    BG32 said: what location? i suspect it depends on your plan price too they wouldnt throw the 3.6 to <$20 plans

    New Jersey - $8, $16, and $32 plans - haven't gone any higher as I'm fine with those plans.

    -edit- I haven't tried the $5 plans for those cores so not sure about those and I have only seen the 3.4GHz cores twice over the past month, now all my deployments are either 2.4 or 3.6.

    I think eva said their dedicated cloud are 3.4ghz so that's good to know because I would love to try that out eventually.

  • eva2000 said: I'm concerned more about real world performance as it relates to my usage for servers

    then use geekbench, that gives very detailed scores and shows CPU performance (also shows how crap most E5's are)

    Thanked by 1GM2015
  • Gulf said: I need something to process data and then kill the server. For example, within 1-10 days. AWS c4.8xlarge will cost 43$ daily, not bad.

    You forgot traffic and disk space, right? :) Give it 100-300$ more daily and you are close.

    Thanked by 1vimalware
  • Does DO have filtered IP's?

  • jarjar Patron Provider, Top Host, Veteran
    edited August 2015

    @Dillybob said:
    Does DO have filtered IP's?

    Negative, but BuyVM makes a perfect selection for that :)

    Thanked by 1Dillybob
  • @Jar said:
    Negative, but BuyVM makes a perfect selection for that :)

    Yeah, was going to head down that road most likely lol.

Sign In or Register to comment.