Howdy, Stranger!

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


Anyone using Dediserve and able to upgrade to Jessie? - Page 3
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.

Anyone using Dediserve and able to upgrade to Jessie?

13

Comments

  • @dediserve - the performance on the Dallas location is fantastic - played with it for an hour or so last night and it was A LOT better then Xen. There was an issue creating a server with the Debian 8 template support gave me (a panel error that said "CPU Priority must be less than or equal to 6 to meet billing requirements.") but they ended up creating the server for me and getting me squared away.

    Thanked by 2dediserve vimalware
  • @dediserve when did KVM go live in Sydney?

  • @bohdans said:
    dediserve when did KVM go live in Sydney?

    About a week ago

  • bohdansbohdans Member
    edited September 2015

    @dediserve I destroyed and rebuilt my VM a few days ago, but am still on Xen, is there any trick to move to KVM?
    Trying to destroy and rebuild again
    YAY, KVM! Tell your tech guys thanks ;)
    Now we are all waiting on a new promo......

    Thanked by 1dediserve
  • sinsin Member
    edited September 2015

    Here's a quick freevps test on Dediserve's Dallas, Texas location (I'm on their regular 250 Mbps port speed).

    I really love this server so far.

    root@dediservebox:~# benchmark
    CPU model : QEMU Virtual CPU version 0.9.1
    Number of cores : 2
    CPU frequency : 2933.542 MHz
    Total amount of ram : 2008 MB
    Total amount of swap : 1023 MB
    System uptime : 7:50,
    Download speed from CacheFly: 35.0MB/s
    Download speed from Coloat, Atlanta GA: 31.5MB/s
    Download speed from Softlayer, Dallas, TX: 31.9MB/s
    Download speed from Linode, Tokyo, JP: 15.6MB/s
    Download speed from i3d.net, Rotterdam, NL: 10.4MB/s
    Download speed from Leaseweb, Haarlem, NL: 28.6MB/s
    Download speed from Softlayer, Singapore: 9.28MB/s
    Download speed from Softlayer, Seattle, WA: 28.0MB/s
    Download speed from Softlayer, San Jose, CA: 18.5MB/s
    Download speed from Softlayer, Washington, DC: 9.58MB/s
    I/O speed : 495 MB/s

    root@dediservebox:~# ioping . -c 10
    4 KiB from . (ext3 /dev/vda1): request=1 time=112 us
    4 KiB from . (ext3 /dev/vda1): request=2 time=442 us
    4 KiB from . (ext3 /dev/vda1): request=3 time=281 us
    4 KiB from . (ext3 /dev/vda1): request=4 time=204 us
    4 KiB from . (ext3 /dev/vda1): request=5 time=253 us
    4 KiB from . (ext3 /dev/vda1): request=6 time=220 us
    4 KiB from . (ext3 /dev/vda1): request=7 time=224 us
    4 KiB from . (ext3 /dev/vda1): request=8 time=225 us
    4 KiB from . (ext3 /dev/vda1): request=9 time=174 us
    4 KiB from . (ext3 /dev/vda1): request=10 time=226 us

    --- . (ext3 /dev/vda1) ioping statistics ---
    10 requests completed in 9.01 s, 4.24 k iops, 16.5 MiB/s
    min/avg/max/mdev = 112 us / 236 us / 442 us / 81 us

    Thanked by 2dediserve vimalware
  • @dediserve said:
    Dallas, SG, Dublin, London, Sydney, Hong Kong and more soon

    Soon (tm) = this week? :)

  • @nfn What location are you looking for an I can check / confirm?

  • @dediserve said:
    nfn What location are you looking for an I can check / confirm?

    London ... the new KVM offer.

  • dediservedediserve Member
    edited September 2015

    London is already available with KVM (Maidenhead) and we'll be re-opening London, Docklands with KVM likely in the coming week.

    Thanked by 1alegeek
  • It's been almost a week since I signed up for Dediserve's KVM at their Dallas location - really loving it so far! I installed a LEMP stack, moved over 6 wordpress blogs, and have been just messing around with things and working on my sites...everything is really snappy. I also love the new 2.93GHz cores :) and I'm happy to be on Debian 8...I remember when I started this thread I was pretty frustrated Debian 8 wouldn't work on Xen at the time.

    Thanked by 3dediserve Lee vimalware
  • @dediserve: I vote for amsterdam next. My gitlab needs a little oomph.

    P.S: can we restore snapshots from xen vm to kvm?

    Thanked by 1dediserve
  • You can restore Xen templates to KVM and yes, KVM is available in AMS

    Thanked by 1vimalware
  • @dediserve said:
    You can restore Xen templates to KVM and yes, KVM is available in AMS

    Receiving negative on both points from support. Ref: ticket 807572

    Thanked by 1dediserve
  • @dediserve said:
    You can restore Xen templates to KVM and yes, KVM is available in AMS

    We want a new offer :P

  • Still waiting on the new Docklands servers.

  • sinsin Member
    edited September 2015

    @dediserve - with the standard 2GB ram resource plan, how much outbound bandwidth/traffic comes with it? Certain pages on the Dediserve site have different amounts...one part says 1TB for each 1GB of ram, another page says 1.5TB for each 1GB of ram. There's nothing that I can find in the control panel that tells me how much outbound I'm allowed each month with my 2GB plan.

    Also...are there any other US locations that will be moving to KVM in the near future? Like maybe Buffalo :).

  • Latest authoritative update: KVM is not ready in AMS.

    I feel silly for deleting my vm. Thank you onapp for snapshots :)

  • dediservedediserve Member
    edited September 2015

    @sin - We bundle 1.5TB per GB in most locations, with 1TB per GB in Hong Kong and Sydney. We've some site edits en route that will help clarify that.

    @vimalware - Apologies, 100% my bad on that information :(

    Thanked by 2vimalware sin
  • @dediserve said:
    vimalware - Apologies, 100% my bad on that information :(

    Is there a date for Frankfurt, yet? :)

  • @vimalware said:
    Latest authoritative update: KVM is not ready in AMS.

    I feel silly for deleting my vm. Thank you onapp for snapshots :)

    Damn that sucks because I'm sure you will really enjoy KVM at Dediserve when it's available at the location you're on :)

  • @sin said:
    New CPUs?? awww yeeee

    root@dediservebox:~# cat /proc/cpuinfo
    processor : 0
    vendor_id : GenuineIntel
    cpu family : 6
    model : 6
    model name : QEMU Virtual CPU version 0.9.1
    stepping : 3
    cpu MHz : 2933.542
    cache size : 512 KB
    physical id : 0
    siblings : 1
    core id : 0
    cpu cores : 1
    apicid : 0
    initial apicid : 0
    fpu : yes
    fpu_exception : yes
    cpuid level : 4
    wp : yes
    flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse36 clflush mmx fxsr sse sse2 syscall nx lm rep_good nopl pni hypervisor
    bogomips : 5867.08
    TLB size : 1024 4K pages
    clflush size : 64
    cache_alignment : 64
    address sizes : 40 bits physical, 48 bits virtual
    power management:

    Which location is this? @dediserve

  • sinsin Member

    JarylW said: Which location is this? @dediserve

    This is Dediserve's Dallas location which is also KVM

    Thanked by 1dediserve
  • @sin said:

    Strange because one Natasha Likandy from @dediserve told me

    "All Platforms are identical and uses same hardware and CPU cores." when I asked about and refered to this thread.

  • dediservedediserve Member
    edited October 2015

    There are a tiny number of older hypervisors still about which have x5000 series xeons at 2.9. You can see the 512kb cache versus the 25mb on the e5 2660 we run now as standard.

  • nfnnfn Veteran

    @dediserve said:
    There are a tiny number of older hypervisors still about which have x5000 series xeons at 2.9. You can see the 512kb cache versus the 25mb on the e5 2660 we run now as standard.

    Hello,

    I got this in London and not the 2660:

    user@host:~$ cat /proc/cpuinfo
    processor   : 0
    vendor_id   : GenuineIntel
    cpu family  : 6
    model       : 13
    model name  : QEMU Virtual CPU version (cpu64-rhel6)
    stepping    : 3
    microcode   : 0x1
    cpu MHz     : 2199.998
    cache size  : 4096 KB
    physical id : 0
    siblings    : 1
    core id     : 0
    cpu cores   : 1
    apicid      : 0
    initial apicid  : 0
    fpu     : yes
    fpu_exception   : yes
    cpuid level : 4
    wp      : yes
    flags       : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse36 clflush mmx fxsr sse sse2 syscall nx lm nopl pni cx16 hypervisor lahf_lm
    bogomips    : 4399.99
    clflush size    : 64
    cache_alignment : 64
    address sizes   : 46 bits physical, 48 bits virtual
    power management:
    
  • edited October 2015

    Is there a list that shows which Dediserve Locations are KVM enabled?

  • @nfn that's the e5-2660

    The qemu driver is showing the wrong cache. We're looking at a fix for that.

    Thanked by 1nfn
  • @Admiral_Awesome said:
    Is there a list that shows which Dediserve Locations are KVM enabled?

    At this stage the majority are and that improves weekly as we add new hardware. All clouds deployed in the last 6 months or so are by default too with Toronto and Jakarta on the way.

  • iKockaiKocka Member
    edited October 2015

    Just curious, why don't your new hypervisors come equiped with the newest generation E5-2660 V3 that has 400 MHz higher clock rate per core?

  • dediservedediserve Member
    edited October 2015

    @iKocka said:
    Just curious, why don't your new hypervisors come equiped with the newest generation E5-2660 V3 that has 400 MHz higher clock rate per core?

    Our clouds run exclusively on HP Blade technology.

    At the moment we run BL 460C Gen 8 Blades, which only support up to the V2 E5.

    We plan to slowly move to Gen 9 which supports the E5 V3 (and other nice features) over the next 6-18 months.

    Thanked by 1JarylW
Sign In or Register to comment.