Resultados 1 a 6 de 6
  1. #1
    Quero ser Guru
    Data de Ingresso
    Jan 2015
    Posts
    77

    [EN] High-Memory Instances and $5 Linodes

    High-Memory Instances and $5 Linodes
    February 14, 2017 12:21 pm
    Happy Valentine’s Day!

    While our standard instances offer a balance of RAM, CPU, and storage and are great for general use-cases, some workloads (and budgets) would benefit greatly from specialization. Because of these varying needs we’re announcing our first specialized instance family: high-memory instances and also a new $5 Linode. The Linode lineup grows.

    High Memory Instances

    High-memory instances are optimized for memory-intensive workloads like high-performance databases, in-memory caching, rendering and data processing. High-memory instances offer a higher ratio of RAM to CPU and storage, start at 16GB of memory and scale up to 200GB, and range from $60 to $960 per month. See the chart below for specifics or visit our simple pricing page.



    $5 plan – Linode 1GB

    We’re also introducing the Linode 1GB, our lowest priced instance ever at only $5 per month. We believe this will add a great deal of utility to our service.



    Resizing

    It’s worth mentioning that Linodes can be easily resized up or down, and even across instance types. Meaning, you can resize your existing Linode up in size, down in size, or even resize a standard instance to become a high-memory instance and vice-versa.

    Eligibility

    Legacy Xen-based Linodes are not eligible to resize into these new plans. You can easily upgrade your legacy Xen-based Linodes to our KVM platform by following the “Upgrade to KVM” link on the right side of your Linode’s dashboard.

    Legacy pre-pay accounts are also not eligible for these new plans. You can easily upgrade your account to hourly billing. Find more information here.

    Linode 2GB Storage Increase

    And finally, the existing Linode 2GB ($10/mo) plan is receiving a free storage upgrade from 24GiB to 30GiB. While the additional space is applied instantly to your Linode, you will need to either resize your existing disk or create a new disk to use the space.

    And finally finally, we’ve also increased the outbound network speed limit on all plans to be at minimum 1000 Mbits. Existing Linodes will need to reboot to pick up the new value, that’s it!

    We’re always looking for ways to improve the ease-of-use and utility of Linode and our platform, so please let us know. We hope you find these new plans useful. Stay tuned; in the coming months we’ll be releasing into beta our new Linode Manager, RESTful API, and block storage service.

    Enjoy!

  2. #2
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,203
    Aparentemente o plano de U$ 5 era 75Mbps unmetered mas foi alterado para 1TB@1G atendendo a gritaria de uma minoria (burra).

    Speed limit é o ...

  3. #3
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,203

    Us$ 5

    Código:
    :~# free
                 total       used       free     shared    buffers     cached
    Mem:       1013056     669284     343772       7764      31000     508680
    -/+ buffers/cache:     129604     883452
    Swap:       524284          0     524284
    Código:
    :~# lscpu
    Architecture:          x86_64
    CPU op-mode(s):        32-bit, 64-bit
    Byte Order:            Little Endian
    CPU(s):                1
    On-line CPU(s) list:   0
    Thread(s) per core:    1
    Core(s) per socket:    1
    Socket(s):             1
    NUMA node(s):          1
    Vendor ID:             GenuineIntel
    CPU family:            6
    Model:                 79
    Model name:            Intel(R) Xeon(R) CPU E5-2697 v4 @ 2.30GHz
    Stepping:              1
    CPU MHz:               2299.990
    BogoMIPS:              4601.64
    Hypervisor vendor:     KVM
    Virtualization type:   full
    L1d cache:             32K
    L1i cache:             32K
    L2 cache:              4096K
    NUMA node0 CPU(s):     0
    Código:
    :~# 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, 1.55826 s, 689 MB/s
    Código:
    Benchmark Run: Thu Feb 16 2017 03:38:18 - 03:59:10
    1 CPU in system; running 1 parallel copy of tests
    
    System Benchmarks Partial Index              BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0   25988667.4   2227.0
    Double-Precision Whetstone                       55.0       4043.6    735.2
    Execl Throughput                                 43.0       5122.4   1191.2
    Pipe Throughput                               12440.0    2178256.0   1751.0
    Pipe-based Context Switching                   4000.0     361028.4    902.6
    Process Creation                                126.0      13861.8   1100.1
    Shell Scripts (1 concurrent)                     42.4       7803.5   1840.5
    Shell Scripts (8 concurrent)                      6.0       1049.8   1749.7
    System Call Overhead                          15000.0    3247189.3   2164.8
                                                                       ========
    System Benchmarks Index Score (Partial Only)                         1421.1
    Código:
    Thu Feb 16 04:08:59 UTC 2017
    Intel(R) Optimized LINPACK Benchmark data
    
    Current date/time: Thu Feb 16 04:08:59 2017
    
    CPU frequency:    2.278 GHz
    Number of CPUs: 1
    Number of cores: 1
    Number of threads: 1
    
    Parameters are set to:
    
    Number of tests: 10
    Number of equations to solve (problem size) : 1000  2000  5000  10000 10000 10000 10000 10000 10000 10000
    Leading dimension of array                  : 1000  2000  5008  10000 10000 10000 10000 10000 10000 10000
    Number of trials to run                     : 4     2     2     2     2     2     2     2     2     2
    Data alignment value (in Kbytes)            : 4     4     4     4     4     4     4     4     4     4
    
    Maximum memory requested that can be used=800204096, at the size=10000
    
    =================== Timing linear equation system solver ===================
    
    Size   LDA    Align. Time(s)    GFlops   Residual     Residual(norm) Check
    1000   1000   4      0.038      17.6089  9.916512e-13 3.381785e-02   pass
    1000   1000   4      0.031      21.7948  9.916512e-13 3.381785e-02   pass
    1000   1000   4      0.031      21.5641  9.916512e-13 3.381785e-02   pass
    1000   1000   4      0.031      21.7695  9.916512e-13 3.381785e-02   pass
    2000   2000   4      0.221      24.1554  4.112481e-12 3.577355e-02   pass
    2000   2000   4      0.222      24.1138  4.112481e-12 3.577355e-02   pass
    5000   5008   4      2.995      27.8411  2.469500e-11 3.443518e-02   pass
    5000   5008   4      2.915      28.6010  2.469500e-11 3.443518e-02   pass
    10000  10000  4      22.714     29.3597  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.699     30.7329  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.555     30.9372  9.741882e-11 3.435086e-02   pass
    10000  10000  4      20.992     31.7675  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.453     31.0852  9.741882e-11 3.435086e-02   pass
    10000  10000  4      20.891     31.9216  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.271     31.3515  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.605     30.8668  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.741     30.6730  9.741882e-11 3.435086e-02   pass
    10000  10000  4      20.926     31.8685  9.741882e-11 3.435086e-02   pass
    10000  10000  4      20.871     31.9525  9.741882e-11 3.435086e-02   pass
    10000  10000  4      20.791     32.0741  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.677     30.7644  9.741882e-11 3.435086e-02   pass
    10000  10000  4      21.864     30.5011  9.741882e-11 3.435086e-02   pass
    Código:
    Performance Summary (GFlops)
    
    Size   LDA    Align.  Average  Maximal
    1000   1000   4       20.6843  21.7948
    2000   2000   4       24.1346  24.1554
    5000   5008   4       28.2210  28.6010
    10000  10000  4       30.0463  30.7329
    10000  10000  4       31.3523  31.7675
    10000  10000  4       31.5034  31.9216
    10000  10000  4       31.1091  31.3515
    10000  10000  4       31.2708  31.8685
    10000  10000  4       32.0133  32.0741
    10000  10000  4       30.6328  30.7644
    
    Residual checks PASSED
    
    End of tests
    
    Done: Thu Feb 16 04:14:46 UTC 2017
    Última edição por 5ms; 16-02-2017 às 01:15.

  4. #4
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,203
    Desenhando: um E3-123x tem 8 pCPU, computando ~180GFLOPS. A vCPU da mariola da Linode é 50% mais rápida comparada à pCPU do 1230 -- lembrando que em geral alta utilização sustentada de recursos em VPS não é garantida e pode estar sujeita à sanções, incluindo suspensão temporária e cancelamento do serviço.
    Última edição por 5ms; 16-02-2017 às 01:30.

  5. #5
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,203

    Byte benchmark, Linpack.

  6. #6
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,203
    ...............................

Permissões de Postagem

  • Você não pode iniciar novos tópicos
  • Você não pode enviar respostas
  • Você não pode enviar anexos
  • Você não pode editar suas mensagens
  •