Resultados 1 a 9 de 9
  1. #1
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106

    Virtualizor com Xen PV

    Alguem con experiencia em Xen PV saberia como configurar uma VM para utilizar toda a CPU?

    no virtualizor existem 2 campos:

    CPU Cores
    Recommended Value : 4


    neste endendo que baste colocar o numero total de cores

    e este outro:

    CPU Units
    CPU units to be allocated
    Recommended Value : 256


    que não consegui descobrir qual seria o "ilimitado"
    Siga-nos em nosso twitter: @wht_brasil

  2. #2
    WHT-BR Top Member
    Data de Ingresso
    Nov 2010
    Localização
    Rio de Janeiro - RJ
    Posts
    2,289
    Uma dúvida, que talvez possa lhe ajudar: esses "CPU Cores" são os reais, ou seja, os existentes fisicamente no processador ou aqueles cores virtuais que as plataformas de virtualização criam? A mesma pergunta vale para os "CPU Units".

  3. #3
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106
    Citação Postado originalmente por tekobr Ver Post
    Uma dúvida, que talvez possa lhe ajudar: esses "CPU Cores" são os reais, ou seja, os existentes fisicamente no processador ou aqueles cores virtuais que as plataformas de virtualização criam? A mesma pergunta vale para os "CPU Units".
    os cores são os reais, no caso do servidor em teste são 8 fisicos, mas não sei a resposta para o units...
    Siga-nos em nosso twitter: @wht_brasil

  4. #4
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106
    creio que encontrei:

    Credit-Based CPU Scheduler

    Introduction

    The credit scheduler is a proportional fair share CPU scheduler built from the ground up to be work conserving on SMP hosts. It is now the default scheduler in the xen-unstable trunk. The SEDF and BVT schedulers are still optionally available but the plan of record is for them to be phased out and eventually removed.

    Description

    Each domain (including Host OS) is assigned a weight and a cap.

    Weight

    A domain with a weight of 512 will get twice as much CPU as a domain with a weight of 256 on a contended host. Legal weights range from 1 to 65535 and the default is 256.

    Cap

    The cap optionally fixes the maximum amount of CPU a domain will be able to consume, even if the host system has idle CPU cycles. The cap is expressed in percentage of one physical CPU: 100 is 1 physical CPU, 50 is half a CPU, 400 is 4 CPUs, etc... The default, 0, means there is no upper cap.

    SMP load balancing

    The credit scheduler automatically load balances guest VCPUs across all available physical CPUs on an SMP host. The administrator does not need to manually pin VCPUs to load balance the system. However, she can restrict which CPUs a particular VCPU may run on using the generic vcpu-pin interface.

    Usage

    The xm sched-credit command may be used to tune the per VM guest scheduler parameters.

    xm sched-credit -d <domain> (lists weight and cap)

    xm sched-credit -d <domain> -w <weight> (sets the weight)

    xm sched-credit -d <domain> -c <cap> (sets the cap)

    Algorithm

    Each CPU manages a local run queue of runnable VCPUs. This queue is sorted by VCPU priority. A VCPU's priority can be one of two value: over or under representing wether this VCPU has or hasn't yet exceeded its fair share of CPU resource in the ongoing accounting period. When inserting a VCPU onto a run queue, it is put after all other VCPUs of equal priority to it.

    As a VCPU runs, it consumes credits. Every so often, a system-wide accounting thread recomputes how many credits each active VM has earned and bumps the credits. Negative credits imply a priority of over. Until a VCPU consumes its alloted credits, it priority is under.

    On each CPU, at every scheduling decision (when a VCPU blocks, yields, completes its time slice, or is awaken), the next VCPU to run is picked off the head of the run queue. The scheduling decision is the common path of the scheduler and is therefore designed to be light weight and efficient. No accounting takes place in this code path.

    When a CPU doesn't find a VCPU of priority under on its local run queue, it will look on other CPUs for one. This load balancing guarantees each VM receives its fair share of CPU resources system-wide. Before a CPU goes idle, it will look on other CPUs to find any runnable VCPU. This guarantees that no CPU idles when there is runnable work in the system.

    Glossary of Terms

    ms: millisecond

    Host: The physical hardware running Xen and hosting guest VMs.

    VM: guest, virtual machine.

    VCPU: Virtual CPU (one or more per VM)

    CPU/PCPU: Physical host CPU.

    Tick: Clock tick period (10ms)

    Time-slice: The time-slice a VCPU receives before being preempted to run another (30ms)

    Period: The accounting period (30ms). Once per period, credits earned are recomputed.

    Weight: Proportional share of CPU per guest VM

    Cap: An optional upper limit on the CPU time consumable by a particular VM.
    fonte: CreditScheduler - Xen Wiki
    Siga-nos em nosso twitter: @wht_brasil

  5. #5
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106
    alterei para 65353, reiniciei a VM, mas o resultado ainda foi estranho:

    BYTE UNIX Benchmarks (Version 5.1.2)

    System: srv.teste1.com: GNU/Linux
    OS: GNU/Linux -- 2.6.32-71.29.1.el6.x86_64 -- #1 SMP Mon Jun 27 19:49:27 BST 2011
    Machine: x86_64 (x86_64)
    Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
    CPU 0: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 1: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 2: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 3: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 4: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 5: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 6: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    CPU 7: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.0 bogomips)
    x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization
    14:43:32 up 0 min, 1 user, load average: 0.17, 0.04, 0.01; runlevel 3

    ------------------------------------------------------------------------
    Benchmark Run: Sun Jun 17 2012 14:43:33 - 15:07:41
    8 CPUs in system; running 1 parallel copy of tests

    Dhrystone 2 using register variables 22620358.3 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 2962.1 MWIPS (10.0 s, 7 samples)
    Execl Throughput 1089.0 lps (30.0 s, 2 samples)
    Pipe Throughput 376646.8 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 67933.6 lps (10.0 s, 7 samples)
    Process Creation 2012.5 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 2410.2 lpm (60.0 s, 2 samples)
    Shell Scripts (16 concurrent) 202.5 lpm (60.2 s, 2 samples)
    Shell Scripts (8 concurrent) 426.3 lpm (60.0 s, 2 samples)
    System Call Overhead 442013.3 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 22620358.3 1938.3
    Double-Precision Whetstone 55.0 2962.1 538.6
    Execl Throughput 43.0 1089.0 253.3
    Pipe Throughput 12440.0 376646.8 302.8
    Pipe-based Context Switching 4000.0 67933.6 169.8
    Process Creation 126.0 2012.5 159.7
    Shell Scripts (1 concurrent) 42.4 2410.2 568.4
    Shell Scripts (16 concurrent) --- 202.5 ---
    Shell Scripts (8 concurrent) 6.0 426.3 710.5
    System Call Overhead 15000.0 442013.3 294.7
    ========
    System Benchmarks Index Score (Partial Only) 399.4

    ------------------------------------------------------------------------
    Benchmark Run: Sun Jun 17 2012 15:07:41 - 15:32:03
    8 CPUs in system; running 8 parallel copies of tests

    Dhrystone 2 using register variables 179234840.6 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 23710.5 MWIPS (9.9 s, 7 samples)
    Execl Throughput 1174.1 lps (29.9 s, 2 samples)
    Pipe Throughput 3002238.3 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 29228.7 lps (10.0 s, 7 samples)
    Process Creation 1798.4 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 2588.1 lpm (60.1 s, 2 samples)
    Shell Scripts (16 concurrent) 169.5 lpm (62.3 s, 2 samples)
    Shell Scripts (8 concurrent) 344.0 lpm (60.7 s, 2 samples)
    System Call Overhead 1864098.6 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 179234840.6 15358.6
    Double-Precision Whetstone 55.0 23710.5 4311.0
    Execl Throughput 43.0 1174.1 273.0
    Pipe Throughput 12440.0 3002238.3 2413.4
    Pipe-based Context Switching 4000.0 29228.7 73.1
    Process Creation 126.0 1798.4 142.7
    Shell Scripts (1 concurrent) 42.4 2588.1 610.4
    Shell Scripts (16 concurrent) --- 169.5 ---
    Shell Scripts (8 concurrent) 6.0 344.0 573.3
    System Call Overhead 15000.0 1864098.6 1242.7
    ========
    System Benchmarks Index Score (Partial Only) 835.3

    enquanto que direto no servidor dava:

    Benchmark Run: Sun Jun 10 2012 07:11:36 - 07:35:47
    8 CPUs in system; running 1 parallel copy of tests

    Dhrystone 2 using register variables 13872544.6 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 2876.0 MWIPS (9.9 s, 7 samples)
    Execl Throughput 2209.2 lps (30.0 s, 2 samples)
    Pipe Throughput 808663.7 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 86101.1 lps (10.0 s, 7 samples)
    Process Creation 12615.8 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 5821.6 lpm (60.0 s, 2 samples)
    Shell Scripts (16 concurrent) 1531.4 lpm (60.0 s, 2 samples)
    Shell Scripts (8 concurrent) 2637.0 lpm (60.0 s, 2 samples)
    System Call Overhead 801505.2 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 13872544.6 1188.7
    Double-Precision Whetstone 55.0 2876.0 522.9
    Execl Throughput 43.0 2209.2 513.8
    Pipe Throughput 12440.0 808663.7 650.1
    Pipe-based Context Switching 4000.0 86101.1 215.3
    Process Creation 126.0 12615.8 1001.3
    Shell Scripts (1 concurrent) 42.4 5821.6 1373.0
    Shell Scripts (16 concurrent) --- 1531.4 ---
    Shell Scripts (8 concurrent) 6.0 2637.0 4394.9
    System Call Overhead 15000.0 801505.2 534.3
    ========
    System Benchmarks Index Score (Partial Only) 806.4

    ------------------------------------------------------------------------
    Benchmark Run: Sun Jun 10 2012 07:35:47 - 08:00:00
    8 CPUs in system; running 8 parallel copies of tests

    Dhrystone 2 using register variables 110937292.5 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 22716.1 MWIPS (9.8 s, 7 samples)
    Execl Throughput 18739.4 lps (30.0 s, 2 samples)
    Pipe Throughput 6421280.7 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 2126477.7 lps (10.0 s, 7 samples)
    Process Creation 66507.2 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 30439.3 lpm (60.0 s, 2 samples)
    Shell Scripts (16 concurrent) 2301.7 lpm (60.1 s, 2 samples)
    Shell Scripts (8 concurrent) 4595.0 lpm (60.0 s, 2 samples)
    System Call Overhead 1785023.3 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 110937292.5 9506.2
    Double-Precision Whetstone 55.0 22716.1 4130.2
    Execl Throughput 43.0 18739.4 4358.0
    Pipe Throughput 12440.0 6421280.7 5161.8
    Pipe-based Context Switching 4000.0 2126477.7 5316.2
    Process Creation 126.0 66507.2 5278.3
    Shell Scripts (1 concurrent) 42.4 30439.3 7179.1
    Shell Scripts (16 concurrent) --- 2301.7 ---
    Shell Scripts (8 concurrent) 6.0 4595.0 7658.4
    System Call Overhead 15000.0 1785023.3 1190.0
    ========
    System Benchmarks Index Score (Partial Only) 4897.7

    então, ou o teste dá resultados diferentes para dedicado x vps ou existe uma perda muito grande...
    Siga-nos em nosso twitter: @wht_brasil

  6. #6
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106
    com openvz tambem não ficou bom....

    BYTE UNIX Benchmarks (Version 5.1.2)

    System: srv.teste1.com: GNU/Linux
    OS: GNU/Linux -- 2.6.18-308.el5.028stab099.3 -- #1 SMP Wed Mar 7 15:56:00 MSK 2012
    Machine: x86_64 (x86_64)
    Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
    CPU 0: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.1 bogomips)
    Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
    CPU 1: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (4999.3 bogomips)
    Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
    CPU 2: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (4999.3 bogomips)
    Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
    CPU 3: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (4999.3 bogomips)
    Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
    01:24:26 up 6 min, 1 user, load average: 0.11, 0.14, 0.05; runlevel 3

    ------------------------------------------------------------------------
    Benchmark Run: Mon Jun 18 2012 01:24:26 - 01:50:45
    4 CPUs in system; running 1 parallel copy of tests

    Dhrystone 2 using register variables 7124428.4 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 2859.5 MWIPS (9.9 s, 7 samples)
    Execl Throughput 1481.5 lps (30.0 s, 2 samples)
    Pipe Throughput 482342.5 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 146805.7 lps (10.0 s, 7 samples)
    Process Creation 5344.2 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 1804.0 lpm (60.0 s, 2 samples)
    Shell Scripts (16 concurrent) 133.7 lpm (60.1 s, 2 samples)
    Shell Scripts (8 concurrent) 259.2 lpm (60.2 s, 2 samples)
    System Call Overhead 408331.4 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 7124428.4 610.5
    Double-Precision Whetstone 55.0 2859.5 519.9
    Execl Throughput 43.0 1481.5 344.5
    Pipe Throughput 12440.0 482342.5 387.7
    Pipe-based Context Switching 4000.0 146805.7 367.0
    Process Creation 126.0 5344.2 424.1
    Shell Scripts (1 concurrent) 42.4 1804.0 425.5
    Shell Scripts (16 concurrent) --- 133.7 ---
    Shell Scripts (8 concurrent) 6.0 259.2 432.0
    System Call Overhead 15000.0 408331.4 272.2
    ========
    System Benchmarks Index Score (Partial Only) 410.4

    ------------------------------------------------------------------------
    Benchmark Run: Mon Jun 18 2012 01:50:45 - 02:30:19
    4 CPUs in system; running 4 parallel copies of tests

    Dhrystone 2 using register variables 7075376.9 lps (10.0 s, 7 samples)
    Double-Precision Whetstone 11425.9 MWIPS (9.9 s, 7 samples)
    Execl Throughput 1787.8 lps (30.0 s, 2 samples)
    Pipe Throughput 475186.1 lps (10.0 s, 7 samples)
    Pipe-based Context Switching 144561.7 lps (10.0 s, 7 samples)
    Process Creation 5286.2 lps (30.0 s, 2 samples)
    Shell Scripts (1 concurrent) 1852.0 lpm (60.1 s, 2 samples)
    Shell Scripts (16 concurrent) 142.5 lpm (60.9 s, 2 samples)
    Shell Scripts (8 concurrent) 283.7 lpm (60.3 s, 2 samples)
    System Call Overhead 404126.7 lps (10.0 s, 7 samples)

    System Benchmarks Partial Index BASELINE RESULT INDEX
    Dhrystone 2 using register variables 116700.0 7075376.9 606.3
    Double-Precision Whetstone 55.0 11425.9 2077.4
    Execl Throughput 43.0 1787.8 415.8
    Pipe Throughput 12440.0 475186.1 382.0
    Pipe-based Context Switching 4000.0 144561.7 361.4
    Process Creation 126.0 5286.2 419.5
    Shell Scripts (1 concurrent) 42.4 1852.0 436.8
    Shell Scripts (16 concurrent) --- 142.5 ---
    Shell Scripts (8 concurrent) 6.0 283.7 472.8
    System Call Overhead 15000.0 404126.7 269.4
    ========
    System Benchmarks Index Score (Partial Only) 492.0
    Siga-nos em nosso twitter: @wht_brasil

  7. #7
    Web Hosting Master
    Data de Ingresso
    Aug 2011
    Localização
    /home
    Posts
    896
    Está utilizando o SolusVM?

  8. #8
    Super Moderador
    Data de Ingresso
    Sep 2010
    Localização
    Procurando...
    Posts
    4,106
    Citação Postado originalmente por marcosv Ver Post
    Está utilizando o SolusVM?
    não, o virtualizor
    Siga-nos em nosso twitter: @wht_brasil

  9. #9
    Web Hosting Master
    Data de Ingresso
    Aug 2011
    Localização
    /home
    Posts
    896
    não, o virtualizor
    Interessante ele, vou fazer testes neles amanha. Com Xen.

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
  •