VxRail: Alta latência do vSAN e erros de CRC nas estatísticas de NIC da rede

Summary: Vários hosts vendo erros de CRC altos, levando à latência do vSAN.

This article applies to This article does not apply to This article is not tied to any specific product. Not all product versions are identified in this article.
Check out other resources

Symptoms

  • No cluster >, monitore> a integridade do vSAN: Verificações de MTU (ping com tamanho de pacote grande): Consulte o artigo VxRail: Verificações de MTU (ping com tamanho de pacote grande)
  • Falha intermitente no teste de ping grande do host (verificação de MTU)
  • Altos erros de CRC observados no vSAN vmnics Contadores de estatísticas
esxcli network nic stats get -n vmnic1

 host1
 NIC statistics for vmnic1:
 Receive packets dropped: 0
 Transmit packets dropped: 0
 Total receive errors: 216001
 Receive length errors: 0
 Receive over errors: 0
 Receive CRC errors: 216001
 Receive frame errors: 0

 host2
 NIC statistics for vmnic1:
 Receive packets dropped: 0
 Transmit packets dropped: 0
 Total receive errors: 283604
 Receive length errors: 0
 Receive over errors: 0
 Receive CRC errors: 283604
 Receive frame errors: 0

 host3
 NIC statistics for vmnic1:
 Receive packets dropped: 0
 Transmit packets dropped: 0
 Total receive errors: 0
 Receive length errors: 0
 Receive over errors: 0
 Receive CRC errors: 0
 Receive frame errors: 0

 host4
 NIC statistics for vmnic1:
 Receive packets dropped: 0
 Transmit packets dropped: 0
 Total receive errors: 170796
 Receive length errors: 0
 Receive over errors: 0
 Receive CRC errors: 170796

Cause

Erros de CRC altos são sintomas de problemas de camada 1. Pode ser um cabo, SFP ou placa de interface de rede (NIC) com defeito.

As estatísticas acima são uma indicação de que o host1, host2 e host4 estavam recebendo CRC (entrada) do host3, e o host3 pode ser a origem dos erros de CRC que causam problemas de desempenho do vSAN.

Resolution

  1. Para ver o incremento de erros de CRC, execute o comando:
watch esxcli network nic stats get -n=vmnic1 | grep "Receive CRC errors"
  1. Desligue o uplink para vmnic1:
esxcli network nic down -n vmnic1

Nota: Certifique-se de que haja redundância de uplink (por exemplo, vmnic0, vmnic1) antes de alterar o status do link para o estado inativo. Neste ponto, você não deve ver nenhum incremento nos erros de CRC e nenhuma latência de vSAN.
 
  1. Substitua o SFP que está conectado ao uplink1 do vSAN e altere o status do uplink para UP. Considere também substituir o cabo no uplink caso a substituição do SFP não interrompa os erros de CRC.

Affected Products

VMWare Cloud on Dell EMC VxRail E560F, VMWare Cloud on Dell EMC VxRail E560N, VxRail 460 and 470 Nodes, VxRail Appliance Family, VxRail Appliance Series, VxRail G Series Nodes, VxRail E Series Nodes, VxRail E560 VCF, VxRail E560F VCF , VxRail E560N VCF ...

Products

VxRail E560, VxRail E560F, VxRail E560N, VxRail E660, VxRail E660F, VxRail E660N, VxRail E665, VxRail E665F, VxRail E665N, VxRail G560, VxRail G560 VCF, VxRail G560F, VxRail G560F VCF, VxRail P Series Nodes, VxRail P570, VxRail P570F, VxRail P580N , VxRail P670F, VxRail P670N, VxRail P675F, VxRail P675N, VxRail S Series Nodes, VxRail S570, VxRail S570 VCF, VxRail S670, VxRail Software, VxRail V470, VxRail V570, VxRail V570 VCF, VxRail V570F, VxRail V570F VCF, VXRAIL V670F, VxRail VD-4510C, VxRail VD-4520C, VxRail VE-660, VxRail VE-6615, VxRail VP-760, VxRail VP-7625, VxRail VS-760 ...
Article Properties
Article Number: 000182663
Article Type: Solution
Last Modified: 10 Sep 2025
Version:  7
Find answers to your questions from other Dell users
Support Services
Check if your device is covered by Support Services.