Rate This Document
Findability
Accuracy
Completeness
Readability

Environment Requirements

Hardware Requirements

Table 1 lists the hardware requirements.

Table 1 Hardware requirements

Server

TaiShan 200 server (model 2280)

Processor

Kunpeng 920 processor

Core

2 x 32-core

CPU Frequency

2600 MHz

Memory Capacity

12 x 16 GB

Memory Frequency

2666 MHz

NIC

IN200 NIC (4 x 25GE)

Drive

System drives: RAID 1 (2 x 960 GB SATA SSDs)

Data drives: JBOD enabled in RAID mode (12 x 4 TB SATA HDDs)

RAID Controller Card

Avago SAS 3508

Software Requirements

Table 2 lists the software requirements.

Table 2 Required software versions

Software

Version

OS

CentOS Linux release 7.6.1810 or RHEL 7.5

Ceph

12.2.11

ceph-deploy

2.0.1

Physical Networking Before Capacity Expansion

Figure 1 shows the physical networking before capacity expansion.

Figure 1 Physical networking before capacity expansion

Table 3 describes the cluster plan before capacity expansion.

Table 3 Cluster plan before capacity expansion

Cluster Node

Management IP Address

Public Network

Cluster Network

ceph1

192.168.2.156

192.168.3.156

192.168.4.156

ceph2

192.168.2.157

192.168.3.157

192.168.4.157

ceph3

192.168.2.158

192.168.3.158

192.168.4.158

Table 4 describes the client plan before capacity expansion.

Table 4 Client plan before capacity expansion

Client

Management IP Address

Service Port IP Address

client1

192.168.2.192

192.168.3.192

  • Management IP Address: specifies the IP address used for BMC management (address of the out-of-band management network port).
  • Cluster Network: specifies the internal IP address (of a 25GE network port) used for data synchronization between clusters.
  • Public Network: specifies the external IP address (of a 25GE network port) for compute nodes to access the storage node (block devices).
  • The clients and the front-end network of the cluster must be in the same network segment. 25GE network ports are recommended.
  • Before expansion, the Ceph cluster is deployed on x86 servers. This document uses Huawei FusionServer Pro 2288H V5 servers as an example.

Physical Networking After Capacity Expansion

Figure 2 shows the physical networking after expansion.

Figure 2 Physical networking after capacity expansion

Table 5 describes the cluster plan after capacity expansion.

Table 5 Cluster plan after capacity expansion

Cluster Node

Management IP Address

Public Network

Cluster Network

ceph1

192.168.2.156

192.168.3.156

192.168.4.156

ceph2

192.168.2.157

192.168.3.157

192.168.4.157

ceph3

192.168.2.158

192.168.3.158

192.168.4.158

ceph4

192.168.2.197

192.168.3.197

192.168.4.197

ceph5

192.168.2.198

192.168.3.198

192.168.4.198

Table 6 describes the client plan after capacity expansion.

Table 6 Client plan after capacity expansion

Client

Management IP Address

Service Port IP Address

client1

192.168.2.192

192.168.3.192

  • Management IP Address: specifies the IP address used for BMC management (address of the out-of-band management network port).
  • Cluster Network: specifies the internal IP address (of a 25GE network port) used for data synchronization between clusters.
  • Public Network: specifies the external IP address (of a 25GE network port) for compute nodes to access the storage node (block devices).
  • The clients and the front-end network of the cluster must be in the same network segment. 25GE network ports are recommended.
  • Before expansion, the Ceph cluster is deployed on x86 servers. This document uses Huawei FusionServer Pro 2288H V5 servers as an example.
  • The ceph4 and ceph5 nodes to be added are deployed on TaiShan 200 servers (model 2280).