大网数据广告活动
服务器运维问答

Stripe Size Raid10 For Vmware - 6X12G 10K 1.8TB Disk H730P Mini Raid Controller

· 52CE 我爱测

Below is our current server configuration. In a few weeks I will be simulating a disaster recovery by installing 7 new disks (1 hot spare) and restoring all VMs from the backups. Will I gain anything by changing the RAID stripe s…

问题原文

原帖链接 · Ferdi KUCUK · CC BY-SA 4.0

Below is our current server configuration. In a few weeks I will be simulating a disaster recovery by installing 7 new disks (1 hot spare) and restoring all VMs from the backups.

Will I gain anything by changing the RAID stripe size to something other than 64KB? The RAID controller has options for 8KB, 16KB, 32KB, 64KB, 128KB, 256KB, 512KB, 1MB.

Any recommendations based on the specification below would be greatly appreciated - thanks.

Hardware:

Dell R630
Dell H730P Mini Raid Controller
2XE5-2670 V3
512GB RAM
12G 1.8TB 10K SAS Disk

    Software:

   Vmware ESX 6.7 U3

    Configuration:

    RAID 10, 128k Stripe Size

已采纳解答

原帖链接 · shodanshok · CC BY-SA 4.0

Generally speaking, selecting a stripe size is a bandwidth vs IOPs tradeoff: smaller stripe size often means higher sequential read/write speed, while bigger stripe size means higher concurrent IOPs (due to less IO spanning multiple disks).

That said, mechanical HDD are highly unbalanced devices: latency dominates until relatively big IO (>= 32 KB) are issued, so stripe element size (or chunk size, in Linux MDRAID parlance) under 64 KB are rarely used (which happens to be the default value).

For a virtualization host, where IOPs are far more important than single-thread sequential speed, I would increase it to 256 KB.

摘自公开归档,保留原文语言,版式经整理,外部媒体与邮箱地址已移除。

资料来源与适用范围

资料来源
Server Fault
适用范围
以原帖系统、软件版本与发布日期为准(2020-03-23)
内容语言
中文;命令、路径和错误标识保留技术原文
本地收录日期
2026-11-15
授权说明
CC BY-SA 4.0

正文与所需资源由本站本地存储。查看来源及更新记录 ↗

请按适用版本和实际日志确认原因;本站没有对每一种系统或设备逐项执行文中的操作。