server configuration
Dell / R730XD 2620V4 * 2 16G DDR4 * 4 300G SAS * 2 + 6T SAS * 12
oracle linux 6.9
Basics
RAID0
Composition raid0 manner: one or a plurality of disks, a disk write part of the data, b writing part, ..., by dividing the data into different disks to improve the speed, so the speed of a monolithic disk n (number of disks ) times.
Advantages: performance, a single disc is n times;
Cons: no safety margin, one bad, all finished.
Configuring single disc raid0 command:
/opt/MegaRAID/MegaCli/MegaCli64 -PDlist -aALL | grep "ID" | uniq | awk -F: '{print $2}' | awk '{print $1}'
Enclosure Device ID: 32
## raid0 created for each dish, of parameters:
## cfgLdAdd can create raid0,1,5,6
##[Enclosure Device ID:磁盘slot]
## [WT | WB] raid write strategy: write through (do not write cache) and write back (write cache), sas disk random write performance is rather poor, so setting WB
## [NORA | RA | ADRA] raid read policy: no read ahead (default) | read ahead | adpter read ahead
## [direct, cached] Read Cache: Default direct, generally does not require a cache read
## [CachedBadBBU | NoCachedBadBBU]: the relationship bbu and write cache, [bad bbu, write back changes to write through | bad bbu, still write back]
## A0 raid 卡 adapters
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:0] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:1] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:2] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:3] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:4] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:5] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:6] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:7] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:8] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:9] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:10] WB Direct -a0
/opt/MegaRAID/MegaCli/MegaCli64 -cfgLdAdd -r0 [32:11] WB Direct -a0
## Viewing Device
/opt/MegaRAID/MegaCli/MegaCli64 -cfgdsply –aALL | grep -E "DISK\ GROUP|Slot\ Number"
[@s26.txyz.db.d ~]# fdisk -l | grep '\/dev\/sd'
Disk / dev / sda: 299.4 GB, 299439751168 bytes
/dev/sda1 * 1 2611 20971520 83 Linux
/dev/sda2 2611 5222 20971520 83 Linux
/dev/sda3 5222 7311 16777216 82 Linux swap / Solaris
/dev/sda4 7311 36405 233700352 5 Extended
/dev/sda5 7311 9922 20971520 83 Linux
/dev/sda6 9922 36405 212726784 83 Linux
Disk /dev/sdb: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdc: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdd: 6000.6 GB, 6000606183424 bytes
Disk /dev/sde: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdf: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdg: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdh: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdi: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdj: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdk: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdl: 6000.6 GB, 6000606183424 bytes
Disk /dev/sdm: 6000.6 GB, 6000606183424 bytes
JBOD
JBOD: If yes raid0 horizontal one kind of combination that is a kind of longitudinal JBOD composition, although there are n blocks of the disc, only after a full, writing the second block; a logical combination of a damaged portion is lost data.
Pros: the loss of a disk, lost only part of the data
Cons: Write performance is equivalent to a single disc.
Configuration steps:
## is open JBOD adapter0 /opt/MegaRAID/MegaCli/MegaCli64 -AdpSetProp EnableJBOD 1 -a0 ## to 32: 0 configured JBOD, unfortunately, can not set some parameters raid card /opt/MegaRAID/MegaCli/MegaCli64 -PDMakeJBOD -physdrv[32:0] -a0 ##
Performance Testing
According to the above characteristic point of view, when a plurality of discs, the performance is not comparable in place, but this mfs distributed storage cluster configuration, a single disk requires a single volume, and therefore the pressure measurement scenario is as follows:
- Single disc raid0
- 5 disk raid0
- Monolithic disk JBOD
- 5 disk JBOD
Are two scenarios: random writes, sequential write. Fio employed for pressure measurement.
iops
| seq-write | rand-write | seq-read | rand-read | |
| RAID0 | 95611 | 7098 | 56266 | 3463 |
| JBOD | 463 | 971 | 55593 | 630 |
bandwidth(kb/s)
| seq-write | rand-write | seq-read | rand-read | |
| RAID0 | 382448 | 28393 | 225065 | 13852 |
| JBOD | 1853.2 | 3886.8 | 222374 | 2521.7 |
See the results, feeling multiple disk arrays have no measurable necessary.
in conclusion
Order raid0 single disk write performance of about 200 times JBOD, random write performance is 10 times. The reason may be soft because JBOD raid, raid card does not apply, and write a raid using WB
Both sequential read performance is similar, but the random read performance, RAID0 about five times the JBOD.