Introduction
We have heard of raid and often discuss raid as an SQL dBA, developer, or architecture engineer. However, many of us are not familiar with raid principles, levels, and how raid affects SQL server performance.
This articleArticleTo make up for this lesson.
Disk Architecture
Today's disk is very similar to the player at 45 rpm in 1970s (transfer/minute) (Do you still remember ?), It is just a media (surface) with an axis (track) and stores data in a disk segment called a sector
Source: http://www.hellodb.net/2011/06/fusionio-performance.html
Test environment: Dell r510, 2 x e5620, 24g, fusion-io iodrive 320g MLC
Test Tool: RedHat Linux 5.3, Oracle Orion 11
Test 1: 8 K random read with an iops of more than 5 W and a throughput of more than 400 m. When the response time reaches 4 W, the inflection point (more than 1 ms) appears and rapidly increases to the maximum value of 9.5 Ms.
######################################## ####
more parity information is used to write data slower than RAID1.4. RAID10RAID10, the name can be seen as RAID0 and RAID1 of the combination, obviously need at least 4 pieces of disk. However, first RAID0 after RAID1, or first RAID1 after RAID0, is not the same.RAID01, is to do RAID0 first, and then to 2 groups RAID0 again do RAID1, assuming that at this time a RAID0 broken a disk, this RAID0 is not available, all the IO points to the remaining RAID0;RAID10, is to do RAID1 first, then to 2 group
http://blog.csdn.net/killmice/article/details/42745937
The test tool FIO is read sequentially as an example, with the following commands: fio-name IOPS-RW = Read-bs = 4k-runtime = 60-iodepth 32-filename/dev/sda6-ioengin E Libaio-direct = 1 where rw = read for random reads, BS = 4k for each read 4k, filename specifies the corresponding partition, here I am/dev/sda6, direct = 1 means the cache through Linux Test SATA Hard Drive, SAS hard drive, SSD har
structure. It is completely semiconductor and there is no data search time, delay time, or disk seek time. The data access speed is fast, the Data Reading capability is more than 100 Mb/s, and the maximum is 300 MB/S.
Second, SSD all uses flash memory chips, which are durable and shockproof. Even if a collision with hard objects occurs, the possibility of data loss can be minimized.
Third, thanks to the absence of mechanical components and flash memory chips, SSD has no noise and low power
disk is 10.5 Ms.
The average physical seek time of the 10000 RPM stat hard disk is 7 ms.
The average physical seek time for 15000 rpm SAS hard disks is 5 ms.
The rotation delay of common hard disks is as follows:
The average rotation delay of a 7200 RPM disk is about 60*1000/7200/2 = 4.17 Ms.
The average rotation delay of a 10000 RPM disk is about 60*1000/10000/2 = 3 ms,
The average rotation delay of a disk with 15000 rpm is about 60*1000/15000/2 = 2 ms.
Theoretical Calculation Method for maxim
, and MHzDDR2 memory, 1066 MHz, 1333 MHz, MHzDdr3 memory.
MemoryIt does not have a crystal oscillator, so the clock signal during memory operation isMotherboard chipsetOr directly provided by the clock generator of the motherboard, that is, the memory cannot determine its ownOperating frequencyThe actual working frequency is determined by the motherboard.
Disk
Disk performance indicators
Iops (input/output operations per second)
That is, t
is easy to understand. For example, if you create a tablespace with a size of 10 GB at a time, it is a Sequential operation and a large data transfer operation. If multiple small transactions insert intensive records to a table in the database, it is a Random operation. However, the number of operations supported by a disk per second is certain, for example, 15000 to 250, that is, per second. if the disk is too busy, the CPU will consume resources on iowait. I didn't talk about the major I ment
disk features and application scenarios
The disk is divided into local SSD disk and cloud disk, in which the cloud disk is divided into efficient cloud disk, SSD cloud disk and ordinary cloud disk. The following is an introduction to the characteristics and usage scenarios of these disks.
High Efficiency cloud Disk
SSD Cloud Disk
Common Cloud Plate
Local SSD Disk
High Efficiency cloud Disk
Product Features
The high efficiency cloud disk uses the solid state hard disk and the mechan
Label:In today's article, I'd like to talk about the cool boost in SQL Server 2014: Now you can finally suppress queries based on the IOPS you need! The resource governor (Resource Governor) was introduced from SQL Server 2008, but the functionality offered is limited: You can only limit CPU time (which is already great), and you can limit the amount of queries (from each independent query) to the memory. But as a DBA, you often do some database maint
In today's article, I want to talk about a really cool promotion in SQL Server 2014: Now you can finally suppress the query based on the IOPS you need! The resource governor (Resource Governor) has been introduced from SQL Server 2008, but the functionality provided is limited: You can limit CPU time (which is already great), and you can limit the amount of queries (from each individual query).
But as a DBA, you often do some database maintenance ope
runs on an SSD bare device, however, this type of performance testing software should not be affected. The random write test results on the bare SSD device are as follows:
root@utumno:~# fio ~/rw4krandwrite: (g=0): rw=randwrite, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=64fio 1.59Starting 1 processJobs: 1 (f=1): [w] [100.0% done] [0K/49885K /s] [0 /12.2K iops] [eta 00m:00s]randwrite: (groupid=0, jobs=1): err= 0: pid=1770 write: io=8192.3MB, bw=47666K
delay + transfer timeThe formula for calculating ioPS (IO per second) is:IOPS = 1000ms/Single io timeThree-disk IOPS calculationWhat is the time required for different disks, their seek time, rotation delay, and data transfer?1. Seek timeConsidering that the data being read and written may be on any track in the disk, it is possible to have the most inner ring of the disk (shortest seek time) or the most o
of load determine that all storage devices must have the highest possible performance to cope. The ideal goal is that both types of load can achieve the same performance as the top-level memory in Figure 2. At the same time, it is also expected that it has a non-volatile external memory as shown in the bottom layer of the figure to make up for the problem that data is easy to lose when there is a power failure in the inner. From the memory to the external storage level, we can see that the idea
Windows Azure Platform Family of articles Catalog This article describes the domestic azure China by the century connected operation Readers familiar with the Azure platform understand that the IOPS per disk of Azure VMS is 500. We take the D-series VMs as an example, and the IOPS information is as follows:
virtual machine type
CPU
RAM
temp disk
number of extern
course, depending on the production environment and the application of the situation also need to be treated differently.Data files:1-5MS, more ideal.? 6-20ms, acceptable.? More than 20ms, there will be performance issues that require a solution.Database transaction log:1-2ms, more ideal.? 2-6ms, acceptable.? 6-15ms, need to be optimized.? More than 15ms, there will be performance issues that require a solution.Data Warehouse:Data Warehouse due to the application of the IO type characteristics,
Raid0~raid7, common raid types are RAID0, RAID1, Raid5,raid10.
In addition, depending on how they are connected, they can also be divided into: Direct attached Storage (DAS), Storage area Networks (SAN), Fibre Channel and Storage area NETWORKS,ISCSI Storage area Networks.
Throughput and IOPS Metrics
Throughput depends primarily on the schema of the array, the size of the fibre Channel, and the number of hard drives. The architecture of the array i
Networks. Throughput and IOPS MetricsThroughput depends primarily on the architecture of the array, the size of the fibre Channel, and the number of hard disks. The architecture of the array differs from each array, but there are internal bandwidths, but in general, the internal bandwidth is well designed, not the bottleneck. The second is the impact of Fibre Channel on data traffic, in order to achieve 1GB/S data traffic requirements, we must use t
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.