Browse Prior Art Database

System and method to do data scrubbing of RAID by leveraging array workload regularity

IP.com Disclosure Number: IPCOM000239983D
Publication Date: 2014-Dec-19
Document File: 4 page(s) / 77K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article show a system and method to perform array scrub by leveraging array workload regurity by using and analysing historical data. According to the workload regularity analysised from historical data,array scrubbing can be performed more during light workload and perform less during heavy workload.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 54% of the total text.

Page 01 of 4

System and method to do data scrubbing of RAID by leveraging array workload regularity

System and method to perform array scrub by leveraging array workload regularity


1. Background:

RAID technology has array scrub, which is a background process which verifies that each data and parity block can be read at least once periodically. Array data scrubbing could consume too much FC-AL and XOR bandwidth in large configurations. If there are some host I/O, array scrubbing impacts host I/O.

In current solution, array scrubbing didn't know array workload regularity. Scrubbing is performed in short bursts once every defined period, no matter host I/O is much or less. Generally, to prevent array scrub impact host I/O much, used bandwidth for array scrubbing is always limited to a certain value. No matter the host I/O is heavy or light, the array scrubbing period and used bandwidth it static. I/O workload is bind to array scrubbing.

The drawbacks are: 1. Array scrubbing consumes too much FC-AL and XOR bandwidth. Known solutions are set a threshold of used bandwidth for array scrubbing. This is a very simple way to constraint array scrub. If the host I/O is heavy, array scrub is still on-going and work as normal. This will impact host I/O. When host I/O is light, array scrub won't use additional resource, despite there are enough resource can be used by array scrub.

2. Above lines is about normal IO output, if io output beyond that, it will impact host io; if io output lower than that, some bandwidth will be wasted and won't use them in scrub either.

3. The frequency of array scrub is static and won't be optimized according to host I/O. It has the similar drawback as bandwidth limitation. The frequency of array scrub keeps the same; no matter the host I/O is heavy or light.


2. Summary of Inventions:

Applications always have regularity. In the storage, arrays I/O statistics data can be gathered and saved in repository. With the historical data, arrays workload regularities can be concluded by intelligent analysis. According to the workload regularity, array scrubbing can be performed more during light workload and perform less during heavy workload. Frequency of array scrub and bandwidth of array scrub can be adjusted, according to workload regularity. With the methodology, data scrubbing minimizes the impact to host I/O and does in the most right time. Another advantage is that, the impact of data scrubbing is minimized, hence, the frequency of data scrubbing can be increased and data integrity of array will be protected better, by data scrubbing.


3. Description:

1



Page 02 of 4

Fig.1

2



Page 03 of 4

2014/8/1 0:00-1:00 400K

......

                    …… 2014/8/1 23:00-24:00 350K 2014/8/2 0:00-1:00 50K

......

                    …… 2014/8/2 23:00-24:00 70K ...... ......

2014/9/1 0:00-1:00 400K

......

                    …… 2014/9/1 23:00-24:00 350K 2014/9/2 0:00-1:00 50K

......

                    …… 2014/9/2 23:00-24:00 70K ...... .......