Electrical computers and digital data processing systems: input/ – Input/output data processing – Input/output access regulation
Reexamination Certificate
2000-05-03
2004-03-30
Ray, Gopal C. (Department: 2181)
Electrical computers and digital data processing systems: input/
Input/output data processing
Input/output access regulation
C710S040000, C711S004000
Reexamination Certificate
active
06715006
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to disk time-sharing apparatus and method for scheduling the use of a disk apparatus on the basis of a plurality of inputs and outputs and, more particularly, to disk time-sharing apparatus and method for scheduling the use of a disk apparatus so as to sequentially switch allocating times for inputs and outputs which compete.
2. Description of the Related Arts
Hitherto, in a storage system for managing data by using a disk apparatus such as a hard disk drive or the like, for example, the disk apparatus is constructed as an apparatus of an RAID structure, the RAID apparatus is connected under domination of a disk control apparatus, and an input/output to/from an upper host is processed, or the RAID apparatus is directly connected to a server and an input/output to/from a server OS is processed. In such a storage system, when a random access in which a guarantee of a response time is requested and a sequential access in which importance is attached to a processing amount per unit time need to be performed to the same disk apparatus, the operation is performed in a time-sharing manner so that the random access and the sequential access do not compete. For instance, in the daytime, an OLTP (On Line Transaction Processing) operation in which the random access is mainly performed is executed to a database of the disk apparatus and, in the nighttime after completion of the OLTP operation, the database is backed up.
(Resource Distribution of Random Access and Sequential Access)
In the storage system, however, in association with the realization of non-stop (fault tolerant) of the operation, the OLTP operation of the random access system needs to be continued even in the nighttime, so that the backup as a sequential access needs to be executed during the OLTP operation of the random access system. In case of only the random access, IOPS (Inputs/Outputs Per Second), for example, 100 IOPS, as the number of inputting/outputting times per unit time which can satisfy a certain average response time, for example, 30 msec can be estimated. In case of only the sequential access, a throughput, for example, 20 MB/sec can be estimated. When the random access and the sequential access are simultaneously performed, however, received input/output requests are processed by a queue using an FIFO. Therefore, there is no mechanism to guarantee a period of time during which the random access can use the disk apparatus and a period of time during which the sequential access can use the disk apparatus. For example, even in the case where the random access of 50 IOPS at an average response time of 30 msec and the sequential access of 5 MB/sec are required, if the sequential access is frequently generated, the throughput of the sequential access rises from 5 MB/sec to 10 MB/sec although it is unnecessary to rise. On the contrary, the IOPS to satisfy the average response time of 30 msec in the random access deteriorates from 50 IOPS to 25 IOPS although the user does not want to reduce it.
(Resource Distribution Between Logic Volumes)
In the conventional storage system, by arranging data having different performance requirements to the different disk apparatuses, respective performance characteristics are derived. For example, data in which a guarantee of a response time is requested in the random access of a small amount of data and data in which importance is attached to a processing amount per unit time in the sequential access of a large amount of data are arranged in the different disk apparatuses. However, in association with the realization of a large capacity of the disk apparatus, the number of cases of arranging data of different performance requirements to the same disk apparatus is increasing. Even when logic volumes of the different performance requirements are arranged to the same disk as mentioned above, a similar problem occurs. Hitherto, there is no mechanism in which the received inputs/outputs are scheduled by the FIFO and a disk resource distribution between the logic volumes is controlled. Therefore, when the input/output to/from some logic volume frequently occurs, input/output performance for the other logic volume deteriorates. For instance, in the case where a volume A in which it is desired to guarantee 10 IOPS and a volume B in which it is desired to guarantee 50 IOPS are arranged to the same disk, if the access to the volume A frequently occurs, the IOPS of the volume A rises from 10 IOPS to 20 IOPS although it is unnecessary to rise. Contrarily, the IOPS of the volume B decreases from 50 IOPS to 40 IOPS although the user does not want to reduce it.
(Resource Distribution Between Ordinary Process and Backup/copying Process)
A case where a plurality of logic volumes exist on the same disk apparatus and a backup or copying process is executed on a logic volume unit basis in the conventional storage system will now be considered. Hitherto, in order to suppress an influence on the ordinary input/output by the backup/copying process, a method whereby a pace (interval) of the backup/copying process is set at the time of executing the backup/copying process. However, when the copying process is executed to the volume B on the same disk apparatus as that of the volume A during the copying process of the volume A, the duplex copying processes are simultaneously operated on the same disk apparatus, so that the influence on the ordinary input/output is doubled.
(Resource Distribution Between Ordinary Process and Rebuilding)
In the RAID apparatus, by making data redundant among a plurality of disk drives, even if a failure occurs in one disk drive, the data can be recovered from the remaining disk drives. Consequently, in the RAID apparatus, even when the failure occurs in any disk drive, the ordinary input/output can be continued. The data is recovered from the remaining disk drives to an exchanged disk drive. The recovering process is called “rebuilding”. Since the rebuilding is accompanied with the input/output process for the disk drives constructing the RAID apparatus, the rebuilding and the ordinary input/output scramble for the same disk drive. Consequently, the performance of the ordinary input/output deteriorates due to the rebuilding. For example, in case of RAID
1
having a mirror structure, the rebuilding is a process for copying data from one disk drive which remains due to the failure of the disk drives to the exchanged new disk drive and a read input/output is generated to the disk drive on the copying source side. The read input/output causes the ordinary input/output to be waited, so that the performance of the ordinary input/output deteriorates. Hitherto, there are two approaches to solve the above problem. According to the first approach, enough small data is copied at an enough long interval so as not to exert an influence on the ordinary input/output. In this case, although the influence on the ordinary input/output can be reduced, a time until the completion of the rebuilding becomes long. For instance, in case of RAID
1
constructed by a disk drive of 9 GB, a time of about 10 hours is needed. According to the second approach, when the disk drive is available, namely, the disk drive is not used in the ordinary input/output, the inputs/outputs of the rebuilding are scheduled. A problem in this case is that the time until the completion of the rebuilding cannot be guaranteed. When the disk drive is hardly available, it takes long time for rebuilding.
(Guarantee of Maximum Response Time)
In a mission critical operation, as requirements of the input/output performance, the maximum response time is important in addition to the average response time. A recent disk apparatus has a re-ordering function for rearranging execution waiting inputs and outputs so as to minimize the processing time. The re-ordering function is such a function that an input/output to minimize a positioning time that is defined by the sum of a seeking time and a rotation waiting time is selected by the disk apparatus as an
Daikokuya Hidejiro
Hotta Yuuji
Ito Mikio
Kato Tadaomi
Take Riichiro
Fujitsu Limited
Ray Gopal C.
Staas & Halsey , LLP
LandOfFree
Disk time-sharing apparatus and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Disk time-sharing apparatus and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Disk time-sharing apparatus and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3234995