JPH04280315A - Storage sub-system - Google Patents

Abstract

PURPOSE:To realize a storage sub-system without the occurrence of a waiting state for the read request of plural continuous data. CONSTITUTION:When the read request of continuous data stored as plural data blocks straddling plural storage devices #1-#4 is used, a read part 4 reads the data block which is accessed next to the data block in the middle of accessing in the storage device #1, for example, by using the spare time of access, when access by a host device is switched from the storage device #1 to the other storage device. The read data is held in an auxiliary storage device 5 till next access.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to the field of information processing, and more particularly to a storage subsystem that combines a plurality of storage devices to store and hold large and continuous data.

0002

[Prior Art] Conventionally, as a means of increasing the capacity of external storage devices and increasing the data transfer speed, there has been a method in which multiple storage devices are connected to a main unit and data is transferred in parallel. Are known.

As an example, a storage subsystem as shown in FIG. 2 has been proposed in order to store and reproduce continuous data without interruption. In FIG. 2, reference numeral 1 denotes a storage unit in which a plurality of (four in FIG. 2) storage devices #1, #2, #3, and #4 are connected in parallel to a host device (not shown).

[0004] In this storage subsystem, a storage unit 1
A synchronization control unit 2 synchronizes the start time of reading and writing between the storage devices #1 to #4, and a storage device that selects the storage devices #1 to #4 to read/write and switches the connection state to the host device. A switching section 3 is added to calculate in advance the holding position of the next data block to be accessed, and a read/write mechanism (not shown) is positioned at that position.

With such a configuration, as shown in FIG. 3, the seek operation time and the rotational wait time associated with the seek operation are concealed, and the seek operation during the conventional write/read operation is avoided. This enables continuous writing/reading of large amounts of necessary data.

[0006] In this system, unlike the case where a large amount of data is held in one storage device, multiple storage devices #1 to
#4 is distributed and held as a data block, and the data is continuously reproduced while the storage devices #1 to #4 are sequentially switched by the storage device switching unit 3. Storage device #1 to #4
The switching procedure is constant regardless of the data type,
Storage devices #1 to #4 are selected in sequence at a cycle of all storage devices #1 to #4, and data in each storage device #1 to #4 is selected.
A tab block is accessed.

[0007] Therefore, unless the same storage device is accessed at the same timing, accesses will not be duplicated in other storage devices, and a plurality of continuous data read requests can be accepted.

For example, in FIG. 3, from point A where reading of the first data block from storage device #1 is completed and access for reproducing the fifth data block is completed, the fifth data block is read. - If it is within the period up to point B where reading of the data block starts, the first storage device #1 is used for reading, for example, the first data block or the first storage device (not shown in FIG. 3). An access request to read the (4N-3)th (N is a natural number) data block held in #1 can be accepted. The same applies to the remaining storage devices No. 2 to No. 4.

[0009] Therefore, the storage subsystem configured in this way can store large amounts of data without interruption for multiple users.
It has the characteristic that it can be provided to the public.

0010

[Problems to be Solved by the Invention] However, in the above-mentioned conventional storage subsystem, when access requests to the same storage device occur at the same timing due to multiple consecutive data read requests, The problem was that it was not possible to tolerate That is, the multiple access capability of the storage subsystem can be effectively utilized only when accesses to the same storage device do not overlap.

The present invention has been made in view of the above circumstances, and its purpose is to allow duplicate accesses to the same storage device at the same time due to multiple consecutive data read requests. An object of the present invention is to provide a storage subsystem that can perform read operations and that does not cause a waiting state for a plurality of consecutive data read requests.

0012

[Means for Solving the Problems] In order to achieve the above object, in claim 1, a plurality of storage devices capable of independently reading and writing operations are combined, and while switching the storage device to be accessed, the plurality of storage devices are connected. multiple days across
In a storage subsystem that reads and writes continuous data consisting of data blocks, the next data block to be accessed in one storage device in response to a continuous data read request is calculated based on the free time for access to that storage device. The present invention is provided with a readout section that reads out data in advance by using the data, and an auxiliary storage device that holds the data read out in advance and from which the held data is read out upon the next access.

[0013] Furthermore, in the second aspect of the present invention, when allocating execution timings for accessing each storage device within a repeated reading cycle that goes around all the storage devices, the reading section reads successive data generated later. The timing closest to the access request is allocated to the access related to the request.

[0014]

According to claim 1, when a request to read continuous data stored as a plurality of data blocks across a plurality of storage devices is issued, for example, if The data block to be accessed next after the data block is read by the reading unit using the free access time when the access by the host device is switched from this storage device to another storage device,
This read data is stored and held in the auxiliary storage device 5. This held data is read out in the next access.

Therefore, even if the same storage device is accessed repeatedly at the same time due to a plurality of continuous data read requests, a waiting state for the read requests does not occur. Further, according to claim 2, when allocating the execution timing of access to each storage device by the reading unit within a repeated read cycle that goes around all the storage devices, the read request for continuous data generated later is For accesses, the timing closest to the access request is allocated.

[0016]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a block diagram showing an embodiment of a storage subsystem according to the present invention, and the same components as those in FIG. 2 showing a conventional example are denoted by the same reference numerals. That is, 1 is a storage device section, #1 to #4 are storage devices, 2 is a synchronization control section, 3 is a storage device switching section, 4 is a reading section, and 5 is an auxiliary storage device. In this embodiment, four storage devices #1 to #4 are configured to continuously record/reproduce a large amount of data.

The reading unit 4 receives a read request from a host device (not shown) via the storage device switching unit 3, and selects the data block to be accessed next to the data block in the storage device currently being accessed. , the read data is read using the free time during which the access by the host device is switched from this storage device to another storage device, and this read data is stored in the auxiliary storage device 5.

Next, the principle of operation of the above configuration will be explained using FIG. 4.

Here, for ease of explanation, storage device #
Focusing on 1, using the free time immediately after reproducing the first data block shown in the figure, the 5 data block shown in the figure is
The th data block is read in advance and this read data is held in the auxiliary storage device 5.

The fifth data block held in the auxiliary storage device 5 is reproduced from the auxiliary storage device 5 at the timing indicated by ■' in the figure when it should originally be reproduced. As a result,■
Since storage device #1 can process the read request for other continuous data that occurs at the timing ', it is possible to allow reading of continuous data that occurs in the same storage device at the same timing.

Needless to say, if there is a read request for other continuous data at the same time as the fifth data block is read out and held in the auxiliary storage device 5, this access will be prioritized and the subsequent access will be Also, switching control is sequentially performed on the auxiliary storage device 5 according to a predetermined procedure. This procedure is exactly the same as normal access.

Thus, the storage subsystem of FIG.
This means that a plurality of successive data read requests can be accepted at any timing.

Next, the relationship among the number of read multiple continuous data, the number of storage devices, and the required storage capacity of the auxiliary storage device, which the storage subsystem according to the present invention has, will be explained using FIG.

As is clear from FIG. 5, the number of multiple accesses Na of the storage subsystem is determined by the period in which the storage device completes one cycle.
In other words, it means how many times data processing, including access, can be executed within the repeated reading period Tc in which one storage device repeatedly reproduces a data block. Therefore, if the number of storage devices is n, the data transfer time is Tt, and the maximum access time of storage devices is Ta, the number of multiple accesses Na of the storage subsystem of the present invention is expressed by the formula (1), and the number of storage devices is n is expressed by formula (2).

Number of multiple accesses Na=(repeated read cycle Tc/data processing time Ts) =nTt/
(Tt+Ta)
...(1) Number of storage devices n=Na(
Tt+Ta)/Tt
...(2) From equations (1) and (2), in order to increase the number of multiple accesses Na, it is necessary to configure the storage subsystem with small-capacity storage devices and increase the number n of storage devices; Furthermore, if the data transfer time Tt is selected so that the maximum access time Ta of the storage device is relatively small with respect to the data transfer time Tt, the number of required storage devices can be reduced. I understand. Finally, when Tt>>Ta, the number Na of multiple accesses approaches the number n of storage devices.

On the other hand, the storage capacity Ms of the auxiliary storage device is determined as shown in equation (3), where Mb is the storage capacity of the data block.

Storage capacity of auxiliary storage device Ms=n・Na・Mb
...(3)
In equation (3), n means that memory for n data blocks corresponding to the number of storage devices is required to reproduce continuous data, and Na means that memory for n data blocks corresponding to the number of storage devices is required to reproduce continuous data. This means that it supports read requests. Formula (3) is replaced by formula (2
), equation (3) can be rewritten as equation (4) below.

Ms=Na2 (M
b/Tt) (Tt+Ta)
=Na2 (Mb/Tt)Ts
...(4) Formula (4)
Here, Mb/Tt is the data transfer rate of the storage device, and Ts is the data processing time required to read one data block. Data transfer speed Mb/T
t and the maximum access time Ta are constants determined by the type of storage device, and no significant improvement is expected. Therefore, it can be seen that in order to reduce the capacity Ms of the auxiliary storage device, it is sufficient to reduce the data block capacity Mb and the data transfer time Tt.

However, if the data transfer time Tt is reduced, it is necessary to increase the number of storage devices according to equation (2), resulting in an increase in cost and space. Therefore, the number of storage devices required for the storage subsystem and the capacity of the auxiliary storage device are determined by their respective balances.

Next, an example of the memory configuration of the auxiliary storage device will be explained using FIG. 6. In the example of FIG. 6, the auxiliary storage device connects continuous data divided into seven storage devices #1 to #7 and records it as a data block with a size corresponding to the repetition period Tc time. By using a pointer PT for reading data that can be set at any timing, data can be reproduced, for example, immediately after writing from the start point STP, or after a time Tc, for example. Furthermore, in response to requests to read four sets of continuous data,
Record and reproduce data simultaneously.

In this example, the storage subsystem consisting of seven storage devices #1 to #7 is sequentially accessed by a continuous data read request, and the address numbers stored in the storage subsystem are in the 000s and 000s. A case is shown in which four consecutive pieces of data starting from the 100s, 200s, and 300s are read.

Access requests 1, 2, and 4 are generated at the same timing in storage device #1, and access request 1, which is generated from the earliest continuous data read request, causes the storage device to perform the data originally. The data is read at the farthest point from the position where the data is read. Therefore, access request 1
The pointer PT1 to the start point STP
located farthest from. Next, the generated access request 2 is originally supposed to follow the access request 1, but since the access request 3 that occurred after that occurred at a timing with no overlap, it is given priority, and the access request 2 is given priority. It is later. The access request 4 generated last almost receives data transfer directly from the storage device.

Furthermore, the capacity of the auxiliary storage device shown in equation (4) indicates the total capacity of the memory configuration of FIG. 6, and actually, in the memory configuration of FIG. It is sufficient if the storage capacity corresponding to the PT position is secured. If a read request for continuous data occurs at a different timing, as in access request 3, the start point and pointer position almost match, and the auxiliary storage device will be in a state where almost no capacity is required. On the other hand, the maximum storage capacity is required when continuous data read requests are concentrated at the same timing.

In this case, due to the action of the reading section 4,
The pointers are positioned at approximately equal pitches from the start point. Therefore, it can be seen that in reality, the storage capacity of the auxiliary storage device 5 is only half of the value calculated by equation (4).

Specifically, approximately 100 two-hour programs are stored in a magnetic disk device, and services are provided to 100 users at the same time.
Let's calculate the capacity of the auxiliary storage device assuming that it will be used as a service.

Maximum access time Ta of magnetic disk device
= 35ms, video transfer rate = 24Mit/s, data transfer time 15ms, allowable multiple access number Na = 100, and the total storage capacity is 20Tbits.
From equation (2), the storage subsystem consists of 334 storage devices, and from equation (4), the auxiliary storage device 5
The required capacity is about 12 Gbits, and it turns out that in reality, it only needs about half this, about 6 GBits (1/3000 of the total capacity).

Furthermore, in order to reduce the storage capacity, start point SPT and pointer PT in auxiliary storage device 5 can be
It is only necessary to reduce the distance between them, and it is sufficient to add some restrictions to the continuous data read requests, such as not accepting continuous data read requests at the same timing within the cycle Tc of making one circuit around the storage device.

It should be noted that since the auxiliary storage device 5 needs to be able to read data at any timing as described above, it is a FIFO (First In First Out).
A type of semiconductor memory is suitable.

Furthermore, in the above embodiment, an example was shown in which the synchronization control unit 2 was provided to synchronize the storage devices, but since the auxiliary storage device 5 can also absorb the synchronization deviation between the storage devices, the synchronization The control unit 2 is not essential for implementing the present invention.

[0040] Furthermore, it is desirable that the start positions of a plurality of continuous data be distributed to each storage device as #1, #2, #3, . . . .

[0041]

As described above, according to claim 1, in a storage subsystem that stores a large amount of data in a distributed manner in a plurality of storage devices, a plurality of continuous data that are generated one after another can be
data read requests at any timing and up to the maximum capacity of this storage subsystem [(1 data block transfer time x number of storage devices)/(data transfer time + maximum access time)] can. Therefore, compared to conventional storage subsystems, no waiting state occurs for multiple consecutive data read requests.

According to claim 2, in addition to the effects of claim 1, the capacity of the auxiliary storage device can be reduced.

[Brief explanation of the drawing]

FIG. 1 is a configuration diagram showing an embodiment of a storage subsystem according to the present invention.

FIG. 2 is a configuration diagram of a conventional storage subsystem.

FIG. 3 is a diagram illustrating the principle of a conventional configuration.

FIG. 4 is a diagram illustrating the principle of a storage subsystem according to the present invention.

FIG. 5 is a diagram illustrating the principle of a storage subsystem according to the present invention.

FIG. 6 is a diagram showing an example of a memory configuration of an auxiliary storage device according to the present invention.

[Explanation of symbols]

1...Storage unit 2...Synchronization control section 3...Storage device switching unit 4...Reading section 5... Auxiliary storage device

Claims (2)

[Claims] [Claim 1] A plurality of storage devices capable of reading and writing independently are combined, and a plurality of data can be stored across the plurality of storage devices while switching the storage device to be accessed.
In a storage subsystem that reads and writes continuous data consisting of data blocks, the next data block to be accessed in one storage device in response to a continuous data read request is calculated based on the free time for access to that storage device. What is claimed is: 1. A storage subsystem comprising: a reading section that reads out data in advance using the auxiliary storage device; 2. The reading unit, when allocating the execution timing of access to each storage device within a repeated reading cycle that goes around all the storage devices, is configured to perform a readout operation for accesses related to subsequent requests for reading continuous data. 2. The storage subsystem according to claim 1, wherein the storage subsystem allocates timing closest to the access request.