TW201740370A - Hard disk data wiping method, server and system - Google Patents

Abstract

A hard disk data wiping method, a server and a system, the method comprising: transmitting a data write command to a disk cluster device; writing first-type data to the plurality of hard disks mounted on the disk cluster to overwrite original data. The method can be used for wiping data from a hard disk in an efficient and non-destructive way.

Description

Hard disk data erasing method, server and system

The present invention relates to the field of computer technologies, and in particular, to a hard disk data erasing method, a server, and a system.

Mechanical hard drives (such as Hard Disk Drives, HDDs) and Solid State Drives (SSDs) are storage components commonly used in data centers, each with its own advantages. For example, solid-state hard disks have advantages in data reading speed, seismic resistance, power consumption, running sound, and heat generation; mechanical hard disks have the advantages of large capacity and low price.

For various reasons, storage components need to be taken out of the data center. In view of data security and related specifications, the data carried on the storage element must be effectively destroyed before the data center is taken out to avoid data leakage. In addition, in the case of fault replacement, relocation, etc., it is also necessary to erase the data.

The current data destruction in some data centres uses permanent destruction of hard drives, such as permanent physical damage to hard drives. After such physical damage, the existing data on the magnetic disk cannot be recovered, but at the same time, the end of the life of the hard disk directly leads to the failure of the hard disk to fully utilize its entire service life, thus increasing the maintenance of the data center. cost.

One of the technical problems solved by the present invention is to provide a hard disk data erasing method, a server and a system.

According to an embodiment of an aspect of the present invention, a hard disk data erasing method is provided, the method comprising: transmitting a data write command to the disk cluster device; and by using the data write command, A plurality of hard disks mounted on the disk cluster write the first type of data to cover the original data.

Optionally, after the data writing operation, the method further includes: sending a verify read command to the disk cluster device to initiate a read verify operation; and according to the verify read command, from the magnetic cluster The mounted plurality of hard disks read the data in parallel; and judge whether the read data is the duplicate data or the random data, thereby completing the verification.

Optionally, before initiating the data writing operation, the method further includes: controlling to start a plurality of hard disks mounted on the disk cluster device, and determining whether there is an unrecognizable hard disk; for an unrecognizable hard disk, Issue an indication for hot swap replacement.

Optionally, the method further includes: generating and saving an operation log for each controlled hard disk, where the operation log records the command and task completion status of the hard disk being executed during the operation.

Optionally, the method further includes: providing an erasing configuration interface to the user; receiving a configuration option input by the user on the erasing configuration interface, and performing erasing control according to the information of the configuration option; the configuration options include: Whether to erase the system hard disk, the model of the hard disk to be erased, and / or erase mode.

Optionally, the method further includes: setting one or more SAS control modules respectively corresponding to the one or more magnetic chip cluster devices; and implementing, in the SAS control module, the SAS control module by using a SAS expander The hard disk array layout of multiple hard disks mounted by the corresponding disk cluster device.

Optionally, the method further includes: configuring, in the SAS control module, the SAS expander to be a multi-stage cascading mode; and expanding the number of controlled hard disks and the parallelism by using a multi-level cascaded multi-layer SAS expander.

Optionally, before the data write operation or after the read verify operation, the method further includes: expanding from the highest-level SAS expander to the first-level SAS according to the cascading manner of the multi-level cascaded multi-layer SAS expander The order of the devices, in turn, starts the hard disk corresponding to each level of the SAS expander.

Optionally, the method further includes: analogizing a hard disk fault recognition panel corresponding to the hard disk array layout; and viewing the status of each hard disk and locating the hard disk with abnormal status by using the hard disk fault recognition panel.

Optionally, the method controls one or more external magnetic cluster device devices by using the SAS protocol, and writes the first type of data to the hard disk mounted by the magnetic disk cluster in parallel, so that the magnetic disk cluster is The data of multiple hard disks mounted on the device is erased in batches.

Optionally, the first type of data is preset data, duplicate data, random data, or template data.

According to an embodiment of another aspect of the present invention, a hard disk data erasing server is provided, the server comprising: a write operation control module, configured to send a data write command to the disk cluster device; Controlling writing to a plurality of hard disks mounted by the slice cluster by the data write command The first type of information, thus covering the original data.

Optionally, the method further includes: a read verification control module, configured to send a verification read command to the magnetic chip cluster device, initiate a read verify operation; and according to the verify read command, from the magnetic disk The plurality of hard disks mounted by the cluster read the data in parallel; and, determining whether the read data is the duplicate data or the random data, thereby completing the verification.

Optionally, the method further includes: a hard disk boot recognition module, configured to control a plurality of hard disks mounted on the magnetic disk cluster device, and determine whether there is an unrecognizable hard disk; and, for unrecognizable A hard disk that issues an indication for hot swap replacement.

Optionally, the method further includes: an operation log module, configured to generate and save an operation log for each controlled hard disk, where the operation log records a command executed by the hard disk during the operation, and a task completion status. .

Optionally, the method further includes: erasing the configuration interface module, configured to provide an erase configuration interface to the user; and receiving configuration options input by the user on the erase configuration interface, according to the configuration option information The erase control is performed; the configuration options include: whether to erase the system hard disk, the model of the hard disk to be erased, and/or the erase mode.

Optionally, the method further includes: one or more SAS control modules respectively corresponding to the one or more magnetic chip cluster devices, and configured to implement a magnetic chip cluster device corresponding to the SAS control module by using a SAS expander The hard disk array layout of multiple hard disks mounted.

Optionally, the SAS control module is further configured to configure the SAS expander to be a multi-stage cascading mode, and the multi-level cascading multi-layer SAS expander is used. Expand the number of hard disks and parallelism controlled.

Optionally, the SAS control module is further configured to start according to the cascading manner of the multi-level cascaded multi-layer SAS expander according to the sequence from the highest-level SAS expander to the first-level SAS expander. The hard disk corresponding to each level of SAS expander.

Optionally, the method further includes: a hard disk fault recognition panel module for analogizing a hard disk fault recognition panel corresponding to the hard disk array layout; and viewing the state of each hard disk by using the hard disk fault recognition panel A hard disk with an abnormal positioning status.

Optionally, the server controls one or more external magnetic disk cluster devices by using the SAS protocol, and writes the first type of data to the hard disk mounted by the magnetic disk cluster in parallel, so that the magnetic disk is The data of multiple hard disks mounted on the cluster device is bulk erased.

Optionally, the first type of data is preset data, duplicate data, random data, or template data.

According to an embodiment of still another aspect of the present invention, a hard disk data erasing system is provided, the system comprising the server of any of the above, and a magnetic disk cluster device.

It can be seen that the present invention designs and constructs a set of parallel erasing methods suitable for the original data of the hard disk by applying the relatively stable SAS interconnection technology. This program can be used for data erasing in data centers. The invention has the advantage of high parallelism. With the SAS extension, nearly one thousand mechanical hard disks and solid state hard disks can be written in parallel, thereby realizing effective and effective erasing of data. Specifically, the SAS command is directly sent to the disk cluster by the erase server. By means of the SAS card control erasing process, the I/O communication with the hard disk by the operating system is avoided in the erasing process, which greatly saves system resources, and is also a manifestation of the high concurrency mentioned above.

The invention only needs one ordinary server as the machine head, and can complete corresponding data writing, erasing verification, log analysis and bad hard disk recording and the like. The overall investment is controllable, and non-destructive data destruction of nearly a thousand large-capacity hard disks can be completed in a short time. The so-called non-destructive means that the hard disk is non-destructive, and the data is permanently destroyed, and no data fragments remain. Compared with the existing permanent physical damage of the hard disk, the solution of the invention can ensure that the original data is effectively covered, so that the erased mechanical hard disk and the solid state hard disk can still be used.

Those skilled in the art will appreciate that although the following detailed description is made with reference to the illustrated embodiments and drawings, the invention is not limited to these embodiments. Rather, the scope of the present invention is intended to be limited only by the scope of the appended claims.

801‧‧‧Write operation control module

802‧‧‧ read calibration control module

803‧‧‧ Hard disk boot recognition module

804‧‧‧Operation Log Module

805‧‧‧Erase the configuration interface module

806‧‧‧SAS control module

807‧‧‧Fault identification module

Other features, objects, and advantages of the present invention will become more apparent from the aspects of the description of the embodiments illustrated in the claims < FIG. 2 is a schematic diagram showing the principle of hard disk writing data in a hard disk data erasing method according to an embodiment of the present invention; FIG. 3 is a schematic diagram of a data erase top layer architecture in a hard disk data erasing method according to an embodiment of the present invention; FIG. 4 is a schematic diagram of an extended manner of a SAS control module in a hard disk data erasing method according to an embodiment of the present invention; FIG. 6 is a schematic diagram showing a process of erasing and erasing a hard disk data erasing method according to an embodiment of the present invention; FIG. 7 is a schematic diagram of a shutdown erasing process in a hard disk data erasing method according to an embodiment of the present invention; FIG. 8 is a schematic structural diagram of a hard disk data erasing server according to an embodiment of the present invention. FIG.

Those skilled in the art will appreciate that although the following detailed description is made with reference to the illustrated embodiments and drawings, the invention is not limited to these embodiments. Rather, the scope of the present invention is intended to be limited only by the scope of the appended claims.

Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as a process or method depicted as a flowchart. Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. In addition, the order of operations can be rearranged. The process may be terminated when its operation is completed, but may also have additional steps not included in the drawing Step. The processing may correspond to methods, functions, procedures, sub-routines, sub-programs, and the like.

The computer device includes a user device and a network device. The user equipment includes, but is not limited to, a computer, a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud-based computing system ( Cloud Computing is a cloud of computers or web servers. Cloud computing is a kind of decentralized computing. It is a super virtual computer composed of a group of loosely coupled computers. Wherein, the computer device can be operated separately to implement the present invention, and can also access the network and implement the present invention by interacting with other computer devices in the network. The network where the computer device is located includes, but is not limited to, an internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

It should be noted that the user equipment, the network equipment, the network, and the like are merely examples, and other existing or future computer equipment or networks may be applicable to the present invention, and should also be included in the scope of the present invention. Within, and by reference.

The methods discussed below (some of which are illustrated by flowcharts) may be implemented by hardware, software, firmware, mediation software, microcode, hardware description language, or any combination thereof. When implemented in software, firmware, mediation software, or microcode, the code or code segments used to perform the necessary tasks can be stored in a machine or computer readable medium (such as a storage medium). The processor(s) can perform the necessary tasks.

The specific structural and functional details disclosed herein are merely representative. It is also an object for describing an exemplary embodiment of the present invention. The present invention may, however, be embodied in many alternative forms and should not be construed as being limited to the embodiments set forth herein.

It should be understood that although the terms "first," "second," etc. may be used herein to describe the various elements, these elements should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, a first unit could be termed a second unit, and similarly a second unit could be termed a first unit, without departing from the scope of the exemplary embodiments. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

It will be understood that when a unit is referred to as "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present. In contrast, when a unit is referred to as being "directly connected" or "directly coupled" to another unit, there is no intermediate unit. Other words used to describe the relationship between the units should be interpreted in a similar manner (eg "between" and "directly between" and "adjacent to" Than "directly adjacent to", etc.).

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It will also be understood that the terms "comprising" and / or "comprising", as used herein, are intended to mean the stated features, integers, steps, operations, units and The existence of elements or components, without the exclusion or addition of one or more other features, integers, steps, operations, units, elements and/or combinations thereof.

It should also be noted that, in some alternative implementations, the functions/acts noted may occur in a different order than that illustrated in the drawings. For example, two figures shown in succession may in fact be executed substantially concurrently or sometimes in the reverse order, depending on the function/acts involved.

First, the terminology that appears in the embodiment of the present invention is explained: SAS (Serial Attached SCSI) is a magnetic disk connection technology that combines the advantages of parallel SCSI and serial connection technology, and adopts SCSI-3 extension. The instruction set is compatible with SATA devices and is a multi-level storage device connection protocol stack.

SAS Expander (SAS Expander) is a functional module in the SAS protocol. It is used to connect multiple SAS devices together, including SAS array cards, SAS hard disks, etc., to form a SAS domain.

The smallest unit of disk file storage management is called "cluster", and the disk cluster device (JBOD device) is a storage device with multiple disk drives installed on one bottom plate.

The first type of data is used to cover the original data to achieve data erasure, including but not limited to preset data, duplicate data, random data or template data. For example, the duplicate data may be all zero data, the random data is data automatically generated by the machine, the preset data is pre-set data, and the template data is data generated according to the preset template. The first type of data is generally meaningless data, as long as the original data is overwritten to achieve data erasure, There are no restrictions on the specific form of the information.

The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings.

1 is a flow chart of a method for erasing a hard disk data according to an embodiment of the present invention, which is used for batch erasing data of a plurality of solid state hard disks or mechanical hard disks, wherein the erase server is by SAS ( Serial Attached SCSI (Serial Attached SCSI) protocol controls one or more Just a Bunch Of Disks (JBOD) devices to batch wipe the data of multiple hard disks mounted on the disk cluster device. except.

The method of this embodiment mainly includes the following steps: S100, the erasing server controls a plurality of hard disks mounted on the boot disk cluster device, and determines whether there is an unrecognizable hard disk; for the unrecognizable hard disk, issues Instructing to perform hot swap replacement; S101, the erase server sends a data write command to the disk cluster device, and writes the first type to the plurality of hard disks mounted by the disk cluster in parallel by the data write command Data, thereby covering the original data; S102, the erasing server sends a verification read command to the magnetic chip cluster device, initiates a read verify operation; according to the check read command, multiple hard loads are mounted from the magnetic disk cluster The disc reads the data in parallel; determines whether the read data is the first type of data, thereby completing the verification.

In the embodiment of the present invention, the hard disk includes, but is not limited to, a high-density storage device such as a mechanical hard disk (such as a hard disk drive, a Hard Disk Drive, HDD) and a solid state disk (SSD).

In this embodiment, the erase server uses the SAS protocol and mounts the hard disk. The magnetic disk cluster communicates to perform data erasing operation on the hard disk mounted on the magnetic disk cluster. SAS is a magnetic disk connection technology that combines the advantages of parallel SCSI and serial connection technology. It uses a SCSI-3 extended instruction set and is compatible with SATA devices. It is a multi-layer storage device connection protocol stack. Magnetic chip cluster (JBOD) devices are an important type of storage device in the storage field. A JBOD device is a storage device with multiple disk drives mounted on a backplane. Also commonly known as Span. Unlike RAID arrays, JBOD has no front-end logic to manage the distribution of data on the disk. Instead, each disk is individually addressed as a separate storage resource, either as part of the host software or as an adapter card for the RAID group.

Specifically, the erasing server is responsible for the faulty hard disk identification (S100), initiating data writing to implement data erasing (S101), reading verification (S102), and the like.

Step S100 is a preparation step of erasing the data, mainly for checking whether all the hard disks are started, determining whether there is a problem such as a failure of the hard disk, and being unrecognizable, and informing the engineer of the hot swap replacement process for the unrecognized hard disk. It can be understood that S100 is an optional preparation step, which is not necessary, that is, this step can be omitted.

Step S101 is a step of completing the data erasing. The erase server sends a data write command to the disk cluster device to initiate a data write operation; according to the data write command, the first type of data is written in parallel to the plurality of hard disks mounted by the disk cluster, thereby overwriting the original There is information. The first type of information here, for example, may be all 0 data, or random data, as long as the original data is overwritten to achieve data erasure, the specific form of the first type of data is not made. limit.

In order to implement write control of the first type of data on the hard disk, it can be implemented by setting a SAS control module in the erase server. Specifically, one or more SAS control modules corresponding to the number of disk cluster devices are set in the erasing server (ie, each SAS control module controls one disk cluster device); in the SAS control module, The hard disk array layout of the plurality of hard disks mounted by the corresponding disk cluster device is implemented by the SAS expander (SAS Expander). Among them, SAS Expander is a functional module in the SAS protocol, which is used to connect multiple SAS devices together, including SAS array cards, SAS hard disks, etc., to form a SAS domain. SAS Expander can connect multiple SAS to a limited number of hosts. In the SAS domain, SAS Expander can serve as a central exchange and can directly connect to end devices.

In order to achieve the expansion of the number and parallelism of the controlled hard disk, a multi-level cascading manner of a multi-layer SAS expander can be adopted. For example, in the SAS control module, a multi-level cascading mode of a four-layer SAS expander is configured; and a multi-level cascading four-layer SAS expander is used to expand the number and parallelism of the controlled hard disks. In the multi-stage cascading mode in which the multi-layer SAS expander is adopted, before the data write operation or after the read verify operation, the order of starting the SAS expanders and the corresponding hard disks at each level is: multi-level SAS expansion according to multi-level cascade The cascading mode of the device starts the hard disk corresponding to each level of the SAS expander in sequence according to the order from the highest-level SAS expander to the first-stage SAS expander. For example, suppose you use a four-layer SAS expander: level1, level2, level3, level4, where level4 is the highest level, then the order of startup is The order of level4, level3, level2 to level1.

Step S102 is mainly to verify whether the written data is a predefined first type of data after the data erasing is completed. It can be seen that this step is mainly for determining the correctness of the data erasing, and is an optional step, not an essential step.

Optionally, a hard disk fault recognition panel corresponding to the layout of the hard disk array (such as a software control interface) can be analogized; the hard disk fault recognition panel is used to view the status of each hard disk and locate the hard disk with abnormal status. .

Optionally, an operation log may also be generated and saved for each controlled hard disk, and the operation log records commands executed by the hard disk during the operation, task completion, and the like.

Optionally, the user can also customize the erase mode, and the user can select a suitable erase mode according to his business scenario. Specifically, the user is provided with an erasing configuration interface; receiving configuration options input by the user on the erasing configuration interface, including: erasing the system hard disk, the model of the hard disk to be erased, and/or , erase the way.

The hard disk in the present invention includes, but is not limited to, a high-density storage device such as a mechanical hard disk or a solid state hard disk. For the sake of intuition, the embodiment of the method of the present invention will be described in detail below by taking a mechanical hard disk as an example.

The present invention writes multiple hard disks in parallel to cover existing content on the hard disk surface. Therefore, the selected fixed data mode, such as the all-zero mode or the random number mode, changes the content recorded by the disk to meaningless data. This action includes erasing all the magnetic regions of the hard disk to avoid any information leakage caused by content residue.

2 is a schematic diagram showing the principle of hard disk writing data in the hard disk data erasing method according to an embodiment of the invention. As shown in FIG. 2, the hard disk surface is covered with a soft magnetic material, which can magnetize the storage medium particles into N->S or S->N two-week different magnetic field directions, and respectively represent the recorded The bit is 0 or 1. The magnetization process achieves magnetic fields in different directions by changing the direction of the current of the energized coil wound on the head in the figure. Therefore, the mechanical hard disk writes the data to directly maintain or reverse the reasonable magnetization direction of the media and directly overwrite the original data with new data, and the entire process does not need to be erased. Therefore, hard disk erasure is to rewrite existing data into unrealistic data, such as all-zero data or random data, which means that the original information cannot be recovered. When the entire magnetic area of the entire hard disk is rewritten, the hard disk can successfully declare that the data security requirements have been met, and there is no possibility of data leakage. The mechanical hard disk thus processed is equivalent to the entire hard disk being written once, and the hard disk itself is not damaged, so that the usability can be maintained.

3 is a schematic diagram of a top-level architecture of data erasing in a hard disk data erasing method according to an embodiment of the invention.

The data provided by the present invention erases the top-level architecture and is mainly composed of two parts:

(1) Wipe the server (head): Erasing the server (head) as the initiator of the data write, the control end of the erase operation, the check management end, and the fault record end. The invention can use only one physical server to realize simultaneous erasure of nearly one thousand mechanical hard disks and related work, and has high resource utilization efficiency.

(2) Plug-in JBOD device: erase server via SAS cable Connect to an external JBOD device, and each JBOD device internally mounts multiple mechanical hard disks. All hard drives are presented in the form of "block" devices on the servo head. The servo head directly controls each hard disk and performs corresponding operations.

In this example, a two-way structure is used, and two SAS cards (SAS control modules) are installed inside the erasing server to expand to each of the hard disks of the respective external JBOD devices. The SAS card is connected to the server CPU and memory system through the PCIe bus. The bandwidth of the single channel is the bandwidth of the PCIe bus. For example, PCIe 3.0 x 8 can achieve a bandwidth of up to 8GB/sec. For mechanical hard disks. A device with low throughput performance can increase the concurrency to write to a large number of hard disk devices at the same time.

Let's take a look at the SAS extension.

Referring to FIG. 4, it is a schematic diagram of an extended manner of a SAS control module in a hard disk data erasing method according to an embodiment of the present invention. 4 shows an expanded architecture of the present invention. For the sake of simplicity, A represents SAS expander A, B represents SAS expander B, and SAS expander B is connected to a plurality of hard disks. With the SAS expander, the interconnect of the present invention continues to extend downward. A single SAS control module drives two paths in parallel, each of which is extended in four stages. SAS expander A has N-way SAS 3.0 channels, while SAS expander B has M-way SAS 3.0 channels, where N>M. By means of the four-layer SAS expander cascading mode as shown in FIG. 4, the purpose is to increase the number of hard disks that can be connected, thereby increasing the degree of parallelism.

Referring to FIG. 5, it is a schematic diagram of a boot erase process in a hard disk data erasing method according to an embodiment of the present invention. The method includes the following steps: S501: booting the highest level, that is, the fourth level (level 4) hard disk; S502: start a secondary level, that is, a third level (level 3) hard disk; S503: start a lower level, that is, a second level (level 2) of the hard disk; S504: start the lowest level, that is, the first level (level 1) of the hard disk; S505 : Start the erase server; S506: Write the first type of data to all visible hard disks in parallel.

Referring to FIG. 6, which is a schematic diagram of a shutdown erasing process in a hard disk data erasing method according to an embodiment of the present invention.

S601: all hard disk erasing is completed and the read verification is completed; S602: booting the highest level, that is, the fourth level (level 4) hard disk; S603: starting the secondary high level, ie, the third level (level 3) hard disk; S604: starting again The lower level is the second level (level 2) hard disk; S605: the lowest level is the first level (level 1) hard disk; S606: the erasing server is started.

In the implementation of the method, there are also the following aspects to be considered. After the plug-in JBOD device is turned on step by step and the erase server is started, the first round will detect the unrecognized hard disk in the server. If any hard disk is inoperable, do a hot swap replacement to start writing data to overwrite the original information. The hot-swappable replacement hard disk will also be tested for offline hard disk and labeled as a bad hard disk that is not working properly. Since the written data is all 0 data, the written data is fixed. Therefore, the amount of user data transmitted from the server is very low, and the main transmission information is control information such as relay data. Write data can be directly cached in the cache module inside the hard disk.

To ensure that all zero fields are successfully written to all the magnetic areas of the hard disk to overwrite the existing content, the read verification operation can be performed after the data is written. Specifically, the data is written After entering, the server starts the read data operation and directly checks whether the data written to the magnetic area is all zero. The read check is performed synchronously with the write cover, and the two deliberately staggered a certain physical interval. Therefore, after writing a full hard disk, the read verification will also be completed in a short time. Both write overwrite and read verify take sequential write and sequential readout to maximize the throughput of the hard disk being manipulated, thus reducing the time for data erase.

In the data erasing, corresponding to each erased hard disk, an operation log can be generated by erasing the server. The operation log records in detail the commands executed by the nearly one thousand hard disks in the respective erases and the completion of the tasks, ensuring that records are retained for each operation. The operation log record will be used in subsequent steps. For example, when the storage disk is taken out of the data center, combined with the serial number of each hard disk, the relevant operation log will be scanned to confirm the hard. The disc has been erased correctly and effectively.

In order to effectively monitor the erasing process, especially to identify the hard disk that has failed during the erasing process, it can be observed by a hard disk fault recognition panel implemented by software. FIG. 7 is a schematic diagram of a hard disk fault identification panel in a hard disk data erasing method according to an embodiment of the present invention. The number of rows Nch represents the number of channels, and the number of columns Ndr represents the number of erased hard disks in each channel. The hard disk is indicated by small dots. During the entire data erasing process, any abnormal situation that occurs on any hard disk at any time for any reason will be reflected by this panel. Based on clear instructions, field engineers can quickly locate the problematic hard drive and replace it accordingly. The fault identification panel receives control signals transmitted from the SAS card and its various levels of SAS expanders and generates a corresponding dynamically updated user interface.

It can be seen that the present invention designs and constructs a set of parallel erasing methods suitable for the original data of the hard disk by applying the relatively stable SAS interconnection technology. This program can be used for data erasing in data centers. The invention has the advantage of high parallelism. With the SAS extension, nearly one thousand mechanical hard disks and solid state hard disks can be written in parallel, thereby realizing effective and effective erasing of data. Specifically, the SAS command is directly sent to the disk cluster device by the erasing server, and the erasing process is controlled by the SAS card, thereby avoiding the I/O being performed by the operating system and the hard disk during the erasing process. O communication, which greatly saves system resources, is also a manifestation of the high concurrency mentioned above.

The invention has the characteristics of high concurrency and high efficiency, and can write nearly 1000 hard disks in parallel. At the same time, only one ordinary server is needed as the head, and the corresponding data writing, erasing verification, log analysis and bad hard disk recording can be completed. The overall investment is controllable, and non-destructive data destruction of nearly a thousand large-capacity hard disks can be completed in a short time. The so-called non-destructive means that the hard disk is non-destructive, and the data is permanently destroyed, and no data fragments remain. Compared with the existing permanent physical damage of the hard disk, the solution of the invention can ensure that the original data is effectively covered, so that the erased mechanical hard disk and the solid state hard disk can still be used.

The invention supports the user self-ordering erasing mode, and the user can select an appropriate erasing mode according to his own business scene, such as whether to erase the SDA system disk, the type of the hard disk to be erased, and the erasing mode.

An embodiment of the present invention provides a hard disk data erasing server corresponding to the foregoing method, wherein one or more external magnetic disk cluster devices are controlled by the SAS protocol, thereby being mounted on the magnetic disk cluster device. Multiple hard drives The data is bulk erased.

Referring to FIG. 8, the server includes: a write operation control module 801, configured to send a data write command to the disk cluster device to initiate a data write operation; and, by using the data write command, control The plurality of hard disks mounted by the cluster of magnetic disks write the first type of data in parallel to cover the original data.

Optionally, the server further includes: a read verification control module 802, configured to send a verify read command to the magnetic chip cluster device, initiate a read verify operation; and according to the check read command, And storing, by the plurality of hard disks mounted by the cluster of magnetic disks, data in parallel; and determining whether the read data is the first type of data, thereby completing verification.

Optionally, the server further includes: a hard disk boot recognition module 803, configured to control a plurality of hard disks mounted on the magnetic disk cluster device, and determine whether there is an unrecognizable hard disk; and An indication for hot swap replacement is issued for an unrecognized hard drive.

Optionally, the server further includes: an operation log module 804, configured to generate and save an operation log for each controlled hard disk, where the operation log records a command that the hard disk is executed during the operation. , task completion.

Optionally, the server further includes: an erase configuration interface module 805, configured to provide a wipe configuration interface to the user; and receive a user input on the erase configuration interface. The option is to perform erasing control according to the information of the configuration option; the configuration options include: whether to erase the system hard disk, the model of the hard disk to be erased, and/or the erasing mode.

Optionally, the server further includes: one or more SAS control modules 806 respectively corresponding to the one or more magnetic chip cluster devices, configured to implement the SAS control module by using a SAS expander A hard disk array layout of multiple hard disks mounted by a disk cluster device.

Optionally, the SAS control module 806 is further configured to configure the SAS expander to be a multi-stage cascading mode, and expand the controlled number of hard disks and the parallelism by using a multi-level cascaded multi-layer SAS expander.

Optionally, the SAS control module 806 is further configured to perform, according to the cascading manner of the multi-level cascaded multi-layer SAS expander, according to the order from the highest-level SAS expander to the first-level SAS expander. Start the hard disk corresponding to each level of SAS expander.

Optionally, the server further includes: a fault identification module 807 for analogizing a hard disk fault identification panel corresponding to the hard disk array layout; and viewing the state of each hard disk by using the hard disk fault recognition panel And locate the hard disk with abnormal status.

In addition, the present invention also provides a hard disk data erasing system, the system comprising the server and the magnetic disk cluster device of FIG. 8, wherein the server controls one or more external magnetic devices by a SAS protocol The chip cluster device performs bulk erase of the data of the plurality of hard disks mounted on the disk cluster device.

It should be noted that the present invention can be implemented in a combination of software and/or software and hardware, for example, using a dedicated integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including related material structures) of the present invention can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. Additionally, some of the steps or functions of the present invention may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

Additionally, a portion of the present invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or solution in accordance with the present invention by operation of the computer. The program instructions for invoking the method of the present invention may be stored in a fixed or removable recording medium and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in accordance with The program instructions are executed in the working memory of the computer device. Herein, an embodiment of the present invention includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, The device is triggered to operate based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present invention.

It is apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. therefore, The embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the scope of the appended claims rather than the description All changes in the meaning and scope of equivalent elements are included in the present invention. Any reference signs in the scope of the patent application should not be construed as limiting the scope of the claimed patent. In addition, it is to be understood that the word "comprising" does not exclude other elements or steps. A plurality of units or devices recited in the scope of the system patent application may also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims (23)

A hard disk data erasing method, comprising: sending a data write command to a magnetic disk cluster device; and writing, by the data write command, a first hard disk mounted on the magnetic disk cluster Type information to cover the original data. The method of claim 1, wherein, after the data writing operation, further comprising: transmitting a verification read command to the magnetic chip cluster device; according to the verify read command, from the A plurality of hard disks mounted on the magnetic disk cluster read data in parallel; and determining whether the read data is the duplicate data or random data, thereby completing verification. The method of claim 1, wherein before the initiating the data writing operation, the method further comprises: controlling to start a plurality of hard disks mounted on the disk cluster device, and determining whether there is an unrecognizable Hard disk; for hot-swap replacement instructions for unrecognized hard drives. The method of claim 1, further comprising: generating and saving an operation log for each controlled hard disk, the operation log recording a command that the hard disk is executed during the operation, Task completion. The method of claim 1, wherein the method further comprises: Providing a wiping configuration interface to the user; receiving configuration options input by the user on the erasing configuration interface, and performing erasing control according to the information of the configuration option; the configuration options include: whether to erase the system hard disk, The model of the hard disk to be erased, and / or erased. The method of any one of claims 1-5, further comprising: setting one or more SAS control modules respectively corresponding to the one or more magnetic chip cluster devices; In the SAS control module, the hard disk array layout of the plurality of hard disks mounted by the disk cluster device corresponding to the SAS control module is implemented by the SAS expander. The method of claim 6, further comprising: configuring the SAS expander to be a multi-stage cascading mode in the SAS control module; and expanding by using a multi-level cascaded multi-layer SAS expander The number of hard disks and the degree of parallelism controlled. The method of claim 7, wherein before the data writing operation or after the reading verifying operation, the method further comprises: according to the cascading manner of the multi-level cascaded multi-layer SAS expander, according to the most The order of the advanced SAS expander to the first-stage SAS expander sequentially starts the hard disk corresponding to each level of the SAS expander. The method of claim 6, wherein the package is further included The analog disk fault recognition panel corresponding to the hard disk array layout; the hard disk fault recognition panel is used to view the status of each hard disk and locate the hard disk with abnormal status. The method of claim 1, wherein the one or more external magnetic cluster devices are controlled by the SAS protocol, and the first type of data is written in parallel to the hard disk mounted by the magnetic cluster. Thereby, the data of the plurality of hard disks mounted on the disk cluster device is bulk erased. The method of claim 1, wherein the first type of data is preset data, duplicate data, random data, or template data. A hard disk data erasing server, characterized in that: the server comprises: a write operation control module, configured to send a data write command to the magnetic chip cluster device; and, according to the data write command, control The plurality of hard disks mounted by the cluster of magnetic disks write the first type of data to cover the original data. The server of claim 12, further comprising: a read verification control module, configured to send a verification read command to the magnetic chip cluster device; and according to the verification read command, And reading data from a plurality of hard disks mounted by the cluster of magnetic disks; and determining whether the read data is the duplicate data or random data, thereby completing verification. The server of claim 12, wherein the method further comprises: a hard disk boot recognition module, configured to control a plurality of hard disks mounted on the disk cluster device, and determine whether there is an unrecognizable hard disk; and, for an unrecognizable hard disk, issue a hot plug Pull out the replacement instructions. The server of claim 12, further comprising: an operation log module, configured to generate and save an operation log for each controlled hard disk, wherein the operation log records the hard disk in the Commands and tasks completed during the operation. The server of claim 12, further comprising: an erase configuration interface module, configured to provide a wipe configuration interface to the user; and the receiving user inputs the erase configuration interface The configuration option is to perform erasing control according to the information of the configuration option; the configuration options include: whether to erase the system hard disk, the model of the hard disk to be erased, and/or the erasing mode. The server of any one of claims 12-16, further comprising: one or more SAS control modules respectively corresponding to the one or more magnetic chip cluster devices, The hard disk array layout of the plurality of hard disks mounted by the disk cluster device corresponding to the SAS control module is implemented by the SAS expander. The server of claim 17, wherein the SAS control module is further configured to configure the SAS expander to be a multi-stage cascade manner, and expand the station by using a multi-level cascaded multi-layer SAS expander. control The number of hard disks and the degree of parallelism. The server of claim 18, wherein the SAS control module is further configured to: according to the cascade manner of the multi-level cascaded multi-layer SAS expander, according to the highest-level SAS expander The order of the first level SAS expander sequentially starts the hard disk corresponding to each level of the SAS expander. The server of claim 17, further comprising: a fault identification module for analogizing a hard disk fault recognition panel corresponding to the hard disk array layout; and, by the hard disk fault recognition panel , view the status of each hard disk and locate the hard disk with abnormal status. The server of claim 12, wherein the server controls one or more external magnetic cluster device by the SAS protocol, and writes to the hard disk mounted by the magnetic cluster in parallel. The first type of data is used to bulk erase the data of the plurality of hard disks mounted on the disk cluster device. The server of claim 12, wherein the first type of data is preset data, duplicate data, random data or template data. A hard disk data erasing system, comprising a magnetic disk cluster device and a server according to any one of claims 12-22.