US20050138285A1 - Computer system management program, system and method - Google Patents

Computer system management program, system and method Download PDF

Info

Publication number
US20050138285A1
US20050138285A1 US10/816,552 US81655204A US2005138285A1 US 20050138285 A1 US20050138285 A1 US 20050138285A1 US 81655204 A US81655204 A US 81655204A US 2005138285 A1 US2005138285 A1 US 2005138285A1
Authority
US
United States
Prior art keywords
threshold value
storage
performance
storage apparatus
performance information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US10/816,552
Inventor
Nobumitsu Takaoka
Yasunori Kaneda
Masayuki Yamamoto
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Assigned to HITACHI, LTD. reassignment HITACHI, LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TAKAOKA, NOBUMITSU, KANEDA, YASUNORI, YAMAMOTO, MASAYUKI
Publication of US20050138285A1 publication Critical patent/US20050138285A1/en
Priority to US11/591,038 priority Critical patent/US7216263B2/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0628Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0662Virtualisation aspects
    • G06F3/0665Virtualisation aspects at area level, e.g. provisioning of virtual or logical volumes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/34Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3466Performance evaluation by tracing or monitoring
    • G06F11/3485Performance evaluation by tracing or monitoring for I/O devices
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0602Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061Improving I/O performance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0628Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0653Monitoring storage devices or systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0668Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671In-line storage system
    • G06F3/0683Plurality of storage devices
    • G06F3/0689Disk arrays, e.g. RAID, JBOD
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2201/00Indexing scheme relating to error detection, to error correction, and to monitoring
    • G06F2201/81Threshold
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2201/00Indexing scheme relating to error detection, to error correction, and to monitoring
    • G06F2201/885Monitoring specific for caches

Definitions

  • the present invention relates to a computer system management program for managing a computer system including a computer and a storage apparatus, a recording medium, a computer system, a management apparatus and a storage apparatus thereof, and in particular to a technique for setting a monitoring unit of a computer system by utilizing a hint used in operation of allocating a storage area in a storage apparatus and upon notifying a warning in the monitoring unit, creating an additional message of warning according to the hint and notifying it together with the warning.
  • the monitoring system acquires from respective apparatuses constituting a computer system, a numerical value (mainly, a performance value) indicating the state of the apparatuses and compares the value with a predetermined threshold value. If the former exceeds (is greater than or smaller than) the threshold value, a warning is generated.
  • a numerical value mainly, a performance value
  • JP-A-2002-215230 discloses a method for easily setting an optimal threshold value. This method is as follows. Firstly, a user (administrator of the computer system) specifies the target number of threshold value violations of the numerical value indicating the state of the apparatuses to be managed for the monitoring system. Next, the monitoring system automatically adjusts the threshold value so that the number of threshold value violations of the numerical value indicating the state of the apparatuses to be managed is identical to the specified target threshold value violation number.
  • a large-scale storage apparatus such as a disk array apparatus, especially a storage region provided by a large-scale storage apparatus has become an important item to be managed.
  • a storage area network is now widely used.
  • This storage area network uses a fibre channel (FC) for connecting the computer to the storage apparatus in a network type format, thereby flexibly connecting a computer to a storage apparatus.
  • FC fibre channel
  • IP Internet Protocol
  • SNIA Storage Networking Industry Association
  • SNIA is promoting spread of the storage network through the activity of formulation of the standard specification of the storage network and peripheral technique.
  • SNIA suggests a standard specification for operation of allocating a storage area in a computer in the computer system including the storage apparatus.
  • This specification is applied to management software managing a computer system.
  • this specification is based on CIM (Common Information Model) defined by DMTF (Distributed Management Task Force).
  • a parameter indicating the storage area feature is defined.
  • an administrator creates this parameter for the user purpose of the storage area and inputs it to the management software, thereby creating a desired storage area. This parameter is called “hint”.
  • the management software mounting CIM should handle the hints in mounting operation of the storage volume allocation.
  • a management computer managing the computer system includes: a unit for creating a storage volume according to a parameter indicating a characteristic of the storage volume; a unit for deciding a threshold value for managing the storage volume according to the parameter; a unit for acquiring a performance value from the storage apparatus; and a unit for comparing the acquired performance value to the threshold value and detecting a threshold value violation.
  • the management computer for managing the computer system includes a unit for notifying a warning when the threshold value violation is detected.
  • the management computer for managing the computer system includes a unit for adding a message to the warning according to the parameter.
  • the message suggests use of a unit for improving the performance of the storage apparatus.
  • the management computer for managing the computer system has the warning notification unit which contains a unit for including in the message a suggestion of use of the unit for improving the performance of the storage apparatus.
  • the present invention it is possible to monitor the computer system appropriately for the use purpose according to the parameter derived from the use purpose of the storage region when allocating a storage volume, i.e., according to the hint.
  • FIG. 1 shows an outline of an embodiment.
  • FIG. 2 shows configuration of a computer system according to a first embodiment.
  • FIG. 3 explains storage volume management information in the first embodiment.
  • FIG. 4 shows a redundant group and a logical volume.
  • FIG. 5 explains allocation management informaiton in the first embodiment.
  • FIG. 6 explains flow of logical volume allocation processing in the first embodiment.
  • FIG. 7 explains threshold value information in the first embodiment.
  • FIG. 8 explains a table for deciding a threshold value in the first embodiment.
  • FIG. 9 explains performance information in the first embodiment.
  • FIG. 10 explains flow of performance information acquisition processing in the first embodiment.
  • FIG. 11 explains flow of warning notification processing in the first embodiment.
  • FIG. 12 shows the entire computer system according to a second embodiment.
  • FIG. 1 is a diagram for explaining three processes: storage volume allocation by an administrator, monitoring setting by the management system, and monitoring and warning notification by the management system.
  • An administrator 3000 is a person who manages the computer system 3100 .
  • the management system 3200 is a part of the computer system 3100 having management unit for managing the computer system 3100 .
  • the management system 3200 as the management unit includes at least a storage allocation section 110 , a threshold composing section 120 , a performance information acquisition section 130 , and a warning notification section 140 .
  • the computer system 3100 includes at least a storage apparatus 3300 .
  • a storage volume 3310 is a storage volume created in the storage apparatus 3300 by the storage allocation section 110 .
  • the administrator instructs the storage allocation section 110 to perform allocation of a storage volume (arrow 3601 ).
  • the parameter (hint 3400 ) indicating the characteristic of the storage volume is notified to the storage allocation section 110 .
  • the storage allocation section 110 creates a preferable storage volume 3310 in the storage apparatus 330 according to the hint (arrow 3602 ).
  • the hint 3400 is stored in the management system 3200 (hint 3401 ). As will be detailed later, the hint 3401 is referenced by the threshold composing section 120 and the warning notification section 140 .
  • the threshold composing section 120 sets a threshold value for the performance information of the storage volume 3310 according to the hint 3401 .
  • the relationship between the hint 3401 and the threshold value is also recorded.
  • the performance information acquisition section 130 acquires performance information from the storage apparatus 3300 (arrow 3603 ).
  • the warning notification section 140 compares the acquired performance information to the aforementioned threshold value. If the performance information exceeds (greater than or smaller than) the threshold value, warning is issued to the administrator 3000 (arrow 3604 ).
  • the warning notification section 140 analyzes how the threshold value is related to the hint and notifies the threshold value violation to the administrator as well as notifies a message based on the hint.
  • the storage allocation section 110 the threshold composing section 120 , the performance information acquisition section 130 , and the warning notification section 140 are depicted outside the storage apparatus but a part or all of them may be arranged inside the storage apparatus 3300 .
  • FIG. 2 shows configuration of the computer system according to the first embodiment of the present invention.
  • the first embodiment of the present invention includes a management computer 100 , a storage apparatus 200 , an LAN 300 , computers 400 ( a ) and 400 ( b ), and an FC switch 500 .
  • the management computer 100 is an ordinary computer including a CPU 101 , a memory 102 , a network interface 103 , a display device, a hard disk, a keyboard, a mouse, and the like and capable of operating software including various operating systems.
  • the management computer 100 is a personal computer. It may also be a computer for workstation and a server or a general-purpose computer. It should be noted that in FIG. 2 , other than the CPU 101 , the memory 102 , and the network interface 103 are omitted.
  • the management computer 100 includes a storage allocation section 110 , a threshold composing section 120 , performance information acquisition section 130 , and a warning notification section 140 .
  • the components 110 to 140 are programs executable by the management computer 100 . That is, the components 110 to 140 are stored in the memory 102 or the hard disk of the management computer 100 and interpreted/executed by the CPU 101 of the management computer 100 .
  • the management computer 100 functions as a computer system management apparatus for managing the computer system including the storage apparatus 200 .
  • the management computer has allocation management information 150 , performance information 160 , and threshold value information 170 .
  • Each of the information 150 to 170 is stored in the memory 102 of the management computer 100 or the hard disk and information read, addition, correction, and deletion are performed by the program executed on the management computer 100 .
  • the storage apparatus 200 includes a CPU 201 , a memory 202 , a network interface 203 , a controller 210 a storage volume management section 220 , storage volume management information 230 , a storage volume allocation section 240 , a performance value notification section 250 , logical volumes 260 to 264 , and an FC interface 270 .
  • Each of the logical volumes 260 to 264 can be accessed from the computer as a read/write-enabled storage region (equivalent to a logical unit in SCSI).
  • the read/write access to the logical volumes by the computer is realized by data communication via the FC interface 270 . This data communication uses the SCSI (Small Computer System Interface) protocol.
  • the computers 400 ( a ) and 400 ( b ) can communicate with the storage apparatus 200 by using their FC interfaces 410 ( a ) and 410 ( b ), respectively.
  • the computers 400 ( a ) and 400 ( b ) request the storage apparatus 200 to read/write to/from the logical volumes 260 to 264 .
  • the storage apparatus 200 receives the read/write request from the computers 400 ( a ) and 400 ( b ) via the FC interface 270 .
  • the computers 400 ( a ) and 400 ( b ) and the interfaces of the storage apparatus 200 are connected via an FC switch 500 .
  • the controller 210 processes the read/write request to the logical volumes 260 to 264 from the computer 400 ( a ) and 400 ( b ). According to the request, the controller 210 performs data transfer to the computer 400 ( a ) and 400 ( b ) or data storage into the logical volumes. Moreover, the controller 210 drives the storage volume management section 220 , the storage volume allocation section 240 , and the performance notification section 250 .
  • the controller 210 includes a CPU 201 and a memory 202 and has capability to interpret/execute a program.
  • the sections 220 , 240 , and 250 are programs stored in the memory 202 and executed by the controller 210 . It should be noted that the present invention can also be implemented by using a storage apparatus in which the functions equivalent to the sections 220 , 240 , and 250 are mounted by the dedicated hardware.
  • the storage storage apparatus 200 uses a plurality of hard disks in combination to obtain the so-called RAID function improving the reliability and performance.
  • the logical volumes 260 to 264 use the RAID function to divide the storage volumes of the hard disks of the storage apparatus 200 and concatenate them. In FIG. 2 , the hard disks of the storage apparatus 200 are not depicted.
  • the storage volume management section 220 is a section for managing such logical volumes.
  • the storage volume management information 230 is information for managing the allocation state of the logical volumes.
  • the storage volume management information 230 is stored in the memory region of the controller 210 .
  • the storage volume management information 230 is used by the storage volume management section 220 , the storage volume allocation section 240 , the controller 210 , and the performance notification section 250 .
  • the storage volume management information will be detailed later.
  • the storage volume allocation section 240 provides a function to constitute a new logical volume in the storage apparatus 200 .
  • An external computer performs data communication with the storage apparatus 200 via LAN 300 , thereby instructing creation of a new logical volume.
  • the controller 210 receives such an instruction and drives the storage volume allocation section 240 to create the instructed logical volume.
  • the performance notification section 250 notifies the performance values of the logical volume of the storage apparatus 200 and the FC interface via the LAN 300 to the external computer.
  • the storage apparatus 200 outputs at least (1) average I/O size of write requests to the logical volume (in kilobyte), (2) average data transfer rate of the write requests to the logical volume per second (in kilobyte), (3) average processing wait time of write requests to the logical volume (in second), (4) average number of write requests to the logical volume per second, (5) average I/O size of read requests to the logical volume (in kilobyte), (6) average data transfer amount of read requests to the logical volume per second (in kilobyte), (7) average processing wait time of the read requests to the logical volume (in second), and (8) performance value of the average number of read requests to the logical volume.
  • the average processing wait time in (3) and (6) is an average value of time from the moment when the controller receives the read/write processing to the moment when transmission of all the data requested is complete. This time includes wait time in data transfer to the hard disk or from the hard disk.
  • the computers 400 ( a ) and 400 ( b ) are ordinary computers including a CPU 4001 ( a ) and 401 ( b ), memories 402 ( a ) and 402 ( b ), network interfaces 403 ( a ) and 403 ( b ), display devices, hard disk devices, keyboards, mouses, and the like and can operate software including an operating system.
  • the components other than the CPU, memories and network interfaces are omitted.
  • the computers 400 ( a ) and 400 ( b ) are used to operate software relating to enterprise activities such as a database server and a Web server.
  • the main purpose of use of the logical volume of the storage apparatus 200 by the computers 400 ( a ) and 400 ( b ) is to store data required by these software.
  • the read/write request by the computers 400 ( a ) and 400 ( b ) is communicated only via the FC interface 410 ( a ) and 410 ( b ).
  • This embodiment of the present invention can also be realized by using LAN 300 for the read/write request.
  • this embodiment of the present invention can also be realized by using the FC interface for the management data communication of the storage apparatus 200 (logical volume creation, performance value output).
  • the two computers 400 ( a ) and 400 ( b ) are used for job purpose.
  • the number of computers is not limited to this according to the present invention.
  • the redundant group is defined as a set of a plurality of hard disks including redundant data for data protection in a storage sub-system having the RAID function such as the storage apparatus 200 .
  • the redundant group is called a RAID group, parity group, or the like.
  • the redundant group of the storage apparatus 200 is at either RAID level 1 or RAID level 5. Moreover, the redundant group of the storage apparatus 200 consists of four hard disks.
  • parity data calculated from the other three stripes is recorded on one of the striping units belonging to the stripe.
  • the parity data is arranged by employing the method called left-symmetric parity distribution.
  • the redundant group composed as the RAID level 1 on the striping units (of the even numbers of the striping unit) having the hard disk number 0 and 2, the same information is recorded while on the striping unit (of the odd numbers of the striping unit) having the hard disk number 1 and 3 the same information is recorded. Moreover, the striping units of the even numbers and the striping units of the odd numbers are handled alternately as a continuous storage region.
  • the logical volumes 260 to 264 are composed of some continuous stripes. Such configuration of the logical volume is recorded in the storage region management information 230 in the storage apparatus 200 .
  • the storage region management information 230 includes two types of information: redundant group management information 230 and the logical volume management information 232 .
  • the redundant group management information 231 uses a table format such as a relation database as the data format. Each line of it has one-to-one correspondence with the redundant group arranged in the storage apparatus 200 and has a field for storing information constituting the redundant group. It should be noted that the fields in the table are called a first field, a second field, . . . starting from the leftmost of the figure.
  • the first field of the redundant group management information 231 stores the redundant group number where the logical volume corresponding to the line is composed. Moreover, the second field stores the RAID level of the redundant group specified by the redundant group number stored in the first field.
  • the third field stores a hard disk ID of the first hard disk among the hard disks constituting the redundant group specified by the redundant group number stored in the first group.
  • the redundant group of the storage apparatus 200 is composed of four hard disks of continuous hard disk ID. Accordingly, the redundant group management information 231 does not contain a field for storing the number of hard disks constituting the redundant group.
  • the logical volume management information 232 also uses a table format as the data format like the redundant group management information 231 . Each line of it has one-to-one correspondence with the logical volume arranged in the storage apparatus 200 and has a field for storing configuration information on the logical volume.
  • the first field of the logical volume management information 232 stores the logical volume number.
  • the second field stores the redundant group number of the redundant group containing the logical volume specified by the first field.
  • the third field indicates the striping unit number indicating the stripe of the redundant group indicated by the second field from which the logical volume indicated by the first field is started.
  • the fourth field indicates the striping unit number indicating the last stripe among the stripes constituting the logical volume indicated by the first field.
  • FIG. 4 shows configuration of the logical volume in the redundant group of the redundant group number 0.
  • reference numerals 600 to 603 respectively indicate the four shelf-shaped rectangular blocks.
  • Each of the shelf-shaped rectangular blocks represent a hard disk contained in the redundant group of the redundant group number 0.
  • Each shelf of the rectangular blocks represent a striping unit of the hard disk.
  • the numerals inside the shelves represent the striping unit numbers.
  • the three dots “ . . . ” in a shelf indicate that a plurality of continuous striping units are present.
  • the logical volume of the logical volume number 260 is composed of stripes of striping units numbers 0 to 99. That is, the logical volume of the logical volume number 260 is composed, in FIG. 4 , by using the striping units of numbers 0 to 99 in the hard disks 600 to 603 .
  • the logical volume of the logical volume number 261 is composed of stripes 100 to 199
  • the logical volume of logical volume number 262 is composed of stripes 200 to 299 .
  • the management computer 100 can acquire the redundant group management information 231 and the logical volume management information 232 from the storage apparatus 200 via LAN 300 .
  • the storage volume allocation section 240 provides a unit for creating a new logical volume in the redundant group. These units can be controlled from the management computer 100 via LAN 300 .
  • the redundant group number and the logical volume size are specified as parameters.
  • the storage volume allocation section 240 receives the redundant group number and the logical volume size, it firstly checks the redundant group management table 231 . From this, the hard disk allocated to the redundant group is specified.
  • the storage volume allocation section 240 checks the logical volume management table 232 . From this, the specified redundant group checks the stripes used. Stripe are allocated for the new volume not to overlap with these stripes already used. An amount of stripes to be allocated are calculated from the specified size. When the stripes to be allocated to the logical volume are decided as has been described above, the storage volume allocation section 240 adds information on the configuration of a new logical volume created as a new line to the logical volume management information 232 .
  • the storage allocation section 110 of the management computer 100 provides a unit for creating a logical volume inside the storage apparatus according to the hint which is a parameter showing a characteristic of the storage volume.
  • the hint is a parameter showing a characteristic of the storage volume.
  • the hint can specify the following:
  • a computer capable of allocating a logical volume may be specified.
  • the storage allocation section 110 creates a logical volume in the storage apparatus and sets the storage apparatus and the computer so that the logical volume can be read/write accessed from the specified computer.
  • the management computer 100 provides a user interface (not depicted) for user to input information for executing storage volume allocation by the storage allocation section 110 .
  • This user interface is provided by the graphical user interface and command line interface.
  • This embodiment provides a user interface which can be operated by using a display, a keyboard, and a mouse of the management computer 100 for executing the storage allocation section 110 by specifying the logical volume size and allocation hint.
  • the hint specified by the user when the logical volume is allocated by the user interface is recorded in the allocation management information 150 .
  • An example of allocation management information is shown in FIG. 5 .
  • the allocation management information data format is a table format. Each line of it corresponds to a logical volume. In this explanation, a logical volume corresponding to the line will be called an object logical volume.
  • the first field of each line stores an identifier for uniquely identifying the storage apparatus of the object logical volume.
  • This identifier will be called a storage ID.
  • the storage ID an IP address for controlling the storage apparatus is used.
  • the first field is filled with “1.0.0.0”. In this specification, this represents an IP address in connection of the storage apparatus 200 to LAN 300 .
  • the storage ID in this first field is provided because it is required in correspondence to the computer system including a plurality of storage apparatuses.
  • the second field stores an identification number of the object logical volume in the storage apparatus specified by the first field. By the first field and the second field, the logical volume is uniquely identified in the entire information system.
  • the third field stores the redundant group number.
  • the fourth to the seventh field store the hint specified when the object logical volume is allocated.
  • the fourth field (R/W) stores the read/write ratio.
  • the fifth field (I/O size) stores the I/O size.
  • the sixth field (Trans) stores the I/O wait time importance.
  • the seventh field (Band) stores the bandwidth importance.
  • FIG. 6 shows a processing flow in the storage allocation section 110 .
  • the processing shown in FIG. 6 uses the size of the logical volume allocated and the hint as the input parameters. These parameters are specified by the user via the aforementioned user interface.
  • step 1000 it is checked whether the AccessDirectionHint (read/write ratio) of the specified hint is 4 or below. If so, it is considered that the access is oriented to read and the RAID level 5 is selected (step 1030 ).
  • step 1010 if the hint AccessSizeHint (average I/O size) is 256 kilobytes or above, the access is considered to be large. The large access means that the data transfer amount required in one access is 256 kilobytes or above. It should be noted that not large access is a small access. If the access is large, the RAID level 5 is selected. Otherwise, the RAID level 1 is selected.
  • the AccessDirectionHint read/write ratio
  • Step 1040 the redundant group for creating a logical volume is selected.
  • the RAID level which has been selected in the preceding step the values of hints AccessLatencyHint (I/O wait time importance) and AccessBandwidthWeight (data transfer bandwidth importance) are referenced.
  • Step 1040 checks whether the AccessLatencyHint or AccessBandwidthWeight is 0 or above. If these values are 8 or above, it is considered that high access performance is required and control is passed to step 1050 . Otherwise, control is passed to the condition judgment of step 1070 .
  • step 1050 a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200 .
  • control is passed to step 1160 . Otherwise, control is passed to step 1080 .
  • Step 1070 checks whether the AccessLatencyHint (I/O wait time importance) or AccessBandwidthWeight (data transfer bandwidth importance) is 4 or above. If these values are 4 or above, control is passed to step 1080 . Otherwise, control is passed to step 1100 .
  • AccessLatencyHint I/O wait time importance
  • AccessBandwidthWeight data transfer bandwidth importance
  • step 1080 a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200 .
  • step 1160 When such a redundant group is detected, control is passed to step 1160 . Otherwise, control is passed to step 1100 .
  • step 1100 a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200 .
  • step 1160 When such a redundant group is detected, control is passed to step 1160 . Otherwise, control is passed to step 1120 .
  • step 1120 a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200 .
  • Condition 1 Can create a logical volume of specified size.
  • step 1160 When such a redundant group is detected, control is passed to step 1160 . Otherwise, control is passed to step 1140 .
  • step 1140 redundant groups which can create a logical volume of the specified size are selected at random. If no such redundant group exists, an error is caused.
  • step 1160 the redundant group detected is selected as a redundant group for allocating the logical volume.
  • step 1170 the selected redundant group and the logical volume size are specified for the storage apparatus 200 and creation of the logical volume is instructed. Thus, a new logical volume is created by the aforementioned storage volume allocation section 240 .
  • step 1180 the configuration information on the logical volume created in step 1170 is added to the allocation management information 150 .
  • the information recorded are storage ID, the logical volume number, the redundant group number, and the hint.
  • step 1170 the algorithm of the logical volume allocation processing explained up to step 1170 is only an example.
  • the present invention can be realized by using an algorithm other than this algorithm.
  • monitoring of the logical volume is performed by using the hint used in volume allocation.
  • the monitoring of the logical volume is performed basically by comparing the various performance values of the logical volume to threshold values.
  • the threshold values are stored in the threshold value information 170 .
  • FIG. 7 explains the contents of the threshold value information 170 .
  • the data format of the threshold value information 170 is a table format.
  • Each line of the threshold value information 170 corresponds to the logical volume of the threshold value management object.
  • Each line consists of five fields.
  • the first field stores the storage ID of the corresponding logical volume.
  • the second field stores the logical volume number of the corresponding logical volume.
  • the third field stores a threshold value of the average wait time for the corresponding logical volume.
  • the fourth field stores a threshold value of the average data transfer amount for the corresponding logical volume.
  • the fifth field stores a threshold value of the average data transfer amount per wait time for the corresponding logical volume. This value is a threshold value of the value decided by the following equation: (average data transfer amount per second)/ ⁇ (average processing wait time)*(average number of requests per second) ⁇
  • the value 0 means that no value is decided. That is, the item whose value is 0 is not monitored. Setting of the threshold value is performed by the threshold composing section 120 .
  • the monitoring object is a performance value of the logical volume.
  • the processing in the threshold composing section is executed when the logical volume is allocated.
  • the parameters input for this processing are the storage ID of the logical volume, the logical volume number, and the hint.
  • the threshold composing section 120 decides a threshold value according to the information indicating the relationship between the hint and the threshold value. In this embodiment, for example, the threshold composing section 120 decides a threshold value according to two tables shown in FIG. 8 .
  • Table 801 shows correspondence between the value of the AccessLatencyHint (I/O wait time importance) of the hint and the logical volume average access wait time threshold value.
  • the first field of each line shows the value of the AccessLatencyHint.
  • the second field shows a threshold value of the average access wait time of the logical volume corresponding to the AccessLatencyHint value shown in the first field.
  • Table 802 shows correspondence between the value of the AccessBandwidthWeight (data transfer bandwidth importance) and the threshold value of the average data transfer amount per the logical volume wait time.
  • the first field of each line shows the value of the AccessBandwidthWeight.
  • the second field shows a threshold value of the average data transfer amount per logical volume wait time. It should be noted that in tables 801 and 802 , the threshold value 0 means that the threshold value is not monitored.
  • the threshold composing section 120 decides the monitoring threshold value of the logical volume for storing the information on the relationship between the hints and the threshold values according to the tables 801 and 802 in the threshold value information 170 .
  • the monitoring threshold values are automatically decided by the management computer 100 .
  • the performance information 160 stores a performance value acquired from the storage apparatus 200 .
  • FIG. 9 explains information stored in the performance information 160 .
  • the performance information of the logical volume 260 is in a table format having 9 fields. Each line corresponds to a time when the performance information concerning the logical volume 260 is acquired.
  • the first field stores the time when the performance information is acquired.
  • the second field stores the average I/O size of read access.
  • the third field stores the average data transfer amount per read access unit time. Here, the unit time is second.
  • the fourth field stores the average processing wait time of read access.
  • the fifth field stores the average number of read accesses per unit time. Here, the unit time is second.
  • the sixth field stores the average I/O size of write access.
  • the seventh field stores the average data transfer amount of write access per unit time. Here, the unit time is second.
  • the eighth field stores write access average processing wait time.
  • the ninth field stores the number of average write accesses per unit time. Here, the unit time is second.
  • the performance information of the logical volumes 261 to 264 are also stored in the performance information 160 like the logical volume 260 .
  • the data format of the performance information of the logical volumes 261 to 264 is identical to the data format of the performance information 161 of the logical volume 260 .
  • the performance information acquisition section 130 periodically acquires the performance information of the logical volumes 260 to 264 from the storage apparatus 200 and adds it to the performance information 160 . Moreover, at the timing when the performance information is acquired from the storage apparatus 200 , the performance information acquired is compared to the threshold value set in the threshold value information 170 .
  • the processing flow in the performance information acquisition section 130 is shown in the flowchart of FIG. 10 . Explanation will be given on the performance acquisition section 130 with reference to FIG. 10 .
  • Steps 1410 to 1440 constitute a loop structure. This loop processing is executed for the logical volume to be monitored. Step 1410 selects a logical volume for which performance information is to be acquired. Here, the logical volume specified by the first field and the second field of each line of the threshold value information 170 is successively selected from the first line of the threshold value information 170 (from the uppermost line in the figure).
  • step 1420 the performance information on the logical volume selected in step 1410 is acquired.
  • the performance information acquired here are values corresponding to the respective fields of the logical volume performance information. That is, the average I/O size of read access, the average data transfer amount per unit time of the read access, the average processing wait time of read access, the average number of read accesses per unit time, the average I/O size of write access, the average data transfer amount per unit time of write access, the average processing wait time of write access, and the average number of write accesses per unit time.
  • the performance information acquisition section 130 request the storage apparatus indicated by the first field of the threshold value information 170 t output performance information.
  • the performance information acquisition request executed in step 1420 of the performance information acquisition section 130 is processed by the performance value notification section 250 .
  • step 1430 the performance information acquired in step 1420 is added to the performance information 160 .
  • the time when the performance information is acquired is stored as the first field.
  • step 1440 if the performance information acquisition processing of all the logical volumes contained in the threshold value information 170 is not complete, the processing from step 1410 is performed to the next logical volume.
  • the management system of the computer system notifies a warning to a user when the various monitoring numeric value items of the device to be monitored violates a predetermined threshold value.
  • a message concerning the hint is also notified. This operation is realized by the warning notification section 140 .
  • FIG. 11 is a flowchart showing a processing flow in the warning notification section 140 .
  • the processing shown in FIG. 11 is executed after the performance information collection processing of the logical volume is executed in the performance information acquisition section 130 .
  • the processing shown in FIG. 11 is for a single logical volume.
  • the processing shown in FIG. 11 is executed for all the logical volumes specified by the first and the second field of the threshold value information 170 .
  • the input parameters of the processing shown in FIG. 11 are a logical volume number and a storage ID of the apparatus providing the logical volume. In the explanation below, the logical volume specified by the input parameter will be referred to as an object logical volume.
  • the performance information used for inspection is the latest acquired by the performance information acquisition section 130 .
  • step 1600 it is checked whether the average data transfer amount per processing wait time of the read and write request is below a threshold value.
  • the threshold value used is the average data transfer amount threshold value per processing wait time of the object logical volume.
  • the value of the inspection object used is based on the latest performance information on the object logical volume stored in the performance information 160 .
  • the average data transfer amount is divided by the average processing wait time to obtain a quotient, which is used. That is, two values of read and write are used as values of inspection objects.
  • the two values of inspection objects are compared to the aforementioned threshold value. If one of them is lower than the threshold value, it is assumed that a performance problem has occurred and control is passed to step 1620 . Otherwise, control is passed to step 1610 .
  • step 1610 it is checked whether the average processing wait time of read and write request for the object logical volume is above a threshold value.
  • the threshold value used here is an average processing wait time threshold value stored in the threshold value information 170 and corresponding to the object logical volume.
  • the value of the inspection object used here is the latest performance information on the object logical volume stored in the performance information 160 , i.e., the average processing time for each of read and write. That is, two values of read and write are used as values of inspection objects. The two values of inspection objects are compared to the aforementioned threshold value. If one of them exceeds the threshold value, it is assumed that a performance problem has occurred and control is passed to step 1620 . Otherwise, control is passed to step 1770 .
  • Step 1620 checks whether the characteristics of actual access to the object logical volume (read/write ratio and I/O size) are appropriate for the RAID level of the redundant group to which the object logical volume belongs.
  • the RAID level of the redundant group of the object logical volume will be referred to simply as the RAID level of the object logical volume.
  • the characteristic of the access to the object logical volume is assumed to be appropriate for the RAID level if both of the following conditions are satisfied:
  • the characteristic of the access to the object logical volume is assumed to be appropriate for the RAID level if one of the conditions 1 or 2 or both of them are not satisfied. If the characteristic of the access to the object logical volume is judged to be appropriate for the RAID level, control is passed to step 1680 . Otherwise, control is passed to step 1640 . It should be noted that the aforementioned conditions 1 and 2 are equivalent to the conditions for selecting the RAID level in the logical volume allocation.
  • step 1640 conformity between the allocation hint and the actual access characteristic of the object logical volume is checked. In this step, if one of the following conditions is satisfied, it is judged that the actual access characteristic is not appropriate for the allocation hint of the object logical volume.
  • Condition 1 The average write I/O size as the latest performance information on the object logical volume stored in the performance information 160 is 256 kilobytes or below and the I/O size of the allocation hint is 250 kilobytes or above.
  • the average write I/O size as the latest performance information on the object logical volume stored in the performance information 160 is 256 kilobytes or above and the I/O size of the allocation hint is 250 kilobytes or below.
  • the read IOPS as the latest performance information on the object logical volume stored in the performance information 160 is the write IOPS multiplied by 1.5 or below and the read/write ratio of the allocation hint is 6 or below.
  • the read IOPS as the latest performance information on the object logical volume stored in the performance information 160 is the write IOPS multiplied by 1.5 or above and the read/write ratio of the allocation hint is 6 or above.
  • a warning message is created to indicate the inconformity between the actual access characteristic for the object logical volume and the allocation hint of the object logical volume judged in step 1640 .
  • a messages created when the respective conditions are satisfies are as follows. It should be noted that the inconformity of the RAID level is generated.
  • Step 1670 After the message is created in step 1650 , control is passed to step 1670 .
  • Steps 1670 to 1750 check the redundant group containing the object logical volume, i.e., the hint and actual access frequency of the logical volume other than the object logical volume contained in the redundant group.
  • the logical volume given a low value for the AccessLatencyHint (I/O wait time importance) and the AccessBandwidthWeight (data transfer bandwidth importance) in the hint during the allocation is assumed to have a low access frequency. Accordingly, for the redundant group containing such logical volumes, a logical volume having a high AccessLatencyHint and AccessBandwidthWeight may be allocated later.
  • the logical volume requiring a high access frequency allocated later may be affected and its performance may be lowered. Although such performance lowering (threshold value violation) may be recognized, its cause may not be known.
  • notification of a logical volume which may possibly a cause to a user will help the user to study the performance improvement of the logical volume.
  • step 1670 for the redundant group to which the object logical volume belongs, one logical volume (other than the object logical volume) belonging to the redundant group is selected. Selection of the logical volume can be performed by checking the logical volume management information 232 . It should be noted that steps 1670 to 1750 constitute a loop structure but in step 1670 , it is assumed that a logical volume which has been selected once will not be selected again. Hereinafter, the logical volume selected in step 1670 will be referred to as the selected logical volume.
  • Step 1680 makes a check for the selected logical volume, i.e., conformity between the AccessLatencyHint (I/O wait time importance) and AccesssBandwidthWeight (data transfer bandwidth importance) which are hints during allocation and the performance value. Here, it is checked whether access to the selected logical volume is increased in spite of the low value of the AccessLatencyHint and AccessBandwidthWeight of the selected logical volume. If the selected logical volume is in such a state, control is passed from step 1690 to step 1700 . Otherwise, control is passed to step 1750 . As will be detailed later, the processing of step 1700 creates a message describing affect to the performance.
  • the AccessLatencyHint I/O wait time importance
  • AccesssBandwidthWeight data transfer bandwidth importance
  • AccessLatencyHint and AccessBandwidthWeight of the selected logical volume are acquired from the allocation management information 150 .
  • the read IOPS and write IOPS are acquired from the performance information by the latest performance information of the selected logical volume. If the AccessLatencyHint and AccessBandwidthWeight is lass than 4 and the sum of the read IOPS and the write IOPS is greater than a predetermined value, the selected logical volume is assumed to be a logical volume affecting the performance of the object logical volume.
  • Step 1700 creates a message describing that the selected logical volume has an affect to the performance of the object logical volume.
  • the message created here is as follows. “ ⁇ The selected logical volume>> is accessed with a high frequency unlike the specified hint”. ⁇ The selected logical volume>> is replaced by a word representing a selected logical volume.
  • Step 1750 is the end of the loop. This step checks whether all the logical volumes contained in the redundant group of the object logical volume have been subjected to the processing of steps 1670 to 1700 . If there is a logical volume not processed, control is returned to step 1670 .
  • the logical volumes belonging to the same redundant group interact their performances as has been described above. Such a phenomenon can also be seen depending on the RAID level.
  • a write access of a small I/O size (equal to the striping unit or below) to the redundant group of RAID level 5 gives a great affect to the performance of the entire redundant group. Accordingly, in the loop of steps 1670 to 1700 , with respect to the selected logical volume, it is effective to check conformity between the RAID level and the performance value by the method described in steps 1620 to 1640 and create a message as has been described in step 1650 .
  • step 1760 The processing of step 1760 is executed when no threshold value violation is recognized in steps 1600 and 1610 .
  • the target is to notify a user that the access frequency is actually low although a high performance is required of the object logical volume by the hint.
  • Step 1760 checks whether the average data transfer amount of the object logical volume is lower than the threshold value.
  • the threshold value in this step is the data transfer amount threshold value of the object logical volume stored in the threshold value information 170 .
  • This step compares the sum of the average read data transfer amount and the average write data transfer amount of the object logical volume stored in the performance information 160 with the aforementioned threshold value. As a result, if the sum is lower than the threshold value, the object logical volume is assumed to be a logical volume which has an excessively high performance for the actual access. And in step 1770 , a message is created. Otherwise, this series of processing is terminated.
  • Step 1770 creates a message as follows. “ ⁇ The object logical volume>> has an excessively high performance for the actual use.” The part ⁇ the object logical volume>> is replaced by a character string representing the object logical volume.
  • Step 1780 notifies a warning of threshold value violation to the user.
  • the messages created in steps 1650 , 1700 , and 1770 are included.
  • the warning is notified to the user via the aforementioned user interface. It is also possible to notify the user by using the log recording function such as syslog. Moreover, it is possible to use the message exchange function such as e-mail. Moreover, it is also possible to notify the warning to the user by using the protocol, for management such as SNMP.
  • the logical volume is monitored and if a threshold value violation is generated, an appropriate message is reported to the user.
  • FIG. 12 shows the second embodiment of the present invention.
  • the sections and information equivalent to the storage allocation section 110 , the threshold composing section 120 , the warning notification section 140 , the allocation management section 150 , the performance information 160 , and the threshold information which are contained in the management computer 100 (see FIG. 2 ) in the first embodiment are contained in the apparatus in the second embodiment.
  • the storage apparatus 2200 is an extended device of the storage apparatus 200 (see FIG. 2 ) for containing these sections and information.
  • the storage apparatus 220 includes a storage allocation section 2110 , a monitoring section 2120 , a warning notification section 2140 , allocation management information 2150 , performance information 2160 , and threshold information 2170 . These sections and information are equivalent to the sections and information of the same names in the management computer 100 of the first embodiment which are operated in the storage apparatus 2200 .
  • the controller 210 includes a CPU 201 and a memory 202 and has an ability to interpret and execute a program.
  • the sections 220 , 240 , 250 , 2250 , 2110 , 2120 , and 2140 are programs which are stored in the memory 202 and executed by the controller 210 . It should be noted that the present invention can also be realized by using the storage apparatus having dedicated hardware for the functions equivalent to the sections 220 , 240 , 2250 , 2110 , 2120 , and 2140 .
  • the functions of the performance information acquisition section 130 and the performance value notification section 250 are realized by the performance value notification section 2250 . That is, the performance value notification section 2250 accumulates information on the performance of the logical volumes 260 to 264 in the performance information 2160 .
  • the management computer 2100 is an ordinary computer having a user interface 180 .
  • the user can control the storage allocation section 2110 , the monitoring section 2120 , and the warning notification section 2140 of the storage apparatus 2200 .
  • the management computer 100 can also have the effect of the present invention in the second embodiment from the explanation of the first embodiment concerning the allocation management information 150 , the performance information 160 , and the threshold value information 170 .
  • the storage apparatus contained in the computer system is the storage apparatus 200 or 2200 .
  • the present invention can also be applied to a computer system containing a plurality of storage apparatuses.
  • only one FC switch is contained in the computer system.
  • the essential quality of the present invention will not be changed by the number of the FC switches.
  • the first and the second embodiment can be extended in such a manner that the performance information can be acquired not only from the storage apparatus but also from the computer or the FC switch and threshold values can be set for them.
  • the aforementioned storage area network has a function for always containing the data stored in the logical volume in the cache memory (cache resident function). This dramatically improves the access performance to the logical volume.
  • a message is created in steps 1650 and 1700 . In these steps, it is possible to create a message to suggest application of the aforementioned cache resident function for the logical volume.
  • the message includes that the cache resident function is automatically applied.
  • the performance improvement function includes a logical volume movement function for moving data stored in a logical volume to another logical volume and a band control function for controlling the bandwidth used by the I/O request from a particular computer in the FC interface.

Abstract

A method for monitoring according to a hint when allocating a storage volume. When a threshold value violation has occurred, judgement is performed from which use purpose the threshold value derives. The management computer for managing a computer system includes a unit for creating a storage volume according to a hint, a unit for deciding a threshold value for managing the storage volume according to the use purpose of the storage volume, a unit for acquiring a performance value from the storage apparatus, and a unit for comparing the acquired performance value to the threshold value and notifying a warning including a message based on the hint when a threshold value violation is detected.

Description

    BACKGROUND OF THE INVENTION
  • The present invention relates to a computer system management program for managing a computer system including a computer and a storage apparatus, a recording medium, a computer system, a management apparatus and a storage apparatus thereof, and in particular to a technique for setting a monitoring unit of a computer system by utilizing a hint used in operation of allocating a storage area in a storage apparatus and upon notifying a warning in the monitoring unit, creating an additional message of warning according to the hint and notifying it together with the warning.
  • Among monitoring systems monitoring a computer system, there is one utilizing a threshold value. The monitoring system acquires from respective apparatuses constituting a computer system, a numerical value (mainly, a performance value) indicating the state of the apparatuses and compares the value with a predetermined threshold value. If the former exceeds (is greater than or smaller than) the threshold value, a warning is generated.
  • When using this kind of monitoring system, there is a problem that it is difficult to select an appropriate threshold value. To cope with this, JP-A-2002-215230 discloses a method for easily setting an optimal threshold value. This method is as follows. Firstly, a user (administrator of the computer system) specifies the target number of threshold value violations of the numerical value indicating the state of the apparatuses to be managed for the monitoring system. Next, the monitoring system automatically adjusts the threshold value so that the number of threshold value violations of the numerical value indicating the state of the apparatuses to be managed is identical to the specified target threshold value violation number.
  • Nowadays, together with monitoring of the computer system, a large-scale storage apparatus such as a disk array apparatus, especially a storage region provided by a large-scale storage apparatus has become an important item to be managed. As a main component of the computer system, a storage area network is now widely used. This storage area network uses a fibre channel (FC) for connecting the computer to the storage apparatus in a network type format, thereby flexibly connecting a computer to a storage apparatus. Thus, for example, it is possible to perform data backup without using LAN (local area network), thereby enabling a new application.
  • Moreover, as a network connecting a computer to a storage apparatus, some techniques using IP (Internet Protocol) network attract attention and are widely spread. Under such a condition, an enterprise organization SNIA (Storage Networking Industry Association) has been organized by enterprises concerning storage network.
  • SNIA is promoting spread of the storage network through the activity of formulation of the standard specification of the storage network and peripheral technique. For example, SNIA suggests a standard specification for operation of allocating a storage area in a computer in the computer system including the storage apparatus. This specification is applied to management software managing a computer system. Moreover, this specification is based on CIM (Common Information Model) defined by DMTF (Distributed Management Task Force).
  • In the operation of this standard storage area allocation, a parameter indicating the storage area feature is defined. When allocating a storage area, an administrator creates this parameter for the user purpose of the storage area and inputs it to the management software, thereby creating a desired storage area. This parameter is called “hint”.
  • A portion associated with the hints is extracted below from the document defining the specification (Device 27_StorageServices. mof (lines 662 to 721) [online], Nov. 12, 2002, Distributed Management Task Force, [searched on Jan. 18, 2003], Internet
    <URL:http://www.dmtf.org/standards/cim_schema_v27.php>.
    ==================================================
    // StorageSettingWithHints
    //
    ==================================================
    [Experimental, Version (“2.7.1”), Description (
      “This subclass of Storage Setting allows a
    client to specify”
      “’hint’s for optimization of the volume
    performance. The effect”
      “of these hints is implementation
    dependent.”)]
    class CIM_StorageSettingWithHints: CIM_StorageSetting{
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication from a client of
    the importance”
      “placed on data availability. Values are 0 =
    Don't Care to”
      “10 = Very Important.”)]
      uint 16 DataAvailabilityHint;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication from a client of
    the randomness”
      “of accesses. Values are 0 = Entirely
    Sequential to”
      “10 = Entirely Random.”)]
      uint 16 AccessRandomnessHint;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication from a client of
    the direction”
      “of accesses. Values are 0 = Entirely Read
    to”
      “10 = Entirely Write.”)]
      uint 16 AccessDirectionHint;
      [Description (
      “This hint is an indication from a client of
    the optimal”
      “access sizes. Several sizes can be
    specified.”),
      Units (“MegaBytes”)]
      uint 16 AccessSizeHint #;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication from a client how
    important”
      “access latency is. Values are 0 = Don't
    Care to”
      “10 = Very important.”)]
      uint 16 AccessLatencyHint;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication from a client of
    bandwidth”
      “prioritization. Values are 0 = Don't Care
    to”
      “10 = Very important.”)]
      uint 16 AccessBandwidthWeight;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication of the importance
    the client”
      “places on the cost of storage. Values are 0
    = Don't Care to”
      “10 = Very important. A Storage Volume
    provider might choose”
      “to place data on low cost or high cost
    drives based on”
      “this parameter.”)]
      uint 16 StorageCostHint;
      [MinValue (0), MaxValue (10), Description (
      “This hint is an indication of the importance
    placed on”
      “storage efficiency by the client. Values
    are 0 = Don't Care”
      “to 10 = Very important. A Storage Volume
    provider might choose”
      “different RAID levels based on this hint.”)]
      uint 16 StorageEfficiencyHint;
    };
  • The management software mounting CIM should handle the hints in mounting operation of the storage volume allocation.
  • SUMMARY OF THE INVENTION
  • In management of a computer system including a storage apparatus, it is necessary to configure monitoring based on a hint when a storage volume is allocated. When applying JP-A-2002-215230 to this, it is difficult to set a target number of the threshold value violations from the hint. Conventionally, there has not been a method for monitoring according to the storage volume hint.
  • Moreover, in the conventional monitoring system, it has been impossible to judge from which hint a threshold value violation derives when one has occurred and a system administrator has had difficulty to study a countermeasure to be taken for the threshold value violation.
  • It is therefore an object of the present invention to provide a technique for managing a computer system including a storage apparatus, the technique monitoring the computer system by using a hint in the storage volume allocation.
  • According to another aspect of the present invention, there is provided a technique for simultaneously notifying a warning explanation including the cause of the warning in the monitoring of the computer system.
  • In order to achieve the object of the present invention, a management computer managing the computer system includes: a unit for creating a storage volume according to a parameter indicating a characteristic of the storage volume; a unit for deciding a threshold value for managing the storage volume according to the parameter; a unit for acquiring a performance value from the storage apparatus; and a unit for comparing the acquired performance value to the threshold value and detecting a threshold value violation.
  • Moreover, the management computer for managing the computer system includes a unit for notifying a warning when the threshold value violation is detected.
  • Moreover, the management computer for managing the computer system includes a unit for adding a message to the warning according to the parameter.
  • Moreover, the message suggests use of a unit for improving the performance of the storage apparatus. The management computer for managing the computer system has the warning notification unit which contains a unit for including in the message a suggestion of use of the unit for improving the performance of the storage apparatus.
  • According to the present invention, it is possible to monitor the computer system appropriately for the use purpose according to the parameter derived from the use purpose of the storage region when allocating a storage volume, i.e., according to the hint.
  • Moreover, from the monitoring system of the computer system, it is possible to rapidly grasp from which hint the notified warning apparatuses when a threshold value violation has occurred. Accordingly, a system administrator can rapidly examine a countermeasure to be taken for the threshold value violation.
  • The other features of the present invention will be made clear in the detailed description below and the attached drawings.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 shows an outline of an embodiment.
  • FIG. 2 shows configuration of a computer system according to a first embodiment.
  • FIG. 3 explains storage volume management information in the first embodiment.
  • FIG. 4 shows a redundant group and a logical volume.
  • FIG. 5 explains allocation management informaiton in the first embodiment.
  • FIG. 6 explains flow of logical volume allocation processing in the first embodiment.
  • FIG. 7 explains threshold value information in the first embodiment.
  • FIG. 8 explains a table for deciding a threshold value in the first embodiment.
  • FIG. 9 explains performance information in the first embodiment.
  • FIG. 10 explains flow of performance information acquisition processing in the first embodiment.
  • FIG. 11 explains flow of warning notification processing in the first embodiment.
  • FIG. 12 shows the entire computer system according to a second embodiment.
  • DESCRIPTION OF THE EMBODIMENTS
  • Description will now be directed to embodiments of the present invention with reference to the attached drawings.
  • Firstly, referring to FIG. 1, explanation will be given on the outline of the embodiment of the present invention. FIG. 1 is a diagram for explaining three processes: storage volume allocation by an administrator, monitoring setting by the management system, and monitoring and warning notification by the management system.
  • Explanation will be given on each component constituting FIG. 1. An administrator 3000 is a person who manages the computer system 3100. The management system 3200 is a part of the computer system 3100 having management unit for managing the computer system 3100. The management system 3200 as the management unit, includes at least a storage allocation section 110, a threshold composing section 120, a performance information acquisition section 130, and a warning notification section 140. The computer system 3100 includes at least a storage apparatus 3300. A storage volume 3310 is a storage volume created in the storage apparatus 3300 by the storage allocation section 110.
  • Hereinafter, explanation will be given on each of the aforementioned three processes. In the process of storage volume allocation operation, the administrator instructs the storage allocation section 110 to perform allocation of a storage volume (arrow 3601). Here, the parameter (hint 3400) indicating the characteristic of the storage volume is notified to the storage allocation section 110. The storage allocation section 110 creates a preferable storage volume 3310 in the storage apparatus 330 according to the hint (arrow 3602). The hint 3400 is stored in the management system 3200 (hint 3401). As will be detailed later, the hint 3401 is referenced by the threshold composing section 120 and the warning notification section 140.
  • In the monitoring setting process by the management system, the threshold composing section 120 sets a threshold value for the performance information of the storage volume 3310 according to the hint 3401. Here, the relationship between the hint 3401 and the threshold value is also recorded.
  • In the monitoring and warning notification process by the management system, firstly, the performance information acquisition section 130 acquires performance information from the storage apparatus 3300 (arrow 3603). Next, the warning notification section 140 compares the acquired performance information to the aforementioned threshold value. If the performance information exceeds (greater than or smaller than) the threshold value, warning is issued to the administrator 3000 (arrow 3604). Here, the warning notification section 140 analyzes how the threshold value is related to the hint and notifies the threshold value violation to the administrator as well as notifies a message based on the hint.
  • It should be noted that in FIG. 1, the storage allocation section 110, the threshold composing section 120, the performance information acquisition section 130, and the warning notification section 140 are depicted outside the storage apparatus but a part or all of them may be arranged inside the storage apparatus 3300.
  • First Embodiment
  • Hereinafter, explanation will be given on the first embodiment of the present invention. FIG. 2 shows configuration of the computer system according to the first embodiment of the present invention. As shown in FIG. 2, the first embodiment of the present invention includes a management computer 100, a storage apparatus 200, an LAN 300, computers 400(a) and 400(b), and an FC switch 500.
  • The management computer 100 is an ordinary computer including a CPU 101, a memory 102, a network interface 103, a display device, a hard disk, a keyboard, a mouse, and the like and capable of operating software including various operating systems. In this embodiment, the management computer 100 is a personal computer. It may also be a computer for workstation and a server or a general-purpose computer. It should be noted that in FIG. 2, other than the CPU 101, the memory 102, and the network interface 103 are omitted.
  • The management computer 100 includes a storage allocation section 110, a threshold composing section 120, performance information acquisition section 130, and a warning notification section 140. The components 110 to 140 are programs executable by the management computer 100. That is, the components 110 to 140 are stored in the memory 102 or the hard disk of the management computer 100 and interpreted/executed by the CPU 101 of the management computer 100. Thus, the management computer 100 functions as a computer system management apparatus for managing the computer system including the storage apparatus 200.
  • Moreover, the management computer has allocation management information 150, performance information 160, and threshold value information 170. Each of the information 150 to 170 is stored in the memory 102 of the management computer 100 or the hard disk and information read, addition, correction, and deletion are performed by the program executed on the management computer 100.
  • The storage apparatus 200 includes a CPU 201, a memory 202, a network interface 203, a controller 210 a storage volume management section 220, storage volume management information 230, a storage volume allocation section 240, a performance value notification section 250, logical volumes 260 to 264, and an FC interface 270. Each of the logical volumes 260 to 264 can be accessed from the computer as a read/write-enabled storage region (equivalent to a logical unit in SCSI). The read/write access to the logical volumes by the computer is realized by data communication via the FC interface 270. This data communication uses the SCSI (Small Computer System Interface) protocol.
  • It should be noted the computers 400(a) and 400(b) can communicate with the storage apparatus 200 by using their FC interfaces 410(a) and 410(b), respectively. By this, the computers 400(a) and 400(b) request the storage apparatus 200 to read/write to/from the logical volumes 260 to 264. The storage apparatus 200 receives the read/write request from the computers 400(a) and 400(b) via the FC interface 270. The computers 400(a) and 400(b) and the interfaces of the storage apparatus 200 are connected via an FC switch 500.
  • The controller 210 processes the read/write request to the logical volumes 260 to 264 from the computer 400(a) and 400(b). According to the request, the controller 210 performs data transfer to the computer 400(a) and 400(b) or data storage into the logical volumes. Moreover, the controller 210 drives the storage volume management section 220, the storage volume allocation section 240, and the performance notification section 250. In this embodiment, the controller 210 includes a CPU 201 and a memory 202 and has capability to interpret/execute a program. The sections 220, 240, and 250 are programs stored in the memory 202 and executed by the controller 210. It should be noted that the present invention can also be implemented by using a storage apparatus in which the functions equivalent to the sections 220, 240, and 250 are mounted by the dedicated hardware.
  • The storage storage apparatus 200 uses a plurality of hard disks in combination to obtain the so-called RAID function improving the reliability and performance. The logical volumes 260 to 264 use the RAID function to divide the storage volumes of the hard disks of the storage apparatus 200 and concatenate them. In FIG. 2, the hard disks of the storage apparatus 200 are not depicted.
  • The storage volume management section 220 is a section for managing such logical volumes. The storage volume management information 230 is information for managing the allocation state of the logical volumes. The storage volume management information 230 is stored in the memory region of the controller 210. The storage volume management information 230 is used by the storage volume management section 220, the storage volume allocation section 240, the controller 210, and the performance notification section 250. The storage volume management information will be detailed later.
  • The storage volume allocation section 240 provides a function to constitute a new logical volume in the storage apparatus 200. An external computer performs data communication with the storage apparatus 200 via LAN 300, thereby instructing creation of a new logical volume. The controller 210 receives such an instruction and drives the storage volume allocation section 240 to create the instructed logical volume.
  • The performance notification section 250 notifies the performance values of the logical volume of the storage apparatus 200 and the FC interface via the LAN 300 to the external computer. In this embodiment, the storage apparatus 200 outputs at least (1) average I/O size of write requests to the logical volume (in kilobyte), (2) average data transfer rate of the write requests to the logical volume per second (in kilobyte), (3) average processing wait time of write requests to the logical volume (in second), (4) average number of write requests to the logical volume per second, (5) average I/O size of read requests to the logical volume (in kilobyte), (6) average data transfer amount of read requests to the logical volume per second (in kilobyte), (7) average processing wait time of the read requests to the logical volume (in second), and (8) performance value of the average number of read requests to the logical volume.
  • Here, the average processing wait time in (3) and (6) is an average value of time from the moment when the controller receives the read/write processing to the moment when transmission of all the data requested is complete. This time includes wait time in data transfer to the hard disk or from the hard disk.
  • The computers 400(a) and 400(b) are ordinary computers including a CPU 4001(a) and 401(b), memories 402(a) and 402(b), network interfaces 403(a) and 403(b), display devices, hard disk devices, keyboards, mouses, and the like and can operate software including an operating system. In FIG. 2, the components other than the CPU, memories and network interfaces are omitted.
  • In this embodiment, the computers 400(a) and 400(b) are used to operate software relating to enterprise activities such as a database server and a Web server. The main purpose of use of the logical volume of the storage apparatus 200 by the computers 400(a) and 400(b) is to store data required by these software.
  • In this embodiment, the read/write request by the computers 400(a) and 400(b) is communicated only via the FC interface 410(a) and 410(b). This embodiment of the present invention can also be realized by using LAN 300 for the read/write request. On the contrary, this embodiment of the present invention can also be realized by using the FC interface for the management data communication of the storage apparatus 200 (logical volume creation, performance value output). It should be noted that in this embodiment, the two computers 400(a) and 400(b) are used for job purpose. However, the number of computers is not limited to this according to the present invention.
  • Next, explanation will be given on the logical volume and hard disk of the storage apparatus 200 and a redundant group. Here, the redundant group is defined as a set of a plurality of hard disks including redundant data for data protection in a storage sub-system having the RAID function such as the storage apparatus 200. According to the storage sub-system, the redundant group is called a RAID group, parity group, or the like.
  • As a combination of hard disks in the redundant group, there is known a concept of the RAID level. The redundant group of the storage apparatus 200 is at either RAID level 1 or RAID level 5. Moreover, the redundant group of the storage apparatus 200 consists of four hard disks.
  • Terms concerning the redundant group are defined below:
      • Hard disk number: Numbers 0 to 3 assigned to hard disks belonging to the redundant group.
      • Hard disk ID: Numbers, different from the hard disk number, starting from 0 uniquely assigned to the hard disks in the entire storage apparatus 200.
      • Logical block address (LBA): Numbers starting from 0 assigned to each logical block consisting of 512 bytes of the storage region of the hard disk.
      • Striping unit: Hard disks belonging to a redundant group divided into a predetermined continuous number of logical blocks. Striping unit number is assigned to the striping unit in the order of LBA.
      • Stripe: Striping units of each hard disk belonging to a redundant group and having identical striping unit number. The striping units are concatenated in the ascending order of the hard disk number and assumed to be a continuous single region.
      • Redundant group number: Unique identification number in the storage apparatus assigned to the redundant group.
  • In the case of the redundant group composed as the RAID level 5, on one of the striping units belonging to the stripe, parity data calculated from the other three stripes is recorded. In this embodiment, the parity data is arranged by employing the method called left-symmetric parity distribution.
  • In the case of the redundant group composed as the RAID level 1, on the striping units (of the even numbers of the striping unit) having the hard disk number 0 and 2, the same information is recorded while on the striping unit (of the odd numbers of the striping unit) having the hard disk number 1 and 3 the same information is recorded. Moreover, the striping units of the even numbers and the striping units of the odd numbers are handled alternately as a continuous storage region. The logical volumes 260 to 264 are composed of some continuous stripes. Such configuration of the logical volume is recorded in the storage region management information 230 in the storage apparatus 200.
  • Explanation will be given on the storage region management information 230 with reference to FIG. 3. The storage region management information 230 includes two types of information: redundant group management information 230 and the logical volume management information 232. The redundant group management information 231 uses a table format such as a relation database as the data format. Each line of it has one-to-one correspondence with the redundant group arranged in the storage apparatus 200 and has a field for storing information constituting the redundant group. It should be noted that the fields in the table are called a first field, a second field, . . . starting from the leftmost of the figure.
  • The first field of the redundant group management information 231 stores the redundant group number where the logical volume corresponding to the line is composed. Moreover, the second field stores the RAID level of the redundant group specified by the redundant group number stored in the first field.
  • Moreover, the third field stores a hard disk ID of the first hard disk among the hard disks constituting the redundant group specified by the redundant group number stored in the first group.
  • In this embodiment, the redundant group of the storage apparatus 200 is composed of four hard disks of continuous hard disk ID. Accordingly, the redundant group management information 231 does not contain a field for storing the number of hard disks constituting the redundant group.
  • The logical volume management information 232 also uses a table format as the data format like the redundant group management information 231. Each line of it has one-to-one correspondence with the logical volume arranged in the storage apparatus 200 and has a field for storing configuration information on the logical volume.
  • The first field of the logical volume management information 232 stores the logical volume number. The second field stores the redundant group number of the redundant group containing the logical volume specified by the first field. The third field indicates the striping unit number indicating the stripe of the redundant group indicated by the second field from which the logical volume indicated by the first field is started. The fourth field indicates the striping unit number indicating the last stripe among the stripes constituting the logical volume indicated by the first field.
  • Explanation will be given on the correspondence between the configuration information stored in the logical volume information 232 and actual logical volume configuration with reference to FIG. 4. FIG. 4 shows configuration of the logical volume in the redundant group of the redundant group number 0.
  • In FIG. 4, reference numerals 600 to 603 respectively indicate the four shelf-shaped rectangular blocks. Each of the shelf-shaped rectangular blocks represent a hard disk contained in the redundant group of the redundant group number 0. Each shelf of the rectangular blocks represent a striping unit of the hard disk. The numerals inside the shelves represent the striping unit numbers. The three dots “ . . . ” in a shelf indicate that a plurality of continuous striping units are present.
  • According to the logical volume information 232 of FIG. 3, the logical volume of the logical volume number 260 is composed of stripes of striping units numbers 0 to 99. That is, the logical volume of the logical volume number 260 is composed, in FIG. 4, by using the striping units of numbers 0 to 99 in the hard disks 600 to 603.
  • Similarly, the logical volume of the logical volume number 261 is composed of stripes 100 to 199, and the logical volume of logical volume number 262 is composed of stripes 200 to 299. The management computer 100 can acquire the redundant group management information 231 and the logical volume management information 232 from the storage apparatus 200 via LAN 300.
  • The storage volume allocation section 240 provides a unit for creating a new logical volume in the redundant group. These units can be controlled from the management computer 100 via LAN 300. When creating a logical volume by using the storage volume allocation section 240, the redundant group number and the logical volume size are specified as parameters.
  • Here, brief explanation will be given on the storage volume allocation section 240 although it is not essential for this invention. When the storage volume allocation section 240 receives the redundant group number and the logical volume size, it firstly checks the redundant group management table 231. From this, the hard disk allocated to the redundant group is specified.
  • Next, the storage volume allocation section 240 checks the logical volume management table 232. From this, the specified redundant group checks the stripes used. Stripe are allocated for the new volume not to overlap with these stripes already used. An amount of stripes to be allocated are calculated from the specified size. When the stripes to be allocated to the logical volume are decided as has been described above, the storage volume allocation section 240 adds information on the configuration of a new logical volume created as a new line to the logical volume management information 232.
  • Hereinafter, explanation will be given on the processing in the management computer. The storage allocation section 110 of the management computer 100 provides a unit for creating a logical volume inside the storage apparatus according to the hint which is a parameter showing a characteristic of the storage volume. When a user performs volume allocation, the user gives at least a desired logical volume size and the hint as parameters to the storage allocation section 110. Then, the storage allocation section 110 creates a logical volume inside the storage apparatus according to the hint.
  • The hint can specify the following:
      • Read/write ratio: A value from 0 to 10. The ratio indicates which of read requests and write requests are greater in the read/write requests for the logical volume. When 0 is specified, it is considered that only read requests are present. When 10 is specified, it is considered that only write requests are present. This ratio may be called DataDirectdionHint below.
      • Average I/O size: An average data transfer amount in the reqd/write requests. In kilo byte unit. This size may be referred to as AccessSizeHint below.
      • I/O wait time importance: A value from 0 to 10. As this value increases, the I/O wait time becomes important. This may be referred to as AccessLatencyHint.
      • Data transfer band width importance: A value from 0 to 10. As this value increases the data transfer band width becomes important. This may be referred to as AccessBandwidthWeight below.
  • Here, as the parameter to the storage allocation section 110, a computer capable of allocating a logical volume may be specified. In this case, the storage allocation section 110 creates a logical volume in the storage apparatus and sets the storage apparatus and the computer so that the logical volume can be read/write accessed from the specified computer.
  • The management computer 100 provides a user interface (not depicted) for user to input information for executing storage volume allocation by the storage allocation section 110. This user interface is provided by the graphical user interface and command line interface. This embodiment provides a user interface which can be operated by using a display, a keyboard, and a mouse of the management computer 100 for executing the storage allocation section 110 by specifying the logical volume size and allocation hint. Moreover, it is possible to provide a user interface capable of executing the storage allocation section 110 from a computer other than the management computer 100.
  • The hint specified by the user when the logical volume is allocated by the user interface is recorded in the allocation management information 150. An example of allocation management information is shown in FIG. 5. As shown in FIG. 5, the allocation management information data format is a table format. Each line of it corresponds to a logical volume. In this explanation, a logical volume corresponding to the line will be called an object logical volume.
  • The first field of each line stores an identifier for uniquely identifying the storage apparatus of the object logical volume. This identifier will be called a storage ID. Here, as the storage ID an IP address for controlling the storage apparatus is used. In all the lines of FIG. 5, the first field is filled with “1.0.0.0”. In this specification, this represents an IP address in connection of the storage apparatus 200 to LAN 300. The storage ID in this first field is provided because it is required in correspondence to the computer system including a plurality of storage apparatuses.
  • The second field stores an identification number of the object logical volume in the storage apparatus specified by the first field. By the first field and the second field, the logical volume is uniquely identified in the entire information system. The third field stores the redundant group number. The fourth to the seventh field store the hint specified when the object logical volume is allocated. The fourth field (R/W) stores the read/write ratio. The fifth field (I/O size) stores the I/O size. The sixth field (Trans) stores the I/O wait time importance. The seventh field (Band) stores the bandwidth importance.
  • FIG. 6 shows a processing flow in the storage allocation section 110. The processing shown in FIG. 6 uses the size of the logical volume allocated and the hint as the input parameters. These parameters are specified by the user via the aforementioned user interface.
  • In steps 1000 to 1030, the RAID level of the redundant group for creating a logical volume is selected. Firstly, in step 1000, it is checked whether the AccessDirectionHint (read/write ratio) of the specified hint is 4 or below. If so, it is considered that the access is oriented to read and the RAID level 5 is selected (step 1030). In step 1010, if the hint AccessSizeHint (average I/O size) is 256 kilobytes or above, the access is considered to be large. The large access means that the data transfer amount required in one access is 256 kilobytes or above. It should be noted that not large access is a small access. If the access is large, the RAID level 5 is selected. Otherwise, the RAID level 1 is selected.
  • In steps 1040 to 1160, the redundant group for creating a logical volume is selected. In this step, the RAID level which has been selected in the preceding step, the values of hints AccessLatencyHint (I/O wait time importance) and AccessBandwidthWeight (data transfer bandwidth importance) are referenced. Step 1040 checks whether the AccessLatencyHint or AccessBandwidthWeight is 0 or above. If these values are 8 or above, it is considered that high access performance is required and control is passed to step 1050. Otherwise, control is passed to the condition judgment of step 1070.
  • In step 1050, a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200.
    • Condition 1: RAID level selected in step 1020 or 1030.
    • Condition 2: Can create a logical volume of specified size.
    • Condition 3: Two or one logical volume is included in the redundant group.
    • Condition 4: For the logical volumes contained in the redundant group, the hint AccessLatencyHint (I/O wait time importance) related to the logical volumes is 4 or below and the AccessBandwidthWeight (data transfer bandwidth importance) is 4 or below.
  • When such a redundant group is detected, control is passed to step 1160. Otherwise, control is passed to step 1080.
  • Step 1070 checks whether the AccessLatencyHint (I/O wait time importance) or AccessBandwidthWeight (data transfer bandwidth importance) is 4 or above. If these values are 4 or above, control is passed to step 1080. Otherwise, control is passed to step 1100.
  • In step 1080, a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200.
    • Condition 1: RAID level selected in step 1020 or 1030.
    • Condition 2: Can create a logical volume of specified size.
    • Condition 3: Ten or less logical volumes are included in the redundant group.
    • Condition 4: For the logical volumes contained in the redundant group, the hint AccessLatencyHint (I/O wait time importance) or the AccessBandwidthWeight (data transfer bandwidth importance) is 3 or below.
  • When such a redundant group is detected, control is passed to step 1160. Otherwise, control is passed to step 1100. In step 1100, a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200.
    • Condition 1: RAID level selected in step 1020 or 1030.
    • Condition 2: Can create a logical volume of specified size.
    • Condition 3: There exists no logical volumes contained in the redundant group having the hint of AccessLatencyHint (I/O wait time importance) or the AccessBandwidthWeight (data transfer bandwidth importance) which is 7 or above.
  • When such a redundant group is detected, control is passed to step 1160. Otherwise, control is passed to step 1120. In step 1120, a redundant group satisfying the following conditions is detected according to the allocation management information 150 and the storage volume management information 230 acquired from the storage apparatus 200.
  • Condition 1: Can create a logical volume of specified size.
  • Condition 2: There exists no logical volumes contained in the redundant group having the hint of AccessLatencyHint (I/O wait time importance) or the AccessBandwidthWeight (data transfer bandwidth importance) which is 7 or above.
  • When such a redundant group is detected, control is passed to step 1160. Otherwise, control is passed to step 1140. In step 1140, redundant groups which can create a logical volume of the specified size are selected at random. If no such redundant group exists, an error is caused. In step 1160, the redundant group detected is selected as a redundant group for allocating the logical volume.
  • In step 1170, the selected redundant group and the logical volume size are specified for the storage apparatus 200 and creation of the logical volume is instructed. Thus, a new logical volume is created by the aforementioned storage volume allocation section 240. In step 1180, the configuration information on the logical volume created in step 1170 is added to the allocation management information 150. Here, the information recorded are storage ID, the logical volume number, the redundant group number, and the hint.
  • It should be noted that the algorithm of the logical volume allocation processing explained up to step 1170 is only an example. The present invention can be realized by using an algorithm other than this algorithm.
  • The method for logical volume allocation based on the hint has been explained.
  • In this embodiment, monitoring of the logical volume is performed by using the hint used in volume allocation. The monitoring of the logical volume is performed basically by comparing the various performance values of the logical volume to threshold values. The threshold values are stored in the threshold value information 170.
  • FIG. 7 explains the contents of the threshold value information 170. As shown in FIG. 7, the data format of the threshold value information 170 is a table format. Each line of the threshold value information 170 corresponds to the logical volume of the threshold value management object. Each line consists of five fields.
  • Hereinafter, a logical volume corresponding to each volume will be referred to as a corresponding logical volume. The first field stores the storage ID of the corresponding logical volume. The second field stores the logical volume number of the corresponding logical volume. The third field stores a threshold value of the average wait time for the corresponding logical volume. The fourth field stores a threshold value of the average data transfer amount for the corresponding logical volume. The fifth field stores a threshold value of the average data transfer amount per wait time for the corresponding logical volume. This value is a threshold value of the value decided by the following equation:
    (average data transfer amount per second)/{(average processing wait time)*(average number of requests per second)}
  • In the threshold value information 170, the value 0 means that no value is decided. That is, the item whose value is 0 is not monitored. Setting of the threshold value is performed by the threshold composing section 120. In this embodiment, the monitoring object is a performance value of the logical volume.
  • The processing in the threshold composing section is executed when the logical volume is allocated. The parameters input for this processing are the storage ID of the logical volume, the logical volume number, and the hint. The threshold composing section 120 decides a threshold value according to the information indicating the relationship between the hint and the threshold value. In this embodiment, for example, the threshold composing section 120 decides a threshold value according to two tables shown in FIG. 8.
  • Table 801 shows correspondence between the value of the AccessLatencyHint (I/O wait time importance) of the hint and the logical volume average access wait time threshold value. The first field of each line shows the value of the AccessLatencyHint. The second field shows a threshold value of the average access wait time of the logical volume corresponding to the AccessLatencyHint value shown in the first field. Table 802 shows correspondence between the value of the AccessBandwidthWeight (data transfer bandwidth importance) and the threshold value of the average data transfer amount per the logical volume wait time. The first field of each line shows the value of the AccessBandwidthWeight. The second field shows a threshold value of the average data transfer amount per logical volume wait time. It should be noted that in tables 801 and 802, the threshold value 0 means that the threshold value is not monitored.
  • The threshold composing section 120 decides the monitoring threshold value of the logical volume for storing the information on the relationship between the hints and the threshold values according to the tables 801 and 802 in the threshold value information 170. Here, in this embodiment, the monitoring threshold values are automatically decided by the management computer 100. However, it is also possible to prompt a user to correct or acknowledge a threshold value by using the aforementioned user interface before deciding the threshold value.
  • The performance information 160 stores a performance value acquired from the storage apparatus 200. FIG. 9 explains information stored in the performance information 160. Especially performance information 161 of the logical volume 260 is detailed. As shown in FIG. 9, the performance information of the logical volume 260 is in a table format having 9 fields. Each line corresponds to a time when the performance information concerning the logical volume 260 is acquired. The first field stores the time when the performance information is acquired. The second field stores the average I/O size of read access. The third field stores the average data transfer amount per read access unit time. Here, the unit time is second. The fourth field stores the average processing wait time of read access. The fifth field stores the average number of read accesses per unit time. Here, the unit time is second. The sixth field stores the average I/O size of write access. The seventh field stores the average data transfer amount of write access per unit time. Here, the unit time is second. The eighth field stores write access average processing wait time. The ninth field stores the number of average write accesses per unit time. Here, the unit time is second.
  • The performance information of the logical volumes 261 to 264 are also stored in the performance information 160 like the logical volume 260. The data format of the performance information of the logical volumes 261 to 264 is identical to the data format of the performance information 161 of the logical volume 260.
  • The performance information acquisition section 130 periodically acquires the performance information of the logical volumes 260 to 264 from the storage apparatus 200 and adds it to the performance information 160. Moreover, at the timing when the performance information is acquired from the storage apparatus 200, the performance information acquired is compared to the threshold value set in the threshold value information 170. The processing flow in the performance information acquisition section 130 is shown in the flowchart of FIG. 10. Explanation will be given on the performance acquisition section 130 with reference to FIG. 10.
  • Steps 1410 to 1440 constitute a loop structure. This loop processing is executed for the logical volume to be monitored. Step 1410 selects a logical volume for which performance information is to be acquired. Here, the logical volume specified by the first field and the second field of each line of the threshold value information 170 is successively selected from the first line of the threshold value information 170 (from the uppermost line in the figure).
  • In step 1420, the performance information on the logical volume selected in step 1410 is acquired. The performance information acquired here are values corresponding to the respective fields of the logical volume performance information. That is, the average I/O size of read access, the average data transfer amount per unit time of the read access, the average processing wait time of read access, the average number of read accesses per unit time, the average I/O size of write access, the average data transfer amount per unit time of write access, the average processing wait time of write access, and the average number of write accesses per unit time.
  • In order to acquire these values, the performance information acquisition section 130 request the storage apparatus indicated by the first field of the threshold value information 170 t output performance information. In the storage apparatus 200, the performance information acquisition request executed in step 1420 of the performance information acquisition section 130 is processed by the performance value notification section 250.
  • In step 1430, the performance information acquired in step 1420 is added to the performance information 160. Here, the time when the performance information is acquired is stored as the first field. In step 1440, if the performance information acquisition processing of all the logical volumes contained in the threshold value information 170 is not complete, the processing from step 1410 is performed to the next logical volume.
  • Next, explanation will be given on the monitoring using a hints and a threshold value. As has been described in the background art, the management system of the computer system notifies a warning to a user when the various monitoring numeric value items of the device to be monitored violates a predetermined threshold value. In this invention, when the warning is notified to the user, a message concerning the hint is also notified. This operation is realized by the warning notification section 140.
  • FIG. 11 is a flowchart showing a processing flow in the warning notification section 140. The processing shown in FIG. 11 is executed after the performance information collection processing of the logical volume is executed in the performance information acquisition section 130. The processing shown in FIG. 11 is for a single logical volume. The processing shown in FIG. 11 is executed for all the logical volumes specified by the first and the second field of the threshold value information 170. The input parameters of the processing shown in FIG. 11 are a logical volume number and a storage ID of the apparatus providing the logical volume. In the explanation below, the logical volume specified by the input parameter will be referred to as an object logical volume. In the processing shown in FIG. 11, the performance information used for inspection is the latest acquired by the performance information acquisition section 130.
  • In step 1600, it is checked whether the average data transfer amount per processing wait time of the read and write request is below a threshold value. The threshold value used is the average data transfer amount threshold value per processing wait time of the object logical volume. Here, the value of the inspection object used is based on the latest performance information on the object logical volume stored in the performance information 160. For each of read and write, the average data transfer amount is divided by the average processing wait time to obtain a quotient, which is used. That is, two values of read and write are used as values of inspection objects.
  • The two values of inspection objects are compared to the aforementioned threshold value. If one of them is lower than the threshold value, it is assumed that a performance problem has occurred and control is passed to step 1620. Otherwise, control is passed to step 1610. In step 1610, it is checked whether the average processing wait time of read and write request for the object logical volume is above a threshold value. The threshold value used here is an average processing wait time threshold value stored in the threshold value information 170 and corresponding to the object logical volume.
  • The value of the inspection object used here is the latest performance information on the object logical volume stored in the performance information 160, i.e., the average processing time for each of read and write. That is, two values of read and write are used as values of inspection objects. The two values of inspection objects are compared to the aforementioned threshold value. If one of them exceeds the threshold value, it is assumed that a performance problem has occurred and control is passed to step 1620. Otherwise, control is passed to step 1770.
  • Step 1620 checks whether the characteristics of actual access to the object logical volume (read/write ratio and I/O size) are appropriate for the RAID level of the redundant group to which the object logical volume belongs. Hereinafter, the RAID level of the redundant group of the object logical volume will be referred to simply as the RAID level of the object logical volume.
  • When the RAID level of the object logical volume is 1, the characteristic of the access to the object logical volume is assumed to be appropriate for the RAID level if both of the following conditions are satisfied:
    • Condition 1: Average write I/O size is 256 kilobytes or below.
    • Condition 2: Average read IOPS is smaller than the average write multiplied by 1.5.
  • When the RAID level of the object logical volume is 5, the characteristic of the access to the object logical volume is assumed to be appropriate for the RAID level if one of the conditions 1 or 2 or both of them are not satisfied. If the characteristic of the access to the object logical volume is judged to be appropriate for the RAID level, control is passed to step 1680. Otherwise, control is passed to step 1640. It should be noted that the aforementioned conditions 1 and 2 are equivalent to the conditions for selecting the RAID level in the logical volume allocation.
  • In step 1640, conformity between the allocation hint and the actual access characteristic of the object logical volume is checked. In this step, if one of the following conditions is satisfied, it is judged that the actual access characteristic is not appropriate for the allocation hint of the object logical volume.
  • Condition 1: The average write I/O size as the latest performance information on the object logical volume stored in the performance information 160 is 256 kilobytes or below and the I/O size of the allocation hint is 250 kilobytes or above.
  • Condition 2: The average write I/O size as the latest performance information on the object logical volume stored in the performance information 160 is 256 kilobytes or above and the I/O size of the allocation hint is 250 kilobytes or below.
  • Condition 3: The read IOPS as the latest performance information on the object logical volume stored in the performance information 160 is the write IOPS multiplied by 1.5 or below and the read/write ratio of the allocation hint is 6 or below.
  • Condition 4: The read IOPS as the latest performance information on the object logical volume stored in the performance information 160 is the write IOPS multiplied by 1.5 or above and the read/write ratio of the allocation hint is 6 or above.
  • In step 1650, a warning message is created to indicate the inconformity between the actual access characteristic for the object logical volume and the allocation hint of the object logical volume judged in step 1640. For Conditions 1 to 4, a messages created when the respective conditions are satisfies are as follows. It should be noted that the inconformity of the RAID level is generated.
  • 1. When Condition 1 or 2 is satisfied, the message says that “the I/O size of access to the <<object logical volume>> does not coincide with the I/O size specified for the hint.”
  • 2. When Condition 3 or 4 is satisfied, the message says that “the read/write ratio to/from the <<object logical volume>> does not coincide with the read/write ratio specified for the hint.”
  • 3. When none of Conditions 1 to 4 is satisfied, the message says that “<<the object logical volume>> allocated is not a logical volume appropriate for the hint.” The part <<object logical volume>> is replaced by a word representing the object logical volume.
  • After the message is created in step 1650, control is passed to step 1670. Steps 1670 to 1750 check the redundant group containing the object logical volume, i.e., the hint and actual access frequency of the logical volume other than the object logical volume contained in the redundant group.
  • Such a check is performed because of the following reasons. In this embodiment, the logical volume given a low value for the AccessLatencyHint (I/O wait time importance) and the AccessBandwidthWeight (data transfer bandwidth importance) in the hint during the allocation is assumed to have a low access frequency. Accordingly, for the redundant group containing such logical volumes, a logical volume having a high AccessLatencyHint and AccessBandwidthWeight may be allocated later.
  • Under such a condition, if the access to the logical volume whose access has been considered low increases, the logical volume requiring a high access frequency allocated later may be affected and its performance may be lowered. Although such performance lowering (threshold value violation) may be recognized, its cause may not be known.
  • Accordingly, for the threshold value violation by the object logical volume, notification of a logical volume which may possibly a cause to a user will help the user to study the performance improvement of the logical volume.
  • In step 1670, for the redundant group to which the object logical volume belongs, one logical volume (other than the object logical volume) belonging to the redundant group is selected. Selection of the logical volume can be performed by checking the logical volume management information 232. It should be noted that steps 1670 to 1750 constitute a loop structure but in step 1670, it is assumed that a logical volume which has been selected once will not be selected again. Hereinafter, the logical volume selected in step 1670 will be referred to as the selected logical volume.
  • Step 1680 makes a check for the selected logical volume, i.e., conformity between the AccessLatencyHint (I/O wait time importance) and AccesssBandwidthWeight (data transfer bandwidth importance) which are hints during allocation and the performance value. Here, it is checked whether access to the selected logical volume is increased in spite of the low value of the AccessLatencyHint and AccessBandwidthWeight of the selected logical volume. If the selected logical volume is in such a state, control is passed from step 1690 to step 1700. Otherwise, control is passed to step 1750. As will be detailed later, the processing of step 1700 creates a message describing affect to the performance.
  • Firstly, AccessLatencyHint and AccessBandwidthWeight of the selected logical volume are acquired from the allocation management information 150. Next, the read IOPS and write IOPS are acquired from the performance information by the latest performance information of the selected logical volume. If the AccessLatencyHint and AccessBandwidthWeight is lass than 4 and the sum of the read IOPS and the write IOPS is greater than a predetermined value, the selected logical volume is assumed to be a logical volume affecting the performance of the object logical volume.
  • Step 1700 creates a message describing that the selected logical volume has an affect to the performance of the object logical volume. The message created here is as follows. “<<The selected logical volume>> is accessed with a high frequency unlike the specified hint”. <<The selected logical volume>> is replaced by a word representing a selected logical volume.
  • Step 1750 is the end of the loop. This step checks whether all the logical volumes contained in the redundant group of the object logical volume have been subjected to the processing of steps 1670 to 1700. If there is a logical volume not processed, control is returned to step 1670. Here, the logical volumes belonging to the same redundant group interact their performances as has been described above. Such a phenomenon can also be seen depending on the RAID level.
  • A write access of a small I/O size (equal to the striping unit or below) to the redundant group of RAID level 5 gives a great affect to the performance of the entire redundant group. Accordingly, in the loop of steps 1670 to 1700, with respect to the selected logical volume, it is effective to check conformity between the RAID level and the performance value by the method described in steps 1620 to 1640 and create a message as has been described in step 1650.
  • The processing of step 1760 is executed when no threshold value violation is recognized in steps 1600 and 1610. Here, the target is to notify a user that the access frequency is actually low although a high performance is required of the object logical volume by the hint. Step 1760 checks whether the average data transfer amount of the object logical volume is lower than the threshold value.
  • The threshold value in this step is the data transfer amount threshold value of the object logical volume stored in the threshold value information 170. This step compares the sum of the average read data transfer amount and the average write data transfer amount of the object logical volume stored in the performance information 160 with the aforementioned threshold value. As a result, if the sum is lower than the threshold value, the object logical volume is assumed to be a logical volume which has an excessively high performance for the actual access. And in step 1770, a message is created. Otherwise, this series of processing is terminated.
  • Step 1770 creates a message as follows. “<<The object logical volume>> has an excessively high performance for the actual use.” The part <<the object logical volume>> is replaced by a character string representing the object logical volume.
  • Step 1780 notifies a warning of threshold value violation to the user. When notifying the warning, the messages created in steps 1650, 1700, and 1770 are included. The warning is notified to the user via the aforementioned user interface. It is also possible to notify the user by using the log recording function such as syslog. Moreover, it is possible to use the message exchange function such as e-mail. Moreover, it is also possible to notify the warning to the user by using the protocol, for management such as SNMP.
  • Thus, the logical volume is monitored and if a threshold value violation is generated, an appropriate message is reported to the user.
  • Second Embodiment
  • Description will now be directed to a second embodiment of the present invention. FIG. 12 shows the second embodiment of the present invention. The sections and information equivalent to the storage allocation section 110, the threshold composing section 120, the warning notification section 140, the allocation management section 150, the performance information 160, and the threshold information which are contained in the management computer 100 (see FIG. 2) in the first embodiment are contained in the apparatus in the second embodiment. The storage apparatus 2200 is an extended device of the storage apparatus 200 (see FIG. 2) for containing these sections and information.
  • The storage apparatus 220 includes a storage allocation section 2110, a monitoring section 2120, a warning notification section 2140, allocation management information 2150, performance information 2160, and threshold information 2170. These sections and information are equivalent to the sections and information of the same names in the management computer 100 of the first embodiment which are operated in the storage apparatus 2200. In the second embodiment, the controller 210 includes a CPU 201 and a memory 202 and has an ability to interpret and execute a program. The sections 220, 240, 250, 2250, 2110, 2120, and 2140 are programs which are stored in the memory 202 and executed by the controller 210. It should be noted that the present invention can also be realized by using the storage apparatus having dedicated hardware for the functions equivalent to the sections 220, 240, 2250, 2110, 2120, and 2140.
  • In the second embodiment, the functions of the performance information acquisition section 130 and the performance value notification section 250 are realized by the performance value notification section 2250. That is, the performance value notification section 2250 accumulates information on the performance of the logical volumes 260 to 264 in the performance information 2160.
  • The management computer 2100 is an ordinary computer having a user interface 180. By using the user interface 2180, like the first embodiment, the user can control the storage allocation section 2110, the monitoring section 2120, and the warning notification section 2140 of the storage apparatus 2200. Moreover, the management computer 100 can also have the effect of the present invention in the second embodiment from the explanation of the first embodiment concerning the allocation management information 150, the performance information 160, and the threshold value information 170.
  • Thus, the two embodiments have been explained. Here, additional explanation will be given on the embodiments.
  • In the first and the second embodiment, the storage apparatus contained in the computer system is the storage apparatus 200 or 2200. However, the present invention can also be applied to a computer system containing a plurality of storage apparatuses. In the first and the second embodiment, only one FC switch is contained in the computer system. However, the essential quality of the present invention will not be changed by the number of the FC switches.
  • The first and the second embodiment can be extended in such a manner that the performance information can be acquired not only from the storage apparatus but also from the computer or the FC switch and threshold values can be set for them.
  • There is a storage apparatus which has a function to improve the performance inside the storage apparatus. For example, the aforementioned storage area network has a function for always containing the data stored in the logical volume in the cache memory (cache resident function). This dramatically improves the access performance to the logical volume. In the processing flow explained with reference to FIG. 11, a message is created in steps 1650 and 1700. In these steps, it is possible to create a message to suggest application of the aforementioned cache resident function for the logical volume.
  • Moreover, it is possible to calculate the size of the appropriate cache memory size for the logical volume and automatically apply the cache resident function. In this case, the message includes that the cache resident function is automatically applied.
  • Moreover, in addition to the cache resident function, the performance improvement function includes a logical volume movement function for moving data stored in a logical volume to another logical volume and a band control function for controlling the bandwidth used by the I/O request from a particular computer in the FC interface.
  • The present invention has been explained through the embodiments. However, the present invention is not to be limited to these embodiments but can be modified in various ways without departing from the spirit of the invention.

Claims (21)

1. A computer-readable storage medium containing a computer system management program for managing a computer system having a storage apparatus and for causing a computer to execute steps of:
creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
deciding a threshold value associated with performance information indicating performance of the storage volume;
acquiring the performance information indicating the performance of the storage volume of the storage apparatus; and
comparing the performance information to the threshold value and detecting a threshold value violation.
2. The storage medium according to claim 1, wherein the medium contains a program causing a computer to execute further a step of notifying a warning when the threshold value violation is detected.
3. The storage medium according to claim 2, wherein a message based on the parameter is added to the warning.
4. The storage medium according to claim 3, wherein the message includes a suggestion of use of a unit for improving the performance of the storage apparatus arranged in the storage apparatus.
5. The storage medium according to claim 4, wherein the step of deciding the threshold value decides the threshold value according to the information indicating the relationship between the parameter and the threshold value.
6. The storage medium according to claim 5, wherein the parameter indicating the characteristic of the storage volume includes at least one of a read/write ratio, a average I/O size, I/O wait time importance, and data transfer bandwidth importance.
7. The storage medium according to claim 6, wherein the threshold value includes at least one of a threshold value of average wait time, a threshold value of an average data transfer amount, and a threshold value of an average data transfer amount per wait time.
8. The storage medium according to claim 7, wherein the performance information indicating the performance of the storage region includes at least one of a read access average I/O size, an average data transfer amount per read access unit time, read access average processing wait time, an average number of read accesses per unit time, a write access average I/O size, an average data transfer amount per write access unit time, write access average processing wait time, and an average number of write accesses per unit time.
9. A computer system management method performed by a management computer for managing a computer system including a storage apparatus, the method comprising steps of:
creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
deciding a threshold value associated with performance information indicating performance of the storage volume;
acquiring the performance information indicating the performance of the storage volume of the storage apparatus; and
comparing the performance information to the threshold value and detecting a threshold value violation.
10. A computer system management system for managing a computer system including a storage apparatus, the system comprising:
a unit for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a unit for deciding a threshold value associated with performance information indicating performance of the storage volume;
a unit for acquiring the performance information indicating the performance of the storage volume of the storage apparatus; and
a unit for comparing the performance information to the threshold value and detecting a threshold value violation.
11. The computer system management system according to claim 10, wherein a warning is notified when the threshold value violation is detected.
12. The computer system management system according to claim 11, wherein a message based on the parameter is added to the warning.
13. The computer system management system according to claim 12, wherein the storage apparatus includes a unit for improving performance of the storage apparatus, and wherein the message includes a suggestion of use of the unit for improving the performance of the storage apparatus.
14. The computer system management system according to claim 10, wherein the unit for deciding the threshold value includes a unit for deciding the threshold value according to information indicating a relationship between the parameter and the threshold value.
15. A computer system management system for managing a computer system including a storage apparatus,
wherein the computer system includes a management apparatus connected via a network or an interface to the storage apparatus, and
the management apparatus comprising:
a storage allocation section for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a monitoring section for deciding a threshold value associated with performance information indicating performance of the storage volume according to the parameter;
a performance information acquisition section for acquiring performance information indicating the performance of the storage volume from the storage apparatus; and
a warning notification section for comparing the performance information to the threshold value, detecting whether a threshold value is violated, and notifying a warning when a threshold value violation is detected.
16. The computer management system according to claim 15, wherein the computer system comprises a computer for performing a read/write request to the storage apparatus.
17. The computer system management system for managing a computer system comprising a storage apparatus, wherein the storage apparatus comprises:
a storage allocation section for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a monitoring section for deciding a threshold value associated with performance information indicating performance of the storage volume according to the parameter;
a performance information acquisition section for acquiring performance information indicating the performance of the storage volume from the storage apparatus; and
a warning notification section for comparing the performance information to the threshold value, detecting whether a threshold value is violated, and notifying a warning when a threshold value violation is detected.
18. The computer management system according to claim 17, wherein the computer system comprises a computer performing a read/write request to the storage apparatus.
19. The management apparatus for a computer system management system for managing a computer system comprising a storage apparatus, the management apparatus comprising:
a storage allocation section for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a monitoring section for deciding a threshold value associated with performance information indicating performance of the storage volume according to the parameter;
a performance information acquisition section for acquiring performance information indicating the performance of the storage volume from the storage apparatus; and
a warning notification section for comparing the performance information to the threshold value, detecting whether a threshold value is violated, and notifying a warning when a threshold value violation is detected.
20. A storage apparatus for a computer system management system for managing a computer system comprising a storage apparatus, comprising:
a storage allocation section for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a monitoring section for deciding a threshold value associated with performance information indicating performance of the storage volume according to the parameter;
a performance information acquisition section for acquiring performance information indicating the performance of the storage volume from the storage apparatus; and
a warning notification section for comparing the performance information to the threshold value, detecting whether a threshold value is violated, and notifying a warning when a threshold value violation is detected.
21. A computer system management system for managing a computer system including a storage apparatus, the system comprising:
a unit for creating a storage volume in the storage apparatus according to a parameter indicating a characteristic of the storage volume;
a unit for deciding a threshold value associated with performance information indicating performance of the storage volume;
a unit for acquiring performance information indicating the performance of the storage volume of the storage apparatus; and
a unit for comparing the performance information to the threshold value and detecting a threshold value violation, wherein:
a warning is notified when the threshold value violation is detected,
a message based on the parameter is added to the warning,
the storage apparatus includes a unit for improving performance of the storage apparatus and the message includes a suggestion of use of the unit for improving the performance of the storage apparatus, and
the unit for deciding the threshold value includes a unit for deciding the threshold value according to the information indicating relationship between the parameter and the threshold value.
US10/816,552 2003-12-17 2004-03-31 Computer system management program, system and method Abandoned US20050138285A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11/591,038 US7216263B2 (en) 2003-12-17 2006-10-31 Performance monitoring and notification in a threshold sensitive storage management system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2003-419425 2003-12-17
JP2003419425A JP4244319B2 (en) 2003-12-17 2003-12-17 Computer system management program, recording medium, computer system management system, management device and storage device therefor

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US11/591,038 Continuation US7216263B2 (en) 2003-12-17 2006-10-31 Performance monitoring and notification in a threshold sensitive storage management system

Publications (1)

Publication Number Publication Date
US20050138285A1 true US20050138285A1 (en) 2005-06-23

Family

ID=34675212

Family Applications (2)

Application Number Title Priority Date Filing Date
US10/816,552 Abandoned US20050138285A1 (en) 2003-12-17 2004-03-31 Computer system management program, system and method
US11/591,038 Expired - Fee Related US7216263B2 (en) 2003-12-17 2006-10-31 Performance monitoring and notification in a threshold sensitive storage management system

Family Applications After (1)

Application Number Title Priority Date Filing Date
US11/591,038 Expired - Fee Related US7216263B2 (en) 2003-12-17 2006-10-31 Performance monitoring and notification in a threshold sensitive storage management system

Country Status (2)

Country Link
US (2) US20050138285A1 (en)
JP (1) JP4244319B2 (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060235649A1 (en) * 2005-04-15 2006-10-19 Larry Lancaster Automated detecting and reporting on field reliability of components
US7156130B2 (en) 2002-07-05 2007-01-02 Ricoh Company, Ltd. Toner filling device and toner production management system
US20070055713A1 (en) * 2005-09-02 2007-03-08 Hitachi, Ltd. Computer system, storage system and method for extending volume capacity
US20070136395A1 (en) * 2005-12-09 2007-06-14 Microsoft Corporation Protecting storage volumes with mock replication
US20080010513A1 (en) * 2006-06-27 2008-01-10 International Business Machines Corporation Controlling computer storage systems
US20080162082A1 (en) * 2006-12-29 2008-07-03 Peter Frazier Two dimensional exponential smoothing
US20090113156A1 (en) * 2007-10-31 2009-04-30 Kazuhisa Fujita Management method of performance history and a management system of performance history
US20110055844A1 (en) * 2009-08-28 2011-03-03 Nguyen Tung M High density multi node computer with integrated shared resources
US8954979B1 (en) * 2011-08-15 2015-02-10 Netapp, Inc. Method and system for managing resources in a network
US20150121088A1 (en) * 2013-10-30 2015-04-30 Lsi Corporation Method of managing aligned and unaligned data bands in a self encrypting solid state drive
CN104932953A (en) * 2015-06-04 2015-09-23 华为技术有限公司 Data distribution method, data storage method, and relevant device and system
CN104937566A (en) * 2013-03-29 2015-09-23 惠普发展公司,有限责任合伙企业 Performance rules and storage units
US9317224B1 (en) * 2013-06-28 2016-04-19 Emc Corporation Quantifying utilization of a data storage system by a virtual storage unit
US20160170650A1 (en) * 2014-12-15 2016-06-16 Fujitsu Limited Storage management device, performance adjustment method, and computer-readable recording medium
US20170228187A1 (en) * 2016-02-08 2017-08-10 Nec Corporation Control device
US11327910B2 (en) * 2016-09-20 2022-05-10 Netapp, Inc. Quality of service policy sets
US11379119B2 (en) 2010-03-05 2022-07-05 Netapp, Inc. Writing data in a distributed data storage system
US11386120B2 (en) 2014-02-21 2022-07-12 Netapp, Inc. Data syncing in a distributed system

Families Citing this family (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7249287B2 (en) * 2004-04-19 2007-07-24 General Electric Company Methods and apparatus for providing alarm notification
JP4576923B2 (en) * 2004-08-09 2010-11-10 株式会社日立製作所 Storage system storage capacity management method
US7408441B2 (en) * 2004-10-25 2008-08-05 Electronic Data Systems Corporation System and method for analyzing user-generated event information and message information from network devices
US20060168170A1 (en) * 2004-10-25 2006-07-27 Korzeniowski Richard W System and method for analyzing information relating to network devices
US7408440B2 (en) 2004-10-25 2008-08-05 Electronics Data Systems Corporation System and method for analyzing message information from diverse network devices
US20060123285A1 (en) * 2004-11-16 2006-06-08 De Araujo Daniel F Dynamic threshold scaling in a communication system
EP1760587A1 (en) * 2005-01-31 2007-03-07 Ubs Ag Method for the scheduling of software modules
JP4313336B2 (en) * 2005-06-03 2009-08-12 株式会社日立製作所 Monitoring system and monitoring method
US7844701B2 (en) * 2005-08-01 2010-11-30 Network Appliance, Inc. Rule-based performance analysis of storage appliances
US20070064736A1 (en) * 2005-09-19 2007-03-22 Fujitsu Network Communications Zero suppressed performance management data interpretation and same value suppression and interpretation
US20070081464A1 (en) * 2005-10-11 2007-04-12 Fujitsu Network Communications, Inc. Real-time performance monitoring of ethernet data over sonet
JP4749930B2 (en) * 2006-04-24 2011-08-17 株式会社日立製作所 Computer system, management computer, storage device, and volume allocation confirmation method
JP2007316725A (en) * 2006-05-23 2007-12-06 Hitachi Ltd Storage area management method and management computer
US8555021B1 (en) * 2006-09-29 2013-10-08 Emc Corporation Systems and methods for automating and tuning storage allocations
US9042263B1 (en) * 2007-04-06 2015-05-26 Netapp, Inc. Systems and methods for comparative load analysis in storage networks
US7853759B2 (en) * 2007-04-23 2010-12-14 Microsoft Corporation Hints model for optimization of storage devices connected to host and write optimization schema for storage devices
JP2008276596A (en) 2007-05-01 2008-11-13 Hitachi Ltd Method for determining storage device and computer
US9717896B2 (en) 2007-12-18 2017-08-01 Gearbox, Llc Treatment indications informed by a priori implant information
US8636670B2 (en) 2008-05-13 2014-01-28 The Invention Science Fund I, Llc Circulatory monitoring systems and methods
US20090287120A1 (en) 2007-12-18 2009-11-19 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Circulatory monitoring systems and methods
JP4519179B2 (en) * 2008-02-25 2010-08-04 富士通株式会社 Logical volume management program, logical volume management apparatus, logical volume management method, and distributed storage system
JP5298594B2 (en) * 2008-03-26 2013-09-25 富士通株式会社 Allocation control program, allocation control device, and allocation control method
JP5081718B2 (en) * 2008-05-20 2012-11-28 株式会社日立製作所 Computer system, management server, and configuration information acquisition method
US8271706B2 (en) * 2008-05-22 2012-09-18 International Business Machines Corporation Stabilization of host to storage subsystem ownership
US8171075B2 (en) * 2009-06-14 2012-05-01 International Business Machines Corporation Generating hints for more optimal processing of requests for information within an environment in which resources are abstracted using a model
US8965937B2 (en) * 2011-09-28 2015-02-24 International Business Machines Corporation Automated selection of functions to reduce storage capacity based on performance requirements
US8850153B2 (en) 2011-09-30 2014-09-30 International Business Machines Corporation Enabling throttling on average write throughput for solid state storage devices
WO2013186870A1 (en) * 2012-06-13 2013-12-19 株式会社日立製作所 Service monitoring system and service monitoring method
US9665630B1 (en) * 2012-06-18 2017-05-30 EMC IP Holding Company LLC Techniques for providing storage hints for use in connection with data movement optimizations
US9088450B2 (en) 2012-10-31 2015-07-21 Elwha Llc Methods and systems for data services
US20140123325A1 (en) 2012-11-26 2014-05-01 Elwha Llc Methods and systems for managing data and/or services for devices
JP6179321B2 (en) * 2013-09-27 2017-08-16 富士通株式会社 Storage management device, control method, and control program
US9229640B2 (en) * 2013-11-15 2016-01-05 Microsoft Technology Licensing, Llc Inexpensive solid-state storage by throttling write speed in accordance with empirically derived write policy table
JP6273966B2 (en) 2014-03-27 2018-02-07 富士通株式会社 Storage management device, performance adjustment method, and performance adjustment program
JP6260407B2 (en) * 2014-03-28 2018-01-17 富士通株式会社 Storage management device, performance adjustment method, and performance adjustment program
JP6529304B2 (en) * 2015-03-25 2019-06-12 株式会社日立ソリューションズ Access control system and access control method
US9569136B2 (en) 2015-04-29 2017-02-14 International Business Machines Corporation Smart load balancing replication when adding or removing storage disks in a distributed storage system
US11093136B2 (en) * 2017-02-01 2021-08-17 Hewlett-Packard Development Company, L.P. Performance threshold
US10621160B2 (en) * 2017-03-30 2020-04-14 International Business Machines Corporation Storage management inconsistency tracker
US10481828B2 (en) * 2017-10-10 2019-11-19 Seagate Technology, Llc Slow drive detection
JP6878369B2 (en) * 2018-09-03 2021-05-26 株式会社日立製作所 Volume allocation management device, volume allocation management method, and volume allocation management program
US11514317B2 (en) * 2020-03-25 2022-11-29 EMC IP Holding Company LLC Machine learning based resource availability prediction

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5761411A (en) * 1995-03-13 1998-06-02 Compaq Computer Corporation Method for performing disk fault prediction operations
US5828583A (en) * 1992-08-21 1998-10-27 Compaq Computer Corporation Drive failure prediction techniques for disk drives
US5935261A (en) * 1997-06-05 1999-08-10 International Business Machines Corporation Method and apparatus for detecting handling damage in a disk drive
US5944782A (en) * 1996-10-16 1999-08-31 Veritas Software Corporation Event management system for distributed computing environment
US5987400A (en) * 1997-05-08 1999-11-16 Kabushiki Kaisha Toshiba System for monitoring the throughput performance of a disk storage system
US6058489A (en) * 1995-10-13 2000-05-02 Compaq Computer Corporation On-line disk array reconfiguration
US6408406B1 (en) * 1999-08-31 2002-06-18 Western Digital Technologies, Inc. Hard disk drive infant mortality test
US20020103969A1 (en) * 2000-12-12 2002-08-01 Hiroshi Koizumi System and method for storing data
US20030135609A1 (en) * 2002-01-16 2003-07-17 Sun Microsystems, Inc. Method, system, and program for determining a modification of a system resource configuration

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003122508A (en) * 2001-10-15 2003-04-25 Hitachi Ltd Volume management method and device
US7363656B2 (en) * 2002-11-04 2008-04-22 Mazu Networks, Inc. Event detection/anomaly correlation heuristics
JP4325843B2 (en) * 2002-12-20 2009-09-02 株式会社日立製作所 Logical volume copy destination performance adjustment method and apparatus
US7251691B2 (en) * 2003-07-11 2007-07-31 International Business Machines Corporation Autonomic predictive load balancing of output transfers for two peer computers for data storage applications
JP4421230B2 (en) * 2003-08-12 2010-02-24 株式会社日立製作所 Performance information analysis method
JP4485256B2 (en) * 2004-05-20 2010-06-16 株式会社日立製作所 Storage area management method and management system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5828583A (en) * 1992-08-21 1998-10-27 Compaq Computer Corporation Drive failure prediction techniques for disk drives
US5761411A (en) * 1995-03-13 1998-06-02 Compaq Computer Corporation Method for performing disk fault prediction operations
US6058489A (en) * 1995-10-13 2000-05-02 Compaq Computer Corporation On-line disk array reconfiguration
US5944782A (en) * 1996-10-16 1999-08-31 Veritas Software Corporation Event management system for distributed computing environment
US5987400A (en) * 1997-05-08 1999-11-16 Kabushiki Kaisha Toshiba System for monitoring the throughput performance of a disk storage system
US5935261A (en) * 1997-06-05 1999-08-10 International Business Machines Corporation Method and apparatus for detecting handling damage in a disk drive
US6408406B1 (en) * 1999-08-31 2002-06-18 Western Digital Technologies, Inc. Hard disk drive infant mortality test
US20020103969A1 (en) * 2000-12-12 2002-08-01 Hiroshi Koizumi System and method for storing data
US20030135609A1 (en) * 2002-01-16 2003-07-17 Sun Microsystems, Inc. Method, system, and program for determining a modification of a system resource configuration

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7156130B2 (en) 2002-07-05 2007-01-02 Ricoh Company, Ltd. Toner filling device and toner production management system
US7181364B2 (en) * 2005-04-15 2007-02-20 Network Appliance, Inc. Automated detecting and reporting on field reliability of components
US20060235649A1 (en) * 2005-04-15 2006-10-19 Larry Lancaster Automated detecting and reporting on field reliability of components
US20090300285A1 (en) * 2005-09-02 2009-12-03 Hitachi, Ltd. Computer system, storage system and method for extending volume capacity
US20070055713A1 (en) * 2005-09-02 2007-03-08 Hitachi, Ltd. Computer system, storage system and method for extending volume capacity
US8082394B2 (en) 2005-09-02 2011-12-20 Hitachi, Ltd. Computer system, storage system and method for extending volume capacity
US20070136395A1 (en) * 2005-12-09 2007-06-14 Microsoft Corporation Protecting storage volumes with mock replication
US7778959B2 (en) * 2005-12-09 2010-08-17 Microsoft Corporation Protecting storages volumes with mock replication
US20080010513A1 (en) * 2006-06-27 2008-01-10 International Business Machines Corporation Controlling computer storage systems
US20080228687A1 (en) * 2006-06-27 2008-09-18 International Business Machines Corporation Controlling Computer Storage Systems
US8185779B2 (en) 2006-06-27 2012-05-22 International Business Machines Corporation Controlling computer storage systems
US20080162082A1 (en) * 2006-12-29 2008-07-03 Peter Frazier Two dimensional exponential smoothing
US8103479B2 (en) * 2006-12-29 2012-01-24 Teradata Us, Inc. Two dimensional exponential smoothing
EP2056200A1 (en) * 2007-10-31 2009-05-06 Hitachi, Ltd. A management method of performance history and a management system of performance history
US20090113156A1 (en) * 2007-10-31 2009-04-30 Kazuhisa Fujita Management method of performance history and a management system of performance history
US8117386B2 (en) 2007-10-31 2012-02-14 Hitachi, Ltd. Management method of performance history and a management system of performance history
US8225041B2 (en) 2007-10-31 2012-07-17 Hitachi, Ltd. Management method of performance history and a management system of performance history
US20110055844A1 (en) * 2009-08-28 2011-03-03 Nguyen Tung M High density multi node computer with integrated shared resources
US9442540B2 (en) * 2009-08-28 2016-09-13 Advanced Green Computing Machines-Ip, Limited High density multi node computer with integrated shared resources
US10467021B2 (en) 2009-08-28 2019-11-05 Advanced Green Computing Machines-Ip High density multi node computer with improved efficiency, thermal control, and compute performance
US11379119B2 (en) 2010-03-05 2022-07-05 Netapp, Inc. Writing data in a distributed data storage system
US8954979B1 (en) * 2011-08-15 2015-02-10 Netapp, Inc. Method and system for managing resources in a network
US10489065B2 (en) 2013-03-29 2019-11-26 Hewlett Packard Enterprise Development Lp Performance rules and storage units
CN104937566A (en) * 2013-03-29 2015-09-23 惠普发展公司,有限责任合伙企业 Performance rules and storage units
US9317224B1 (en) * 2013-06-28 2016-04-19 Emc Corporation Quantifying utilization of a data storage system by a virtual storage unit
US9176896B2 (en) * 2013-10-30 2015-11-03 Seagate Technology Llc Method of managing aligned and unaligned data bands in a self encrypting solid state drive
US20150121088A1 (en) * 2013-10-30 2015-04-30 Lsi Corporation Method of managing aligned and unaligned data bands in a self encrypting solid state drive
US11386120B2 (en) 2014-02-21 2022-07-12 Netapp, Inc. Data syncing in a distributed system
US20160170650A1 (en) * 2014-12-15 2016-06-16 Fujitsu Limited Storage management device, performance adjustment method, and computer-readable recording medium
US9836246B2 (en) * 2014-12-15 2017-12-05 Fujitsu Limited Storage management device, performance adjustment method, and computer-readable recording medium
CN104932953A (en) * 2015-06-04 2015-09-23 华为技术有限公司 Data distribution method, data storage method, and relevant device and system
CN107844268A (en) * 2015-06-04 2018-03-27 华为技术有限公司 A kind of data distributing method, date storage method, relevant apparatus and system
US10248344B2 (en) * 2016-02-08 2019-04-02 Nec Corporation Control device
US20170228187A1 (en) * 2016-02-08 2017-08-10 Nec Corporation Control device
US11327910B2 (en) * 2016-09-20 2022-05-10 Netapp, Inc. Quality of service policy sets
US11886363B2 (en) 2016-09-20 2024-01-30 Netapp, Inc. Quality of service policy sets

Also Published As

Publication number Publication date
JP4244319B2 (en) 2009-03-25
US7216263B2 (en) 2007-05-08
US20070050684A1 (en) 2007-03-01
JP2005182274A (en) 2005-07-07

Similar Documents

Publication Publication Date Title
US7216263B2 (en) Performance monitoring and notification in a threshold sensitive storage management system
US7502904B2 (en) Information processing system and management device for managing relocation of data based on a change in the characteristics of the data over time
US7895398B2 (en) System and method for dynamically adjusting the caching characteristics for each logical unit of a storage array
US7467143B2 (en) Storage operation management system
US9069476B2 (en) Method for managing storage system using flash memory, and computer
US8863145B2 (en) Storage apparatus and load distribution method
US8775730B2 (en) Storage apparatus and method for arranging storage areas and managing error correcting code (ECC) groups
US7096337B2 (en) Disk storage accessing system and method for changing access path to storage devices
US8260986B2 (en) Methods and apparatus for managing virtual ports and logical units on storage systems
US7647450B2 (en) Method, computer and computer system for monitoring performance
US20210334030A1 (en) Storage device parameter monitoring for load balancing
US20100082900A1 (en) Management device for storage device
US20080065850A1 (en) Data storage system and control method thereof
US7702962B2 (en) Storage system and a method for dissolving fault of a storage system
JP2005228278A (en) Management method, management device and management program of storage area
JP2004013547A (en) Data allocation method and information processing system
JP5222876B2 (en) System management method and management system in computer system
JP2007102762A (en) Resource management method in logically partition divisioned storage system
JP4784974B2 (en) Computer system, management computer, and database management system control method
US20100325314A1 (en) Information apparatus and method of generating tuning plan for resource configuration of storage system
US20100057989A1 (en) Method of moving data in logical volume, storage system, and administrative computer
JP2005149283A (en) Information processing system, control method therefor, and program
US20070277018A1 (en) Storage area allocating apparatus, storage area allocating method, and computer product
JPH09223047A (en) Control method for computer network
JP2004078999A (en) Access system of disk storage

Legal Events

Date Code Title Description
AS Assignment

Owner name: HITACHI, LTD., JAPAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:TAKAOKA, NOBUMITSU;KANEDA, YASUNORI;YAMAMOTO, MASAYUKI;REEL/FRAME:015685/0788;SIGNING DATES FROM 20040507 TO 20040517

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION