JP2021190000A - Storage performance monitoring device and storage performance monitoring program - Google Patents

Abstract

To provide a storage performance monitoring device capable of easily grasping the state of the volume in a storage device.SOLUTION: The storage performance monitoring device includes: a performance comparison value creation unit 52 that calculates performance comparison value for each predetermined period 57 for each volume based on first read performance information of each of the multiple volumes; a volume extraction unit 52 that compares each of the multiple volumes to the latest first read performance information and extracts a volume that is determined that the latest first read performance information deviates greater than the first read performance from the threshold value; and an output unit 51 that outputs a notification representing the extracted volume.SELECTED DRAWING: Figure 2

Description

The present invention relates to a storage performance monitoring device and a storage performance monitoring program.

Some storage systems have a performance management function for managing the performance of storage devices, switches, and the like provided in the storage system.

In the conventional performance management function, the target range for acquiring performance information is limited to each volume by designating the volume provided by the storage device as the management target.

However, since the target volume for which performance information should be confirmed changes due to various requirements such as changes in operation and configuration, basically, in general operation, performance information should be acquired for all volumes. Is being done.

Japanese Unexamined Patent Publication No. 2008-192020

In the performance management function of the conventional storage device, the acquired performance information is displayed in chronological order as a performance graph on the display of the terminal device used by the system administrator, for example. In order to display such a performance graph, it is necessary to specify the target volume, but in the storage device, the number of volumes may be, for example, up to 65,000, and the performance of a specific volume. Displaying the graph can be cumbersome.

Further, in the conventional performance management function, it is also known that the acquired performance information is output to a file as CSV (comma-separated values) format data. However, in such data output, it is not possible to specify the target volume and output it, and in order to obtain the performance information of the desired volume, the output CSV format data may be searched or narrowed down. It is necessary to process the data. This is complicated due to the time and effort required for data processing, and it is difficult to detect performance problems that have a business impact at an early stage.

In the conventional performance management function, there is also known a method of notifying that the performance value exceeds the threshold value by setting the threshold value in advance. However, such a method is used for the purpose of checking that the storage performance required for a predetermined business is secured. Therefore, in order to set the optimum threshold value, it is necessary to grasp how each volume is operated, and it is difficult to set the optimum threshold value for each of all the volumes.
In one aspect, the purpose is to make it easy to grasp the state of the volume in the storage device.

Therefore, this storage performance monitoring device is a storage performance monitoring device that monitors the performance of a plurality of volumes managed by the storage device, and is used for each volume based on the first read performance information of each of the plurality of volumes. , The latest first read performance information is compared with the performance comparison value for each of the plurality of volumes and the performance comparison value creation unit for obtaining the performance comparison value for each predetermined period, and the latest first read performance is compared. It includes a volume extraction unit that extracts a volume determined to deviate from the original data by the first read performance threshold or more, and an output unit that outputs a notification representing the extracted volume.

According to one embodiment, the state of the volume in the storage device can be easily grasped.

It is a figure which shows typically the structure of the storage system as an example of an embodiment. It is a figure which illustrates the functional structure of the management server of the storage system as an example of an embodiment. It is a figure which illustrates the performance information storage file in the storage system as an example of an embodiment. It is a figure which illustrates the 1H data storage table in the storage system as an example of an embodiment. It is a figure which illustrates the log information of the performance data in the storage system as an example of an embodiment. It is a figure which illustrates the evaluation data table in the storage system as an example of an embodiment. It is a figure which illustrates the analysis processing setting information in the storage system as an example of an embodiment. It is a figure which illustrates the ranking table in the storage system as an example of an embodiment. It is a figure which illustrates the display screen displayed on the operation terminal of the storage system as an example of an embodiment. It is a flowchart for demonstrating the performance information acquisition process of a volume in the storage system as an example of an embodiment. It is a flowchart for demonstrating the analysis processing of the performance information by the performance information analysis processing part in the storage system as an example of an embodiment. It is a flowchart for demonstrating the table update process by the performance information analysis processing part in the storage system as an example of embodiment. It is a flowchart for demonstrating display control of the ranking table to the operation terminal in the storage system as an example of embodiment. It is a figure which illustrates the hardware configuration of the management server as an example of an embodiment.

Hereinafter, embodiments relating to the storage performance monitoring device and the storage performance monitoring program will be described with reference to the drawings. However, the embodiments shown below are merely examples, and there is no intention of excluding the application of various modifications and techniques not specified in the embodiments. That is, the present embodiment can be variously modified and implemented within a range that does not deviate from the purpose. Further, each figure does not have the purpose of having only the components shown in the figure, but may include other functions and the like.

(A) Configuration FIG. 1 is a diagram schematically showing a configuration of a storage system 1 as an example of an embodiment.

The storage system 1 illustrated in FIG. 1 includes a storage device 4, a management server 5, and an operation terminal 3. These storage devices 4, the management server 5, and the operation terminal 3 are configured to be able to communicate with each other via the communication line 2.

The communication line 2 may be, for example, a LAN (Local Area Network). Further, in the example shown in FIG. 1, these storage devices 4, the management server 5, and the operation terminal 3 are connected to each other via one communication line 2, but the present invention is not limited to these. The connection form of can be changed as appropriate.

Further, a host device (not shown) is communicably connected to the storage system 1. The storage device 4 provides a storage area (volume) to the host device, and reads or writes data to the volume in response to a data read request or write request issued from the host device.

The host device is an information processing device, and is, for example, a computer provided with a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory) and a CPU (Central Processing Unit).

The host device issues a read or write data access request (I / O request) to the volume managed by the storage device 4, thereby writing or reading data to the storage area (volume) provided by the storage device 4. To do.
The storage device 4 makes data access to the volume in response to this I / O request, and responds to the host device.

[Storage device 4]
The storage device 4 is an example of an information processing device, and may include one or more CMs (Controller Modules) 41 and storage 42 (one in the example shown in FIG. 1) as illustrated in FIG.

The storage 42 has a storage area provided by the storage device 4 to the host device and the like. For example, the storage 42 may include a plurality of disks (physical disks). For example, the storage 42 may form a disk array such as RAID (Redundant Arrays of Inexpensive Disks) with a plurality of disks.

A disk is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), and a storage class memory (SCM), and stores various data.

CM41 is an example of a storage control device or a control device. The CM 41 may, for example, control the storage device 4 and perform various controls for providing the storage area of the storage 42 to the host device. The storage device 4 may be provided with a plurality of CM 41s to form a redundant configuration.
The CM 41 may be, for example, a RAID controller that controls a storage device constituting a RAID system.

The CM 41 may optionally include a CPU, a memory, and a non-volatile storage medium. The memory is an example of a volatile memory that stores various information used for the operation of the CM 41. A part of the storage area of the memory is used as a cache memory. That is, this memory is used as a read cache for temporarily storing the data read from the storage 42. This memory is also used as a write cache in which data to be written to the storage 42 is temporarily stored.

The cache hit rate (read cache hit rate) in these read caches and the cache hit rate in the write cache are collected in the CM 41 and managed by the management server 5.

Further, the CM 41 may be provided with a CA (Channel Adapter) port (not shown), and may be connected to the host device via an optical communication cable connected to the CA port.

[Operation terminal 3]
The operation terminal 3 is an information processing device used by a storage administrator (system administrator) or the like, and is, for example, a computer provided with a memory such as a RAM or a ROM or a CPU. Hereinafter, a system administrator or the like may be referred to as a storage administrator. Further, the operation terminal 3 includes an input device (not shown) such as a mouse and a keyboard and a display, and the storage manager performs various input operations on the operation screen or the like displayed on the display by using the input device. ..

For example, the storage manager uses the input device of the operation terminal 3 to input an instruction to acquire performance information of the storage device 4 and an instruction to request response time ranking information described later. For example, information presented (output, transmitted) from the management server 5 is displayed on the display of the operation terminal 3.

For example, the operation terminal 3 executes a Web browser to display the data of the Web GUI (Graphical User Interface) transmitted from the storage management unit 51 of the management server 5, which will be described later, on the display.
Ranking information and abnormality-related information regarding the volume, which will be described later, are output to the display of the operation terminal 3.

[Management server 5]
The management server 5 is, for example, an information processing device having a server function, and manages the storage device 4. The management server 5 is a storage performance monitoring device that monitors the performance of a plurality of volumes managed by the storage device 4.
FIG. 2 is a diagram illustrating a functional configuration of the management server 5 of the storage system 1 as an example of the embodiment.
As shown in FIG. 2, the management server 5 has functions as a storage management unit 51, a performance information analysis processing unit 52, and a storage unit 53.

--Performance information analysis processing unit 52--
The performance information analysis processing unit 52 analyzes the performance information of the storage device 4 and lists volumes in which performance problems are likely to occur. By presenting the volumes that are expected to have a business impact due to the occurrence of performance problems, it is possible to narrow down the volumes that need to be dealt with.

-Comparison source data creation process-
The performance information analysis processing unit 52 creates comparison source data.
The performance information analysis processing unit 52 compares using the read response time (first read performance information, performance data) of the volume in the storage device 4 acquired by the storage management unit 51, which will be described later, and stored in the performance information storage file 54. Create the original data.

The performance information storage file 54 is information representing the performance of a volume (logical volume) in the storage device 4, and is information collected from the storage device 4 by the storage management unit 51.
FIG. 3 is a diagram illustrating a performance information storage file 54 in the storage system 1 as an example of the embodiment.
The performance information storage file 54 illustrated in FIG. 3 includes a file name, a header line, and a data line as items.

The file name stores identification information (logical volume number) that identifies the volume. The type of performance information is stored in the header line. In the example shown in FIG. 3, a read response time (Read Response Time), a read cache hit rate (Read Cache Hit Rate), a write cache hit rate (Write Cache Hit Rate), and the like are shown.

The data line stores specific performance information data (read response time, read cache hit rate, write cache hit rate) and the like transmitted from the storage device 4.

The performance information analysis processing unit 52 acquires (extracts) a read response time from the performance information storage file 54 created by the storage management unit 51, and uses it for creating performance data. The performance data is an actual value (history) of the read response time of the volume managed by the storage device 4. Hereinafter, the read response time acquired from the performance information storage file 54 may be referred to as a process target read response time. The processing target read response time is the latest read response time (first read performance information) processed by the performance information analysis processing unit 52.

The storage management unit 51, which will be described later, collects the read response time of each volume at intervals of 30 seconds. In the storage system 1, the performance information analysis processing unit 52 obtains an average value in 1-hour units using the read response time acquired at intervals of 30 seconds in this way.

The performance information analysis processing unit 52 obtains an average value in 1-hour units by, for example, calculating the average value of the read response times for 120 times acquired at these 30-second intervals.
The performance information analysis processing unit 52 uses the 1H data storage table 56 to calculate the average value of the read response times of each volume in units of one hour.
FIG. 4 is a diagram illustrating the 1H data storage table 56 in the storage system 1 as an example of the embodiment.

In the 1H data storage table 56 illustrated in FIG. 4, the volume name and the average value of the read response time are associated with each other. Information that identifies each volume managed by the storage device 4 is used for the volume name.

The performance information analysis processing unit 52 stores the read response time of each volume acquired by the storage management unit 51 every 30 seconds in the 1H data storage table 56 in correspondence with the volume name of each volume. Further, the performance information analysis processing unit 52 calculates the average value of a plurality of read response times acquired from the same volume, and updates the value in the 1H data storage table 56.
The average value of the hourly read response time of each volume is stored in the 1H data storage table 56.

The performance information analysis processing unit 52 may recognize that, for example, by detecting that the time has reached 0 minutes per hour, the average value of the read response times for one hour has been calculated.

Further, the performance information analysis processing unit 52 recognizes that the average value of the latest 120 read response times has been calculated by counting the number of read response times used for calculating each average value, and 1 hour. It may be recognized that the average value of the read response times for the minutes has been calculated. Even if the performance information analysis processing unit 52 recognizes that the average value of the latest 120 times of read response time has been calculated by calculating the elapsed time since the calculation of the average value of the read response time is started. good.
The storage unit 53 may store the average value of the read response times in each time zone as log information 59 for each volume.
FIG. 5 is a diagram illustrating log information 59 of performance data in the storage system 1 as an example of the embodiment.

In the performance data log information 59 illustrated in FIG. 5, for the plurality of volumes (Vol. 1 to 3 are shown) managed by the storage device 4, each day of the week from Monday to Sunday is from 0 to 23:00. The average value of the read response time for each time zone is shown.
Hereinafter, the average value of the read response time in each time zone may be referred to as the read response time for each hour or the performance data for each time zone.

Further, in FIG. 5, in the log information 59, information on the read response time for 5 weeks from the 1st to the 5th week is shown. In the log information 59 illustrated in FIG. 5, the read response time in some time zones (3 to 22:00) is not shown for convenience.

The performance information analysis processing unit 52 updates the average value of the read response times in each time zone using the data in the 1H data storage table 56. For example, when the average value of the read response times of each volume stored in the 1H data storage table 56 is calculated using the read response time for one hour, the performance information analysis processing unit 52 of the 1H data storage table 56 The value is used to update the value that matches the time condition for the volume.

The performance information analysis processing unit 52 may update the evaluation data table 57 using the values in the 1H data storage table 56 every hour. Further, the performance information analysis processing unit 52 may update the evaluation data table 57 using the values of the 1H data storage table 56 at the timing of 0 minutes per hour.

The performance information analysis processing unit 52 uses, for example, the data for the last four weeks of the log information 59 to calculate the average value of the read response times of each time zone of each day of the week to obtain the evaluation data table 57. create.
FIG. 6 is a diagram illustrating an evaluation data table 57 in the storage system 1 as an example of the embodiment.

The evaluation data table 57 illustrated in FIG. 6 is based on the performance data for each time zone illustrated in FIG. 5, and uses the response time data of the latest predetermined period (4 weeks in the present embodiment) for each day of the week. It is composed by calculating the average value of the performance data for each time zone of. Each of the values registered in the evaluation data table 57 for each time zone is the comparison source data.

The performance information analysis processing unit 52 extracts read response times on the same day of the week and in the same time zone based on the performance data for four weeks, and calculates the average value of these to obtain the comparison source data. Hereinafter, there are cases where the time conditions are the same for the same day of the week and the same time zone.

For example, on March 2, 2020, in order to calculate the comparison source data for Vol.3 in the time zone from 2:00 to 3:00, the performance information analysis processing unit 52 may perform on February 10, 2020. Calculate the average value of each read response time in the time zones of 2:00 to 3:00 on February 17, February 24, and March 2 (see reference numeral P1 in FIG. 5).

There are a wide variety of tasks that use the volume of the storage device 4, and the usage and purpose of the volume are also different. Therefore, in the storage system 1, the performance information analysis processing unit 52 prepares comparison source data for all the volumes in the storage device 4, for example, every hour and every day of the week. In this way, the validity of the comparison source data can be enhanced by calculating the average value of the data for the latest four weeks and using it as the comparison source data.

The performance information analysis processing unit 52 holds the average value of the read response time for each hour calculated as described above for 24 hours (= 1 day) in the storage unit 53 (number of comparison source data = 24). Further, the performance information analysis processing unit 52 holds the collected values for one day for seven days (= one week) for each day of the week, so that the average value of the read response time for one week is held in the storage unit 53. (Number of comparison source data = 24 × 7 = 168).

Further, the performance information analysis processing unit 52 sets the average value of the read response times for one week as the log information 59 for four weeks or more (five weeks in the example shown in FIG. 5) in the storage unit 53. Hold.

Each comparison source data registered in the evaluation data table 57 corresponds to a performance comparison value for each predetermined period (every hour) for each of the plurality of volumes created based on the read response times of the plurality of volumes. do.

Further, the performance information analysis processing unit 52 that creates the evaluation data table 57 is used for each of the plurality of volumes for each predetermined period (1 hour) based on the first read performance information (read response time) of each of the plurality of volumes. It corresponds to the performance comparison value creation unit for obtaining the performance comparison value (comparison source data, evaluation data table 57) of each).

Further, when the performance information analysis processing unit 52 uses the read response time acquired from the performance information storage file 54 to create the performance data, the comparison source data in the evaluation data table 57 has the same time condition as the processing target read response time. If there is, the validity of the read response time is judged.

That is, the performance information analysis processing unit 52 compares the processing target read response time with the comparison source data whose time conditions are the same as the processing target read response time in the evaluation data table 57, and is equal to or higher than a predetermined threshold value (first threshold value). Determine if there is a divergence. Here, the first threshold value is, for example, 50%. The first threshold value may be arbitrarily set by the storage administrator or the like. The first threshold value is registered as Analysis_deviation_range in the analysis processing setting information 55.
FIG. 7 is a diagram illustrating analysis processing setting information 55 in the storage system 1 as an example of the embodiment.

The analysis processing setting information 55 stores the threshold value used by the performance information analysis processing unit 52. In the analysis processing setting information 55 illustrated in FIG. 7, a keyword name, a value, and a description are associated with each other.

The keyword name is information for specifying the threshold value, and in the example shown in FIG. 7, three types of threshold values are set for the keyword name: Analysis_deviation_range, Analysis_target_range, and Analisys_cache_hit_rate.

Analysis_deviation_range is the above-mentioned first threshold value (abnormality determination threshold value), and in the example shown in FIG. 7, 50% is set as a value. Further, as an explanation of this Analysis_deviation_range, it is set to be the deviation rate of the data used for determining the data to be excluded from the creation of the performance data.

Analysis_target_range is a second threshold value (first read performance threshold value) described later, and in the example shown in FIG. 7, 20% is set as a value. Further, as an explanation of this Analysis_target_range, it is set to be a deviation rate from the average value used for determining whether there is a problem in performance. This second threshold will be described later.

Analisys_cache_hit_rate is a third threshold value (second read performance threshold value) described later, and in the example shown in FIG. 7, 80% is set as a value. Also, as an explanation of this Analisys_cache_hit_rate, it is set to be a cache hit rate. This third threshold will also be described later.

When the process target read response time deviates from the comparison source data having the same time condition by a predetermined threshold value (first threshold value) or more, the process target read response time is generated due to a sudden factor. It is considered to be abnormal data. Therefore, the performance information analysis processing unit 52 determines that the processing target read response time is not appropriate for use in creating performance data.

The performance information analysis processing unit 52 excludes the processing target read response time determined to be inappropriate for use in the creation of performance data from the creation of performance data, that is, the calculation target of the average value.

Further, when the performance information analysis processing unit 52 detects a processing target read response time (abnormal data) that is determined to be inappropriate for use in creating performance data, the following information (1) to (5) is used. Is collected from the storage device 4 and notified to the storage administrator. These information (1) to (5) are extracted from the performance information storage file 54 collected from the same volume (target volume) at the same timing as the processing target read response time, for example.
(1) Read response time and cache hit rate of the target volume (2) Read response time and cache hit rate of the RAID group in which the volume exists (3) Busy rate of the disks constituting the RAID group (4) RAID group Busy rate of CM41 to which is connected (5) Data transfer amount of the CA port to which the volume is connected

The performance information analysis processing unit 52 notifies the storage administrator of the abnormality by, for example, creating an e-mail containing such information and transmitting the e-mail to the storage administrator. Hereinafter, the above information (1) to (5) may be referred to as abnormality-related information.

The storage administrator who has received the abnormality notification including the abnormality-related information can receive this e-mail using, for example, the operation terminal 3 and confirm the occurrence of the abnormality data in real time.
It should be noted that the acquisition of the above-mentioned abnormality-related information from the storage device 4 can be realized by a known method, and the description thereof will be omitted.

-First comparison process-
The performance information analysis processing unit 52 compares the processing target read response time with the comparison source data whose time conditions are the same as the processing target read response time.

The performance information analysis processing unit 52 compares the processing target read response time with the comparison source data in the evaluation data table 57 whose time conditions are the same as the processing target read response time. Then, the performance information analysis processing unit 52 determines whether the processing target read response time deviates from the comparison source data in a direction in which it increases by a predetermined threshold value (second threshold value) or more. Here, the second threshold value is, for example, 20%. The second threshold corresponds to the first read performance threshold.

The second threshold value may be arbitrarily set by the storage administrator or the like. The second threshold value is registered as Analysis_target_range in the analysis processing setting information 55.

A state in which the read response time deviates from the comparison source data by a second threshold value or more and increases indicates that the read response time is longer than in normal times and the performance is deteriorated.

The performance information analysis processing unit 52 compares the latest first read performance information (processed read response time) with the performance comparison value for each of the plurality of volumes, and the latest first read performance is compared with the comparison source data. It corresponds to the volume extraction unit that extracts the volume determined to deviate by the second threshold value (first read performance threshold value) or more.

-Second comparison process-
The performance information analysis processing unit 52 performs a second comparison process when, as a result of the first comparison process, the process target read response time deviates from the comparison source data by a predetermined threshold value (second threshold value) or more. To execute.

In the second comparison process, the performance information analysis processing unit 52 acquires the read cache hit rate (second read performance information) of the volume from the performance information storage file 54 and compares it with a predetermined threshold value (third threshold value). do.

The read cache hit rate is a value extracted from the latest performance information storage file 54 at the time when it is detected that the read response time to be processed deviates from the comparison source data by a predetermined threshold value (second threshold value) or more. There may be. Further, a value extracted from the performance information storage file 54 collected by the collection unit 102 at the same timing as the processing target read response time when it is detected that the comparison source data deviates from a predetermined threshold value (second threshold value) or more. May be. Therefore, it is desirable that the performance information storage file 54 stores the read cache hit rates for a plurality of generations in the storage unit 53.

Here, the third threshold value is, for example, 80%. The third threshold value may be arbitrarily set by the storage administrator or the like. The second threshold value is registered as Analisys_cache_hit_rate in the analysis processing setting information 55.

If the read response time deviates from the comparison source data by the second threshold value or more and the read cache hit rate is equal to or less than the third threshold value (80%), some performance problem may have occurred in the volume. It can be judged that there is sex. The third threshold corresponds to the second read performance threshold.
The performance information analysis processing unit 52 registers the volume determined that the read cache hit rate is equal to or less than the third threshold value (80%) in the ranking table 58.
FIG. 8 is a diagram illustrating a ranking table 58 in the storage system 1 as an example of the embodiment.

The ranking table 58 shows the ranking of the deviation rate of the read response time in the direction in which the performance deteriorates with respect to the second threshold value (Analysis_target_range).

In the ranking table 58 illustrated in FIG. 8, the device name, date and time, rank, volume number, volume name, response time, busy rate, and deviation rate are associated with each other.

The device name is identification information that identifies the storage device 4. Since one storage device 4 is provided in the storage system 1, in the example shown in FIG. 8, the storage name “device A” of the storage device 4 is set in all the entries. When a plurality of storage devices 4 are provided, device names of the plurality of storage devices 4 may be set.

The date and time may be, for example, the date and time when the volume is registered in the ranking table 58. The rank represents the ranking of the volume in the ranking table 58, and the higher the divergence rate, the higher the ranking is set.

The volume number is identification information for identifying the volume, and the volume name is a name arbitrarily set for the volume. The volume name should be unique. The response time is the read response time in the volume, and the busy rate is the busy rate in the volume. The deviation rate is a deviation rate with respect to the second threshold value of the read response time calculated by the performance information analysis processing unit 52.
The device name, volume number, volume name, response time, and busy rate can be obtained by, for example, extracting from the performance information storage file 54.

Then, in the ranking table 58, the entries are arranged in the order of rank. That is, the volumes are arranged in order from the one with the highest divergence rate.

The ranking table 58 shows a plurality of volumes in which the read response time is increased so as to deviate from the comparison source data by the second threshold value or more, and the read cache hit rate is equal to or less than the third threshold value. .. Further, these plurality of volumes are arranged in order from the one having the highest deviation rate from the comparison source data of the read response time.

The performance information analysis processing unit 52 updates the ranking table 58 every hour, for example, to update the latest information. The performance information analysis processing unit 52 may update the ranking table 58 periodically or irregularly.

--Memory 53--
The storage unit 53 stores (stores) the performance information storage file 54, the analysis processing setting information 55, the 1H data storage table 56, the evaluation data table 57, the ranking table 58, and the log information 59.
The storage unit 53 is realized by, for example, a storage device 13 or a memory 12, which will be described later with reference to FIG.

--Storage Management Department 51--
The storage management unit 51 collects performance information of the storage device 4. The storage management unit 51 issues a notification requesting transmission of performance information to the storage device 4 at predetermined time intervals (for example, at intervals of 30 seconds).

The storage device 4 responds to the transmission request of the performance information with the performance information of the volume managed by itself. The performance information is each information registered in the performance information storage file 54 described above. The performance information includes at least the read response time (response time) for each volume and the read cache hit rate. The collection of these performance information in the storage device 4 and the response to the management server 5 can be realized by a known method, and the description thereof will be omitted.
The storage management unit 51 receives these performance information transmitted from the storage device 4 and registers them in the performance information storage file 54.
In this way, the storage management unit 51 realizes a performance management function for managing the performance information of the storage device 4.

Further, the storage management unit 51 issues an execution instruction for performance analysis of the storage device 4 to the performance information analysis processing unit 52. The storage management unit 51 issues an execution instruction for performance analysis of the storage device 4 to the performance information analysis processing unit 52 at predetermined time intervals (for example, at intervals of 30 seconds).

Further, when the storage management unit 51 receives the request for ranking information from the operation terminal 3, the storage management unit 51 extracts the ranking information with reference to the ranking table 58 and presents it to the operation terminal 3. The storage management unit 51 corresponds to an output unit that outputs a notification representing the extracted volume.

For example, the storage management unit 51 may extract information on volumes registered at the top of the ranking table 58 (for example, 1st to 5th places) and notify the storage manager by e-mail. Further, the storage management unit 51 may generate the display data of the Web GUI using the ranking information and transmit it to the operation terminal 3.
FIG. 9 is a diagram illustrating a display screen displayed on the operation terminal 3 of the storage system 1 as an example of the embodiment.

The display screen shown in FIG. 9 shows a dashboard screen generated by the Web GUI. The dashboard screen shows information about the storage device 4, and in the example shown in FIG. 9, the deviation rate ranking is shown together with the device status, log, RADIUS group capacity summary, etc. (see reference numeral P2 in FIG. 9). ).

The device status indicates the state (status) of the storage device 4 managed by the management server 5. The log shows the history of the processing performed in the storage system 1. The RAID group capacity summary shows information about the capacity of each RAID group managed in the storage system 1.

The divergence rate ranking presents ranking information extracted from the ranking table 58 by the storage management unit 51. In the example shown in FIG. 9, in the deviation rate ranking, among the volumes managed by the storage device 4, the top 5 (1st to 5th) in the ranking table 58 set by the performance information analysis processing unit 52. The two volumes are arranged in order from the one with the highest divergence rate.

Further, in the deviation rate ranking illustrated in FIG. 9, the deviation rate is shown in association with each volume, and the response time and the busy rate are also shown in association with each other.

In this deviation rate ranking, a plurality of volumes in which the read response time deviates from the comparison source data by the second threshold value or more and the read cache hit rate is equal to or less than the third threshold value are shown. There is. Then, these plurality of volumes are arranged in order from the one having the highest deviation rate from the comparison source data of the read response time.
In the divergence rate ranking, it can be considered that the higher the volume, the more likely the performance problem will occur.

Therefore, the storage administrator who uses the operation terminal 3 can grasp the volume at which a performance problem may occur by referring to this deviation rate ranking.

In the example shown in FIG. 9, five volumes are shown in the divergence rate ranking, but the volume is not limited to this. Volumes of 4 or less or 6 or more may be displayed in the deviation rate ranking. Further, the storage administrator may arbitrarily set the number of volumes to be displayed in the deviation rate ranking.

Further, the performance information analysis processing unit 52 also describes the above-mentioned abnormality-related volume with respect to the volume in which the state ranked high in the deviation rate ranking (for example, 1st to 5th) is a predetermined number of times (for example, 3 times) or more. Information similar to the information may be collected from the storage device 4 and notified to the storage administrator.

The performance information analysis processing unit 52 notifies the storage administrator of the abnormality by, for example, creating an e-mail containing the above-mentioned abnormality-related information and transmitting the e-mail to the storage administrator. For example, the storage administrator can receive this e-mail using the operation terminal 3 and confirm the occurrence of abnormal data in real time.

(B) Operation The volume performance information acquisition process in the storage system 1 as an example of the embodiment configured as described above will be described with reference to the flowcharts (steps A1 to A10) shown in FIG.

In FIG. 10, steps A1 and A2 show processing in the operation terminal 3, steps A3 to A7 show processing in the management server 5, and steps A8 to A10 show processing in the storage device 4.

In step A1, for example, when the storage administrator operates the operation terminal 3 to perform an input operation for viewing the performance information acquisition, the operation terminal 3 instructs the management server 5 to start the performance information acquisition. do.

In step A3, the storage management unit 51 of the management server 5 confirms the instruction content received from the operation terminal 3, and issues a notification to the storage device 4 as soon as possible to transmit the performance information.

In step A8, the storage device 4 starts acquiring the performance information of each volume based on the transmission request of the performance information received from the storage management unit 51. The storage device 4 responds to the management server 5 (storage management unit 51) to the effect that performance information is being acquired. Based on the response from the storage device 4, the storage management unit 51 sets information (for example, a flag) indicating that the performance information is being acquired is set in the storage unit 53 or the like (step A4). Further, the storage management unit 51 notifies the operation terminal 3 that the performance information is being acquired. For example, the storage management unit 51 generates display screen data indicating that the performance information is being acquired by the Web GUI or the like, and transmits the display screen data to the operation terminal 3.
In step A2, the display of the operation terminal 3 displays information indicating that the volume performance information is being acquired.
Further, in the management server 5, the storage management unit 51 issues a notification requesting transmission of performance information to the storage device 4 (step A5).

In step A9, the storage device 4 creates performance information of each volume managed by itself, and in step A10, responds to the performance information to the management server 5.

In step A6, the storage management unit 51 of the management server 5 stores the performance information received from the storage device 4 in the performance information storage file 54. After that, the storage management unit 51 instructs the performance information analysis processing unit 52 to execute the performance information analysis processing (step A7), and returns to step A5. The storage management unit 51 repeatedly executes the processes of steps A5, A9, A10, A6, and A7 at predetermined time (30 seconds in this embodiment) interval.

Next, the analysis processing of the performance information by the performance information analysis processing unit 52 in the storage system 1 as an example of the embodiment will be described according to the flowcharts shown in FIGS. 11 and 12.
Note that FIG. 11 shows the processing of steps B1 to B10, and FIG. 12 shows the processing of steps C1 to C8.

In step B1, the performance information analysis processing unit 52 reads the analysis processing setting information 55 from the storage unit 53 and acquires the first threshold value, the second threshold value, and the third threshold value, respectively. The acquired threshold value is stored in, for example, a predetermined storage area of the memory 12 (see FIG. 14).

In step B2, the performance information analysis processing unit 52 acquires the current day of the week and the time from, for example, a calendar or clock application provided in the system.

In step B3, the performance information analysis processing unit 52 refers to the performance information storage file 54 and extracts the performance data (process target read response time) of the volume managed by the storage device 4.
In step B4, the performance information analysis processing unit 52 performs table update processing using the processing target read response time.
The table update process by the performance information analysis processing unit 52 will be described with reference to the flowcharts (steps C1 to C8) shown in FIG.

In step C1, the performance information analysis processing unit 52 confirms whether the volume corresponding to the processing target read response time acquired in step B3 is registered in the 1H data storage table 56.

When the volume corresponding to the process target read response time is not registered in the 1H data storage table 56 (see the NO route in step C1), in step C2, the performance information analysis processing unit 52 sets the process target read response time. The corresponding volume is added as an entry to the 1H data storage table 56. After that, the process proceeds to step C3.

On the other hand, as a result of the confirmation in step C1, if the volume corresponding to the process target read response time is registered in the 1H data storage table 56 (see the YES route in step C1), the process proceeds to step C6.

In step C6, the performance information analysis processing unit 52 confirms whether the processing target read response time is appropriate data to be used for table update. That is, the performance information analysis processing unit 52 compares the processing target read response time with the comparison source data whose time conditions are the same as the processing target read response time in the evaluation data table 57, and deviates from the first threshold value (50%) or more. Determine if you are doing it.

When the process target read response time deviates by 50% or more from the comparison source data, it is determined that the process target read response time is not appropriate for use in updating the table (see NO route in step C6). Therefore, in step C8, the performance information analysis processing unit 52 collects abnormality-related information, creates an e-mail containing the collected abnormality-related information, sends it to the storage administrator, and proceeds to step C4.

On the other hand, when the process target read response time does not deviate by 50% or more from the comparison source data, it is determined that the process target read response time is appropriate to be used for table update (step C6). See the YES route in). Therefore, in step C7, the performance information analysis processing unit 52 calculates the average value of the read response time by using the data stored in the 1H data storage table 56 and the process target read response time.

In step C3, the performance information analysis processing unit 52 stores the calculated average value of the read response times in the 1H data storage table 56. That is, the performance information analysis processing unit 52 updates the read response time of the volume corresponding to the processing target read response time in the 1H data storage table 56 by using the processing target read response time, and proceeds to step C4.

In step C4, the performance information analysis processing unit 52 confirms whether it is necessary to update the evaluation data table 57. For example, the performance information analysis processing unit 52 determines whether or not the log information 59 and the evaluation data table 57 need to be updated by determining whether or not the time has passed 0 minutes per hour and the time zone has changed. to decide. Further, the performance information analysis processing unit 52 determines whether or not the log information 59 and the evaluation data table 57 need to be updated by determining whether or not the time zone has changed after one hour has passed since the previous confirmation. You may.

If the time zone has changed since the previous confirmation and it is determined that the evaluation data table 57 needs to be updated (see the YES route in step C4), the process proceeds to step C5.

In step C5, the performance information analysis processing unit 52 updates the log information 59 using the value of the 1H data storage table 56, and updates the evaluation data table 57 using the updated log information 59. After that, the process proceeds to step B5 in FIG. Further, even if it is determined that the evaluation data table 57 does not need to be updated as a result of the confirmation in step C4 (see the NO route in step C4), the process proceeds to step B5 in FIG.

The performance information analysis processing unit 52 refers to the evaluation data table 57 based on the processing target read response time (step B5), and sets the processing target read response time to the comparison source having the same time condition as the processing target read response time. Compare with the data (step B6: first comparison process).

In step B7, the performance information analysis processing unit 52 determines whether or not the processing target read response time is an appropriate value. Here, when the processing target read response time is a value suggesting the occurrence of some abnormality in the volume, it is determined that the processing target read response time is not an appropriate value. That is, the performance information analysis processing unit 52 determines whether the processing target read response time deviates from the comparison source data in a direction in which it increases by a predetermined threshold value (second threshold value) or more.

When the process target read response time deviates from the comparison source data in the direction of increasing by a predetermined threshold value (second threshold value) or more, the process target read response time suggests that some abnormality has occurred in the volume. It is determined that the read response time to be processed is not an appropriate value (see NO route in step B7).

Therefore, in step B8, the performance information analysis processing unit 52 acquires the read cache hit rate of the volume from the performance information storage file 54 and compares it with a predetermined threshold value (third threshold value) (second comparison processing).

In step B9, the performance information analysis processing unit 52 determines whether or not the read cache hit rate of the volume corresponding to the processing target read response time is an appropriate value. Specifically, the performance information analysis processing unit 52 determines whether or not the read cache hit rate is larger than the third threshold value (80%).

When the read cache hit rate is equal to or less than the third threshold value (80%) (see the NO route in step B9), the performance information analysis processing unit 52 determines that the read cache hit rate is not an appropriate value, and steps B10. Move to the processing of.

In step B10, the performance information analysis processing unit 52 registers the volume corresponding to the processing target read response time in the ranking table 58. Further, the performance information analysis processing unit 52 rearranges the ranking table 58 to which a new volume is added in order from the one having the highest deviation rate with respect to the second threshold value of the read response time. After that, the process returns to step B3.

On the other hand, when the read cache hit rate is larger than the third threshold value (80%) (see the YES route in step B9), the performance information analysis processing unit 52 determines that the read cache hit rate is an appropriate value. do. In that case, the process target read response time returns to step B3.

Further, as a result of the determination in step B7, if the processing target read response time does not deviate from the comparison source data in the direction of increasing by a predetermined threshold value (second threshold value) or more, the processing target read response time is set. It is determined to be a reasonable value (see YES route in step B7). In this case as well, the process returns to step B3.

Next, the display control of the ranking table 58 on the operation terminal 3 in the storage system 1 as an example of the embodiment will be described according to the flowchart (steps D1 to D5) shown in FIG.

In the flowchart shown in FIG. 13, steps D1 and D2 show the processing in the operation terminal 3, and steps D3 to D5 show the processing in the management server 5 (performance information analysis processing unit 52).

In step D1, the storage administrator operates the input device of the operation terminal 3 to perform an input requesting output of the response time ranking. The output request of the response time ranking is transmitted to the storage management unit 51 of the management server 10.

In step D3, the storage management unit 51 refers to the ranking table 58. Then, in step D4, the storage management unit 51 extracts the volume information (ranking information, deviation rate ranking) registered at the top of the ranking table 58 (for example, the 1st to 5th places), and sends an email to the storage administrator. Notice.

In step D5, the storage management unit 51 generates the display data of the Web GUI using the ranking information (deviation rate ranking) and responds to the operation terminal 3.

In step D2, the operation terminal 3 displays the display data of the ranking information received from the storage management unit 51 on the display, and ends the process. The storage administrator who uses the operation terminal 3 can grasp the volume at which a performance problem may occur by referring to this deviation rate ranking.

(C) Effect As described above, according to the storage system 1 as an example of the embodiment, the performance information analysis processing unit 52 uses the actual value of the read response time (performance data) of the volume in the storage device 4 for evaluation data. Create table 57. The evaluation data table 57 is configured by calculating the average value of the performance data for each time zone of each day of the week using the response time data of the latest predetermined period (4 weeks in the above embodiment). ..

Further, the performance information analysis processing unit 52 compares the processing target read response time detected in the volume with the comparison source data in the evaluation data table 57 whose time conditions are the same as the processing target read response time. Perform processing.

As a result of this first comparison processing, when the processing target read response time deviates from the comparison source data by a second threshold value or more, a processing delay occurs in the volume for some reason. It can be determined that an operational problem has occurred. In this way, as a result of the first comparison process, the storage administrator can notify the storage administrator of the information of the volume whose process target read response time deviates from the comparison source data by the second threshold value or more. , Volumes that may cause performance problems can be easily grasped. In addition, preventive measures and preparations for the occurrence of a failure can be taken as necessary. This can improve reliability.

Further, the performance information analysis processing unit 52 acquires the read cache hit rate of the volume from the performance information storage file 54 when the process target read response time deviates from the comparison source data by a second threshold value or more. , Perform a second comparison process for comparison with the third threshold value.

Then, the performance information analysis processing unit 52 registers the volume determined that the read cache hit rate is equal to or less than the third threshold value in the ranking table 58. The ranking table 58 shows a plurality of volumes in which the read response time is increased so as to deviate from the comparison source data by the second threshold value or more, and the read cache hit rate is equal to or less than the third threshold value. .. Further, these plurality of volumes are arranged in order from the one having the highest deviation rate from the comparison source data of the read response time. The storage management unit 51 extracts information on volumes registered at the top of the ranking table 58 (for example, 1st to 5th) and presents the information to the storage manager.

In the ranking table 58, it is considered that the higher the volume, the more the performance problem may occur. Therefore, the storage administrator can easily grasp the volume where the performance problem may occur by referring to the presented information, and take preventive measures and preparations for the occurrence of a failure as necessary. be able to. This can improve reliability.

When the performance information analysis processing unit 52 detects abnormal data whose processing target read response time deviates from the first threshold value or more with respect to the comparison source data having the same time condition, the processing target read response time is set. Discard it and do not use it to create performance data. This makes it possible to improve the reliability of the performance data.

Further, the performance information analysis processing unit 52 includes abnormality-related information when the abnormality data whose processing target read response time deviates from the first threshold value or more with respect to the comparison source data having the same time condition is detected. Notify the storage administrator of the error notification. This allows the storage administrator to confirm the occurrence of abnormal data in real time. The storage administrator can estimate the cause of the occurrence of the abnormal data in the storage device 4 by referring to the abnormality-related information. As a result, the storage manager can take preventive measures, prepare for the occurrence of a failure, and the like before the failure actually occurs in the storage device 4, and can improve the reliability.

Further, the performance information analysis processing unit 52 also describes the above-mentioned abnormality-related volume with respect to the volume in which the state ranked high in the deviation rate ranking (for example, 1st to 5th) is a predetermined number of times (for example, 3 times) or more. Information similar to the information is collected from the storage device 4 and notified to the storage administrator.

Also with this, the storage administrator can estimate the cause of the occurrence of the abnormal data in the storage device 4 by referring to the abnormality-related information. As a result, the storage manager can take preventive measures, prepare for the occurrence of a failure, and the like before the failure actually occurs in the storage device 4, and can improve the reliability.

In the storage system 1, the read response time (response time) and the read cache hit rate of the volume are focused on among the performance information acquired by the performance management function provided in the storage device 4. When the target data is in the cache in the read process in the storage device 4, the response time is faster than reading the data from the storage 42.

If the read response time is worse than usual even though the read cache hit rate is high, it is assumed that some problem has occurred in the storage device 4. Therefore, by displaying the information only for the volume in this state, it is possible to confirm the target volume for which the presence or absence of business influence should be confirmed without omission.

Information indicating the I / O performance of the storage 42 includes I / O response time (response time) and IOPS (Input / Output Per Second: throughput value), but IOPS is the I / O state (read). / The value varies greatly depending on the write ratio and Random / Sequential of the access status, etc., and is not preferable for use in volume performance judgment. Therefore, in this storage system 1, the response time (response time) is adopted as an index for constantly determining the business impact.

Further, the cache of the storage device 4 includes a read cache and a write cache, but the write process is completed when the write data is written to the write cache. Therefore, in the volume performance determination, the accuracy for determining the presence or absence of business influence can be improved by excluding the response time of such write processing.

(D) Others FIG. 14 is a diagram illustrating a hardware configuration of the management server 5 as an example of the embodiment.
The management server 5 is an information processing device (computer) having a server function, and is, for example, a processor 11, a memory 12, a storage device 13, a graphic processing device 14, an input interface 15, an optical drive device 16, and a device connection interface 17. And the network interface 18 as a component. These components 11 to 18 are configured to be communicable with each other via the bus 19.

The processor (processing unit) 11 controls the entire management server 5. The processor 11 may be a multiprocessor. The processor 11 is, for example, one of a CPU, an MPU (Micro Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). You may. Further, the processor 11 may be a combination of two or more types of elements among the CPU, MPU, DSP, ASIC, PLD, and FPGA.

Then, by the processor 11 executing the control program for the management server 5 (storage performance monitoring program: not shown), the functions as the storage management unit 51 and the performance information analysis processing unit 52 illustrated in FIG. 2 are realized. To.

The management server 5 executes a program (storage performance monitoring program or OS (Operating System) program) recorded on a computer-readable non-temporary recording medium, for example, to execute the storage management unit 51 and performance information analysis. The function as the processing unit 52 is realized.

The program that describes the processing content to be executed by the management server 5 can be recorded on various recording media. For example, a program to be executed by the management server 5 can be stored in the storage device 13. The processor 11 loads at least a part of the program in the storage device 13 into the memory (RAM) 12, and executes the loaded program.

Further, the program to be executed by the management server 5 (processor 11) can be recorded on a non-temporary portable recording medium such as an optical disk 16a, a memory device 17a, and a memory card 17c. The program stored in the portable recording medium can be executed after being installed in the storage device 13 by control from the processor 11, for example. The processor 11 can also read and execute the program directly from the portable recording medium.

The memory 12 is a storage memory including a ROM and a RAM. The RAM of the memory 12 is used as the main storage device of the management server 5. At least a part of the OS program and the control program to be executed by the processor 11 is temporarily stored in the RAM. Further, various data necessary for processing by the processor 11 are stored in the memory 12.

The storage device 13 is a storage device such as a hard disk drive (HDD), SSD, SCM, etc., and stores various data. The storage device 13 is used as an auxiliary storage device for the management server 5. The storage device 13 stores an OS program, a control program, and various data.

As the auxiliary storage device, a semiconductor storage device such as an SCM or a flash memory can also be used. Further, the RAID may be configured by using a plurality of storage devices 13.

Further, the storage device 13 stores data constituting the performance information storage file 54, the analysis processing setting information 55, the 1H data storage table 56, the evaluation data table 57, the ranking table 58, and the log information 59.

A monitor 14a is connected to the graphic processing device 14. The graphic processing device 14 displays an image on the screen of the monitor 14a according to an instruction from the processor 11. Examples of the monitor 14a include a display device using a CRT (Cathode Ray Tube), a liquid crystal display device, and the like.

A keyboard 15a and a mouse 15b are connected to the input interface 15. The input interface 15 transmits signals sent from the keyboard 15a and the mouse 15b to the processor 11. The mouse 15b is an example of a pointing device, and other pointing devices can also be used. Other pointing devices include touch panels, tablets, touchpads, trackballs and the like.

The optical drive device 16 reads the data recorded on the optical disk 16a by using a laser beam or the like. The optical disc 16a is a portable non-temporary recording medium in which data is readablely recorded by reflection of light. Examples of the optical disk 16a include a DVD (Digital Versatile Disc), a DVD-RAM, a CD-ROM (Compact Disc Read Only Memory), a CD-R (Recordable) / RW (ReWritable), and the like.

The device connection interface 17 is a communication interface for connecting peripheral devices to the management server 5. For example, a memory device 17a or a memory reader / writer 17b can be connected to the device connection interface 17. The memory device 17a is a non-temporary recording medium equipped with a communication function with the device connection interface 17, for example, a USB (Universal Serial Bus) memory. The memory reader / writer 17b writes data to the memory card 17c or reads data from the memory card 17c. The memory card 17c is a card-type non-temporary recording medium.

The network interface 18 is connected to the network. In the network interface 18, the operation terminal 3 transmits / receives data to / from the storage device 4 via the network. Other information processing devices, communication devices, and the like may be connected to the network.

The disclosed technique is not limited to the above-described embodiment, and can be variously modified and implemented without departing from the spirit of the present embodiment. Each configuration and each process of the present embodiment can be selected as necessary, or may be combined as appropriate.

For example, in the above-described embodiment, the evaluation data table 57 and the ranking table 58 each have a format as a table, but the present invention is not limited to this, and the data format is appropriately changed. Can be done.

Further, in the above-described embodiment, the storage system 1 is provided with one storage device 4, but the storage system 1 is not limited to this, and two or more storage devices 4 may be provided.

Further, in the above-described embodiment, the storage system 1 is provided with one management server 5, and the management server 5 is provided with functions as a storage management unit 51, a performance information analysis processing unit 52, and a storage unit 53. It is not limited to this. A plurality of management servers 5 may be provided, and the plurality of management servers 5 may be provided with functions as a storage management unit 51, a performance information analysis processing unit 52, and a storage unit 53 in a distributed manner.
Further, according to the above-mentioned disclosure, it is possible to carry out and manufacture this embodiment by a person skilled in the art.

(E) Additional notes The following additional notes will be further disclosed with respect to the above embodiments.
(Appendix 1)
A storage performance monitoring device that monitors the performance of multiple volumes managed by the storage device.
A performance comparison value creating unit that obtains a performance comparison value for each predetermined period for each volume based on the first read performance information of each of the plurality of volumes.
For each of the plurality of volumes, the latest first read performance information is compared with the performance comparison value, and the latest first read performance information is equal to or higher than the first read performance threshold (second threshold) with respect to the comparison source data. A volume extraction unit that extracts volumes that are determined to be divergent,
A storage performance monitoring device including an output unit that outputs a notification representing the extracted volume.

(Appendix 2)
The volume extraction unit determines that the latest first read performance information deviates from the comparison source data by the first read performance threshold value or more, and the second read performance information is equal to or less than the second read performance threshold value. The storage performance monitoring device according to Appendix 1, characterized in that the volume of the above is extracted.

(Appendix 3)
The storage performance monitoring device according to Appendix 1 or 2, wherein the volume extraction unit compares the latest first read performance information with the performance comparison value having the same time condition as the first read performance information. ..

(Appendix 4)
When the first read performance information deviates from the performance comparison value having the same time condition as the first read performance information by an abnormality determination threshold value or more, the output unit performs the same timing as the first read performance information. The storage performance monitoring device according to any one of Items 1 to 3, wherein the abnormality-related information collected from the same volume is output.

(Appendix 5)
The volume extraction unit extracts two or more of the volumes,
Any of the appendices 1 to 4, wherein the output unit sets and outputs a ranking according to the deviation rate of the first read performance threshold value with respect to the comparison source data to the two or more extracted volumes. The storage performance monitoring device according to item 1.

(Appendix 6)
The storage performance monitoring according to Appendix 5, characterized in that, when the same volume is set more than a predetermined number of times in a predetermined order or higher in the ranking, the output unit outputs the abnormality-related information collected from the volume. Device.

(Appendix 7)
For the processor of the storage performance monitoring device that monitors the performance of multiple volumes managed by the storage device,
Based on the first read performance information of each of the plurality of volumes, the performance comparison value for each predetermined period is obtained for each volume.
For each of the plurality of volumes, the latest first read performance information is compared with the performance comparison value, and the latest first read performance information deviates from the comparison source data by the first read performance threshold value or more. Extract the determined volume and
A storage performance monitoring program that executes a process that outputs a notification representing the extracted volume.

(Appendix 8)
A process of extracting a volume in which the latest first read performance information is determined to deviate from the comparison source data by the first read performance threshold value or more and the second read performance information is equal to or less than the second read performance threshold value. 7. The storage performance monitoring program according to Appendix 7, which causes the processor to execute the above.

(Appendix 9)
The storage performance monitoring program according to Supplementary note 7 or 8, which causes the processor to execute a process of comparing the latest first read performance information with the performance comparison value having the same time condition as the first read performance information.

(Appendix 10)
When the first read performance information deviates from the performance comparison value having the same time condition as the first read performance information by an abnormality determination threshold value or more, it is collected from the same volume at the same timing as the first read performance information. The storage performance monitoring program according to any one of Supplementary note 7 to 9, which causes the processor to execute a process of outputting the abnormal abnormality-related information.

(Appendix 11)
Extract two or more of the volumes and
Any one of Supplementary note 7 to 10, which causes the processor to execute a process of setting and outputting a ranking according to the deviation rate of the first read performance threshold value with respect to the comparison source data to the two or more extracted volumes. The storage performance monitoring program described in Section.

(Appendix 12)
The storage performance monitoring program according to Appendix 11, which causes the processor to execute a process of outputting abnormality-related information collected from the volume when the same volume is set a predetermined number of times or more in a predetermined order or higher in the ranking.

1 Storage system 2 Communication line 3 Operation terminal 4 Storage device 5 Management server 11 Processor 12 RAM
13 HDD
14 Graphic processing device 14a Monitor 15 Input interface 15a Keyboard 15b Mouse 16 Optical drive device 16a Optical disk 17 Device connection interface 17a Memory device 17b Memory reader / writer 17c Memory card 18 Network interface 19 Bus 41 CM
42 Storage 51 Storage management unit 52 Performance information analysis processing unit 53 Storage unit 54 Performance information storage file 55 Analysis processing setting information 56 1H Data storage table 57 Evaluation data table 58 Ranking table 59 Log information

Claims (7)

A storage performance monitoring device that monitors the performance of multiple volumes managed by the storage device.
A performance comparison value creating unit that obtains a performance comparison value for each predetermined period for each volume based on the first read performance information of each of the plurality of volumes.
For each of the plurality of volumes, the latest first read performance information is compared with the performance comparison value, and the latest first read performance information deviates from the comparison source data by the first read performance threshold value or more. A volume extractor that extracts the determined volume, and
A storage performance monitoring device including an output unit that outputs a notification representing the extracted volume. The volume extraction unit determines that the latest first read performance information deviates from the comparison source data by a predetermined threshold value or more, and extracts a volume whose second read performance information is equal to or less than the second read performance threshold value. The storage performance monitoring device according to claim 1, wherein the storage performance monitoring device is characterized by the above. The storage performance monitoring according to claim 1 or 2, wherein the volume extraction unit compares the latest first read performance information with the performance comparison value having the same time condition as the first read performance information. Device. When the first read performance information deviates from the performance comparison value having the same time condition as the first read performance information by an abnormality determination threshold value or more, the output unit performs the same timing as the first read performance information. The storage performance monitoring device according to any one of claims 1 to 3, wherein the abnormality-related information collected from the same volume is output. The volume extraction unit extracts two or more of the volumes,
The first to fourth aspects of the present invention, wherein the output unit sets and outputs a ranking according to the deviation rate of the first read performance threshold value with respect to the comparison source data to the two or more extracted volumes. The storage performance monitoring device according to any one of the items. The storage performance according to claim 5, wherein when the same volume is set a predetermined number of times or more in a predetermined order or higher in the ranking, the output unit outputs the abnormality-related information collected from the volume. Monitoring device. For the processor of the storage performance monitoring device that monitors the performance of multiple volumes managed by the storage device,
Based on the first read performance information of each of the plurality of volumes, the performance comparison value for each predetermined period is obtained for each volume.
For each of the plurality of volumes, the latest first read performance information is compared with the performance comparison value, and the latest first read performance information deviates from the comparison source data by the first read performance threshold value or more. Extract the determined volume and
A storage performance monitoring program that executes a process that outputs a notification representing the extracted volume.

Images