Skip to main content

We've Moved!

Product Documentation has moved to docs.hitachivantara.com
Hitachi Vantara Knowledge

Monitoring Dynamic Tiering pools

Improving performance by monitoring pools

When the multi-tier pool is enabled, and the performance of the pools and DP-VOLs is not as expected, use the workflow below to detect problems and improve the performance.

GUID-1EBCF7C0-C839-40B0-8548-59EEB56307B6-low.png
1. Confirm the performance of pools and DP-VOLs

Using Performance Monitor, confirm the performance of pools and DP-VOLs. If the performance of pools and DP-VOLs is poor, go to Step 2.

2. Confirm the Dynamic Tiering setting

Using Hitachi Device Manager - Storage Navigator or Command Control Interface, confirm the Dynamic Tiering setting. If the values are set but do not conform to the design of pools or LDEVs, change the settings. If the values are set and conform to the design of pools or LDEVs, go to Step 3.

3. Confirm and improve the progress of tier relocation processing

Confirm the progress of tier relocation processing in Completed Rate (%) in the tier relocation log file. If the progress of the tier relocation process is low, there might be many pages where the page allocation is not optimized. In this case, change the Monitoring Mode or Cycle Time setting. The recommended values are as follows:

Monitoring Mode: If Period Mode is set, change to Continuous Mode.

Cycle Time: Set a longer period than the current setting.

If the recommended values are already set or if the progress of tier relocation processing is still low even after the settings are changed, go to Step 4.

4. Confirm Performance Utilization of each tier

You can confirm the performance utilization of each tier in the View Tier Properties window or with the raidcom get dp_pool command. The performance utilization is the ratio (%) of the number of I/Os against the performance potential of the tier. For example, if the performance utilization is 90% or more, a workload greater than the processing capacity of the tier is being applied to the tier.

If Performance Utilization is 90% or more on one or more of the tiers, or if Performance Utilization is 60% on all tiers, add drives and expand the pool capacity.

1. In the case that Performance Utilization is 90% or more on a tier:

Add drives to the tier where Performance Utilization is 90% or more and confirm the usage ratio of the capacity. The recommended drives to be added are as follows:

Drives to be added to the tier where Performance Utilization is 90% or more

Recommended pool volumes to be added

SSD

Add SSD pool volumes.

SAS10K or SAS15K

If the performance is given greater priority than the bit-cost: Add SSD pool volumes.

If the bit-cost is given greater priority than the performance: Add SAS10K or SAS15K pool volumes. However, add SSD pool volumes if the capacity utilization of the SAS tier (SAS10K or SAS15K) is low.

SAS7.2K

If the performance is given greater priority than the bit-cost: Add SAS (SAS10K or SAS15K) pool volumes.

If the bit-cost is given greater priority than the performance: Add SAS7.2K pool volumes. However, add SAS (SAS10K or SAS15K) pool volumes if the capacity utilization of the SAS 7.2K tier is low.

2. In the case that Performance Utilization is 90% or more on two or more tiers:

a. Collect the frequency distribution on the View Tier Properties window.

b. From the frequency distribution and the performance limit of each tier, seek the ratio of the most suitable tier capacity.

The performance limit of tier 2 is the maximum average IOPH on one page that the drive related to tier 2 can process. The performance limit of tier 3 is the maximum average IOPH on one page that the tier 3 drive can process. Based on these values, calculate the most suitable tier capacity for the tier 1, tier 2, and tier 3.

The most suitable tier capacity for tier 1: The capacity from 0 GB to the capacity related to the performance limit of tier 2

The most suitable tier capacity for tier 2: The capacity from the performance limit of tier 2 to tier 3 of that capacity.

The most suitable tier capacity for tier 3: The capacity from the performance limit of tier 3 to the maximum capacity of tier 3

Then, based on the most suitable tier capacity for each tier, calculate the most suitable capacity ratio of tier 1, tier 2, and tier 3 as follows:

The most suitable tier capacity for tier 1 : The most suitable tier capacity for tier 2 : The most suitable tier capacity for tier 3

c. Compare the ratio of the real tier capacity to the ratio of the most suitable tier capacity.

Comparing the ratio of tier capacity

Pool volumes suggested to be added

The ratios of the most suitable tier capacity and real tier capacity are different.

Add pool volumes to the tier that is lacking capacity.

The ratios of the most suitable tier capacity and real tier capacity are the same.

If the performance is given greater priority than the bit-cost: Add SSD or SAS (SAS10K or SAS15K) pool volumes.

If the bit-cost is given greater priority than the performance: Add SAS (SAS10K or SAS15K) pool volumes. However, add SSD pool volumes if the capacity utilization of the SAS tier (SAS10K or SAS15K) is low.

d. Add drives and expand the pool capacity.

3. In the case that Performance Utilization is 60% on all tiers:

Add drives in the upper tier and expand the pool capacity.

Monitoring modes

When you create or edit a pool, you set the Dynamic Tiering monitoring mode: period mode, or continuous mode. When you change the monitoring mode, the new monitoring setting becomes effective when the next monitoring period starts.

Period mode

When Period mode is enabled, tier range values and page relocations are determined based solely on the monitoring data from the last complete cycle. Relocation is performed according to any changes in I/O loads. However, if the I/O loads vary greatly, relocation might not finish in one cycle.

Continuous mode (default)

When Continuous mode is enabled, the weighted average efficiency is calculated by weighting the latest monitoring information and the collected monitoring information in the past cycles. By performing the tier relocation based on the weighted average efficiency, even if a temporary decrease or an increase of the I/O load occurs, unnecessary relocation can be avoided.

GUID-262DD15C-4CC6-4477-BCCF-4651638D8644-low.gif
Cautions when using monitoring modes
  • When Continuous monitoring mode is used, best practice is to collect monitoring information using the following execution modes:
    • Auto execution mode
    • Manual execution mode with collecting the periodic monitoring information by defining a script using CCI

    If Manual execution mode is used without scripts, Continuous monitoring mode can be set. However, in this case, unexpected results might be calculated because the weighted average efficiency is calculated based on very different duration (short and long) periods information obtained in the past cycles.

  • When Continuous monitoring mode is used, the frequency distributions are displayed for each pool and V-VOL calculated by using the monitor value on which the weighted calculation is done.

    These calculated values are the predictive values for the next cycle after successfully relocating all pages. Therefore, these values might differ from an actual monitoring result when they appear.

    In Performance Utilization of each tier, regardless of the type of the monitoring mode setting, the monitor values that were already collected in the current cycle are displayed.

    If you switch the monitoring mode from Period to Continuous or from Continuous to Period, the current cycle's monitoring data that is being collected is not discarded. However, the data calculated by using past monitor cycle information on which the weighted calculation is done will be reset.

Thresholds for monitoring pools

Dynamic Provisioning monitors pool capacity using thresholds. A threshold is the proportion (%) of the used capacity of the pool to the total capacity of the pool, or the proportion (%) of the physical used capacity of the pool to the total capacity reserved for writing of the pool.

Monitoring the pool capacity

If you are regularly monitoring pool capacity and notice that a pool has insufficient space, or if insufficient space is reported in a related SIM report, you need to estimate the capacity to be added.

GUID-A9E77077-8005-4D38-8587-6DEE0263BE7B-low.png

Pool utilization thresholds

When the used capacity of a pool reaches or exceeds the utilization thresholds set for the pool, you will be alerted so that you can take the appropriate action.

You can set the following threshold values for each pool:

  • Warning Threshold: Range = 1% to 100%, in 1% increments. Default = 70%.
  • Depletion Threshold: Range = 1% and 100%, in 1% increments. Default = 80%. The Depletion Threshold must be higher than the Warning Threshold.

If the pool used-capacity is equal to or greater than the Warning or Depletion Threshold, a service information message (SIM) is issued by the storage system. SIMs are displayed by Device Manager - Storage Navigator and other management software and reported to the open-system hosts as SNMP traps.

The following figure shows a pool with a total pool capacity of 1,000 GB, a Warning Threshold of 50%, and a Depletion Threshold of 80%. If the used capacity of this pool is equal to or greater than 50% (500 GB) of the total pool capacity, a SIM and an SNMP trap are reported. If the used capacity of this pool increases further and is equal to or greater than the Depletion Threshold (80%), another SIM and SNMP trap are reported.

GUID-ABC19D56-F694-4A58-9B1B-1A62CEB538A4-low.gif
NoteWhen the Depletion Threshold is reached, the following functions will no longer work:
  • Pool Rebalance
  • Pool Relocation
  • Creation of DP-VOLs
  • Creation of Replication Pairs (HTI)

Changing pool thresholds

Use this procedure to change the threshold of a pool.

Before you begin

The Storage Administrator (Provisioning) role is required to perform this task.

Procedure

  1. Click Storage Systems, and then expand the Storage Systems tree.

  2. Click Pools.

  3. From the Pools table, select the pool with the threshold you want to change.

  4. Click More Actions, and then select Edit Pools.

  5. In the Edit Pools window, check Warning Threshold or Depletion Threshold.

  6. Type the threshold values in the text box.

    The threshold value can be within the range of values indicated below the text box. The Depletion Threshold value can be equal to or greater than the Warning Threshold.
  7. Click Finish.

    The Confirm window appears.
  8. In the Task Name text box, type a unique name for the task or accept the default.

    You can enter up to 32 ASCII characters and symbols, with the exception of: \ / : , ; * ? " < > |. The value "date-window name" is entered by default.
  9. Click Apply.

    If the Go to tasks window for status check box is selected, the Tasks window appears.

Controlling Thin Image pair behavior in a Dynamic Provisioning pool

Use this procedure to control whether Thin Image pairs are suspended when the free capacity of a Dynamic Provisioning pool that contains Thin Image pairs and snapshot data is depleted.

The Suspend TI pairs when depletion threshold is exceeded option enables you to stop Thin Image pair copy operations in a Dynamic Provisioning pool and prioritize the writing process to DP-VOLs when the free capacity of the pool is depleted. When this option is enabled and the pool used capacity exceeds the depletion threshold, SIM code 62Exxx is output. After this SIM code is output, if you split a Thin Image pair in the depleted pool, the operation fails and the pair is suspended by error (PSUE). You can restore the suspended Thin Image pairs when the pool used capacity has decreased below the depletion threshold and the SIM code has been cleared.

Before you begin

  • The Storage Administrator (Provisioning) role is required to perform this task.
  • The target pool must be a Dynamic Provisioning pool that contains Thin Image pairs and snapshot data.

Procedure

  1. Click Storage Systems, and then expand the Storage Systems tree.

  2. Click Pools.

  3. In the Pools table, select the pool you want to edit, click More Actions, and select Edit Pools.

  4. In the Edit Pools window, expand Options, and then select Suspend TI pairs when depletion threshold is exceeded.

  5. Select Yes to enable the option, or select No to disable the option.

  6. Click Finish.

  7. Check the settings in the Confirmation window, and then enter the task name in Task Name.

    You can enter up to 32 ASCII characters and symbols in all, except for \ / : , ; * ? " < > |. The value "date-window name" is entered by default.
  8. Click Apply.

    The task is registered. If you selected Go to tasks window for status, the Tasks window appears.

Tier monitoring and relocation cycles

Performance monitoring and tier relocation can be set to execute in one of two execution modes: Auto and Manual. You can set up execution modes, or switch between modes by using either Hitachi Device Manager - Storage Navigator or Command Control Interface.

In Auto execution mode, monitoring and relocation are continuous and automatically scheduled. In Manual execution mode, the following operations are initiated manually.

  • Start monitoring
  • Stop monitoring and recalculate tier range values
  • Start relocation
  • Stop relocation

In both execution modes, relocation of data is automatically determined based on monitoring results. The settings for these execution modes can be changed nondisruptively while the pool is in use.

Auto execution mode

Auto execution mode performs monitoring and tier relocation based on information collected by monitoring at a specified constant frequency: every 0.5, 1, 2, 4, or 8 hours. All auto execution mode cycle frequencies have a starting point at midnight (00:00). For example, if you select a 1 hour monitoring period, the starting times would be 00:00, 01:00, 02:00, 03:00, and so on.

As shown in the following table, the 24-hour monitoring cycle allows you to specify the times of day to start and stop performance monitoring. The 24-hour monitoring cycle does not have to start at midnight. Tier relocation begins at the end of each cycle.

Monitoring cycle (hours)

Start Times

Finish Times

0.5

0.5 hours from 00:00 AM. For example 00:00, 00:30, and 01:00

0.5 hours after the start time

1

1 hour from 00:00 AM. For example 00:00, 01:00, and 02:00

1 hour after the start time

2

2 hours from 00:00 AM. For example 00:00, 02:00, and 04:00

2 hours after the start time

4

4 hours from 00:00 AM. For example 00:00, 04:00, and 08:00

4 hours after the start time

8

8 hours from 00:00 AM. For example 00:00, 08:00, and 16:00

8 hours after the start time

24 (monitoring time period can be specified)

Specified time

Specified time

If the setting of the monitoring cycle is changed, performance monitoring begins at the new start time. The collection of monitoring information and tier relocation operations already in progress are not interrupted when the setting is changed.

Example 1: If the monitoring cycle is changed from 1 hour to 4 hours at 01:30 AM, the collection of monitoring information and tier relocation in progress at 01:30 AM continues. At 02:00 AM and 03:00 AM, however, monitoring information is not collected and tier relocation is not performed. From 04:00 AM, the collection of monitoring information and tier relocation operations are started again. These operations are then performed at 4-hour intervals.

Example 2: If the monitoring cycle is changed from 4 hours to 1 hour at 01:30 AM, the collection of monitoring information and tier relocation in progress at 01:30 AM continues. From 04:00 AM, the collection of monitoring information and tier relocation operations are started again. These operations are then performed at 1-hour intervals.

GUID-D6019F75-9F9C-4628-A8D7-39EDE31B1989-low.png

In auto execution mode, the collection of monitoring data and tier relocation operations are performed in parallel in the next cycle. Data from these parallel processes are stored in two separate fields.

  • Data while monitoring is in progress in the next cycle.
  • Fixed monitoring information used in the tier relocation.

Manual execution mode

You can start and stop performance monitoring and tier relocation at any time. You should keep the duration of performance monitoring to less than 7 days (168 hours). If performance monitoring exceeds 7 days, then monitoring stops automatically.

Manual execution mode starts and ends monitoring and relocation at the time the command is issued. You can use scripts, which provide flexibility to control monitoring and relocation tasks based on a schedule for each day of the week.

In manual execution mode, the next monitoring cycle can be started with the collection of monitoring data and tier relocation operations performed in parallel. Data from these parallel processes are stored in two separate fields.

  • Data while monitoring is in progress in the next cycle.
  • Fixed monitoring information used in the tier relocation.

The following figure illustrates the collection of monitoring data to tier relocation workflow in manual execution mode.

GUID-D90E26C3-E328-4767-A413-2CF28BD112AC-low.png

Case 1: If the second collection of the monitoring information is finished during the first tier relocation, the latest monitoring information is the second collection. In that case, the first collection of monitoring information is referenced only after the first tier relocation has completed.

GUID-69ECA429-F5F9-442A-BC5C-3C6FC159BEF9-low.png

Case 2: When tier relocation is performed with the first collection of monitoring information, the second collection of monitoring information can be performed. However, the third collection cannot be started. Because only two fields are used store collected monitoring information, the third collection cannot be overwritten.

In that case, the third collection of the monitoring information is started after the first tier relocation is stopped or tier relocation has completed.

The collection of the monitoring information is not started under these conditions as well:

  • When the second tier relocation is performed, the fourth collection of monitoring information cannot be started.
  • When the third tier relocation is performed, the fifth collection of monitoring information cannot be started.

If such conditions exist, two cycles of monitoring information cannot be collected continuously while tier relocation is performed.

The following figure illustrates the third collection of monitoring information while tier relocation is performed.

GUID-2FF80EF0-9CCD-4178-8F64-A7289B5D4B14-low.png

 

  • Was this article helpful?