Performance metrics for DS8000

Monitor the performance metrics that are collected for DS8000 storage systems.

Overview

Performance metrics are available for the following resources:

A performance metric might apply to one or more storage resources. To check which resources the performance metric applies to, see the tips and the table footnotes.

Storage system

Storage system is divided into the following category:
  • Environmental
Table 1. Environmental
Metric Definition
Total Power Consumed It is the total power consumed by all the components of the storage devices including nodes, enclosures, etc. in Watts.
System Temperature (oC) It is the average temperature of the storage device in Celsius.
System Temperature (oF) It is the average temperature of the storage device in Fahrenheit.
Power Efficiency It is the total power consumed by the storage systems in Watts. It denotes how much and how efficiently the power is consumed by the storage devices. The value of power efficiency is the consumption of total power divided by raw capacity bytes of the device.
Carbon Emission The carbon emissions per hour by the storage system.
Note: The carbon emission information is available for the DS8000 storage systems with firmware version 7.7.2.0 or later only.

Volume metrics

Volume performance metrics are divided into the following categories:
Tip: Unless otherwise noted, you can view the volume metrics in Table 2, Table 3, Table 4, and #tpch_r_metrics_ds.dita__v_miscellaneous_metrics for the following resources:
  • Volumes
  • Pools
  • Controllers
  • Host connections
  • Storage systems
Table 2. Key volume metrics
Metric Description
Cache Holding Time 1 The average number of seconds that I/O data for a storage system node is held in the cache. A short cache-holding time indicates adverse performance.
Pool Activity Score 2 The activity level of pools, which is set to the following value:

[Read I/O Rate × (1− Read I/O Cache Hit %)] ÷ Total Pool Capacity
Write-Cache Delay Percentage The percentage of I/O operations that are delayed because of space constraints in the write cache, or because of other conditions. The value is a percentage of all operations. This value applies only to resources that are running a version of IBM Storage Virtualize earlier than 7.3. The metric is an approximation because actual transfer rates are different for each cache layer. Therefore, you cannot directly compare this metric from resources that are 7.3 or later with earlier versions.
Note:
  1. This metric is only available when you view the performance of controllers or storage systems.
  2. This metric is only available when you view the performance of pools.
Table 3. I/O Rates
Metric Description
Average Transfer Rate (Cache-to-Disk)1 The average number of sectors or tracks per second that are transferred from the cache to the disks.
Average Transfer Rate (Disk-to-Cache)1 The percentage of cache hits for record-mode read operations. For record-mode read operations, only the requested data, rather than a full track of data, is managed in the cache.
High Performance FICON® (Read) The average number of read operations per second that are issued by the High Performance FICON feature of the storage system.
High Performance FICON (Write) The average number of write operations per second that are issued by the High Performance FICON feature of the storage system.
High Performance FICON (Total) The average number of I/O operations per second that are issued by the High Performance FICON feature of the storage system. This value includes both read and write operations.
Normal I/O Rate (Read) The average number of nonsequential read operations per second.
Normal I/O Rate (Write) The average number of nonsequential write operations per second.
PPRC Transfer Rate The average number of tracks per second that are transferred to the secondary device of a Peer-to-Peer Remote Copy (PPRC) pair. This value shows the activity for the source of the PPRC relationship, but shows no activity for the target.
Record Mode Read I/O Rate 1 The average number of I/O operations per second for record-mode read operations. For record-mode read operations, only the requested data is managed in the cache rather than a full track of data.
Sequential I/O Rate (Read) The average number of sequential read operations per second.
Sequential I/O Rate (Write) The average number of sequential write operations per second.
Note:
  1. This metric is only available when you view the performance of volumes, pools, controllers, and host connections.
Table 4. Cache hit percentages
Metric Description
Normal I/O Cache Hits (Read) The percentage of nonsequential read operations that find data in the cache.You can use this value to understand throughput or response times. Low cache-hit percentages can increase response times because a cache miss requires access to the back-end storage resources.
Normal I/O Cache Hits (Write) The percentage of nonsequential write operations that are handled in the cache.
Record Mode Read Cache Hit Percentage 1 The percentage of cache hits for record-mode read operations. For record-mode read operations, only the requested data, rather than a full track of data, is managed in the cache.
Sequential I/O Cache Hits (Read) The percentage of sequential read operations that find data in the cache. You can use this value to understand throughput or response times. Low cache-hit percentages can increase response times because a cache miss requires access to the back-end storage resources.
Sequential I/O Cache Hits (Write) The percentage of sequential write operations that are handled in the cache.
Note:
  1. This metric is only available when you view the performance of volumes, pools, controllers, and host connections.

Disk metrics

Disk performance metrics are divided into the following categories:
Tip: Unless otherwise noted, you can view the volume metrics in Table 5 and Table 6 for the following resources:
  • Ranks
  • RAID arrays
  • Pools
  • Controllers
  • Storage systems
Table 5. Key disk metrics
Metric Description
Data Rate (Read) The average number of MiB per second that are read from the back-end storage resources.
Data Rate (Write) The average number of MiB per second that are written to the back-end storage resources.
Data Rate (Total) The average rate at which data is transmitted between the back-end storage resources and the component. The rate is measured in MiB per second and includes both read and write operations.
Disk Utilization Percentage 1 The average percentage of time that the disks that are associated with an array are busy. No value is calculated for this property if there are multiple ranks in the extent pool where the thin-provisioned volumes are allocated. In this case, the value N/A is displayed. This limitation applies only to DS8000 storage systems. If there is only a single rank in the extent pool, the value for this property is calculated regardless of the thin-provisioned volumes.
Available for: RAID arrays on DS8000 version 8.5.0 and later. For earlier versions, the value N/A is shown in the performance table view and the metric is not shown on the performance chart.
I/O Rate (Read) The average number of read operations per second that are issued to the back-end storage resources.
I/O Rate (Write) The average number of write operations per second that are issued to the back-end storage resources.
I/O Rate (Total) The average number of I/O operations per second that are transmitted between the back-end storage resources and the component. This value includes both read and write operations.
Response Time (Read) The average number of milliseconds for the back-end storage resources to respond to a read operation.
Response Time (Write) The average number of milliseconds for the back-end storage resources to respond to a write operation.
Response Time (Overall) The average number of milliseconds for the back-end storage resources to respond to a read or a write operation.
Note:
  1. This metric is only available when you view the performance of RAID arrays.
Table 6. Transfer size metrics
Metric Description
Average Transfer Size (Read) The average number of KiB that are transferred per read operation from the back-end storage resources.
Average Transfer Size (Write) The average number of KiB that are transferred per write operation to the back-end storage resources.
Average Transfer Size (Overall) The average transfer size, in KiB, of a read or a write operation to the back-end storage resources.

Port metrics

Port performance metrics are divided into the following categories:
Tip: Unless otherwise noted, you can view the port metrics in Table 7, Table 11, Table 12, and Table 13 for ports and storage systems. The port metrics in Table 8, Table 9, Table 10 are only available for ports.
Table 7. Key port metrics
Metric Description
Data Rate (Receive) The average rate at which data is received by the port. The rate is measured in MiB per second.
Data Rate (Send) The average rate at which data is sent from the port. The rate is measured in MiB per second.
Data Rate (Total) The average rate at which data is transferred through the port. The rate is measured in MiB per second and includes both send and receive operations.
I/O Rate (Receive) The average number of I/O operations per second for operations in which the port receives data.
I/O Rate (Send) The average number of I/O operations per second for operations in which data is sent from a port.
I/O Rate (Total) The average number of send operations and receive operations per second.
Response Time (Receive) The average number of milliseconds to complete a receive operation.
Response Time (Send) The average number of milliseconds to complete a send operation.
Bandwidth (Receive)1 The percentage of the port bandwidth that is used for receive operations. This value is an indicator of port bandwidth usage that is based on the speed of the port.
Bandwidth (Send)1 The percentage of the port bandwidth that is used for send operations. This value is an indicator of port bandwidth usage that is based on the speed of the port.
Note:
  1. This metric is only available when you view the performance of ports.
Table 8. Port I/O rate metrics
Metric Description
FICON I/O Rate (Send) The average number of send operations per second for Fibre Channel connection (FICON) usage.
FICON I/O Rate (Receive) The average number of receive operations per second for FICON usage.
FCP I/O Rate (Send) The average number of send operations per second for Fibre Channel Protocol (FCP) usage.
FCP I/O Rate (Receive) The average number of receive operations per second for FCP usage.
Table 9. Port data rates
Metric Description
FICON Data Rate (Send) The average number of MiB per second that is sent for FICON usage.
FICON Data Rate (Receive) The average number of MiB per second that is received for FICON usage.
FCP Data Rate (Send) The average number of MiB per second that are sent for FCP usage.
FCP Data Rate (Receive) The average number of MiB per second that are received for FCP usage.
Table 10. Port response times
Metric Description
FICON Response Time (Send) The average number of milliseconds to complete a send operation for FICON usage.
FICON Response Time (Receive) The average number of milliseconds to complete a receive operation for FICON usage.
FICON Response Time (Overall) The average number of milliseconds to complete a send or receive operation for FICON usage. This value includes both send and receive FICON operations.
FCP Response Time (Send) The average number of milliseconds to complete a send operation for FCP usage.
FCP Response Time (Receive) The average number of milliseconds to complete a receive operation for FCP usage.
FCP Response Time (Overall) The average number of milliseconds to complete a send or receive operation for FCP usage.
Table 11. Error rate metrics
Metric Description
Frame Errors (CRC Errors) The average number of frames per second that are received in which a cyclic redundancy check (CRC) error is detected. A CRC error is detected when the CRC in the transmitted frame does not match the CRC computed by the receiver. For Brocade switches, this metric includes only the CRC Errors with a good end-of-frame (EOF) indicator.
Frame Errors (Error Frame) The average number of error frames per second that are received. An error frame is a frame that violates the Fibre Channel Protocol.
Frame Errors (Invalid Relative Offset Rate) The average number of times per second that frames are received with an invalid relative offset in the frame header.
Link Errors (Invalid Link Transmission) The average number of times per second that an invalid transmission word was detected by the port while the link did not experience any signal or synchronization loss.
Link Errors (Invalid Transmission Words) The average number of bit errors per second that are detected.
Link Errors (Link Failures) The average number of miscellaneous fibre channel link errors per second for ports. Link errors might occur when an unexpected Not Operational (NOS) is received or a link state machine failure was detected.
Link Errors (Primitive Sequence Protocol Error Rate) The average number of primitive sequence protocol errors per second that are detected. This error occurs when there is a link failure for a port.
Link Errors (Sequence Timeouts) The average number of times per second that the port detects a timeout condition after the port receives a sequence initiative for a Fibre Channel exchange.
Link Errors (Signal Loss) The average number of times per second at which the port lost communication with its partner port. These types of errors usually indicate physical link problems, caused by faulty SFP modules or cables, or caused by faulty connections at the switch or patch panel. However, in some cases, this error can also occur when the maximum link distance between ports is exceeded, for the type of connecting cable and light source.
Link Errors (Sync Loss) The average number of times per second that the port lost synchronization with its partner port. These types of errors usually indicate physical link problems, caused by faulty SFP modules or cables, or caused by faulty connections at the switch or patch panel. However in some cases this can also occur due to mismatching port speeds between the partner ports, when auto-negotiation of link speed is disabled.
Port Protocol Errors (Credit Recovery Link Resets) The estimated average number of link resets per second that a switch or port completed to recover buffer credits. This estimate attempts to disregard link resets that were caused by link initialization. When you troubleshoot a SAN, use this metric to help identify port conditions that might slow the performance of the resources to which those ports are connected.
Port Protocol Errors (Duplicate Frames) The average number of duplicate frames per second that are received. A duplicate frame is a frame that the system previously processed for the port.
Port Protocol Errors (Link Reset Received) The average number of times per second that the port changes from an active (AC) state to a Link Recovery (LR2) state.
Port Protocol Errors (Link Reset Transmitted) The average number of times per second that the port changes from an active (AC) state to a Link Recovery (LR1) state.
Port Protocol Errors (Out of Order ACK) The average number of times per second that an out-of-order acknowledge (ACK) frame is detected.An ACK frame is used for end-to-end flow control and is sent to verify receipt of a frame.
Port Protocol Errors (Out of Order Data) The average number of times per second that an out-of-order frame is detected.
Total Physical Port Error Rate (cnt/s) The sum of all the physical error rates such as Error Frames, CRC Errors, Short Frames, and Link Failures that are detected on the FC port for a storage system.
Total Physical Port Error Rate is the sum of the following physical error rates:
  • Error Frame Rate
  • CRC Error Rate
  • Short Frame Rate
  • Long Frame Rate
  • Bad EOF CRC Error Rate
  • Link Failure Rate
  • Loss of Sync Rate
  • Loss of Signal Rate
  • Primitive Sequence Protocol Error Rate
  • Invalid Word Transmission Rate
Total Logical Port Error Rate (cnt/s) The sum of all the logical error rates such as F-BSY Frames, F-BSY Frames, Discarded Frames, and Encoding Disparity that are detected on the FC port for a storage system.
Total Logical Port Error Rate is the sum of the following logical error rates:
  • F-BSY Frame Rate
  • F-RJT Frame Rate
  • Discarded Class 3 Frame Rate
  • Discarded Frame Rate
  • Link Reset Transmitted Rate
  • Link Reset Received Rate
  • Class 3 Send Timeout Frame Rate
  • Class 3 Receive Timeout Frame Rate
  • Encoding Disparity
Table 12. Remote mirror metrics
Metric Description
PPRC Data Rate (Receive) The average number of MiB per second that are received by using the Peer-to-Peer Remote Copy (PPRC) protocol.
PPRC Data Rate (Send) The average number of MiB per second that are sent by using the PPRC protocol.
PPRC I/O Rate (Receive) The average number of operations per second that are received by using the PPRC protocol.
PPRC I/O Rate (Send) The average number of operations per second that are sent by using the PPRC protocol.
PPRC I/O Rate (Total) The average number of send operations and receive operations per second using the PPRC protocol.
PPRC Response Time (Receive) The average number of milliseconds to complete a receive operation by using the PPRC protocol.
PPRC Response Time (Send) The average number of milliseconds to complete a send operation by using the PPRC protocol.
Table 13. Transfer size metrics
Metric Description
Average Transfer Size (Receive) The average number of KiB that are transferred per receive operation.
Average Transfer Size (Send) The average number of KiB that are transferred per send operation.
Average Transfer Size (Overall) The average number of KiB that are transferred per I/O operation. This value includes both send and receive operations.

Host adapter metrics

Host adapter performance metrics are divided into the following categories:
Table 14. Key metrics
Metric Description
Data Rate (Receive) The average rate at which data is received by the port. The rate is measured in MiB per second.
Data Rate (Send) The average rate at which data is sent from the port. The rate is measured in MiB per second.
Data Rate (Total) The average rate at which data is transferred through the port. The rate is measured in MiB per second and includes both send and receive operations.
I/O Rate (Receive) The average number of I/O operations per second for operations in which the port receives data.
I/O Rate (Send) The average number of I/O operations per second for operations in which data is sent from a port.
I/O Rate (Total) The average number of send operations and receive operations per second.
Response Time (Receive) The average number of milliseconds to complete a receive operation.
Response Time (Send) The average number of milliseconds to complete a send operation.
Response Time (Overall) The average number of milliseconds to complete a send or receive operation.
Table 15. I/O rate metrics
Metric Description
FICON I/O Rate (Send) The average number of send operations per second for Fibre Channel connection (FICON) usage.
FICON I/O Rate (Receive) The average number of receive operations per second for FICON usage.
FICON I/O Rate (Total) The average number of send and receive operations per second for FICON usage.
FCP I/O Rate (Send) The average number of send operations per second for Fibre Channel Protocol (FCP) usage.
FCP I/O Rate (Receive) The average number of receive operations per second for FCP usage.
FCP I/O Rate (Total) The average number of send operations and receive operations per second for FCP usage.
Table 16. Data rates
Metric Description
FICON Data Rate (Send) The average number of MiB per second that is sent for FICON usage.
FICON Data Rate (Receive) The average number of MiB per second that is received for FICON usage.
FICON Data Rate (Total) The average number of MiB per second that is transferred for FICON usage. This value includes both send and receive FICON operations.
FCP Data Rate (Send) The average number of MiB per second that are sent for FCP usage.
FCP Data Rate (Receive) The average number of MiB per second that are received for FCP usage.
FCP Data Rate (Total) The average number of MiB per second that are transferred for FCP usage. This value includes both send and receive FCP operations.
Table 17. Response times
Metric Description
FICON Response Time (Send) The average number of milliseconds to complete a send operation for FICON usage.
FICON Response Time (Receive) The average number of milliseconds to complete a receive operation for FICON usage.
FICON Response Time (Overall) The average number of milliseconds to complete a send or receive operation for FICON usage. This value includes both send and receive FICON operations.
FCP Response Time (Send) The average number of milliseconds to complete a send operation for FCP usage.
FCP Response Time (Receive) The average number of milliseconds to complete a receive operation for FCP usage.
FCP Response Time (Overall) The average number of milliseconds to complete a send or receive operation for FCP usage.
Table 18. Remote mirror metrics
Metric Description
PPRC Data Rate (Receive) The average number of MiB per second that are received by using the Peer-to-Peer Remote Copy (PPRC) protocol.
PPRC Data Rate (Send) The average number of MiB per second that are sent by using the PPRC protocol.
PPRC Data Rate (Total) The average number of MiB per second that are transferred by using the PPRC protocol. This value includes both send and receive PPRC operations.
PPRC I/O Rate (Receive) The average number of operations per second that are received by using the PPRC protocol.
PPRC I/O Rate (Send) The average number of operations per second that are sent by using the PPRC protocol.
PPRC I/O Rate (Total) The average number of send operations and receive operations per second using the PPRC protocol.
PPRC Response Time (Receive) The average number of milliseconds to complete a receive operation by using the PPRC protocol.
PPRC Response Time (Send) The average number of milliseconds to complete a send operation by using the PPRC protocol.
PPRC Response Time (Overall) The average number of milliseconds to complete a send or receive operation by using the PPRC protocol.
Table 19. Transfer size metrics
Metric Description
Average Transfer Size (Receive) The average number of KiB that are transferred per receive operation.
Average Transfer Size (Send) The average number of KiB that are transferred per send operation.
Average Transfer Size (Overall) The average number of KiB that are transferred per I/O operation. This value includes both send and receive operations.
Table 20. Error rate metrics
Metric Description
Extreme I/O Concurrency Rate The average number of times per second that the port on DS8000 had more than 1500 concurrent I/O operations or exchanges. The number of concurrent I/O operations for a port on DS8000 cannot exceed 2000.
Extreme I/O Concurrency Percentage The average percentage of I/O operations for which the port on DS8000 had more than 1500 concurrent I/O operations or exchanges. The number of concurrent I/O operations for ports on DS8000 cannot exceed 2000.
I/O Busy Rate The average number of times per second that the port on DS8000 returned a SCSI Queue Full or a Busy status to the server. Ports can return these statuses if the number of I/O operations or exchanges exceeds an internal DS8000 threshold.
I/O Busy Percentage The average percentage of I/O operations or exchanges for which the port on DS8000 returned a SCSI Queue Full or a Busy status to the server. Ports can return these statuses if the number of I/O operations exceeds an internal DS8000 threshold.
I/O Overrun Rate The average number of times per second that the port on DS8000 had to discard commands because the number of concurrent I/O operations or exchanges for the port exceeded 2000.
I/O Overrun Percentage The average percentage of I/O operations that the port on DS8000 had to discard because the number of concurrent I/O operations or exchanges for the port exceeded 2000.
Zero Send Buffer Credit Percentage The amount of time, as a percentage, that the port on DS8000 had depleted its send buffer credits. That is, the percentage of time that the receiving port had no credit to provide to the port on DS8000.
Zero Receive Buffer Credit Percentage The amount of time, as a percentage, that the port on DS8000 had depleted its receive buffer credits. That is, the percentage of time that the port on DS8000 had no credit to provide to the sending port.