NetApp File Layouts (WAFL) Test

WAFL is the NetApp Write Anywhere File Layout, which defines how NetApp lays out data on disk. The WAFL buffer cache is a read cache maintained by WAFL in system memory. On a storage system, if you attempt to read data that is not in the WAFL buffer cache, it results in a direct disk read. Disk reads are expensive operations that increase the processing overheads of your storage system. A well-tuned, right-sized buffer cache can alone help in keeping disk reads minimal. By closely tracking the requests to the storage system and how the WAFL buffer cache services these requests, the NetApp File Layouts test points you to the ineffective usage (if any) of the buffer cache, which can be attributed to insufficient cache memory. Based on the findings of this test, you can then proceed to increase the cache memory (if required).

Target of the test : A NetApp Unified Storage

Agent deploying the test : An external/remote agent

Outputs of the test : One set of results the NetApp storage system being monitored.

Configurable parameters for the test
Parameters	Description
Test Period	How often should the test be executed.
Host	The host for which the test is to be configured.
Port	Specify the port at which the specified host listens in the Port text box. By default, this is NULL.
User	Here, specify the name of the user who possesses the following privileges: login-http-admin,api-aggr-check-spare-low,api-aggr-list-info,api-aggr-mediascrub-list-info,api-aggr-scrub-list-info,api-cifs-status,api-clone-list-status,api-disk-list-info,api-fcp-adapter-list-info,api-fcp-adapter-stats-list-info,api-fcp-service-status,api-file-get-file-info,api-file-read-file,api-iscsi-connection-list-info,api-iscsi-initiator-list-info,api-iscsi-service-status,api-iscsi-session-list-info,api-iscsi-stats-list-info,api-lun-config-check-alua-conflicts-info,api-lun-config-check-cfmode-info,api-lun-config-check-info,api-lun-config-check-single-image-info,api-lun-list-info,api-nfs-status,api-perf-object-get-instances-iter,api-perf-object-instance-list-info,api-quota-report-iter,api-snapshot-list-info,api-vfiler-list-info,api-volume-list-info-iter*. If such a user does not pre-exist, then, you can create a special user for this purpose using the steps detailed in Creating a New User with the Privileges Required for Monitoring the NetApp Unified Storage.
Password	Specify the password that corresponds to the above-mentioned User.
Confirm Password	Confirm the Password by retyping it here.
Authentication Mechanism	In order to collect metrics from the NetApp Unified Storage system, the eG agent connects to the ONTAP management APIs over HTTP or HTTPS. By default, this connection is authenticated using the LOGIN_PASSWORD authentication mechanism. This is why, LOGIN_PASSWORD is displayed as the default authentication mechanism.
Use SSL	Set the Use SSL flag to Yes, if SSL (Secured Socket Layer) is to be used to connect to the NetApp Unified Storage System, and No if it is not.
API Port	By default, in most environments, NetApp Unified Storage system listens on port 80 (if not SSL-enabled) or on port 443 (if SSL-enabled) only. This implies that while monitoring the NetApp Unified Storage system, the eG agent, by default, connects to port 80 or 443, depending upon the SSL-enabled status of the NetApp Unified Storage system - i.e., if the NetApp Unified Storage system is not SSL-enabled (i.e., if the Use SSL flag above is set to No), then the eG agent connects to the NetApp Unified Storage system using port 80 by default, and if the NetApp Unified Storage system is SSL-enabled (i.e., if the Use SSL flag is set to Yes), then the agent-NetApp Unified Storage system communication occurs via port 443 by default. Accordingly, the API Port parameter is set to default by default. In some environments however, the default ports 80 or 443 might not apply. In such a case, against the API Port parameter, you can specify the exact port at which the NetApp Unified Storage system in your environment listens, so that the eG agent communicates with that port for collecting metrics from the NetApp Unified Storage system.
vFilerName	A vFiler is a virtual storage system you create using MultiStore, which enables you to partition the storage and network resources of a single storage system so that it appears as multiple storage systems on the network. If the NetApp Unified Storage system is partitioned to accommodate a set of vFilers, specify the name of the vFiler that you wish to monitor in the vFilerName text box. In some environments, the NetApp Unified Storage system may not be partitioned at all. In such a case, the NetApp Unified Storage system is monitored as a single vFiler and hence the default value of none is displayed in this text box.
Timeout	Specify the duration (in seconds) beyond which the test will timeout if no response is received from the device. The default is 120 seconds.

Measurements made by the test
Measurement	Description	Measurement Unit	Interpretation
Name cache hits	Indicates the rate at which the name cache buffer was successfully queried for an entry during the last measurement period.	Hits/Sec	While a high value is desired for the Name cache hits measure, a low value is ideal for Name cache misses. A large number of cache misses and very few cache hits indicate that adequate entries are not available in the cache to service requests to the storage system. This in turn will force direct disk reads, thereby increasing the processing overheads of the storage system. To minimize disk reads and maximize cache reads, you can increase the WAFL cache memory using WAFL extended cache and the Performance Acceleration Module (PAM) family. WAFL extended cache is a software component of Data ONTAP and requires a license. WAFL extended cache provides extra WAFL cache memory to improve the performance of the storage system by reducing the number of disk reads. Once the extended cache is enabled, you can cache the following in it: Cache normal user data blocks: If you cache normal user data blocks, the WAFL extended cache interprets this setting as the buffer cache policy of keep and saves normal user data blocks in the extended cache. Caching low-priority user data blocks: You can cache low-priority user data blocks that are not normally stored by WAFL extended cache. Low-priority blocks include blocks read in large sequential scans that are not normally reused, and blocks that have been written to the storage system through a network-attached storage (NAS) protocol such as Network File System (NFS). Caching low-priority user data blocks is useful if you have workloads that fit within WAFL extended cache memory and if the workloads consist of either write followed by read or large sequential reads.
Name cache misses	Indicates the rate at which the user query for an entry failed in the name cache buffer during the last measurement period.	Misses/Sec	Caching only system metadata: If the working set of the storage system is very large, such as a large e-mail server, you can cache only system metadata in WAFL extended cache memory by turning off both normal user data block caching and low-priority user data block caching. Integrating FlexShare buffer cache policies with WAFL extended cache: For additional cache control, you can integrate FlexShare buffer cache policies with the WAFL extended cache options. Doing so allows you to set caching policies on specific volumes. You can choose to enable only the FlexShare buffer cache policies without enabling all other FlexShare options.
Directory find hits	Indicates the rate at which the user request successfully found a directory using the WAFL buffer during the last measurement period.	Hits/Sec	A large number of cache misses and very few cache hits indicate that adequate entries are not available in the cache to service requests to the storage system. This in turn will force direct disk reads, thereby increasing the processing overheads of the storage system. To minimize disk reads and maximize cache reads, you can increase the WAFL cache memory using WAFL extended cache and the Performance Acceleration Module (PAM) family. WAFL extended cache is a software component of Data ONTAP and requires a license. WAFL extended cache provides extra WAFL cache memory to improve the performance of the storage system by reducing the number of disk reads. Once the extended cache is enabled, you can cache the following in it: Cache normal user data blocks: If you cache normal user data blocks, the WAFL extended cache interprets this setting as the buffer cache policy of keep and saves normal user data blocks in the extended cache. Caching low-priority user data blocks: You can cache low-priority user data blocks that are not normally stored by WAFL extended cache. Low-priority blocks include blocks read in large sequential scans that are not normally reused, and blocks that have been written to the storage system through a network-attached storage (NAS) protocol such as Network File System (NFS). Caching low-priority user data blocks is useful if you have workloads that fit within WAFL extended cache memory and if the workloads consist of either write followed by read or large sequential reads.
Directory find misses	Indicates the rate at which the user request failed to find a directory using the WAFL buffer during the last measurement period.	Misses/Sec	Caching only system metadata: If the working set of the storage system is very large, such as a large e-mail server, you can cache only system metadata in WAFL extended cache memory by turning off both normal user data block caching and low-priority user data block caching. Integrating FlexShare buffer cache policies with WAFL extended cache: For additional cache control, you can integrate FlexShare buffer cache policies with the WAFL extended cache options. Doing so allows you to set caching policies on specific volumes. You can choose to enable only the FlexShare buffer cache policies without enabling all other FlexShare options.
Buffer hash hits	Indicates the rate at which the hash queue of the WAFL buffer was successfully queried for an entry during the last measurement period.	Hits/Sec	A large number of cache misses and very few cache hits indicate that adequate entries are not available in the cache to service requests to the storage system. This in turn will force direct disk reads, thereby increasing the processing overheads of the storage system. To minimize disk reads and maximize cache reads, you can increase the WAFL cache memory using WAFL extended cache and the Performance Acceleration Module (PAM) family. WAFL extended cache is a software component of Data ONTAP and requires a license. WAFL extended cache provides extra WAFL cache memory to improve the performance of the storage system by reducing the number of disk reads. Once the extended cache is enabled, you can cache the following in it: Cache normal user data blocks: If you cache normal user data blocks, the WAFL extended cache interprets this setting as the buffer cache policy of keep and saves normal user data blocks in the extended cache. Caching low-priority user data blocks: You can cache low-priority user data blocks that are not normally stored by WAFL extended cache. Low-priority blocks include blocks read in large sequential scans that are not normally reused, and blocks that have been written to the storage system through a network-attached storage (NAS) protocol such as Network File System (NFS). Caching low-priority user data blocks is useful if you have workloads that fit within WAFL extended cache memory and if the workloads consist of either write followed by read or large sequential reads.
Buffer hash misses	Indicates the rate at which the user request failed to find an entry in the hash queue of the WAFL buffer during the last measurement period.	Misses/sec	Caching only system metadata: If the working set of the storage system is very large, such as a large e-mail server, you can cache only system metadata in WAFL extended cache memory by turning off both normal user data block caching and low-priority user data block caching. Integrating FlexShare buffer cache policies with WAFL extended cache: For additional cache control, you can integrate FlexShare buffer cache policies with the WAFL extended cache options. Doing so allows you to set caching policies on specific volumes. You can choose to enable only the FlexShare buffer cache policies without enabling all other FlexShare options.
Inode cache hits	Indicates the rate at which the inode information of a file was successfully found using the WAFL buffer during the last measurement period.	Hits/Sec	A large number of cache misses and very few cache hits indicate that adequate entries are not available in the cache to service requests to the storage system. This in turn will force direct disk reads, thereby increasing the processing overheads of the storage system. To minimize disk reads and maximize cache reads, you can increase the WAFL cache memory using WAFL extended cache and the Performance Acceleration Module (PAM) family. WAFL extended cache is a software component of Data ONTAP and requires a license. WAFL extended cache provides extra WAFL cache memory to improve the performance of the storage system by reducing the number of disk reads. Once the extended cache is enabled, you can cache the following in it: Cache normal user data blocks: If you cache normal user data blocks, the WAFL extended cache interprets this setting as the buffer cache policy of keep and saves normal user data blocks in the extended cache. Caching low-priority user data blocks: You can cache low-priority user data blocks that are not normally stored by WAFL extended cache. Low-priority blocks include blocks read in large sequential scans that are not normally reused, and blocks that have been written to the storage system through a network-attached storage (NAS) protocol such as Network File System (NFS). Caching low-priority user data blocks is useful if you have workloads that fit within WAFL extended cache memory and if the workloads consist of either write followed by read or large sequential reads.
Inode cache misses	Indicates the rate at which the inode information of a file was not found in the WAFL buffer during the last measurement period.	Misses/sec	Caching only system metadata: If the working set of the storage system is very large, such as a large e-mail server, you can cache only system metadata in WAFL extended cache memory by turning off both normal user data block caching and low-priority user data block caching. Integrating FlexShare buffer cache policies with WAFL extended cache: For additional cache control, you can integrate FlexShare buffer cache policies with the WAFL extended cache options. Doing so allows you to set caching policies on specific volumes. You can choose to enable only the FlexShare buffer cache policies without enabling all other FlexShare options.
Buffer cache hits	Indicates the rate at which the WAFL buffer cache was successfully queried during the last measurement period.	Hits/Sec	A large number of cache misses and very few cache hits indicate that adequate entries are not available in the cache to service requests to the storage system. This in turn will force direct disk reads, thereby increasing the processing overheads of the storage system. To minimize disk reads and maximize cache reads, you can increase the WAFL cache memory using WAFL extended cache and the Performance Acceleration Module (PAM) family. WAFL extended cache is a software component of Data ONTAP and requires a license. WAFL extended cache provides extra WAFL cache memory to improve the performance of the storage system by reducing the number of disk reads. Once the extended cache is enabled, you can cache the following in it: Cache normal user data blocks: If you cache normal user data blocks, the WAFL extended cache interprets this setting as the buffer cache policy of keep and saves normal user data blocks in the extended cache. Caching low-priority user data blocks: You can cache low-priority user data blocks that are not normally stored by WAFL extended cache. Low-priority blocks include blocks read in large sequential scans that are not normally reused, and blocks that have been written to the storage system through a network-attached storage (NAS) protocol such as Network File System (NFS). Caching low-priority user data blocks is useful if you have workloads that fit within WAFL extended cache memory and if the workloads consist of either write followed by read or large sequential reads.
Buffer cache misses	Indicates the rate at which an entry was not found in the the WAFL buffer cache upon a user query during the last measurement period.	Misses/sec	Caching only system metadata: If the working set of the storage system is very large, such as a large e-mail server, you can cache only system metadata in WAFL extended cache memory by turning off both normal user data block caching and low-priority user data block caching. Integrating FlexShare buffer cache policies with WAFL extended cache: For additional cache control, you can integrate FlexShare buffer cache policies with the WAFL extended cache options. Doing so allows you to set caching policies on specific volumes. You can choose to enable only the FlexShare buffer cache policies without enabling all other FlexShare options.
Total number of buffers	Indicates the total number of buffers in this storage system.	Number
Number of available buffers	Indicates the number of available buffers in this storage system.	Number	A high value is desired for this measure.
Total blocks read	Indicates the total number of blocks read from the WAFL buffer cache.	Number
Total blocks written	Indicates the total number of blocks written to the WAFL buffer cache.	Number
WAFL message rate	Indicates the total number of WAFL messages in this storage system.	Number
Average message latency	Indicates the average time taken for the execution of the WAFL messages during the last measurement period.	Milliseconds	Ideally, the value of this measure should be low. A high value indicates a slowdown indicating a processing bottleneck.
Failures allocating extent messages	Indicates the total number of times the WAFL buffer failed to allocate the extent messages.	Number	Ideally, the value of this measure should be 0. Too many failures may result in processing bottlenecks thus leading to the slowdown of the storage system.