Stay organized with collections
Save and categorize content based on your preferences.
This page provides details on parameters that directly affect volume performance.
Volume considerations
When you assign capacity to your volumes, consider the following:
Your choice of access protocol (Server Message Block (SMB) or Network File
System (NFS)) might impact throughput.
Your choice of service level affects the throughput limit.
Volume considerations for the Flex service level
The following considerations apply to volumes created within the Flex
service level:
The pool provides a common aggregate throughput limit for all volumes in the
pool. Volumes share the pool's throughput.
Adding pool capacity increases the maximum throughput limit for volumes in
the pool.
Adding additional capacity to a volume doesn't increase the maximum volume
throughput limit.
Volume considerations for the Standard, Premium, and Extreme service levels
The following considerations apply to volumes created within the Standard,
Premium, and Extreme service levels:
The volume capacity defines the common throughput limit, independent of the
storage pool capacity.
Adding volume capacity increases the maximum throughput limit of the volume.
Workload characteristics
When you use NetApp Volumes, your application sends input/output
(I/O) operation requests to volumes that define your workload and are
characterized by the following parameters:
Client VM read cache size: you can't adjust a workload's read and write
ratio, but you can add more buffer cache in your virtual machines (VMs),
which can help reduce the number of necessary read operations.
Block size: Fewer, larger I/O operations are much more efficient than many
smaller ones. Strive to use large block sizes of 64 KiB or more. Consult your
application manual to determine if you can change block size.
I/O concurrency: you can increase I/O concurrency to process more I/O
operations in parallel without increasing the overall runtime.
Metadata operations
Metadata operations are small, protocol-specific operations. Metadata operation
performance is primarily limited by latency. Examples of metadata operations
include the following:
List contents of a folder
Delete a file
Set permissions
Latency
Latency is the total amount of time it takes for an I/O operation to complete.
This includes the wait time in queue and the service time where the I/O is acted
upon. To improve your latency, we recommend that you test the connection to
NetApp Volumes from all the zones in your region and select the
zone with the lowest latency.
Latency considerations
When a client's network bandwidth is smaller than required, the client
latency reported by perfmon in Windows or nfsiostat in Linux is higher than
the latency reported by NetApp Volumes because the I/O
operation spends time queueing on the client.
Storage latency becomes high when a volume's throughput ceiling is lower
than required for a given workload. This also causes the client latency to be
higher because of the additional client-side queuing.
When the capacity-defined throughput ceiling is reached, you can improve the
client and storage latencies by increasing the throughput limit.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Performance considerations\n\nThis page provides details on parameters that directly affect volume performance.\n\nVolume considerations\n---------------------\n\nWhen you assign capacity to your volumes, consider the following:\n\n- Your choice of access protocol (Server Message Block (SMB) or Network File\n System (NFS)) might impact throughput.\n\n- Your choice of service level affects the throughput limit.\n\n### Volume considerations for the Flex service level\n\nThe following considerations apply to volumes created within the Flex\nservice level:\n\n- The pool provides a common aggregate throughput limit for all volumes in the\n pool. Volumes share the pool's throughput.\n\n- Adding pool capacity increases the maximum throughput limit for volumes in\n the pool.\n\n- Adding additional capacity to a volume doesn't increase the maximum volume\n throughput limit.\n\n### Volume considerations for the Standard, Premium, and Extreme service levels\n\nThe following considerations apply to volumes created within the Standard,\nPremium, and Extreme service levels:\n\n- The volume capacity defines the common throughput limit, independent of the\n storage pool capacity.\n\n- Adding volume capacity increases the maximum throughput limit of the volume.\n\nWorkload characteristics\n------------------------\n\nWhen you use NetApp Volumes, your application sends input/output\n(I/O) operation requests to volumes that define your workload and are\ncharacterized by the following parameters:\n\n- **Client VM read cache size**: you can't adjust a workload's read and write\n ratio, but you can add more buffer cache in your virtual machines (VMs),\n which can help reduce the number of necessary read operations.\n\n- **Block size**: Fewer, larger I/O operations are much more efficient than many\n smaller ones. Strive to use large block sizes of 64 KiB or more. Consult your\n application manual to determine if you can change block size.\n\n- **I/O concurrency**: you can increase I/O concurrency to process more I/O\n operations in parallel without increasing the overall runtime.\n\nMetadata operations\n-------------------\n\nMetadata operations are small, protocol-specific operations. Metadata operation\nperformance is primarily limited by latency. Examples of metadata operations\ninclude the following:\n\n- List contents of a folder\n\n- Delete a file\n\n- Set permissions\n\nLatency\n-------\n\nLatency is the total amount of time it takes for an I/O operation to complete.\nThis includes the wait time in queue and the service time where the I/O is acted\nupon. To improve your latency, we recommend that you test the connection to\nNetApp Volumes from all the zones in your region and select the\nzone with the lowest latency.\n\n### Latency considerations\n\n- When a client's network bandwidth is smaller than required, the client\n latency reported by perfmon in Windows or `nfsiostat` in Linux is higher than\n the latency reported by NetApp Volumes because the I/O\n operation spends time queueing on the client.\n\n- Storage latency becomes high when a volume's throughput ceiling is lower\n than required for a given workload. This also causes the client latency to be\n higher because of the additional client-side queuing.\n\n- When the capacity-defined throughput ceiling is reached, you can improve the\n client and storage latencies by increasing the throughput limit.\n\nWhat's next\n-----------\n\n[Expected performance](/netapp/volumes/docs/performance/expected-performance)."]]
