You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/azure-netapp-files/azure-netapp-files-performance-considerations.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,14 @@
1
1
---
2
-
title: Performance considerations for Azure NetApp Files | Microsoft Docs
2
+
title: General performance considerations for Azure NetApp Files | Microsoft Docs
3
3
description: Learn about performance for Azure NetApp Files, including the relationship of quota and throughput limit and how to dynamically increase/decrease volume quota.
4
4
services: azure-netapp-files
5
5
author: b-hchen
6
6
ms.service: azure-netapp-files
7
7
ms.topic: conceptual
8
-
ms.date: 08/31/2023
8
+
ms.date: 10/17/2024
9
9
ms.author: anfdocs
10
10
---
11
-
# Performance considerations for Azure NetApp Files
11
+
# General performance considerations for Azure NetApp Files
12
12
13
13
> [!IMPORTANT]
14
14
> This article addresses performance considerations for *regular volumes* only.
Copy file name to clipboardExpand all lines: articles/azure-netapp-files/performance-benchmarks-linux.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
---
2
2
title: Azure NetApp Files performance benchmarks for Linux | Microsoft Docs
3
-
description: Describes performance benchmarks Azure NetApp Files delivers for Linux.
3
+
description: Describes performance benchmarks Azure NetApp Files delivers for Linux with a regular volume.
4
4
services: azure-netapp-files
5
5
author: b-hchen
6
6
ms.service: azure-netapp-files
@@ -9,9 +9,9 @@ ms.topic: conceptual
9
9
ms.date: 03/24/2024
10
10
ms.author: anfdocs
11
11
---
12
-
# Azure NetApp Files performance benchmarks for Linux
12
+
# Azure NetApp Files regular volume performance benchmarks for Linux
13
13
14
-
This article describes performance benchmarks Azure NetApp Files delivers for Linux.
14
+
This article describes performance benchmarks Azure NetApp Files delivers for Linux with a [regular volume](azure-netapp-files-understand-storage-hierarchy.md#volumes).
Copy file name to clipboardExpand all lines: articles/azure-netapp-files/performance-virtual-machine-sku.md
+10-10Lines changed: 10 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
---
2
2
title: Azure virtual machine SKUs best practices for Azure NetApp Files | Microsoft Docs
3
-
description: Describes Azure NetApp Files best practices about Azure virtual machine SKUs, including differences within and between SKUs.
3
+
description: Describes Azure NetApp Files best practices about Azure virtual machine stocking keeping units (SKUs), including differences within and between SKUs.
4
4
services: azure-netapp-files
5
5
author: b-hchen
6
6
ms.service: azure-netapp-files
@@ -10,26 +10,26 @@ ms.author: anfdocs
10
10
---
11
11
# Azure virtual machine SKUs best practices for Azure NetApp Files
12
12
13
-
This article describes Azure NetApp Files best practices about Azure virtual machine SKUs, including differences within and between SKUs.
13
+
This article describes Azure NetApp Files best practices about Azure virtual machine stock keeping units (SKUs), including differences within and between SKUs.
14
14
15
15
## SKU selection considerations
16
16
17
17
Storage performance involves more than the speed of the storage itself. The processor speed and architecture have a lot to do with the overall experience from any particular compute node. As part of the selection process for a given SKU, you should consider the following factors:
18
18
19
-
* AMD or Intel: For example, SAS uses a math kernel library designed specifically for Intel processors. In this case, Intel SKUs are preferred over AMD SKU.
20
-
* The F2, E_v3, and D_v3 machine types are each based on more than one chipset. In using Azure Dedicated Hosts, you might select specific models (Broadwell, Cascade Lake, or Skylake when selecting the E type for example). Otherwise, the chipset selection is non-deterministic. If you are deploying an HPC cluster and a consistent experience across the inventory is important, then you can consider single Azure Dedicated Hosts or go with single chipset SKUs such as the E_v4 or D_v4.
19
+
* AMD or Intel: For example, SAS uses a math kernel library designed specifically for Intel processors. In this case, Intel SKUs are preferred over AMD SKU.
20
+
* The F2, E_v3, and D_v3 machine types are each based on more than one chipset. In using Azure Dedicated Hosts, you might select specific models (Broadwell, Cascade Lake, or Skylake when selecting the E type for example). Otherwise, the chipset selection is non-deterministic. If you are deploying an HPC cluster and a consistent experience across the inventory is important, then you can consider single Azure Dedicated Hosts or go with single chipset SKUs such as the E_v4 or D_v4.
21
21
* Performance variability with network-attached storage (NAS) has been observed in testing with both the Intel Broadwell based SKUs and the AMD EPYC™ 7551 based SKUs. Two issues have been observed:
22
-
* When the accelerated network interface is inappropriately mapped to a sub optimal NUMA Node, read performance decreases significantly. Although mapping the accelerated networking interface to a specific NUMA node is beneficial on newer SKUs, it must be considered a requirement on SKUs with these chipsets (Lv2|E_v3|D_v3).
23
-
* Virtual machines running on the Lv2, or either E_v3 or D_v3 running on a Broadwell chipset are more susceptible to resource contention than when running on other SKUs. When testing using multiple virtual machines running within a single Azure Dedicated Host, running network-based storage workload from one virtual machine has been seen to decrease the performance of network-based storage workloads running from a second virtual machine. The decrease is more pronounced when any of the virtual machines on the node have not had their accelerated network interface/NUMA node optimally mapped. Keep in mind that the E_v3 and D_V3 may between them land on Haswell, Broadwell, Cascade Lake, or Skylake.
22
+
* When the accelerated network interface is inappropriately mapped to a sub optimal NUMA Node, read performance decreases significantly. Although mapping the accelerated networking interface to a specific NUMA node is beneficial on newer SKUs, it must be considered a requirement on SKUs with these chipsets (Lv2|E_v3|D_v3).
23
+
* Virtual machines running on the Lv2, or either E_v3 or D_v3 running on a Broadwell chipset are more susceptible to resource contention than when running on other SKUs. When testing using multiple virtual machines running within a single Azure Dedicated Host, running network-based storage workload from one virtual machine has been seen to decrease the performance of network-based storage workloads running from a second virtual machine. The decrease is more pronounced when any of the virtual machines on the node have not had their accelerated network interface/NUMA node optimally mapped. Keep in mind that the E_v3 and D_V3 may between them land on Haswell, Broadwell, Cascade Lake, or Skylake.
24
24
25
-
For the most consistent performance when selecting virtual machines, select from SKUs with a single type of chipset – newer SKUs are preferred over the older models where available. Keep in mind that, aside from using a dedicated host, predicting correctly which type of hardware the E_v3 or D_v3 virtual machines land on is unlikely. When using the E_v3 or D_v3 SKU:
25
+
For the most consistent performance when selecting virtual machines, select from SKUs with a single type of chipset – newer SKUs are preferred over the older models where available. Keep in mind that, aside from using a dedicated host, predicting correctly which type of hardware the E_v3 or D_v3 virtual machines land on is unlikely. When using the E_v3 or D_v3 SKU:
26
26
27
27
* When a virtual machine is turned off, de-allocated, and then turned on again, the virtual machine is likely to change hosts and as such hardware models.
28
28
* When applications are deployed across multiple virtual machines, expect the virtual machines to run on heterogenous hardware.
29
29
30
30
## Differences within and between SKUs
31
31
32
-
The following table highlights the differences within and between SKUs. Note, for example, that the chipset of the underlying E_v3 and D_v3 vary between the Broadwell, Cascade Lake, Skylake, and also in the case of the D_v3.
32
+
The following table highlights the differences within and between SKUs. Note, for example, that the chipset of the underlying E_v3 and D_v3 vary between the Broadwell, Cascade Lake, Skylake, and also in the case of the D_v3.
33
33
34
34
| Family | Version | Description | Frequency (GHz) |
35
35
|-|-|-|-|
@@ -49,7 +49,7 @@ The following table highlights the differences within and between SKUs. Note,
| F | 2 | Gen 2 Intel® Xeon® Platinum 8272CL (Skylake) | 2.1 (3.8) |
51
51
52
-
When preparing a multi-node SAS GRID environment for production, you might notice a repeatable one-hour-and-fifteen-minute variance between analytics runs with no other difference than underlying hardware.
52
+
When preparing a multi-node SAS GRID environment for production, you might notice a repeatable one-hour-and-fifteen-minute variance between analytics runs with no other difference than underlying hardware.
53
53
54
54
| SKU and hardware platform | Job run times |
55
55
|-|-|
@@ -60,7 +60,7 @@ In both sets of tests, an E32-8_v3 SKU was selected, and RHEL 8.3 was used along
60
60
61
61
## Best practices
62
62
63
-
* Whenever possible, select the E_v4, D_v4, or newer rather than the E_v3 or D_v3 SKUs.
63
+
* Whenever possible, select the E_v4, D_v4, or newer rather than the E_v3 or D_v3 SKUs.
64
64
* Whenever possible, select the Ed_v4, Dd_v4, or newer rather than the L2 SKU.
0 commit comments