load balancing netapp storagegrid · 6. load balancing netapp storagegrid a netapp storagegrid...

Load Balancing NetApp StorageGRIDDeployment Guide

v1.0.0

Contents1. About this Guide................................................................................................................................................................................................................................................................ 42. Loadbalancer.org Appliances Supported................................................................................................................................................................................................... 43. Loadbalancer.org Software Versions Supported................................................................................................................................................................................. 44. StorageGRID Software Versions Supported.......................................................................................................................................................................................... 45. NetApp StorageGRID.................................................................................................................................................................................................................................................. 4

StorageGRID Node Types...................................................................................................................................................................................................................................................5

6. Load Balancing NetApp StorageGRID......................................................................................................................................................................................................... 5Load Balancer Configuration............................................................................................................................................................................................................................................6

Operating Mode..................................................................................................................................................................................................................................................... 6Alternative Operating Mode........................................................................................................................................................................................................................ 6Timeouts....................................................................................................................................................................................................................................................................... 6Port Requirements............................................................................................................................................................................................................................................... 6SSL/TLS Termination......................................................................................................................................................................................................................................... 6Port Redirection...................................................................................................................................................................................................................................................... 6Health Checks.......................................................................................................................................................................................................................................................... 6Multisite (GSLB)..................................................................................................................................................................................................................................................... 7Virtual Service (VIP) Requirements...................................................................................................................................................................................................... 7Deployment Concept (Within a Single Site)................................................................................................................................................................................. 7VM Deployments................................................................................................................................................................................................................................................... 7

7. Loadbalancer.org Appliance – the Basics................................................................................................................................................................................................... 8Virtual Appliance Download & Deployment.......................................................................................................................................................................................................8Initial Network Configuration............................................................................................................................................................................................................................................8Accessing the Web User Interface (WebUI)......................................................................................................................................................................................................8HA Clustered Pair Configuration...................................................................................................................................................................................................................................9

8. Appliance Configuration for NetApp StorageGRID........................................................................................................................................................................ 10Enabling Multithreaded Load Balancing..............................................................................................................................................................................................................10Configuring VIP1 – S3 Client Requests (HTTPS)........................................................................................................................................................................................10

Configuring the Virtual Service (VIP)................................................................................................................................................................................................ 10Defining the Real Servers (RIPs)............................................................................................................................................................................................................ 11

Configuring VIP2 – S3 Client Requests (HTTP)..........................................................................................................................................................................................12

Configuring the Virtual Service (VIP)................................................................................................................................................................................................ 12Defining the Real Servers (RIPs)........................................................................................................................................................................................................... 12

f) Finalizing the Configuration........................................................................................................................................................................................................................................13

9. Testing & Verification................................................................................................................................................................................................................................................. 13Using System Overview......................................................................................................................................................................................................................................................13

10. Technical Support....................................................................................................................................................................................................................................................... 1411. Further Documentation........................................................................................................................................................................................................................................... 1412. Conclusion......................................................................................................................................................................................................................................................................... 1413. Appendix.............................................................................................................................................................................................................................................................................. 15

1 – Using GSLB for Multi-site Deployments....................................................................................................................................................................................................15

Conceptual Overview...................................................................................................................................................................................................................................... 15Appliance Configuration............................................................................................................................................................................................................................... 16DNS Server Configuration.......................................................................................................................................................................................................................... 17

2

© Copyright Loadbalancer.org • www.loadbalancer.org • [email protected]

2 – Alternative Load Balancing Method for Read-Intensive Deployments (Direct Server Routing)...........................................................183 – Clustered Pair Configuration – Adding a Slave Unit.......................................................................................................................................................................19

14. Document Revision History................................................................................................................................................................................................................................ 21

3


1. About this GuideThis guide details the steps required to configure a load balanced NetApp StorageGRID environment utilizing Loadbalancer.org appliances. It covers the configuration of the load balancers and also any NetApp StorageGRID node configuration changes that are required to enable load balancing.

For more information about initial appliance deployment, network configuration and using the Web User Interface (WebUI), please also refer to the Administration Manual.

2. Loadbalancer.org Appliances SupportedAll our products can be used for load balancing StorageGRID. The complete list of models is shown below:

Discontinued Models Current Models *

Enterprise R16 Enterprise R20

Enterprise VA R16 Enterprise MAX

Enterprise VA Enterprise 10G

Enterprise R320 Enterprise 40G

Enterprise Ultra

Enterprise VA R20

Enterprise VA MAX

Enterprise AWS **

Enterprise AZURE **

* For full specifications of these models please refer to: http://www.loadbalancer.org/products/hardware

** Some features may not be supported, please check with Loadbalancer.org support

3. Loadbalancer.org Software Versions Supported

• V8.3.4 and later

4. StorageGRID Software Versions Supported

• NetApp StorageGRID – all versions

5. NetApp StorageGRIDNetApp StorageGRID is a software-defined, object-based storage solution that supports industry-standard object APIs such as Amazon S3 and Swift. It allows you to build a single name space across up to 16 data centers worldwide, with multiple service levels for metadata-driven object life-cycle policies.

StorageGRID provides two methods for protecting object data from loss: Replication and Erasure Coding. Integrated Life-cycle Management (ILM) policies are configured to govern how these methods are use to ensure data durability

4


http://www.loadbalancer.org/products/hardware

http://pdfs.loadbalancer.org/loadbalanceradministrationv8.pdf

and availability.

StorageGRID can be deployed as optimized hardware appliances, virtual machines, Docker containers or a combinationof all three.

StorageGRID Node Types

• Admin Node – Admin Nodes provide system administration services such as system configuration, monitoring, and logging. Each StorageGRID system includes one primary Admin Node. The primary Admin Node hosts the Configuration Management Node (CMN) service which manages system-wide configurations and grid task. Forredundancy, a StorageGRID system can have additional, non-primary Admin Nodes.

• Storage Node – Storage Nodes manage the storage of objects to disk. This object management (both object data and object metadata) includes the evaluation of objects against ILM rules to determine how an object’s data is stored over time and protected from loss.

• API Gateway Node (Optional) – API Gateway Nodes provide a load balancing interface to the StorageGRID system through which applications can connect. The Gateway Nodes host the Connection Load Balancer (CLB)service which acts as a switchboard for connecting clients to the most efficient Local Distribution Router (LDR)service.

Note: As mentioned here, although the API Gateway Node is low cost and requires no configuration, it’s not as robust or as flexible as deploying a dedicated 3rd party load balancer appliance.

• Archive Node (Optional) – Archive Nodes provide an interface that the grid's active Information Life-cycle Management (ILM) policy can use to send object data to an external archival storage system (tape or the cloud) for long-term storage. Archiving to tape is achieved by connecting to Tivoli Storage Manager (TSM) middleware, while archiving to the cloud is achieved by connecting to a system that is capable of interfacing through the S3 API.

6. Load Balancing NetApp StorageGRIDA NetApp StorageGRID deployment consists of multiple storage nodes and is often deployed across multiple sites. The storage nodes provide a service endpoint for applications, and they manage storage, replication, erasure-coding, and metadata.

Within a particular site, a load balancer is deployed to direct clients to a healthy storage node. Clients connect to a Virtual Service (VIP) on the load balancer rather than connecting directly to one of the nodes. Clients are distributed across the healthy nodes based on the load balancing method selected. The default distribution method is least connection and is used for the configuration presented in this guide.

For multiple sites, the load balancer’s built-in GSLB (Global Server Load Balancing) functionality can be used to direct clients to the best site based on location and site health – please refer to page 15 for more details.

5


https://www.netapp.com/us/media/tr-4626.pdf#page=4

Load Balancer Configuration

Operating ModeThe load balancer is deployed using Layer 7 SNAT mode. This mode offers high performance and requires no configuration changes to the load balanced NetApp StorageGRID Nodes.

Alternative Operating ModeFor deployments that are read-intensive, it’s possible to use an alternative load balancing method known as Direct Server Return. This allows reply traffic to flow directly from the StorageGRID nodes to the clients, thus removing the load balancer as a potential bottleneck for reply traffic. Direct Server Return can benefit read-intensive deployments with a large reply traffic to request traffic ratio. A more detailed explanation of this alternative load balancing method canbe found in section 2 of the appendix on page 18.

TimeoutsFor NetApp StorageGRID, the load balancer’s client and server timeouts are set to 10 minutes.

Port RequirementsThe following table shows the port(s) that are load balanced:

Port Protocols Use

18082 TCP/HTTPS S3 API (HTTPS)

18084 TCP/HTTP S3 API (HTTP)

Note: If you are using the Swift API rather than the S3 API, then ports 18083 and 18085 should be used instead of 18082 & 18084.

SSL/TLS TerminationSSL termination on the load balancer can be very CPU intensive. In most cases, for a scalable solution, terminating SSL on the Real Servers is the best option. The configuration presented in this guide assumes SSL is terminated on the StorageGRID nodes.

Port RedirectionTo allow clients to connect on standard HTTP & HTTPS ports (80 & 443) port redirection is used on the load balancer to remap port 443 18082 and port 80 18084.→ →

Health ChecksNetApp recommends that the HTTP OPTIONS method is used to perform the health check. The load balancer issues HTTP OPTIONS requests to each individual storage node and expects a 200 OK response.

6


Multisite (GSLB)For multi-site StorageGRID deployments, it’s possible to use the load balancer’s GSLB functionality to provide high availability and location affinity across multiple sites. Using GSLB enables local clients to be automatically directed to a functioning StorageGRID cluster at another site should their local cluster become unavailable. A detailed explanation ofthis feature can be found in section 2 of the appendix on page 15.

Virtual Service (VIP) RequirementsTo load balance NetApp StorageGRID Storage Nodes, 2 VIPs are required:

• VIP1: S3-HTTPS – for S3 HTTPS API communication

• VIP2: S3-HTTP – for S3 HTTP API communication

Deployment Concept (Within A Single Site)

Note: Please refer to page 15 for details of using GSLB for multi-site deployments.

Note: The load balancer can be deployed as a single unit, although Loadbalancer.org recommends a clustered pair for resilience & high availability. Please refer to section 2 in the appendix on page 19 for more details on configuring a clustered pair.

VM DeploymentsThe Loadbalancer.org appliance can be deployed as a virtual appliance. To achieve the best level of performance and throughput when load balancing NetApp StorageGRID, the Loadbalancer.org virtual appliance should be configured to

7


allow multi-threading which in turn enables the layer 7 engine (HAProxy) to use multi-threading. For example, to achievea 10GB throughput, HAProxy typically requires 3 threads. To support this, the VA must allow a minimum of 4 threads (n+1). This can be achieved by configuring the VA with one vCPU and 4 cores (by default the VA is allocated 1vCPU and a single core). Please refer to page 10 for more details on configuring hyper-threading at layer 7.

7. Loadbalancer.org Appliance – the Basics

Virtual Appliance Download & DeploymentA fully featured, fully supported 30 day trial is available if you are conducting a PoC (Proof of Concept) deployment. The VA is currently available for VMware, Virtual Box, Hyper-V, KVM and XEN and has been optimized for each Hypervisor. Bydefault, the VA is allocated 1 CPU, 2GB of RAM and has an 8GB virtual disk. The Virtual Appliance can be downloaded here.

Note: The same download is used for the licensed product, the only difference is that a license key file(supplied by our sales team when the product is purchased) must be applied using the appliance's WebUI.

Note: Please refer to the Administration Manual and the ReadMe.txt text file included in the VA download for more detailed information on deploying the VA using various Hypervisors.

Initial Network ConfigurationThe IP address, subnet mask, default gateway and DNS settings can be configured in several ways as detailed below:

Method 1 – Using the Network Setup Wizard at the console

After boot up, follow the instructions on the console to configure the IP address, subnet mask, default gateway and DNSsettings.

Method 2 – Using the WebUI

Using a browser, connect to the WebUI on the default IP address/port: https://192.168.2.21:9443

To set the IP address & subnet mask, use: Local Configuration > Network Interface Configuration

To set the default gateway, use: Local Configuration > Routing

To configure DNS settings, use: Local Configuration > Hostname & DNS

Accessing the Web User Interface (WebUI)The WebUI can be accessed via HTTPS at the following URL: https://192.168.2.21:9443/lbadmin

* Note the port number → 9443

(replace 192.168.2.21 with the IP address of your load balancer if it's been changed from the default)

8


http://pdfs.loadbalancer.org/v8/loadbalanceradministrationv8.pdf

http://www.loadbalancer.org/resources/free-trial

Login using the following credentials:

Username: loadbalancer

Password: loadbalancer

Note: To change the password , use the WebUI menu option: Maintenance > Passwords.

Once logged in, the WebUI will be displayed as shown below:

HA Clustered Pair ConfigurationLoadbalancer.org recommend that load balancer appliances are deployed in pairs for high availability. In this guide a single unit is deployed first, adding a secondary slave unit is covered in section 2 of the appendix on page 19.

9


8. Appliance Configuration for NetApp StorageGRID

Enabling Multithreaded Load BalancingAs mentioned on page 7 Loadbalancer.org recommend that the appliance should be configured to use multiple vCPU cores. This is required to achieve the high level of performance and throughput typically required when load balancing a NetApp StorageGRID deployment.

To enable multithreaded mode from the WebUI:

1. Navigate to Cluster Configuration > Layer 7 – Advanced Configuration

2. Check the Enable Multithreading checkbox

3. Set Number of Threads to a value appropriate for your environment. For 10GB throughput we typically recommend setting this to 3. As mentioned on page 7 the appliance should be allocated with at least 4 CPU cores to support this setting

4. Click Update to apply the changes

Configuring VIP1 – S3 Client Requests (HTTPS)

Configuring The Virtual Service (VIP)

1. Using the web user interface, navigate to Cluster Configuration > Layer 7 – Virtual Services and click on Add a new Virtual Service

2. Enter the following details:

10


3. Enter an appropriate name for the VIP in the Label field, e.g. StorageGRID-S3-HTTPS

4. Set the Virtual Service IP address field to the required IP address, e.g. 10.0.0.10

5. Set the Virtual Service Ports field to 443

6. Set the Layer 7 Protocol to TCP Mode

7. Click Update

8. Now click Modify next to the newly created VIP

9. Scroll down to the Persistence section and set Persistence Mode to None

10. Scroll down to the Health Checks section and set the Health Check to Negotiate HTTPS (OPTIONS)

11. Leave Response Expected blank – this will cause the load balancer to look for a 200 OK response from each Storage Node

12. Scroll down to the Other section and click [Advanced]

13. Enable (check) the Timeout checkbox and set both Client Timeout & Real Server Timeout to 10m (i.e. 10 minutes)

14. Click Update

Defining The Real Servers (RIPs)

1. Using the web user interface, navigate to Cluster Configuration > Layer 7 – Real Servers and click on Add a newReal Server next to the newly created StorageGRID-S3-HTTPS VIP

2. Enter an appropriate name for the server in the Label field, e.g. StorageNode1

3. Change the Real Server IP Address field to the required IP address, e.g. 10.0.0.11

4. Set the Real Server Port field to 18082

5. Click Update

6. Now repeat these steps to add the other Storage Node(s)

11


Configuring VIP2 – S3 Client Requests (HTTP)

Configuring The Virtual Service (VIP)

1. Using the web user interface, navigate to Cluster Configuration > Layer 7 – Virtual Services and click on Add a new Virtual Service

2. Enter the following details:

3. Enter an appropriate name for the VIP in the Label field, e.g. StorageGRID-S3-HTTP

4. Set the Virtual Service IP address field to the required IP address, e.g. 10.0.0.10

5. Set the Virtual Service Ports field to 80

6. Set the Layer 7 Protocol to TCP Mode

7. Click Update

8. Now click Modify next to the newly created VIP

9. Scroll down to the Persistence section and set Persistence Mode to None

10. Scroll down to the Health Checks section and set the Health Check to Negotiate HTTP (OPTIONS)

11. Leave Response Expected blank – this will cause the load balancer to look for a 200 OK response from each Storage Node

12. Scroll down to the Other section and click [Advanced]

13. Enable (check) the Timeout checkbox and set both Client Timeout & Real Server Timeout to 10m (i.e. 10 minutes)

14. Click Update

Defining The Real Servers (RIPs)

1. Using the web user interface, navigate to Cluster Configuration > Layer 7 – Real Servers and click on Add a newReal Server next to the newly created StorageGRID-S3-HTTP VIP

12


2. Enter an appropriate name for the server in the Label field, e.g. StorageNode1

3. Change the Real Server IP Address field to the required IP address, e.g. 10.0.0.11

4. Set the Real Server Port field to 18084

5. Click Update

6. Now repeat these steps to add the other Storage Node(s)

f) Finalizing the ConfigurationTo apply the new settings, reload HAProxy using the button in the blue box at the top of the screen.

9. Testing & VerificationOnce the load balancer and storage nodes are configured, ensure that you can successfully connect to the StorageGRID deployment. Connect to the VIP address on the load balancer rather than directly to one of the StorageGRID nodes.

Using System OverviewThe System Overview can be viewed using the WebUI. It shows a graphical view of all VIPs & RIPs (i.e. the StorageGRID nodes) and shows the state/health of each node as well as the state of the cluster as a whole. The example below shows that all NetApp StorageGRID nodes are healthy and available to accept connections.

13


10. Technical SupportFor more details about configuring the appliance and assistance with designing your deployment please don't hesitate to contact the support team using the following email address: [email protected]

11. Further DocumentationThe Administration Manual contains much more information about configuring and deploying the appliance. It's available here:http://pdfs.loadbalancer.org/loadbalanceradministrationv8.pdf.

12. ConclusionLoadbalancer.org appliances provide a very cost effective solution for highly available load balanced NetApp StorageGRID environments.

14


http://pdfs.loadbalancer.org/loadbalanceradministrationv8.pdf

mailto:[email protected]

13. Appendix

1 – Using GSLB for Multi-site Deployments

Conceptual OverviewFor multi-site StorageGRID deployments, it’s possible to use the load balancer’s GSLB functionality to provide high availability and location affinity across multiple sites.

• Clients across multiple sites use the same domain name to access StorageGRID services

• Under normal operation, clients are directed to their site’s local StorageGRID cluster

• In the event that a site’s StorageGRID service and/or load balancers are offline then local clients are automatically directed to a functioning StorageGRID cluster at another site

For the sake of simplicity, the diagram presented below shows a two site setup. The principle can be extended to encompass up to 16 sites.

15


Explanation:

1. A client tries to access the S3 service by using the service’s domain, in this example netapp-s3.domain.com

2. The client sends a DNS lookup request for netapp-s3.domain.com to its local DNS server

3. The local site’s DNS server has the domain netapp-s3.domain.com delegated to the load balancers

4. The DNS server sends a delegated DNS lookup request for netapp-s3.domain.com to one of the load balancers

5. The load balancer that received the delegated DNS lookup request replies to the DNS server by serving up the appropriate, local VIP address. For example, if the request originated from the 10.0.0.0/24 subnet then the VIP inthat subnet is served up. Likewise, if the request originated from the 172.16.0.0/24 subnet then the VIP in that subnet is served up. As such, clients are always directed to their local, on-site StroageGRID instance, provided that the on-site instance is online and available

6. The DNS server sends the delegated reply to the client

7. The client connects to the S3 service at netapp-s3.domain.com by using the local VIP address

Note: In the event that the NetApp StorageGRID cluster and/or load balancers at one site should completely fail then local clients will be directed to the StorageGRID cluster at the other site and the service will continue to be available. This style of multi-site failover is possible because the load balancers’ GSLB functionality continuously health checks the service at each site. When the service at a site is observed to be unavailable then that site’s IP address is no longer served when responding to DNS queries.

Appliance ConfigurationThe GSLB service must be configured on the master load balancer appliance at each site. The GSLB configuration must be identical across all sites. The GSLB configuration depends on 2 configuration files:

• Polaris – this is the main configuration file for the Polaris service which handles GSLB

• Topology – this defines the network topology, mapping network subnets to sites

Both files are configured via the appliance’s WebUI.

Sample Polaris Configuration:

globalnames: netapp-s3.domain.com: pool: s3-nodes ttl: 5

pools: s3-nodes: monitor: TCP monitor_params:

16


port: 18084 timeout: 2 retries: 2 lb_method: twrr fallback: any members: - ip: 10.0.0.10 name: netapp-s3-dc1 weight: 1 - ip: 172.16.0.10 name: netapp-s3-dc2 weight: 1

Sample Topology Configuration:

datacenter1:- 10.0.0.0/24

datacenter2:- 172.16.0.0/24

Note: the GSLB configuration is not auto-replicated to the slave. Make sure that you also configure the slave appliance with the required GSLB configuration.

Note: If you want to configure a multi-site StorageGRID deployment using GSLB and require further assistance, please don’t hesitate to contact [email protected].

DNS Server ConfigurationOnce the GSLB service has been configured on the master & slave load balancer at every site, ensuring that the configuration is identical across all sites, the DNS server at each site must then be configured for GSLB. The DNS server at each site must be configured to delegate DNS requests for the subdomain in question to the load balancers; the load balancers’ GSLB services will serve the appropriate IP addresses to the DNS servers. Using the example presented throughout this appendix, the DNS server at each site would be configured with a delegation for the domain netapp-s3.domain.com. The domain would be delegated to every load balancer across every site, which provides multi-site redundancy.

The exact steps for creating a DNS delegation vary between different DNS servers and are outside the scope of this document. For further information, a blog post that walks through creating a DNS delegation on a Microsoft DNS serverin the context of setting up GSLB on our appliance can be found here (see the section titled “Delegating your subdomain to your GSLB's using Microsoft's DNS Server”.)

17


https://www.loadbalancer.org/blog/loadbalancer-org-releases-a-gslb/

mailto:[email protected]

2 – Alternative Load Balancing Method for Read-Intensive Deployments (Direct Server Routing)Direct Server Return or DSR, is a method of load balancing. With DSR, reply traffic flows directly from the back end servers to the clients. In this way, the load balancer is completely bypassed on the return journey for a given connection, thus removing the load balancer as a potential bottleneck for traffic on the return path.

This alternative method of load balancing can benefit read-intensive deployments which feature a large reply traffic to request traffic ratio. For example, consider the scenario where a typical client request is 10 kB in size while a typical replyis 10 GB in size (perhaps file retrieval or video streaming). Direct routing benefits such scenarios: the much larger volume of reply traffic bypasses the load balancer and is not limited by the load balancer’s network throughput. The reply traffic is instead limited by the total available network bandwidth between the servers and the clients, which is limited only by the underlying infrastructure.

Caveats

There are caveats for using the DSR load balancing method which should be considered:

• The load balancers must be on the same network segment / switching fabric as the StorageGRID nodes (due to the fact that this load balancing method works by rewriting MAC addresses, i.e. operates at layer 2 of the OSImodel)

• Each StorageGRID node must own the VIP address so that they can all accept and reply to the load balanced traffic. This address should be assigned to a loopback network adaptor

18


• Each StorageGRID node must be configured to not reply to ARP requests for the VIP address or advertise that they own the address

For guidance on configuring the StorageGRID nodes for direct routing, in the context of the caveats described above, please consult with NetApp Support.

3 – Clustered Pair Configuration – Adding a Slave UnitIf you initially configured just the master unit and now need to add a slave – our recommended procedure, please follow the steps below.

Note: A number of settings are not replicated as part of the master/slave pairing process and therefore must be manually configured on the slave appliance. These are listed below:

• Hostname & DNS settings

• Network settings including IP addresses, bonding configuration and VLANs

• Routing configuration including default gateways and static routes

• Date & time settings

• Physical – Advanced Configuration settings including Internet Proxy IP address & port, Firewall table size, SMTP relay and Syslog server• SNMP settings

• Graphing settings

• Firewall Script & Firewall Lockdown Script settings

• Software updates

To add a slave node – i.e. create a highly available clustered pair:

• Deploy a second appliance that will be the slave and configure initial network settings

• Using the WebUI, navigate to: Cluster Configuration > High-Availability Configuration

19


• Specify the IP address and the loadbalancer users password (the default is 'loadbalancer') for the slave (peer) appliance as shown above

• Click Add new node

• The pairing process now commences as shown below:

• Once complete, the following will be displayed:

• To finalize the configuration, restart heartbeat and any other services as prompted in the blue message box at the top of the screen

Note: Clicking the Restart Heartbeat button on the master appliance will also automatically restart heartbeat on the slave appliance.

Note: Please refer to chapter 9 – Appliance Clustering for HA in the Administration Manual for more detailed information on configuring HA with 2 appliances.

20


http://pdfs.loadbalancer.org/v8/loadbalanceradministrationv8.pdf

14. Document Revision History

Version Date Change Reason for Change Changed By

1.0.0 5th November 2019 First draft RJC

21


About Loadbalancer.orgLoadbalancer.org’s mission is to ensure that its clients’ businesses are never interrupted. The load balancer experts ask the right questions to get to the heart of what matters, bringing a depth of understanding to each deployment. Experience enables Loadbalancer.org engineers to design less complex, unbreakable solutions – and to provide exceptional personalized support.

United Kingdom

Loadbalancer.org Ltd.Compass House, North HarbourBusiness Park, Portsmouth, PO6 4PSUK:+44 (0) 330 380 [email protected]@loadbalancer.org

Canada

Loadbalancer.org Appliances Ltd.300-422 Richards Street, Vancouver,BCV6B 2Z4, CanadaTEL:+1 [email protected]@loadbalancer.org

United States

Loadbalancer.org, Inc.4550 Linden Hill Road, Suite 201Wilmington, DE 19808, USATEL: +1 [email protected]@loadbalancer.org

Germany

Loadbalancer.org GmbHTengstraße 2780798,München, GermanyTEL: +49 (0)89 2000 [email protected]@loadbalancer.org

22


load balancing netapp storagegrid · 6. load balancing netapp storagegrid a netapp storagegrid...

Documents