Configuring Optimization Features : Improving Performance
  
Improving Performance
You enable settings to improve network and RiOS data store performance in the Optimization > Data Replication: Performance page. This section describes the default settings and the cases in which you might consider changing the default values.
Selecting a RiOS Data Store Segment Replacement Policy
The RiOS data store segment replacement policy selects the technique used to replace the data in the RiOS data store. While the default setting works best for most SteelHeads, occasionally we recommend changing the policy to improve performance.
Note: We recommend that the segment replacement policy matches on both the client-side and server-side SteelHeads.
To select a RiOS data store segment replacement policy
1. Choose Optimization > Data Replication: Performance to display the Performance page.
2. Under Data Store, select one of these replacement algorithms from the drop-down list.
Control
Description
Segment Replacement Policy
•  Riverbed LRU - Replaces the least recently used data in the RiOS data store, which improves hit rates when the data in the RiOS data store aren’t equally used. This is the default setting.
•  FIFO - Replaces data in the order received (first in, first out).
3. Click Apply to apply your settings.
4. Click Save to Disk to save your settings permanently.
5. Restart the optimization service. For details, see Starting and Stopping the Optimization Service.
Optimizing the RiOS Data Store for High-Throughput Environments
You optimize the RiOS data store for high-throughput Data Replication (DR) or data center workloads in the Optimization > Data Replication: Performance page.
You might benefit from changing the performance settings if your environment uses a high-bandwidth WAN. DR and Storage Area Network (SAN) replication workloads at these high throughputs might benefit from the settings that enhance RiOS data store performance while still receiving data reduction benefits from SDR.
To maintain consistent levels of performance, we recommend using separate SteelHeads for DR workloads than for optimization of other application traffic.
Setting an Adaptive Streamlining Mode
The adaptive data streamlining mode monitors and controls the different resources available on the SteelHead and adapts the utilization of these system resources to optimize LAN throughput. Changing the default setting is optional; we recommend you select another setting only with guidance from Riverbed Support or the Riverbed Sales Team.
Generally, the default setting provides the most data reduction. When choosing an adaptive streamlining mode for your network, contact Riverbed Support to help you evaluate the setting based on:
•  the amount of data replication your SteelHead is processing.
•  the type of data being processed and its effects on disk throughput on the SteelHeads.
•  your primary goal for the project, which could be maximum data reduction or maximum throughput. Even when your primary goal is maximum throughput you can still achieve high data reduction.
To select an adaptive data streamlining mode
1. Choose Optimization > Data Replication: Performance to display the Performance page.
2. Under Adaptive Data Streamlining Modes, select one of these settings.
Setting
Description
Default
This setting is enabled by default and works for most implementations. The default setting:
•  Provides the most data reduction.
•  Reduces random disk seeks and improves disk throughput by discarding very small data margin segments that are no longer necessary. This margin segment elimination (MSE) process provides network-based disk defragmentation.
•  Writes large page clusters.
•  Monitors the disk write I/O response time to provide more throughput.
SDR-Adaptive
Legacy - Includes the default settings and also:
•  Balances writes and reads.
•  Monitors both read and write disk I/O response, and CPU load. Based on statistical trends, can employ a blend of disk-based and non-disk-based data reduction techniques to enable sustained throughput during periods of disk/CPU-intensive workloads.
Use caution with the SDR-Adaptive Legacy setting, particularly when you are optimizing CIFS or NFS with prepopulation. Contact Riverbed Support for more information.
Advanced - Maximizes LAN-side throughput dynamically under different data workloads. This switching mechanism is governed with a throughput and bandwidth reduction goal using the available WAN bandwidth. Both SteelHeads must be running RiOS 6.0.x or later.
SDR-M
Performs data reduction entirely in memory, which prevents the SteelHead from reading and writing to and from the disk. Enabling this option can yield high LAN-side throughput because it eliminates all disk latency. This is typically the preferred configuration mode for SAN replication environments.
SDR-M is most efficient when used between two identical high-end SteelHead models: for example, 7055 - 7055. When used between two different SteelHead models, the smaller model limits the performance.
After enabling SDR-M on both the client-side and the server-side SteelHeads, restart both SteelHeads to avoid performance degradation.
Note: You can’t use peer RiOS data store synchronization with SDR-M.
3. Click Apply to apply your settings.
4. Click Save to Disk to save your settings permanently.
5. If you have selected a new adaptive data streamlining mode, you must restart the optimization service on the client-side and server-side SteelHeads. For details, see Starting and Stopping the Optimization Service.
Note: If you select SDR-M as the adaptive data streamlining mode, the Clear the Data Store option isn’t available when you restart the optimization service because the SDR-M mode has no effect on the RiOS data store disk.
Note: After changing the RiOS data store adaptive streamlining setting, you can verify whether changes have had the desired effect by reviewing the Optimized Throughput report. From the menu bar, choose Reports > Optimization: Optimized Throughput.
Configuring CPU Settings
Use the CPU settings to balance throughput with the amount of data reduction and balance the connection load. The CPU settings are useful with high-traffic loads to scale back compression, increase throughput, and maximize Long Fat Network (LFN) utilization.
To configure the CPU settings
1. Choose Optimization > Data Replication: Performance to display the Performance page.
2. Under CPU Settings, complete the configuration as described in this table.
Setting
Description
Compression Level
Specifies the relative trade-off of data compression for LAN throughput speed. Generally, a lower number provides faster throughput and slightly less data reduction.
Select a RiOS data store compression value of 1 (minimum compression, uses less CPU) through 9 (maximum compression, uses more CPU) from the drop-down list. The default value corresponds to level 6.
We recommend setting the compression level to 1 in high-throughput environments such as data center-to-data center replication.
Adaptive Compression
Detects LZ data compression performance for a connection dynamically and disables it (sets the compression level to 0) momentarily if it’s not achieving optimal results. Improves end-to-end throughput over the LAN by maximizing the WAN throughput. By default, this setting is disabled.
Multi-Core Balancing
Enables multicore balancing, which ensures better distribution of workload across all CPUs, thereby maximizing throughput by keeping all CPUs busy. Core balancing is useful when handling a small number of high-throughput connections (approximately 25 or less). By default, this setting is disabled and should be enabled only after careful consideration and consulting with Sales Engineering or Riverbed Support.
3. Click Apply to apply your settings.
4. Click Save to Disk to save your settings permanently.
Related Topics
•  Configuring In-Path Rules
•  Synchronizing Peer RiOS Data Stores