The Memcached Management Pack enables customers to use Evident ClearStone Live to monitor Memcached instances. Customers define a logical grouping (aka "cluster") of multiple Memcached instances. ECSL can perform parallel collections from the Memcached instances in the group. As the statistics are collected, ECSL can aggregate various Memcached metrics in the group. Users can utilize the pre-build perspectives in the Real-Time Dashboard to monitor the activity and performance characteristics of the Memcached environment. In addition, administrators can configure monitoring policies to alert operators when there are performance issues with the Memcached instances.
The current management pack produces the following metrics for Memcached environments. The raw stats are collected from each Memcached instance; more statistics are aggregated/derived to produce more meaningful information for the Memcached cluster. To understand what these statistics mean, please see the Memcached Wiki.
| Cluster Stats |
Node Stats |
Slab Stats |
Key Prefix Activity Statistics |
Cluster Name
Connection Stuctures Allocated
Max Memory
Max # of Connections
Evictions Per Sec
Evictions
Items
Items Added Per Sec
Items Added
% Memory Free
Memory Used
Memory Free
% Wasted Memory
Wasted Memory
Current Connections
New Connections Per Sec
New Connections
Reclaimed Items
Bytes In Per Sec
Bytes In
Bytes Out Per Sec
Bytes Out
Get Requests Per Sec
Get Requests
Set Requests Per Sec
Set Requests
Get Hits Per Sec
Gets Hits
Get Misses Per Sec
Get Misses
Delete Hits Per Sec
Delete Hits
Delete Misses Per Sec
Delete Misses
Threads
Threads Requests
Authentication Commands
Authentication Errors
Requests Denied
Incr Hits
Incr Misses
Decr Hits
Decr Misses
CAS Hits
CAS Misses
CAS Bad Value |
Cluster Name
Hostname
Port
Process ID
Uptime
Version
Pointer Size
Connection Stuctures Allocated
Max Memory
Max # of Connections
TCP Port
UDP Port
Growth Factor
Min Chunk Size
SASL Auth Enabled
Evictions
Evictions Per Sec
Items
Items Added Per Sec
Items Added
% Memory Used
Memory Used
% Memory Free
Memory Free
% Memory Wasted
Wasted Memory
Current Connections
New Connections Per Sec
New Connections
Reclaimed Items
Bytes In Per Sec
Bytes In
Bytes Out Per Sec
Bytes Out
Get Requests Per Sec
Get Requests
Set Requests Per Sec
Set Requests
% Get Hits
Get Hits Per Sec
Get Hits
Get Misses Per Sec
Get Misses
Delete Hits Per Sec
Delete Hits
Delete Misses Per Sec
Delete Misses
Threads
Authentication Commands
Authentication Errors
Thread Requests
Requests Denied
Incr Hits
Incr Misses
Decr Hits
Decr Misses
CAS Hits
CAS Misses
CAS BadVals |
Cluster Name
Hostname
Port
Slab Class ID
Total Chunks
Total Pages
Chunk Size
Chunks Per Page
Wasted Memory
Items
Get Requests Per Sec
Get Requests
Set Requests Per Sec
Set Requests
Failed Sets
% of Node's Gets
% of Node's Sets
Storage Used
Age of Oldest Item
Evictions Per Sec
Evictions
Evictions w/ Expiry
Time Since Access of Latest Eviction
Reclaimed Items
Used Chunks
Free Chunks
Free Chunks (End)
Delete Hits
Incr Hits
Decr Hits
CAS Hits
CAS BadVals
RefCount Leaks |
Cluster Name
Key Prefix
Gets
Hits
Sets
Deletes
Misses |
The remainder of this document covers the following topics for the Memcached Management Pack.
- Deployment of the Memcached Management Packs
- Collection Configuration
- Real-Time Dashboard Perspectives
Memcached Management Pack Deployment
A single ECSL instance can support concurrent monitoring of multiple Memcached clusters. If the Memcached clusters are deployed in different data centers, then Evident recommends deploying separate instances of ECSL or at minimal deploy ECSL Collectors at the remote data centers. Given these options for deployment, Evident has provided two Memcached Management Packs to accommodate a local deployment and a remote deployment.
The two management packs for monitoring are bundles as:
- MgmtPack_Memcached.zip - deployed locally on top of an existing ECSL instance that has been configured with the Collector, Pipeline Server, and User Interfaces. This distribution includes all the collection, pipeline plugins, and user interface artifacts for the main ECSL server.
- MgmtPack_Memcached_Standalone.zip - deployed on a standalone remote ECSL Collector-only instance. This package only contains artifacts for collection only.
Management Pack Installation
- Before deploying either version of the Memcached Management Pack, stop the current ECSL system.
- If there is only a single server where ECSL is installed, proceed to extract the contents of the MgmtPack_Memcached.zip on top of the ECSL installation directory. This deploys all the necessary artifacts to support Memcached.
- If the ECSL environment is set up with a remote ECSL Collector, then proceed to extract the contents of the MgmtPack_Memcached_Standalone.zip on top of the ECSL installation directory of the remote ECSL Collector . This deploys all the necessary artifacts to support Memcached.
- After deployment is completed, restart ECSL.
Collection Configuration
Prerequisites
- Memcached 1.4.5 (earlier versions will work, but some stats will be missing)
Configure Memcached Instances for Collection
Multiple Memcached instances that belong to the same application can be grouped together into a single collection group ("cluster") for parallel collection and processing. During this collection configuration process, the administrator decides which Memcached instances to assign to this logical cluster. In addition, the administrator also decides which ECSL Collector would be configured to collect from the cluster.
If the Memcached clusters are geographically distributed, it is recommended to deploy ECSL Collectors at each local site to perform the data collection locally at each site. The following steps requires knowledge of the host or IP address and TCP port # for each of the Memcached instances.
- Follow the previous instructions to deploy the Memcached Management Pack.
- Launch the Admin Console application URL: http://localhost:8080/evidentcsadmin
-
Click on Memcached Collection Configuration option.

- Click on New.
- In Step 1 of the dialog, select the Memcached family.
- Select all of available collection types for the Memcached family.
- Provide a user friendly cluster name of for the cslCluster tag (i.e. CustomerCluster). This will name of the logical cluster that will be applied to the current group.
- In Step 2 of the dialog, click on Add to populate the Memcached instances. This requires the hostname/IP address and the TCP port # for each instance.
- Leave the security tag as is. The data from this specific JVM will use the security tag from this collection group.
- Continue to add other instances for this group.
- In Step 3 of the dialog, specify a name for the Collection Group (i.e. Production)
- To secure the data collected from all these instances in the group, select the desired security tag. Security tags are defined in the User Administration panel.
- Select the collection interval.
- Update the thread pool for collecting data from this group. Recommendation is to change thread pool to match the # instances.
- Save and Commit this configuration.
- After this configuration is saved, restart ECSL.
|
Memcached Perspectives (Real-Time Dashboard)
Users can monitor and visualize the performance data collected from the Memcached instances with the Evident ClearStone Live Real-Time Dashboard. This web-based user interface is an Adobe Flex application that provides a number of customizable interactive visualizations such as charts (line, bar, pie, plot ), tree map, and tables.
The Memcached Management Pack comes with a few pre-configured perspectives. Here are some examples.

Memory throughput

Cluster-wide aggregated key prefix activity

Put throughput for multiple instances

Wasted Memory
Beyond these examples, users can configure additional perspectives to visualize dozens of other metrics. Perspectives can be saved and shared among ECSL users.
|