Buyer’s Guide to Data Centre Monitoring
The Buyer’s Guide to Monitoring the Data Centre outlines the uses of environment monitors as well as the available solutions from an I.T. perspective.
Environment monitors have moved a long way from being simple temperature measurement devices. A sophisticated environment monitor can measure a wide range of environment variables as well as react to conditions as they change.
We recognise that choosing the right solution can be difficult. This guide is intended to help you choose an appropriate solution to your requirements.
Why monitor your data centre environment?
Before environment monitors are introduced in detail it makes sense to understand what motivations you may have for monitoring your environment in the first place. Plainly, your requirements direct the equipment you will need.
Alert on heat emergency
Probably the biggest motivation for monitoring the data centre environment is the anxiety many sys admins feel that a heat emergency will happen. I'm sure you dread entering your data centre after a pleasent weekend at home only to find it in the midst of a severe heat emergency.
Plainly, in order to detect a heat emergency you need to be actively monitoring your data centre. The primary cause of heat emergencies is the operation of the air conditioner. If one or more air conditioners fail then the heat generated by the servers will not be removed from the data centre. Data centres are sealed environments so when cold air is not introduced into the cold aisles and hot air is not expelled from the hot aisles, the servers will be recycling air that is already hot.
The quickest way to detect air conditioner failure is by monitoring the air conditioning system itself. However, if you can't monitor the air conditioning system directly, then monitoring the temperature is a good proxy.
Monitoring air conditioner health
It is arguable that the air conditioner is the single most important piece of equipment in your data centre. Without modern air conditioning systems the data centre would not exist in its current form.
Air conditioning plays a central role in the successful operation of the data centre, consequently, air conditioning systems require careful monitoring. Unfortunately, given the amount of heat generated by modern servers, you won't have very long to react to an air conditioner failure. So the earlier you are able to detect the failure the more time you will have to mitigate the effects.
The fastest way to detect air conditioning system failure is to monitor the unit's operational status dry contact point. The main benefit of using the operational status of the air conditioner is that you are informed immediately of system failure rather than waiting for the temperature to rise above your alert threshold.
Ensure you aren't wasting energy
Whilst a major concern with the data centre environment is the air being too hot, equally you could be wasting money by running the data centre too cold. If you place a bunch of data centre admins in a room each one will have their own idea as to what the ideal temperature should be. ASHRAE, the American Society of Heating, Refrigeration and Air-Conditioning Engineers, in their booklet Thermal Guidelines for Data Processing Environments recommends a temperature between 18-27°C.
If the temperature inside your data centre is lower than the ASHRAE recommendation, ie below 18°C, then you may well be over cooling and consequently consuming more electricity than is necessary. Of course, you can only find out precisely what the temperature is by actively monitoring the environment.
Find hotspots
In (very) small server room environments, without hot/cold aisle configuration, the variability of air temperature is likely to be minimal. In more structured environments the temperature variability is likely to be much higher. In addition, the likelihood of hotspots developing is much higher too. A hotspot is a location where the air being fed into one or more devices is too hot.
One of the reasons to monitor the environment is to detect hotspots within the data centre. Hotspots may be very localised and could only affect a few servers. Consequently they can be hard to locate. One tell tale sign may be one or more servers manifesting component failure. Hard disks are especially prone to heat issues. If you begin to see patterns of component failure that may be indicative of a hotspot. If you find servers are shutting themselves down for no apparent reason you may find that the servers thermal shutdown is being invoked.
Hotspots are most likely to be created during data centre re-organisations when equipment is re-arranged. Consequently, it can be helpful to provide high sensor density monitoring after the move to ensure that no hotspots have been created. When you have established that the move has not adversely affected the environment, move back to a more normal level of sensor density.
ISO 9001 Mandate
Many organisations have implemented the ISO 9001 family of standards in order to improve their product and service delivery. The operation of I.T. systems is of critical importance to product or service delivery in many organisations. It would be sensible to place the operation of the I.T. systems within the scope of the quality system.
ISO 9001 mandates that the performance of processes critical to your ability to implement a high quality product and service delivery should be specified, monitored and verified. Consequently, you need to specify in your policy document what are acceptable environmental conditions for your data centre. In addition, you need to maintain a continuous log of the environmental conditions so you can demonstrate that you have maintained the environment as per your specification in your policy document during a quality system audit.
Unfortunately, things don't stop at providing an auditable log. You also need to verify that the equipment measuring the environment is working as expected. Typically you will need to calibrate your measuring equipment every year to ensure that it is working within the levels of accuracy you have specified in your quality document. Calibration can usually be performed on site in order minimise the downtime of your monitoring system.
Your calibration provider is usually certified by an acreditation body such as UKAS in the United Kingdom and NIST in the U.S.A.
Introduction to Environment Monitors
Environment monitors are available with widely differing capabilities. This section outlines the main features and provides a summary table matching the features to the specific make and model of monitor.
Integrated website
All network enabled environment monitors have an integrated website. The capabilities of the website tend to reflect the underlying features of the environment monitor.
Integrated websites are particularly helpful for managing remote locations. You can place the monitor anywhere on your network and still be able to access it as if it was in the same room.
Environment monitors with integrated websites also mean that you don’t need to install third party applications, you only need a standard web browser.
SNMP
The Simple Network Management Protocol (SNMP) is a standard for managing network enabled devices.
Any environment monitor supporting SNMP can be integrated into a wide range of network management software like HP OpenView, SolarWinds Orion or Nagios.
Log readings
Whilst the primary purpose of most environment monitors is to alert you to unusual environmental conditions, retaining a log of your environmental conditions can be very useful for future planning.
Once the data has been logged you can export the data from the environment monitor using CSV. You can then visualise the data using a tool such as Microsoft Excel or Open Office.
A number of environment monitors can log the environment data as well as graph the information in a highly accessible way. Whilst a data log is very useful, nothing beats a graph for quick and easy comprehension.
Graph
A number of environment monitors can log the environment data as well as graph the information in a highly accessible way. Whilst a data log is very useful, nothing beats a graph for quick and easy comprehension.
Server Shutdown
Whilst a number of environment monitors support sensor controlled relays, able to switch on and off a power supply to a device, few are able to safely shut down servers.
The main drawback of a sensor controlled relay when shutting down a none-abended server is that the server may not be in a state to safely shut down without data loss. By using a safe shutdown the server goes through its normal shutdown procedure that ensures that data is properly written to disk.
A relay can be very useful when a server abend has occurred. An abended server is unlikely to respond to a normal shutdown request.
Models
AVTECH TemPageR
The AVTECH TemPageR is a temperature only device which can be rack or wall-mounted and has an internal temperature probe plus capacity for 2 external probes. It is supplied with DeviceManageR software which enables the user to set upper and lower thresholds, email alerts, graphs and logs, together with management of network cameras. A sophisticated range of optional plug-ins provides further options such as SMS alerting, automatic server shutdown and sophistciated reporting.
AVTECH Room Alert Series
The AVTECH Room Alert series (models 4E, 11E, 24E, 32E/W) provides a full function range of environment monitoring options, for example humidity, flooding, smoke, power, room entry; and on some models (4E, 32E, 32W) additional features such as relay out and signal tower.
The 32E and 32W also include UPS (Uninterruptible Power Supply). The differing model numbers indicate the number of ports available and therefore the number of sensors it is possible to attach and the 32W is a wireless version.
All models are supplied with DeviceManageR software which enables the user to set upper and lower thresholds, email alerts, graphs and logs, together with management of network cameras. A sophisticated range of optional plug-ins provides further options such as SMS alerting, automatic server shutdown and sophistciated reporting.
AKCP sensorProbe2/8
The AKCP sensorProbe range provide high quality, fully featured environment monitors with a vast range of probes.
The sensorProbe2 supports up to two external probes. The sensorProbe8 supports up to eight external probes.
The sensorProbe range are highly functional devices that are able to log and graph environmental readings as well as alarm when things go wrong.
All probes are auto-sensed by the environment monitor and use CAT5 cable so that you can use your existing structured cabling to extend the range of your monitoring.
The sensorProbe8 is also available with either 20 or 60 extra dry contact ports.
AKCP securityProbe8
The AKCP securityProbe is a high quality, fully featured environment monitors with a vast range of probes.
The securityProbe8 supports up to eight external probes.
The securityProbe8 range are highly functional devices that are able to log and graph environmental readings as well as alarm when things go wrong.
The securityProbe8 supports the addition of a dedicated SMS modem for integrated SMS and MMS alerting.
The securityProbe8 also supports up to four additional cameras so can function as a security solution for your data centre.
All probes are auto-sensed by the environment monitor and use CAT5 cable so that you can use your existing structured cabling to extend the range of your monitoring.
The securityProbe8 is also available with either 20 or 60 extra dry contact ports.
Summary
For a simple and easy way to choose an environment monitor that fits your requirements, please go to the Environment Monitor Product Finder.
| Feature / Monitor | AKCP sensorProbe | AKCP securityProbe |
| Integrated website | X | X |
| SNMP | X | X |
| Log readings | X | X |
| Graph | X | X |
[1] The AKCP sensorProbe2 logs probe readings but does not store them in permanent memory. A device restart will lose all logged readings. The sensorProbe8 does log the readings into permanent memory
Probe options
There are two basic types of probe: sensors and actuators. Sensors measure an environmental condition and report the current reading to the monitor. The monitor is then able to decide whether the sensor is in an alarm state.
If an alarm state is entered then one or more actions can be performed by the monitor. The monitor can perform regular alarm functions like send an email and it can instigate an action using an actuator probe.
Actuator probes perform some kind of action in the real world. For instance, a sensor controlled relay can switch on the power to a device, or a dry contact probe can trigger an alarm in a fire alarm system.
Some probes, like dry contact probes, can be both a sensor and an actuator.
It can be confusing to figure out which probes are required when purchasing an environmental monitoring system. A summary is presented at the end of this section to help you decide which environment monitors support the probes you wish to use.
Temperature
Temperature is by far the #1 concern for I.T. people when monitoring their data centre environment.
Why is the temperature so important when computer manufacturers advertise wide operating temperature ranges in their technical specifications?
The temperature range specified for our main Dell server[1] is 10° to 35°C (50° to 95°F). Given the wide operating temperature range, why can’t we run our server at a sizzling 34.9°C?
Data centre temperature is of critical importance to the lifetime and reliability of electrical equipment. High temperatures reduce the lifetime and reliability of electrical equipment. So, we could run our server at 34.9°C but we should expect reduced reliability as a consequence.
Combined temperature & relative humidity
Relative humidity is unlikely to be a major headache in more temperate climes, it is good to keep an eye on it to make sure that your air conditioning system is keeping the air humidity within reasonable bounds.
High humidity can cause a problem because under some conditions the water vapour in the air can condense on the electrical components inside your data centre. Water and electronics don’t mix too well.
Low humidity can cause just as many problems as high humidity. Low humidity can cause static electricity to build up in electrical equipment. Static build up can damage electrical components.
Wetness
Water and I.T. equipment don’t mix well.
Wetness probes are most commonly deployed underneath the air conditioning system or underneath the raised floor area.
Wetness probes are available in two types.
The first type, as shown in the image above, uses a conductive rope. When the rope is wet it conducts an electric current more easily and so a measure 1 to 100 can be made denoting the level of wetness. The main downside to using the rope type of wetness probe is that when the rope gets wet it can take awhile to dry out. Use in dirty environments can also inhibit the accurate operation of the wetness probe.
The second type of wetness probe is a single point probe where water is measured in a single location. The black box in the image above has an inlet where water is measured. Instead of a level of wetness, the probe above is a simple wet or dry probe.
The single point wetness probe is best when combined with a plastic tray to catch all of the water dropped into it and concentrate it into a single point. The probe would then be placed at the point where the water concentrates. This type of wetness probe is typically used beneath your air conditioning unit where the area to be covered is limited.
The rope based wetness monitor is best used where a large area needs to be monitored like underneath a raised floor for instance. It wouldn’t be ideal to place a large tray underneath a typical raised floor because of the large area to be covered.
Security
A security probe is able to detect the break of an electrical circuit held together by two weak magnets. A security probe is commonly used to alarm on the opening of a door, usually a cabinet door when it is expected that the door will remain closed. Security probes are often paired up with a camera. The opening of a server cabinet door often triggers a camera to take a photo of the unauthorised person. The image can then be emailed or recorded for later examination.
Power presence
Most data centres have, at the very least, a backup power supply provided by a UPS. Larger data centres typically also have a fully redundant power supply backed by an off grid electricity generator.
UPS battery life is typically only an hour or two so your servers will be powered for a short time usually long enough that they can be shut down safely.
In addition, the air conditioning system typically won’t be supplied with power when the primary power fails due to their massive electricity drain. Consequently, the heat level in the data centre is going rise quite quickly.
That’s where the power detector probe comes into its own. You can alarm when your primary power source fails giving you time to take action before the secondary power starts to fail.
The power presence alarm only detects the presence or absence of power. If you need to monitor the quality and/or quantity of the electricity, a power monitor probe is required.
Power monitor
In these more energy conscious times knowing how much power your equipment is consuming is increasingly important. You can’t know that you’ve reduced power consumption unless you can measure it.
In addition, you can measure the quality of the power delivered by your energy supplier. Many types of equipment are very sensitive about the electricity feed into them.
Smoke detector
Personally I’m not convinced exactly where a smoke detector probe fits into a data centre manager’s tool bag given that, in the United Kingdom and probably the rest of Europe, there are tight fire regulations in data centres.
Data centres have to be fire proof to at least one hour with regularly tested fire alarms and, in many cases, automatic fire suppression systems too.
Given that, I’m not sure exactly where a smoke detector probe fits in. Perhaps, if your facilities people can’t be relied upon to let you know of an incident then a smoke detector provides a relatively cheap way to remain in the loop.
Motion detector
A motion detector probe is usually combined with a camera to provide a security solution.
The probe uses passive infrared to detect movement so it can be used in low light conditions.
When movement is detected the system will alarm permitting you to specify one or more actions to be performed. The most common action is to take a picture using a camera and then email the image to an interested party.
Sensor Controlled Relay
The relay probe controls a single power supply. It is able to switch the power on or off or to cycle the power to a device.
The relay probe is generally used as a method to control a single device as part of an alarm action. Typically a probe will enter an alarm state, like a temperature probe exceeds a given threshold, and an alarm is triggered. The environment monitor will then switch on an appropriate piece of equipment.
Dry contact
Dry contacts have been standard for many years in the alarm industry. More recently Uninterruptible Power Supply (UPS) and air conditioner manufacturers have used the dry contact to indicate alarm conditions. The dry contact is a binary indicator, it can only be in an on or off condition. In order to provide information on a number of alarm conditions a manufacturer will provide more than one dry contact port.
Dry contact probes can detect an alarm condition in a device and/or they can indicate an alarm to a device.
In the case of the AKCP products the dry contact probe can be used to detect an alarm condition or to indicate an alarm condition to a device.
The Sensatronics environment monitors can detect an alarm condition but not trigger an alarm.
Air flow
Data centres rely on a constant stream of cold air being introduced into a data centre and hot air being removed.
The air flow probe allows you to measure the speed of air flowing over the probe giving you a good indication as to how well the air conditioner is performing. Though the probe only indicates the speed of air flow. It will not tell you what the temperature of the air is. In order to measure both the air flow and the temperature you will require a temperature probe in addition to the air flow probe.
Camera
With the addition of a camera your environment monitor can become a convenient, integrated security solution for your data centre when combined with security and movement probes.
Siren & strobe
The siren & strobe sensor provides a visual and/or audible alert, ideal for situations where it is imperative that an alarm is acted upon immediately. Plainly, a siren & strobe is best used in a staffed environment.
A common situation is for a sensorProbe or securityProbe to monitor the temperature in a server room. When the temperature rises above an acceptable level the Siren and/or strobe light is activated in a manned Network Operation Centre (NOC) or other permanently manned area. The personnel can then undertake whatever action is needed to mitigate the problem.
Summary
[1] The Sensatronics E4 takes up to 4 temperature probes. The Sensatronics E16 takes up to 16 temperature probes
[1] See http://www.dell.com/content/products/productdetails.aspx/pedge_sc430
Alerting options
One of the major concerns driving the adoption of environment monitoring solutions in I.T. is the desire to be alerted when conditions in the server room become abnormal.
A number of alerting options exist, which you choose will largely depend upon your own particular circumstances.
By far the most popular alerting method. Has the great advantage that many people can access their emails away from the office using devices like the Blackberry.
In addition, with Intellipool, you can embed a graph of the offending probe readings with your alert.
SMS
Another popular alerting mechanism is the Short Message Service (SMS) available for most, if not all, mobile phones. Very popular with IT shops who have an “on duty” mobile phone.
The main disadvantage of SMS is the priority networks give to your messages. When the mobile network is busy SMS messages can take a while to get through to the recipient.
One problem with SMS alerting is that the data centre can be hostile to mobile phone GSM signals.
Email to SMS gateways provide a good “zero installation” way to send SMS messages. The only prerequisite being that you must have access to a mail server. Many customers use email to SMS conversion services in situations where installing a dedicated SMS modem is impractical.
With the increased availability of email on mobile phones SMS is less important than it used to be.
If timely and guaranteed delivery of your alerts is a priority then an email integrated mobile phone, like the BlackBerry, may well be worth considering.
Phone based
One way almost guaranteed to get you out of bed at 3am on a Sunday morning is the phone. Phones intrude in a way that texts and emails rarely do.
There are two ways to alarm using the phone. One very easy, the other not so easy.
A little heard of technology rolled out recently by many telcos has been fixed line SMS. One little known fact is that you can use fixed line SMS to receive text messages using your regular phone (in the UK and most of Europe anyway, fixed line SMS hasn’t been implemented in the USA).
If you want to test the service, send a text message using your mobile phone to your home phone number. You will receive a call and hear a computerised voice reading out your text message.
The more difficult option involves installing software like VoiceGuide into your monitoring system.
VoiceGuide is a Windows based software tool for dialling your phone and talking to you. The software can be integrated with any application including Intellipool.
VoiceGuide requires your server to have a modem and access to a telephone line. A modest amount of integration work is required too.
SNMP Trap
All of the featured network enabled environment monitors include the ability to generate SNMP traps when environmental conditions go out of bounds you select.
The management system, when it receives the trap, then performs the steps required to inform you of the problem.
If you do not already have a network management system, I wouldn’t recommend using SNMP traps. Much simpler alerting mechanisms are available.
Buzzer
The Senturion has an on-board buzzer and red light alarm on the front panel. Both can be very useful indications of a problem with your environment when you are in your data centre.
The main problem with physical alarms is that somebody needs to be around to see them. Many data centres are unmanned for much of the time.
Relying upon physical alarms as the sole means of informing you of a problem is not recommended.
Siren & strobe
The siren & strobe sensor provides a visual and/or audible alert, ideal for situations where it is imperative that an alarm is acted upon immediately. Plainly, a siren & strobe is best used in a staffed environment.
Sensor controlled relay
The sensor controlled relay probe allows you to control a single power supply. It is able to switch the power on or off or to cycle the power to a device.
Dry contact
If you have an existing alarm system which takes as input one or more dry contact ports then an environment monitor supporting dry contact alarms would be able to trigger your existing alarm system.
Summary
| Probe / Monitor | AKCP sensorProbe | AKCP securityProbe |
| X | X | |
| SMS | X | X |
| SNMP trap | X | X |
| Buzzer | ||
| Siren & strobe | X | X |
| Sensor controlled relay | X | X |
| Dry contact | X | X |
Structured cabling solutions
One major problem when installing an environment monitor is that often the location to be monitored is some distance away from the monitor.
One solution is to run the probe cable from the monitor to the location that you desire to monitor.
A better solution is to use your existing structured cabling infrastructure. The AKCP range of probes all use CAT5 cable and can simply be plugged into a RJ45 outlet and then be patched through your patch panel to the central monitor unit.
By using your existing infrastructure you can have a much tidier installation. You don’t need to install any new cabling and you get a lot of flexibility in where your probes are located. Moving a probe becomes a simple matter of re-locating the probe and patching the right cable on the patch panel.
The AKCP probes can be located up to 300 metres (in cable length) from the central unit.
Conclusion
Whilst there are many reasons for performing environmental monitoring in your data centre there is a lot of overlap. If you have a mandate for monitoring then your data centre then you may as well do the job right and find hotspots and ensure that you're not wasting energy at the same time. None of the different motivations outlined above are mutually exclusive, you can do most of the above quite easily and at relatively modest cost.
When choosing a solution it is helpful to understand what your requirements so that you don't find yourself spending more money than you need to.
If you want help selecting the right solution for you visit the Environment Monitor Product Finder. If you want to have a one-to-one consultation with an environment monitoring expert we are happy to help, please get in touch here.