Tag Archives: performance

How to gather performance statistics from an EMC XtremIO

XtremIO

The XtremIO GUI looks very slick and it has this chronometer with IOps and MBps and everything, but when you need to have MiTrend analyze the statistics, the questions comes to mind: what statistics, what files?

How do I get my hands on these files?

First log on to the XtremIO GUI. Then click on the administration button

Administration

Now click on the “CLI Terminal TAB” and type:

create-debug-info

Read more »

Uptime defined, or what is uptime exactly?

Five nines

You often hear vendors mentioning their system has five 9s of uptime, but what exactly is uptime?

Some define uptime only for their own specific piece of technology. For example, a storage array with five 9s uptime, can only tolerate 5 minutes and 15 seconds of downtime per year, but if your network vendor also has a five 9 uptime specification and your power company and your data center and your internet provider and a whole lot of other components…. do the math!

Read more »

Is the SCM promise really worth the wait?

HP SCM

HP and SanDisk are making revolutionary memory market ready

The IT companies HP and SanDisk are promising that their Storage Class Memory (SCM) will be 1000 times as fast as the current generation of flash memory. That’s quite an assumption or is it really proven that it will be this fast.

HP SCM

Storage Class Memory (SCM) is a combination of the memristor technology HP is working on for years already and SanDisk’s ReRAM technology. The new type of memory has some pretty impressive characteristics:

  • It’s 1000x faster
  • It lasts a 1000x longer

Read more »

Enhance your WiFi by using beer!

Beer can WiFi booster

Bad WiFi reception

Bad WiFi reception is one of the most common annoyances these days. Especially in residential areas where every house has at least 1 access point and each family is working hard to fill the ether with their own signals. A quick fix can solve this problem relatively easy by using an empty beer can (a soda can also works).

The aluminum of an empty beer can enhance the WiFi-signal significantly. You could buy an expensive repeater, but a beer can is immensely cheaper (and is more fun to get too). Our good friend youtube shows us this instructional video.

Step by step

  1. Go to the supermarket
  2. Buy (at least) 1 can of beer (a premium brand will do better than some random cheap brand)
  3. Empty the can (don’t throw the beer in the sink at all times! Drinking is the preferred method!)
  4. Clean the inside of the can by flushing it with some water
  5. you will need a knife or scissors to open up the can and some material to fix the empty can to your router
  6. Remove the lid, used to open the can
  7. Cut off the bottom of the can
  8. Cut off the top of the can, leaving a small piece near the old drinking opening
  9. Cut the can from top to bottom at the opposite side from the drinking opening
  10. Carefully bend the metal so it (sort of) looks like a satellite dish
  11. Place the brand new dish shaped beer can on your access point, by sticking the antenna through the old drinking opening
  12. Fix the “dish” so it doesn’t fall off

steps

This little trick should enhance the signal strength by a factor 2 or 3. This only works for access points equipped with an external antenna. For antenna-less models you could try creating a somewhat larger dish and placing the whole access point on the bigger dish, but I don’t guarantee this works. You could for example use a keg, but I doubt that you can cut it by using scissors ūüėČ

 

Optimizing performance using VAAI and the ESX MaxHWTransferSize setting

xcopy transfer size

If you’re running an EMC¬†VNX¬†using a lower version than block OE version 05.32.000.5.209, you might want to upgrade to the latest and greatest version (patch 209 or newer). The 209¬†offers EMC‚Äôs latest fixes and enhancements for VAAI¬†performance. Many¬†of the¬†found performance issues have been fixed in the 209 code.¬†However, in¬†some environments sub-optimal performance has been detected¬†with xcopy¬†operations, or in some cases with the performance of non-xcopy¬†IO during xcopy operations to the same pool.

Read more »

CX or VNX Mirrorview with Snapview active on the remote side

If you have a primary LUN which is replicated using MirrorView/S and you decide to run SnapView snapshots on the remote side, consider that writes to the secondary LUN may have to wait for the COFW activity to complete before an acknowledgement is sent back to the primary array.

So if you’re performing tests on the remote site by using SnapView snapshots, you may want to consider suspending the MirrorView session(s) first in order to guarantee performance on the production site.

A good scenario would be to create clones from the temporary fractured mirrors and as soon as the clones are fully in sync, split the clone from its primary – being the MirrorView secondary – and start the resync in MirrorView.

MirrorView has to wait for SnapViewAfter the write from the primary array (1) a COFW (Copy On First Write) (2) must take place if the write (1) overwrites a block that hasn’t been written to yet in order to maintain the point in time of the snapshot. After the COFW (2) is complete the acknowledgement (ACK) (3) can be sent back to the primary array.

So even if the snapshot isn’t used by a host, there’s already an increased activity on the remote array.

If the snapshot is in use by a host that writes to the snapshot, an unchanged block on the secondary LUN need to be copied to the RLP (Reserved LUN Pool) first before the overwrite can take place. This will also slow down any ACKs that need to be sent back to the primary array.

Conclusion

Be very careful when starting SnapView sessions on a secondary LUN and even more careful when using the secondary LUNs since it can have a severe impact on the response times of the primary LUN.

The importance of keeping fibers clean

Fiber patch cables seem to be very forgiving, when light shines through everything is great and everybody’s happy, right? Wrong!!!
You shouldn’t underestimate the importance of keeping the ends of patch cables and the SFPs clean, since the actual diameter of a fiber is either 9 or 50 (or even 62.5) mu (micron).

fiber

Read more »

Performance Calculations on Clariion/VNX

Although the actual story I want to point out to you is on the EMC Community Network website (also called ECN), I would like to invite you to join the discussion there:

https://community.emc.com/thread/148025?tstart=0

 

If you’d like to discuss anything here, you’re welcome to do so.

 

Let’s join the discussion!

Accelerating your storage array by using SSD technology

It’s out there since quite a few years already. It started becoming available to the general public about 12 years ago or so and was commonly seen in digital cameras: FLASH storage! At first the devices couldn’t store more than just a few MB and prices were high, but over time the size went up and prices went down and the first SSD drives (should we say “drives”?) were born. Still expensive but they were very usable in the computer industry. Mainly heavily used databases could be accelerated by using SSD because there was no rotational latency and avg access latency was in the sub mili second range instead of multiple mili seconds! The common problem in the last few years was mainly durability, but currently the SSD technology is just as reliable as the old rotating disks.

Read more »