Finally! I’ve just passed the USPEED Performance Guru exam! I first got aware of the SPEED programs during a Celerra Performance Workshop a couple of years ago. Initially it was an EMC Internal program, so I couldn’t get in without switching employers. In the beginning of 2013 this changed and EMC Partners could also enroll. Too bad I ran out of time with a mountain of projects and other training material… up until now! So what does it mean when someone is USPEED certified?
The storage market has gradually been using more and more flash to increase speed and lower cost for high I/O workloads. Think FAST VP or FAST Cache in a VNX or SSDs in an Isilon for metadata acceleration. A little bit of flash comes a long way. But as soon as you need enormous amounts of flash, you start running into problems. The “traditional” systems were designed in an era where flash wasn’t around or extremely expensive and thus simply weren’t designed to cope with the huge throughput that flash can deliver. As a result, if you add too much flash to a system, components that previously (with mechanical disks) never were a bottleneck now start to clog up your system. To accommodate for this increased usage of flash drives the VNX system was recently redesigned and is now using MCx to remove the CPU bottleneck. But what if you need even more performance at low latency? Enter EMC XtremIO, officially GA as of November 14th 2013!
EMC sends out a VNX Uptime Bulletin every quarter to update customers on best practices and fixes which will help you in achieving the maximum possible uptime and robustness for your VNX. You can subscribe to them as you would to with any other ETA (EMC Technical Advisory): log in at http://support.emc.com, go to Support by Product, open your product page (in this case the VNX) and click “Get Advisory Alerts” to subscribe. This bulletin discusses pools and LUN ownership, vault drives, software versions, etc.
Recently I ran into an environment with a couple of VNX5700 systems that were attached to the front-end SAN switches with only two ports per storage processor. The customer was complaining: performance was OK most of the time but at some times during the day the performance was noticeably lower. Analysis revealed that the back-end was coping well with the workload (30-50% load on the disks and storage processors). The front-end ports were a bit (over)loaded and spewing QFULL errors. Time to cable in some extra ports and to rebalance the existing hosts over the new storage paths!