Working on the new Dell EMC Ready Solution for SQL Server was like going from 0 to 60 mph in under 3 seconds. The exhilaration of being pushed into the seat as the road roars past in a blur is absolute fun. That’s what the combination of Dell EMC PowerEdge R840 servers and the new Dell EMC XtremIO X2 storage array did for us in our recent tests.The classic challenge with most database infrastructures is diminishing performance over time. To use an analogy, it’s like gradually increasing the load a supercar must pull until its 0-to-60 time just isn’t impressive anymore. In the case of databases, the load is input/output operations per second (IOPS). As IOPS increase, response times can slow and database performance suffers. What is interesting is how this performance problem happens over time. As more databases are gradually added to an infrastructure, response times slow by a fraction at a time. These incremental hits on performance can condition application users to accept slower performance—until one day someone says, “Performance was good two years ago but today it’s slow.”When reading about supercars, we usually learn about their 0-to-60 mph time and their top speed. While the top speed is interesting, how many supercars have you seen race by at 200+ mph? Top speeds apply to databases too. Perhaps you have read a third-party study that devoted a massive hardware infrastructure to one database, thereby showing big performance numbers. If only we had the budget to do that for all our databases, right? Top speeds are fun, but scalability is more realistic as most infrastructures will be required to support multiple databases.Dell EMC Labs took the performance scalability approach in testing the new SQL Server architecture. Our goals were aggressive: Run 8 virtualized databases per server for a total of 16 databases running in parallel, with a focus on generating significant load while maintaining fast response times. To make the scalability tests more interesting, 8 virtualized databases used Windows Server Datacenter on one server and the other 8 databases used Red Hat Enterprise Linux on another server. Figure 1 shows the two PowerEdge R840 servers and the 8-to-1 consolidation ratio (on each server) achieved in the tests.Figure 1: PowerEdge R840 serversQuest Benchmark Factory was used to create the same TPC-E OLTP workload across all 16 virtualized databases. On the storage side, XtremIO X2 was used to accelerate all database I/O. The XtremIO X2 configuration included two X-Brick modules, each with 36 flash drives for a total of 72. According to the XtremIO X2 specification sheet, a 72-drive configuration can achieve 220,000 IOPS at .5 milliseconds (ms) of latency with a mixture of 70 percent reads and 30 percent writes using 8K blocks. Figure 2 shows the two X-Brick configuration of the X2 array with some of key features that make the all-flash system ideal for SQL Server databases.Figure 2: XtremIO X2Before we review the performance findings, let’s talk about IOPS and latency. IOPS is a measure that defines the load on a storage system. This measurement has greater context if we understand the maximum recommended IOPS for a storage system for a specific configuration. For example, 16 databases running in parallel don’t represent a significant load if they are only generating 20,000 IOPS. However, if the same databases generated 200,000 IOPS, as they did on the XtremIO X2 array that we used in our tests, then that’s a significant workload. Thus, IOPS are important in understanding the load on a storage system.Response time and latency are used interchangeably in this blog and refer to the amount of time used to respond to a request to read or write data. Latency is our 0-to-60 metric that tells us how fast the storage system responds to a request. Just like with supercars, the lower the time, the faster the car and the storage system. Our goal was to determine if average read and write latencies remained under .5 ms.Looking at IOPS and latency together brings us to our overall test objective. Can this SQL Server solution remain fast (low latency) under a heavy IOPS load? To answer this question is to understand if the database solution can scale. Scalability is the capability of the database infrastructure to handle increased workload with minimal impact to performance. The greater the scalability of the database solution, the more workload it can support and the greater return on investment it provides to customers. So, for our tests to be meaningful we must show a significant load; otherwise, the database system has not been challenged in terms of scalability.We broke the achievable IOPS barrier of 220,000 IOPS by more than 55,000 IOPS! In large part, the PowerEdge R840 servers enabled the SQL Server databases to really push the OLTP workload to the XtremIO X2 array. We were able to simulate overloading the system by placing a load that is greater than recommended. In one respect we were impressed that XtremIO X2 supported more than 275,000 IOPS, but then we were concerned that there might have been a trade-off with performance.The average latency for all physical reads and writes was under .5 ms. So not only did the SQL Server solution generate a large database workload, the XtremIO X2 storage system maintained consistently fast latencies throughout the tests. The test results show that this database solution was designed for performance scalability: The system maintained performance under a large workload across 16 databases. Figure 3 summarizes the test findings.Figure 3: Summary of test findingsThe capability to scale without having to invest in more infrastructure provides greater value to customers. Would I recommend pushing the new SQL Server solution past its limits like Dell EMC Labs did in testing for scalability? No. Running database tests involves achieving a steady state of performance that is uncharacteristic of real-world production databases. Production databases have peak processing times that must be planned for so that the business does not experience any performance issues. Dell EMC has SQL Server experts that can design the Ready Solution for different workloads. In my opinion, one of the key strengths of this solution is that each physical component can be sized to address database requirements. For example, the number of servers might need to be increased, but no additional investment is necessary on XtremIO X2, thus, saving the business money.If I were to address just one other topic, I would pick the space savings achieved with a 1 TB SQL Server database. In figure 4, test results show a 3.52-to-1 data reduction ratio, which translates to a 71.5 percent space savings for a 1 TB database on the XtremIO X2 array. Always-on inline data reduction saves space by writing only unique blocks and then compressing those blocks to storage. The value of inline data reduction is the resulting ability to consolidate more databases to the XtremIO X2 array.Figure 4: XtremIO X2 inline data reductionAre you interested in learning how SQL Server performed on Windows Server Datacenter edition and Red Hat Enterprise Linux Server? I recommend reading the design guide for Dell EMC XtremIO X2 with PowerEdge R840 servers. The validation and use case section of that guide takes the reader through all the performance findings. Or schedule a meeting with your local Microsoft expert at Dell EMC to explore the solution.Why Ready Solutions for Microsoft SQL?The Ready Solutions for Microsoft SQL Server team at Dell EMC is a group of SQL Server experts who are passionate about building database solutions. All of our solutions are fully integrated, validated, and tested. Figure 5 shows how we approach developing database solutions. Many of us have been on the customer or consulting side of the business, and these priorities reflect our passion to develop specialized database solutions that are faster and more reliable.Figure 5: Our database solutions development approachI hope you enjoyed this blog. If you have any questions, please contact me.Additional Resources:Microsoft SQL Server Info Hub—A list of recent Dell EMC solutions for SQL ServerDell EMC Ready Solutions for Microsoft SQL—A good resource for all Dell EMC solutions for SQL Server
The Vermont Department of Education mailed FY2012 individualized education spending reduction targets Monday to each supervisory union, supervisory district, and the three technical center districts across the state, as required by Act 146 of the 2010 Legislative session. Overall the recommendations are for a 2.34 percent reduction across the state in education spending in order to meet the goal of saving $23.2 million dollars. District-level recommendations range from a 0.5 percent reduction to a 2.68 percent reduction.The determinations were made at the district levels, but aggregated to the supervisory union level as the law requires. The determinations considered factors outlined in the law, such as per pupil spending, student-to-staff ratios and demonstrated fiscal restraint. The department examined data from the past four budget cycles on· total education spending,· spending per equalized pupil,· student enrollment to direct instruction staff,· direct instruction staff to administrative staff,· and student enrollment to administrative staff. ‘We expect most school districts and supervisory unions to take these recommendations seriously,’ said Commissioner Vilaseca. ‘And they will do their best to meet them, just as they responsibly reduced spending last year. This is new territory, both for our department and for local school districts.’The boards of each supervisory union and district shall notify the commissioner on or before December 15, 2010 whether their combined budgets will meet the recommended reductions. By January 15, 2011, the commissioner shall report to the legislative education committees the total projected amount of FY2012 budgets, with a detailed proposal by which the Legislature can ensure the targets will be met.See Page 76, sections E1 and E2, for this specific requirement at http://www.leg.state.vt.us/DOCS/2010/ACTS/ACT146.PDF(link is external). A complete explanation of the formula begins on the following page.Challenges for Change School Budget Reduction Targets Calculations Brief overview of methodologyFor any given data element, the percent change between any two consecutive years was calculated (i.e., the percent change in netted education spending from FY2010 to FY2011). Percent changes were capped at plus or minus 50 percent to compensate for very large percentage changes resulting from small changes in very small districts. Additionally, some data were either clearly entered incorrectly or not entered at all, resulting in very large or low percentage changes.The four years of data resulted in three percentage changes. Those three changes were averaged for a district. Again, to accommodate small districts, the averages were capped at plus or minus one standard deviation from the mean. As supervisory unions are different from school districts and perform different functions, a separate mean and standard deviation was calculated and used for supervisory unions and supervisory districts. School districts and the three technical center school districts used a mean and a standard deviation based on their combined data.The resulting average (capped if necessary) was divided by the relevant group mean to normalize the data. This figure became the weight for any given factor. The exception was the factor for direct instruction FTEs per administration and support staff FTEs. That factor had a low mean for the school district and technical center (0.15%), resulting in disproportionately large weights for a modest average (e.g., with a mean of 0.15%, an average of 10% results in a weight of 67). Therefore, the DI per Admin & Support weight was decreased by a factor of 0.50 to mitigate the effect of the small mean.Weights from the various factors were aggregated. To account for the varying magnitudes of education spending (Burlington versus Eden, for example), the total weights for a district were multiplied by the ratio of the district’s netted education spending to the netted education spending as a whole.Some districts had a negative total weight, resulting in a negative factor after applying the relative netted education spending factor. Statistically, it is valid to add a constant to transform the negative values to positive. This was done by adding a constant of 1 to all weighted totals. This result was then multiplied against the ratio of the required $23,200,000 reduction versus the netted education spending total (2.348%), to give a weighted percentage for reduction.That weighted percentage was multiplied by the netted education spending for all districts, SUs, SDs, and technical center districts. The aggregated targets for the State exceeded the $23,200,000, so a reduction factor of the legislated target divided by the calculated target state total was applied to each district, bringing the targets to the $23,200,000 figure.Source: Vermont DOE. 8.4.2010http://education.vermont.gov/new/html/dept/press_releases.html(link is external) OverviewSection E2 of Act 146 of the 2010 Legislative session specifies that FY2012 education spending will be reduced by $23,200,000 from the FY2011 level, while achieving the outcomes for education listed in section E1. The commissioner of education is directed to develop reduction targets for each supervisory union and technical center school district.These targets were developed by looking at the member districts of supervisory unions, the supervisory unions themselves, and the three technical center school districts. Additionally, supervisory costs for Supervisory Districts were removed from the school costs (e.g., supervisory costs for the Montpelier Supervisory District were removed from the Montpelier School District costs).Entities excludedSchool districts excluded from these targets were districts that:did not operate a school and tuitioned all grades;belonged to a union school and tuitioned all other grades;were members of two unions offering combined grades K ‘ 12;were members of joint school agreements as individuals but data were aggregated to the joint school level and were included; andunorganized towns and gores.Data elementsData used were the most recent available for the following elements and are as reported by the districts:education spending (FY08-FY11);equalized pupils as calculated with the maximum allowable 3.5% loss (FY08-FY11);enrollments (FY07-FY10); andteacher / staff data (FY07-FY10)direct instruction ‘ all licensed teachers in the classroom;administrative and support staff ‘ central office staff personnel for both school and general administration, including paid teachers aides.Education spending for school districts was decreased by supervisory union assessments, costs for grades tuitioned, capital debt, and costs for technical center students.Factors usedThe above data elements were used in the following six factors:netted education spending (after removal of aforementioned costs);netted education spending per equalized pupil;enrollment per direct instruction staff FTEs;enrollment per administration and support staff FTEs;direct instruction FTEs per administration and support staff FTEs; andnetted education spending as a percent of total netted education spending, applied to the aggregated weights from 10 – 14.
LIVE TV Last Updated: 29th August, 2020 11:29 IST Grandal Hits Game-winning HR, White Sox Beat Royals 6-5 Yasmani Grandal hit his third career game-ending home run in the ninth after a defensive miscue as the Chicago White Sox beat the Kansas City Royals 6-5 on Friday night SUBSCRIBE TO US Written By First Published: 29th August, 2020 11:29 IST COMMENT Yasmani Grandal hit his third career game-ending home run in the ninth after a defensive miscue as the Chicago White Sox beat the Kansas City Royals 6-5 on Friday night.Yoan Moncada had an RBI single in the seventh, Eloy Jimenez added a two-run homer and Luis Robert also homered for the White Sox who have won 10 of their last 11 games and eight straight at home.Trailing 5-4 in the ninth, Ryan O’Hearn drew a one-out walk off White Sox closer Alex Colome. Maikel Franco followed with a liner to left-center. The White Sox caught Franco in between first and second. First baseman Jose Abreu tried to run him down but Franco got to second base before Abreu’s diving attempt of a tag. While Abreu was sitting on the ground near second base, Abreu threw to the plate. Grandal wasn’t looking for the throw and the ball got by Grandal, allowing pinch-runner Bubba Starling to score to tie the score.“A very bizarre play. As I am thinking, it’s a dead ball as soon as Abreu falls on the ground. I am looking at the runner at third and he is standing at third, he’s not going anywhere,” Grandal said. “Right after that, I have to figure out if the dugout wants to challenge or not and let the umpire know we’re trying to challenge the play. As that happens, I turn around and see the ball going through my legs. Like I said before, it’s something to learn from, make sure I am aware as to when the play is over and when the umpire is actually calling timeout.”Grandal made up for everything when he broke a 5-5 tie with a leadoff homer off Ian Kennedy (0-2) in the bottom of the inning.“I’ve caught Kennedy before and I had plenty of AB’s against him. I kind of had a pretty good idea of what I wanted off of him in order to take a good swing at it,” said Grandal.Colome (1-0) finished the game by getting the final four outs after blowing his first save attempt.The White Sox moved into a tie with the Twins for first place in the AL Central.Jorge Soler hit a two-run home run and Whit Merrifield added a solo shot for the Royals, who have lost all four of their games to the White Sox this season.“We fought so hard to get back, every time in that game, multiple times. … That’s one of the worst feelings as a reliever, getting walked off,” said Kennedy.Royals manager Mike Matheny wants to see his team take advantage of situations when opponents give them a break.“For our team to take that next step, we have to be relentless in those situations,” Matheny said. “We can’t let teams off the hook as often as we have. We’re facing major league-caliber pitching. I get it. It’s just that it’s going to continue to be the conversation. They’re going to get sick and tired of hearing about it, but it’s too big of a piece of the puzzle for us, to not make a mark early, to not figure out how to get it done late.”Royals reliever Tyler Zuber, activated from the bereavement list before the game, walked Jimenez to start the seventh on four straight pitches. He gave up a single to Grandal, One out later, he was relieved by Scott Barlow, who walked Edwin Encarnacion to load the bases. After Franco was unable to make a running overhead catch in foul territory, Moncada ripped a single to right to put the White Sox ahead 5-4. Barlow escaped further damage by getting Robert to line out and Danny Mendick swinging.Trailing 2-1 in the fifth inning with two outs, Tim Anderson hit a liner off the right thigh of Royals starter Danny Duffy. Duffy didn’t appear hurt despite getting a visit from the team trainer. Two pitches later, Jimenez teed off on a fastball, driving it deep into the ivy in center-field to give the White Sox a 3-2 lead. It was Jimenez’s 11th of the season and it measured at 452-feet.Moncada chased Duffy with a two-out single in the sixth inning. Robert reached on a single off Royals reliever Jesse Hahn and Mendick struck out but reached on a passed ball by catcher Cam Gallagher to load the bases. Pinch-hitter Nomar Mazara added another run by drawing a bases-loaded walk to extend the lead.The White Sox lead was short-lived. Reliever Matt Foster allowed a one-out walk in the seventh, then Soler followed with a two-run shot on an 0-2 pitch to tie the game at four it was his eighth of the season.With two outs in the second, Robert hit an opposite-field home run into the Royals’ right-field bullpen. It was the rookie’s 8th of the season.Merrifield tied the game in the third with a leadoff shot on a high 2-1 fastball. It was his sixth of the season. White Sox starter Reynaldo Lopez then surrendered three consecutive hits. Ryan O’Hearn hit an RBI single to put the Royals ahead 2-1.Lopez was pitching in and out of trouble all night. Lopez allowed two runs on six hits in four innings. He struck out four and walked two.Before the game, the White Sox acquired speedy outfielder Jarrod Dyson in a trade with Pittsburgh to boast their depth as they make a run for the postseason. Dyson came in as a defensive replacement in the ninth for Jimenez in left.Duffy allowed four runs, three earned on seven hits. He struck out six and walked one in the no-decision.JACKIE ROBINSON DAYGrandal and his teammates weren’t looking to make a statement by not playing on Friday. Grandal pointed to the significance of Jackie Robinson Day. If you don’t play today than what is the point? We thought today was the day to play. If it wouldn’t have been Jackie Robinson Day today we could’ve possibly taken a different route, but we thought today was definitely the one day we needed to play.”TRAINER’S ROOMINF Nick Madrigal, one of Chicago’s top prospects, returned to the White Sox. He separated his left shoulder in his fifth game with the team. The 23-year-old second baseman was selected by the White Sox with the fourth overall pick in the 2018 draft. Catcher Zack Collins was optioned to Schaumburg to create a spot for Madrigal. Madrigal did not play on Friday night.UP NEXTBrady Singer (1-3) is scheduled to start for the Royals against the White Sox on Saturday. The right-hander is 0-1 in three road starts this season with a 4.02 ERA.RHP Dylan Cease (4-2) is scheduled to start for the White Sox on Saturday. He is 4-1 with a 2.15 ERA in his last five starts. He is 1-1 with a 4.50 ERA against the Royals in his career.Image credits: AP Associated Press Television News WATCH US LIVE FOLLOW US