AndreSchmitz

Member
  • Content count

    16
  • Joined

  • Last visited

Community Reputation

0 Neutral

About AndreSchmitz

  • Rank
    Member
  1. Hey all, we just tried to escape the ENORMOUS licensing-costs of our favorite SQL-DBMS in decreasing corecount but increasing corepower. So wo interchanged 2 x E5-2690 v4 (56 cores over all (HT) * 3,2Ghz) with 4 x E7-8893 V4 (32 cores over all (HT) * 3,4Ghz). We unfortunately found noone who could provide us with some information if this would be a good deal ( 4 x E7 is about 5 times more expensive in hardware-costs, but saving 12 core-licenses), neither intel but MS could deliver us some sort of suggestion. So i try to share my experience here. But like everytime: i wont guarantee that this results are representativ, complete, correct or reproducable for you etc! Both servers use the same amount / type or Ram, uses the same Stripeset ob Intel PCIe-SSD's to store the database + are identically configured regarding the MS SQL / Windows 2012 R2. Here is a quick Overview of HammerDB 2.21 OLTP Maybe i could over some ultra-quick facts regarding performance-comparison between our specific OLAP-Workload
  2. Hardwarereseller-Pricings...is this normal?

    Please excuse the late reply! No, we didn't ask other resellers, because of company-politics. Looking backwards, every order / offer is similar: - we ask for a specific server - reseller sends offer with some fantastic moon-pricings and tells: this are fantastic moon-prices, we can do it much better! - we ask for much better prices - reseller sends offer with some realistic prices. EVERY time...for years. This is odd!
  3. Good Morning all, im a DBA and shortly envolved in Hardwarepurchases. We are mainly using fujitsu-servers, ordered by some fujitsu-reseller. Now getting a look at the prices i was astonished! In EVERY offer we get the CPU-Prices are WAY above the intel arc recommended customer price. (add 500 - 2000 bucks to the listprice, depending on the exact cpu!!) Is this normal in serverbuisness or is our reseller crappy? Please help the new gui!
  4. Intel P3700 in Raid 1

    MS SQL Server 2014 Enterprise. We want to use the P3700 to store the Log-Files for some write-intense Databases and TempDB to ease our SAN-Preasure. Afaik there is no way to create log-file-redundancy withing the MS SQL Server. Looking at the Fujitsu doc linked above a SW Raid 1 sadly performns not so good as a single card. (for high-io-workload! looking at file-transfers etc it looks different!) As you said, no huge impact. But i just wanted to ask ;-) Screenshot from the above linked Fujitsu-Doc, Page 10 attached. Thank you, Andre
  5. Intel P3700 in Raid 1

    Good morning all, does anyone have experience in Raiding Intel P3700 Cards? We are looking to boost a DB-Server with redundant P3700s. As far as i can see the only possibility to Raid these Cards is Software-Raid? Reading Performance Report PCIe SSDs P3700 Software-Raid1 works but with some performance-penalty. Additional i read that PCIe SSD- Softwareraids consume "lots of" CPU-Power under IO-Stress. Can someone share his experience in Raiding PCIe-Flash? Kind regards, Andre
  6. How mutch Drives in Raid5?

    We are using Fujitsu JX40 DAS-Boxes. As Fujitsu only puts 1TB-Drives on the compatibility-list we would, according to our reseller, lose waranty and compromise our service/support-agreement. Thats why 1TB .-(
  7. Good morning! We are going to extend the last Storage-Tier with 43 7.2k Drives (ST9100640SS). The primary aim is capacity, secondary is speed. - Te used controller is a MegaRaid 9285W-8e featuring a LSI2208-Chipset+1GB Cache - As our hole SAN is completely mirrored we decided to configure the Drives in Raid5-Stripes. - Because we have to reconfigure the SAN online we can put together a maximum of 10 Drives in a singel Raidset (put in 10 drives, configure, migrate date from old drives to new, remove old drives, put in another set of new drives and so on) - We want to use at least 1 Drive as Hotspare! - Our san spreds datablocks across all Raidsets within a Tier theoreticaly accumulating the Performance of all Raidsets in best case. What Raid-size should we choose? We are debating Sets of 7 x 6 Drives + 2 HS, 5 x 8 Drives + 3 HS or 4 x 10 Drives + 3 HS. For all 3 configurations the theoretical MTTDL / propability of Dataloss is acceptabel We benchmarkt all three sizes. The relativ Raidset-Performance is exactly what we theoreticaly calculated ( Handling the 10Drive-Raidsetiops as 100% we reached: 10Drive Raidset: 100% / 8 Drive Raidset: 76% (75 calculated) / 6 Drive Raidset 61% (60% calculated) ) Of corse 4 Sets of 10 Drives gives the highest netto-capacity 7 Sets of 6 Drives benefits in a slightliy higher (~5%) accumulated Performance We are trending to use the 4 x 10 Drives configuration but our reseller continously jells us to use the 6drive-set configuration. Now im a little bit helpless. Can someone give me a hint?
  8. Tiered Storage best practices?

    Hello and good morning! Please excuse the late reply, i've been off for christmas. Unfortunately my question is intended as broud as it is .-( I worked with Storage/Fileservers years ago and now have to be part of a projectteam with the aim to overhaul a Datacore-SAN because we run into differences with our Storagereseller. Now my problem is that our reseller / consultant continously throws statements in the room i realy cant believe to be true. So what im am looking for are good guides / bestpractices or books for modern SAN / Hardware (vendor independend or Datacore) discussing: - good ways to configure Storagetiers (How many Tiers, how big should the speedstep betweens tiers be, how should tiers differs in capacity) - good ways to configure Raidsets (for Sets with 10, 20, 30 or more Drives, controllerpenaltys for larger raidsets etc,) Im confidence in doing the theoretical math of configuring storage, but i still have no practical experiance with modern Storagehardware. Maybe you have some lecturehints for me? Thank you very mutch, Andre
  9. Good morning! Are there some best practices, literature or tools you could use to try configuring/sizing your SAN-Tiers in a most optimal way? Thank you very mutch!
  10. Helloo! We have some RX350 S7 with JX40 DAS attached. To optimize our Storage it would be nice to swap drives from the RX350 to the JX40. Unfortunateliy our reseller told us that the HDD-Frames of the RX350 are not compatible to the JX40 and, interchanging HDD and Frames would compromise our warranty and supportagreements. Is this generaly speaking correct? And, shouldnt at least our reseller/serviceprovider be able/allowed to interchange the drives from the Server to the DAS? Thank you! Andre
  11. Need help metering a Software defined SAN

    Very well! But all our Server-Hardware/SAN-Hardware AND Datacorelicensing/Support lies by a small reseller who is not very ... helpfull. Look at the config above: The original config was done by the reseller. We figured out our new config and got comments like "on your owne risk!", "good luck", "in our oppinion you need a future concept" etc. As i said im not a SAN-Guy and so easy to intimidate ;-) What we can say fpr now: This weekend we updatet our SanSymphonies to the actual SPS including the "Parallel IO"-Feature greatly promoted by Datacore. On the first look we had an improvement up to about 10% for long running processes.
  12. Need help metering a Software defined SAN

    Yesterday i recalculated the Tier's our reseller configured for our SAN. This is what it looks like: Tier1: 2 x Raid 5 (4 x SSD, 35000IOPS per Raid) 3TB at all Tier2: 1 x Raid10 (4 x HDD 10k, 520IOPS per Raid) 1,2TB at all Tier3: 1 x Raid 5 (6 x HDD 10k, 390IOPS per Raid), 3TB at all 2 x Raid 5 (5 x HDD 7.2k, 130IOPS per Raid), 8TB at all Tier4: 1 x Raid 5 (5 x HDD 10k, 325IOPS per Raid), 2,4TB at all Tier5: 3 x Raid 5 (5 x HDD 7.2k, 130IOPS per Raid),12TB at all Tier6: 1 x Raid 5 (3 x HDD 7.2k, 80IOPS per Raid), 2TB at all We will mix all the Drives new like this: Tier1: 2 x Raid 5 (4 x SSD, 35000IOPS per Raid) 3TB at all Tier2: 1 x Raid10 (16 x HDD 10k, 2080IOPS per Raid) 4,8TB at all Tier3: 4 x Raid5 (7 x HDD 7.2k, 157IOPS per Raid) 24TB at all. Both configurations offers round about 32TB capacity, but in second one the average IOPS/TB is doubled. Thank you for your help!
  13. Need help metering a Software defined SAN

    Today our Datacore-Consultant told us that in his oppinion the Problem is designated to Tier2, a Raid10-Set of SAS-HDD. We configured our SAN to use 100% of the Tier2-Capacity, so usinig the last x% results in a performancedegradation for Tier2-accesse duo to the nature of HDD. His solution is now: Expand the Tier2 Raid10 by additional drives to increase the overall volume by 20% and then letting the last 20% untouched to force the SAN not to use the least speady 20% of the HDD I know the Problem using the last parts of HD, but is this a common way? This would ONLY make sense if the last 20% of Tier2 is slower then the average of Tier3 or? And, even if this is given, our performancebottlenecks are in IOPS-Regions far above the Tier2-performance, so i would still point to Tier1.
  14. Need help metering a Software defined SAN

    Good Morning! We are using to Raidsets for the Toptier. #1 Hitachi HUSSL4040ASS600 (~13k IOPS Randomwrite 8kb each, 4 active+1hotspare drives in Raid5) #2 Toshiba PX02SMF080 (~15k IOPS Randomwrite 8kb each, 4 active+1hotspare drives in Raid5) Both Raid together hosts about 3TB of space. As the budged is limited we suggested to either a) place a new TopTier with 800GB DC-P3700 b )or expand each Raid5 by "a few" (1-2) SSD to increase the Raid5 write-throughput. Streetprices of the P3700 and the PX02SMF080 seems to be equal. c) Our Datacore/Serverhardwaresupplier suggested to double the amount of the existing SSDs and use them as RAID10. Of course the 2nd way looks less promising but it eliminates the use of in our company unknown technologie like pcie-Storage. For know i looks like we can test 3) for free and then decide to by or not. Talking in Numbers: a) Using 1 x DC-P3700 ~2000€ / 45k IOPS as new Tier0 resulting in Tier0 = 800GB 45k IOPS + Tier1 ~23k IOPS, 3TB b )Using 1 x additional SSD per Raid 5 ~2 x 2000€ / 15k IOPS increasing Tier0 from 3TB/23k IOPS to 4,2TB / 28,8k IOPS c) Switching to Raid 10 using 10x additional SSD ~ 10 * 2000€ / 15k IOPS increasing Tier0 from 3TB / 23k IOPS to 3TB / 60k IOPS asking me i would prefer a) The Host-CPU is way bigger then Datacore recommended and dont show significant load. The used Raid-controller are some kind of MegaRaid SAS-Conroller, but dont know the exact model :-( Have a nice day, Andre
  15. Need help metering a Software defined SAN

    Good morning! Thank you for your reply and excuse my late one. ATM there is a Datacore-Crew inspecting our SAN. for now it looks like our SSD-Tiers (about 10% of the overall SAN-volume) is - to small for our Hot Data - to slow for our demands. So we are thinking of compensating our bottlenecks with a new Top-Tier of Intel DC-P3700 SSD's as first step "emergency-solution" Thank you for your patience!