We once again return to the classic block storage benchmark, the latest StoragePerformance Council (SPC) results*. Also we report on the new SPC-1/E energyusage benchmark for the first time.SPC-1*resultsThere have been four new SPC-1 results this past quarter, IBM Power 595 withSSDs, TMS RamSan-620 with SSDs, Sun Storage 6180 and Fujitsu ETERNUSDX80 (rebadged 8000) storage subsystems. Both SSD subsystems made it into thetop 10 on a number of charts. Let’s start with IOPS .Figure 1 Top 10 SPC-1* IOPS The top IOPS storage subsystem now stands as an IBM Power 595 server usingSSDs and comes in at 301K IOPS. TMS’s RamSan-620 at number 5, hit almost255K IOPS. All the remaining, non-SSD, top-10 IOPS results save one (IBMSVC 3.1), had over 1000 drives. In contrast, the TMS RamSan-620 used only 20SSDs. Not sure what the IBM Power 595 is doing in a storage subsystembenchmark but for SAS attached SSD storage, it’s a screamer.*SilvertonConsulting, Inc.StorInt DispatchAll results from as of 27 August 2009 2008 Silverton Consulting, Inc.All Rights Reserved

SPC Performance StorInt DispatchSCISPC091119-010Figure 2 Top 10 SPC-1* LRT Both the RamSan-620 and the IBM Power 595 tied for 3rd at 0.5 msec LRT. All therotating disk results range from 0.9 to 1.7 msec LRT. It’s almost inconceivable that theTMS RamSan 400 hit a 0.1 msec LRT and its counterpart, the TMS RamSan-320 hit only0.2 msec but both have been reported before. What’s somewhat surprising is that the FCattached SSDs (TMS) and the SAS attached SSDs (IBM) perform equally well in LRTresults, probably indicating that LRT performance does not always depend on driveinterface.P.O. Box 492 Broomfield, CO 80038-0492 720-221-7270 2009 Silverton Consulting, Inc.All Rights ReservedPage 2 of 6

SPC Performance StorInt DispatchSCISPC091119-010Figure 3 Top 10 SPC-1* IOPS/driveRecall that in our last report we now restrict the IOPS/drive chart to only thosesubsystems using 140GB drives or larger. To that we now must add that results for SSDsare also excluded along with other memory subsystems. We would need a log scale toinclude the latest SSD results here, as the TMS RamSan-620 hit over 12.7K IOPS/Driveand the IBM Power 595 hit over 3.5K IOPS/Drive.In contrast, both the Sun 6180 and Fujitsu’s DX80 made it into the top 10 for IOPS/driveat 326 and 300 IOPS/drive respectively. Also the Sun 6180 and IBM’s DS5020 Expressperform exactly alike and seem to represent almost the same storage subsystem (OEMedprobably from LSI, see also SPC-2 results below).P.O. Box 492 Broomfield, CO 80038-0492 720-221-7270 2009 Silverton Consulting, Inc.All Rights ReservedPage 3 of 6

SPC Performance StorInt DispatchSCISPC091119-010Figure 4 SPC-1 Bubble chart of IOPS against LRT, bubble size proportional tosubsystem priceReaders will recall that this chart used to show a minimum LRT of 1.5 msec. With theaddition of the TMS RamSan-620 we have had to rescale the chart below 1.5 msec. Theother two additions to this chart were the Sun 6180 and the Fujitsu DX80, although theyare difficult to discern in the crowd around 25K IOPs and 2.0 msec LRT. This chartalways seems to tell us that subsystem price is not the lone factor in determining SPC-1performance.SPC-1/EThere have been no new SPC-1C or SPC-1C/E benchmarks this last quarter but a newbenchmark has been released for subsystem wide energy use, the SPC-1/E. Xiotech hasreleased results for their Emprise 5000 system with both 146GB/15Krpm and600GB/10Krpm drives.P.O. Box 492 Broomfield, CO 80038-0492 720-221-7270 2009 Silverton Consulting, Inc.All Rights ReservedPage 4 of 6

SPC Performance StorInt DispatchSCISPC091119-010Figure 5 SPC-1/E* ResultsXiotech used the same number of drives in each case (20), probably why the 600GBdrive subsystem cost so much more (note bubble size). But more significant is that evenwith over 4 times the storage capacity the subsystem running the newer drives operates at 26% less power. In all honesty the new 600GB drives operate slower, at 10Krpm thanthe 15Krpm 146GB drives. However, peak performance dropped only 14% from 6962 to6057 IOPS and as such, seems a viable tradeoff.SPC-2 resultsThere were eight new SPC-2 results submitted this last quarter, Sun 6180 and IBMDS5020 Express at RAID5 and RAID6 and Sun 6780 and IBM DS5300 with 8GFC atRAID5 and RAID6. Similar to the discussions above (see IOPS/drive), these two sets ofsubsystems perform exactly alike, i.e., the Sun 6180 equals the IBM DS5020 Express andthe Sun 6780 equals the IBM DS5300 in performance, and so seem to be two of the samesubsystems OEMed from the same vendor (probably LSI).P.O. Box 492 Broomfield, CO 80038-0492 720-221-7270 2009 Silverton Consulting, Inc.All Rights ReservedPage 5 of 6

SPC Performance StorInt DispatchSCISPC091119-010Figure 6 SPC-2* Top 10 MB/s resultsActually the Top 11 are shown as the old (4GFC) Sun 6780/IBM 5300 results are tied forlast place here. One can see the new (8GFC) Sun 6780/IBM DS5300 showing up atpositions 5 through 7. We would have thought the 8GFC might make more of adifference with the SPC-2 throughput oriented testing but it only seemed to boost MBPSby 17% (for RAID5). From our perspective, the sad part about this chart is that therereally are only four subsystems represented here the HDS and it’s OEM, the two (LSI)OEMs, and the IBM SVC.SignificancePower use continues to gain more interest. We again applaud SPC for providing yetanother new energy benchmark. The other items of note from these results are that SSDsperform well whether FC or SAS attached and that a subsystem with only 20 SSDs (TMSRamSan-620) can easily break into the top 10 IOPS chart.As always we welcome any feedback on how to do this better. So, if you have anycomments please don’t hesitate to contact us.Silverton Consulting, Inc. is a Storage, Strategy & Systems consulting services company,based in the USA offering products and services to the data storage communityP.O. Box 492 Broomfield, CO 80038-0492 720-221-7270 2009 Silverton Consulting, Inc.All Rights ReservedPage 6 of 6