SCI 29Jan2015 Latest ESRP (Exchange 2013) performance results analysis

In ESRP, ESRP v3/Exchange 2010, ESRP v4/Exchange 2013, ETERNUS DX200 S3, ETERNUS DX600 S3, Fujitsu, HPE D6000, HPE P2000 G3 MSA, HPE ProLiant DL380p G8, HPE Proliant SL450 G8by AdministratorLeave a Comment

This Storage Intelligence (StorInt™) dispatch covers Microsoft Exchange 2010 (E2010) and Exchange 2013 (E2013) Solution Review Program (ESRP) results.[1] Since we last reviewed this 1001 to 5000-mailbox category nine months ago, there have been at least eight new submissions, three from HP (Proliant DL380p Gen 8, Proliant SL4540 Gen 8, & D6000 Disk enclosure), two from Dell (Compellent SC4020 v6.5 & EqualLogic PS 6210E), two from Fujitsu (ETERNUS DX200 S3 & ETERNUS DX600 S3) and one from IBM (Storwize V7000 Gen 2). Given the amount of new submissions, many of Top 10 charts have new results. We present some highlights below.

Latest ESRP V3.0 & 4.0 (E2010&E2013) performance

In Figure 1 we show our top ten normalized database transfers per second results

SCIESRP150129-001Figure 1 SCI’s top 10 ESRP normalized database transfers per second

Two of the new results landed in the top ten in normalized database transfers per second. Specifically #3 HP Proliant SL4540 Gen 8 with 2.5K mailboxes and #8 HP D6000 Disk Enclosure with 5K mailboxes driven by a BL640c Gen 8 blade server. Recall that our “normalized” results are actual results divided by the number of 1000 mailboxes in a submission. We feel normalized results show better performance comparisons than actual results due to the increase in activity associated with each mailbox.

All the new results and the rest of the top #2-10 normalized DB xfer submissions can’t seem to stand up to the #1 HP StorageWorks P2000 Gen 3 SAS MSA solution, which is a rather old submission (E2010) but still towers over all the other results by a wide and seemingly unapproachable margin.

Next we discuss the average time it takes to playback log files in Figure 2.

SCIESRP150129-002Figure 2 Top 10 average time to playback 1-1MB log file

Smaller is better on ESRP log playback time which is calculated as the average time required to play back 1MB log files under a specified database workload. As such, it is not that dependent on mailbox counts, IO rates or other factors that typically confound other ESRP performance metrics, which is why we like it so much. The only new result on this chart is at #9, the HP Prolient DL380p Gen 8. It’s somewhat amusing that the top 3 log-playback results were all HP StorageWorks P2000 Gen 3 MSA solutions using iSCSI, FC and SAS storage connections respectively.

Next we discuss another of our favorite ESRP metrics, total database backup throughput Figure 3.

Figure 3 Top 10 ESRP total database backup throughput resultsSCIESRP150129-003

In Figure 3, we have five new submissions #1-3 (HP Prolient DL380P Gen 8, HP Proliant SL4540 Gen 8, & HP D6000 Disk Enclosure) and at #9-10 (Fujitsu ETERNUS DX200 S3 and Fujitsu ETERNUS DX600 S3). I had to almost double the scale to accommodate the new top 3 entries.

Recall, that ESRP reports average backup throughput per database and for servers but not for storage systems. We compute our total backup throughput for the whole storage system as it presents a better overall view of storage system backup performance than either of the two ESRP reported backup metrics. Moreover, similar to log playback above, the total database throughput is somewhat immune to factors that confound other ESRP performance metrics, as it’s as fast as a system can backup Exchange databases under a standard database load.

Note that none of the HP P2000 Gen 3 MSA systems placed in top ten in database backup.

Finally, in Figure 4 we show the top ten database transfers per second per disk drive.

SCIESRP150129-004Figure 4 Top 10 ESRP Database transfers per second per disk drive

In Figure 4, we see the two new Fujitsu systems at #3 and #9, the ETERNUS DX600 S3 and ETERNUS DX200 S3 respectively and at fifth place the HP Proliant DL380p Gen 8. Recall that database transfers/sec/spindle ignores any results that report NAND/SSD use in the controller or backend storage, so this chart includes disk-only storage systems. We don’t use mailbox count normalized data base transfers here because the activity is normalized by disk drives instead. Our assumption is that larger mailbox counts would result in more disk drives but this is somewhat confounded by the fact that mailbox size can vary across ESRP submissions.

Summary

There were a lot of new submissions in this 1001 to 5000 mailbox category, which produced some interesting new results. There were other changes to top 10 charts but we believe the above are a good representation of the true storage system performance under Exchange simulated workloads.

If you are interested in even more information on block storage performance please checkout our SAN Storage Buying Guide available for purchase on our website, which includes ChampionCharts™ for OLTP, Throughput and Email workloads across enterprise, mid-range and SMB storage systems. Use the QR code below left for more information on the SAN Storage Buying Guide. We also provide some additional ESRP results analysis in our SAN-NAS Buying Guide also available on our website.

Any constructive criticisms on how to improve our analyses for any of our performance reports are always welcome. Moreover, if you detect errors in this or any other of our performance reports please do let us know and we will correct it as soon as possible.

[Also we offer more block storage performance information plus our OLTP, Email and Throughput ChampionsCharts™ charts in our recently updated (May 2019) SAN Storage Buying Guide, or for more information on some select ESRP performance results please see our recently updated (May 2019) SAN-NAS Storage Buying Guide, both of which are available for purchase on our website.]

[This performance dispatch was originally sent out to our newsletter subscribers in January of 2014.  If you would like to receive this information via email please consider signing up for our free monthly newsletter (see subscription request, above right) and we will send our current issue along with download instructions for this and other reports. Dispatches are posted to our website at least a quarter or more after they are sent to our subscribers, so if you are interested in current results please consider signing up for our newsletter.]  

Silverton Consulting, Inc., is a U.S.-based Storage, Strategy & Systems consulting firm offering products and services to the data storage community

[1] ESRP results from http://technet.microsoft.com/en-us/exchange/ff182054.aspx, as of 26Jan2015

Leave a Reply