Reviews Leaderboard Database Reference Search StorageReview Discussion Reliability Survey Search About StorageReview.com Contents

Battle of the Titans: Promise SuperTrak 100 vs. 3Ware Escalade 6400


StorageReview.com PayPal Donations



Battle of the Titans: Promise SuperTrak 100 vs. 3Ware Escalade 6400
  February 14, 2001 Author: Terry Baranski  

Confused? The StorageReview.com RAID Guide explains RAID 5!


RAID 5...

Click here to jump to analysis text...

Jump To AnalysisIOMeter - File Server Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 3 Drives62.12 0.67 16.09 ms 0.76 % 81.74
Escalade 6400 RAID 5 w/ 3 Drives54.82 0.59 18.23 ms 0.69 % 79.45
Load = Very Light
SuperTrak-100 RAID 5 w/ 3 Drives62.44 0.67 64.06 ms 0.70 % 89.20
Escalade 6400 RAID 5 w/ 3 Drives98.35 1.07 40.66 ms 1.41 % 69.75
Load = Light
SuperTrak-100 RAID 5 w/ 3 Drives67.58 0.74 236.74 ms 0.78 % 86.64
Escalade 6400 RAID 5 w/ 3 Drives105.63 1.14 151.40 ms 1.49 % 70.89
Load = Moderate
SuperTrak-100 RAID 5 w/ 3 Drives73.93 0.80 865.24 ms 0.87 % 84.98
Escalade 6400 RAID 5 w/ 3 Drives112.76 1.22 567.62 ms 1.58 % 71.37
Load = Heavy
SuperTrak-100 RAID 5 w/ 3 Drives82.18 0.89 3106.98 ms 1.05 % 78.27
Escalade 6400 RAID 5 w/ 3 Drives138.97 1.50 1840.72 ms 2.37 % 58.64

Jump To AnalysisIOMeter - Workstation Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 3 Drives71.65 0.56 13.95 ms 0.71 % 100.92
Escalade 6400 RAID 5 w/ 3 Drives62.84 0.49 15.91 ms 0.75 % 83.79
Load = Very Light
SuperTrak-100 RAID 5 w/ 3 Drives72.14 0.56 55.44 ms 0.78 % 92.49
Escalade 6400 RAID 5 w/ 3 Drives112.45 0.88 35.56 ms 1.41 % 79.75
Load = Light
SuperTrak-100 RAID 5 w/ 3 Drives76.72 0.60 208.53 ms 0.86 % 89.21
Escalade 6400 RAID 5 w/ 3 Drives119.90 0.94 133.43 ms 1.73 % 69.31
Load = Moderate
SuperTrak-100 RAID 5 w/ 3 Drives83.33 0.65 767.47 ms 0.99 % 84.17
Escalade 6400 RAID 5 w/ 3 Drives127.68 1.00 501.19 ms 1.71 % 74.67
Load = Heavy
SuperTrak-100 RAID 5 w/ 3 Drives92.52 0.72 2762.13 ms 1.34 % 69.04
Escalade 6400 RAID 5 w/ 3 Drives154.92 1.21 1650.93 ms 2.72 % 56.96

Jump To AnalysisIOMeter - Database Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 3 Drives67.07 0.52 14.91 ms 0.72 % 93.15
Escalade 6400 RAID 5 w/ 3 Drives51.04 0.40 19.59 ms 0.74 % 68.97
Load = Very Light
SuperTrak-100 RAID 5 w/ 3 Drives67.01 0.52 59.68 ms 0.74 % 90.55
Escalade 6400 RAID 5 w/ 3 Drives83.21 0.65 48.06 ms 1.17 % 71.12
Load = Light
SuperTrak-100 RAID 5 w/ 3 Drives71.02 0.55 225.26 ms 0.78 % 91.05
Escalade 6400 RAID 5 w/ 3 Drives88.12 0.69 181.52 ms 1.34 % 65.76
Load = Moderate
SuperTrak-100 RAID 5 w/ 3 Drives76.78 0.60 832.94 ms 0.87 % 88.25
Escalade 6400 RAID 5 w/ 3 Drives92.54 0.72 691.97 ms 1.36 % 68.04
Load = Heavy
SuperTrak-100 RAID 5 w/ 3 Drives83.99 0.66 3042.84 ms 1.17 % 71.79
Escalade 6400 RAID 5 w/ 3 Drives113.08 0.88 2261.67 ms 2.06 % 54.89

Jump To AnalysisIOMeter - Random Write PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 3 Drives73.31 0.57 13.64 ms 0.72 % 101.82
Escalade 6400 RAID 5 w/ 3 Drives35.52 0.28 28.14 ms 0.66 % 53.82
Load = Very Light
SuperTrak-100 RAID 5 w/ 3 Drives73.26 0.57 54.60 ms 0.80 % 91.58
Escalade 6400 RAID 5 w/ 3 Drives42.22 0.33 94.72 ms 0.84 % 50.26
Load = Light
SuperTrak-100 RAID 5 w/ 3 Drives78.00 0.61 205.06 ms 0.95 % 82.11
Escalade 6400 RAID 5 w/ 3 Drives43.10 0.34 371.21 ms 0.94 % 45.85
Load = Moderate
SuperTrak-100 RAID 5 w/ 3 Drives81.60 0.64 783.68 ms 0.89 % 91.69
Escalade 6400 RAID 5 w/ 3 Drives45.90 0.36 1394.71 ms 0.98 % 46.84
Load = Heavy
SuperTrak-100 RAID 5 w/ 3 Drives86.60 0.68 2949.68 ms 1.19 % 72.77
Escalade 6400 RAID 5 w/ 3 Drives55.24 0.43 4625.33 ms 1.41 % 39.18

Jump To AnalysisIOMeter - Sequential Write PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 3 Drives27.46 6.87 36.40 ms 1.15 % 23.88
Escalade 6400 RAID 5 w/ 3 Drives14.04 3.51 71.19 ms 3.93 % 3.57
Load = Very Light
SuperTrak-100 RAID 5 w/ 3 Drives27.54 6.88 145.25 ms 1.15 % 23.95
Escalade 6400 RAID 5 w/ 3 Drives20.02 5.00 199.82 ms 6.32 % 3.17
Load = Light
SuperTrak-100 RAID 5 w/ 3 Drives27.53 6.88 581.07 ms 1.19 % 23.13
Escalade 6400 RAID 5 w/ 3 Drives18.96 4.74 843.63 ms 98.19 % 0.19
Load = Moderate
SuperTrak-100 RAID 5 w/ 3 Drives27.52 6.88 2324.42 ms 1.72 % 16.00
Escalade 6400 RAID 5 w/ 3 Drives19.10 4.77 3359.09 ms 98.58 % 0.19
Load = Heavy
SuperTrak-100 RAID 5 w/ 3 Drives26.99 6.75 8529.51 ms 1.40 % 19.28
Escalade 6400 RAID 5 w/ 3 Drives19.45 4.86 13313.50 ms 99.27 % 0.20

Jump To AnalysisIOMeter - File Server Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 4 Drives61.04 0.65 16.38 ms 0.68 % 89.76
Escalade 6400 RAID 5 w/ 4 Drives55.75 0.60 17.93 ms 0.73 % 76.37
Load = Very Light
SuperTrak-100 RAID 5 w/ 4 Drives60.88 0.66 65.69 ms 0.65 % 93.66
Escalade 6400 RAID 5 w/ 4 Drives115.98 1.25 34.48 ms 1.60 % 72.49
Load = Light
SuperTrak-100 RAID 5 w/ 4 Drives64.79 0.71 246.83 ms 0.75 % 86.39
Escalade 6400 RAID 5 w/ 4 Drives134.94 1.47 118.55 ms 1.72 % 78.45
Load = Moderate
SuperTrak-100 RAID 5 w/ 4 Drives71.59 0.77 893.39 ms 0.87 % 82.29
Escalade 6400 RAID 5 w/ 4 Drives141.66 1.53 451.68 ms 2.03 % 69.78
Load = Heavy
SuperTrak-100 RAID 5 w/ 4 Drives79.73 0.86 3203.32 ms 1.02 % 78.17
Escalade 6400 RAID 5 w/ 4 Drives175.44 1.89 1458.14 ms 2.85 % 61.56

Jump To AnalysisIOMeter - Workstation Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 4 Drives69.85 0.55 14.31 ms 0.75 % 93.13
Escalade 6400 RAID 5 w/ 4 Drives63.37 0.50 15.78 ms 0.77 % 82.30
Load = Very Light
SuperTrak-100 RAID 5 w/ 4 Drives69.91 0.55 57.21 ms 0.79 % 88.49
Escalade 6400 RAID 5 w/ 4 Drives127.75 1.00 31.31 ms 1.50 % 85.17
Load = Light
SuperTrak-100 RAID 5 w/ 4 Drives73.47 0.57 217.70 ms 0.87 % 84.45
Escalade 6400 RAID 5 w/ 4 Drives154.47 1.21 103.56 ms 1.97 % 78.41
Load = Moderate
SuperTrak-100 RAID 5 w/ 4 Drives81.03 0.63 789.16 ms 0.93 % 87.13
Escalade 6400 RAID 5 w/ 4 Drives161.40 1.26 396.77 ms 2.03 % 79.51
Load = Heavy
SuperTrak-100 RAID 5 w/ 4 Drives89.69 0.70 2847.61 ms 1.19 % 75.37
Escalade 6400 RAID 5 w/ 4 Drives196.46 1.53 1302.13 ms 3.26 % 60.26

Jump To AnalysisIOMeter - Database Access PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 4 Drives64.01 0.50 15.62 ms 0.77 % 83.13
Escalade 6400 RAID 5 w/ 4 Drives52.35 0.41 19.10 ms 0.77 % 67.99
Load = Very Light
SuperTrak-100 RAID 5 w/ 4 Drives64.25 0.50 62.26 ms 0.81 % 79.32
Escalade 6400 RAID 5 w/ 4 Drives104.08 0.81 38.43 ms 1.42 % 73.30
Load = Light
SuperTrak-100 RAID 5 w/ 4 Drives67.24 0.53 237.91 ms 0.85 % 79.11
Escalade 6400 RAID 5 w/ 4 Drives112.22 0.88 142.47 ms 1.50 % 74.81
Load = Moderate
SuperTrak-100 RAID 5 w/ 4 Drives73.19 0.57 873.73 ms 0.82 % 89.26
Escalade 6400 RAID 5 w/ 4 Drives116.31 0.91 550.18 ms 1.63 % 71.36
Load = Heavy
SuperTrak-100 RAID 5 w/ 4 Drives81.01 0.63 3153.56 ms 1.03 % 78.65
Escalade 6400 RAID 5 w/ 4 Drives142.01 1.11 1800.74 ms 2.61 % 54.41

Jump To AnalysisIOMeter - Random Write PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 4 Drives65.58 0.51 15.24 ms 0.75 % 87.44
Escalade 6400 RAID 5 w/ 4 Drives37.81 0.30 26.44 ms 0.57 % 66.33
Load = Very Light
SuperTrak-100 RAID 5 w/ 4 Drives66.01 0.52 60.59 ms 0.75 % 88.01
Escalade 6400 RAID 5 w/ 4 Drives53.79 0.42 74.35 ms 0.89 % 60.44
Load = Light
SuperTrak-100 RAID 5 w/ 4 Drives72.48 0.57 220.65 ms 0.82 % 88.39
Escalade 6400 RAID 5 w/ 4 Drives55.00 0.43 290.86 ms 1.06 % 51.89
Load = Moderate
SuperTrak-100 RAID 5 w/ 4 Drives76.85 0.60 832.34 ms 0.89 % 86.35
Escalade 6400 RAID 5 w/ 4 Drives57.61 0.45 1111.87 ms 1.16 % 49.66
Load = Heavy
SuperTrak-100 RAID 5 w/ 4 Drives81.15 0.63 3146.87 ms 1.17 % 69.36
Escalade 6400 RAID 5 w/ 4 Drives69.41 0.54 3682.43 ms 1.64 % 42.32

Jump To AnalysisIOMeter - Sequential Write PatternJump To Analysis
IOMeter TestsIO/secMB/secResponse TimeCPU Util.IO/CPU%
Load = Linear
SuperTrak-100 RAID 5 w/ 4 Drives31.43 7.86 31.80 ms 1.26 % 24.94
Escalade 6400 RAID 5 w/ 4 Drives12.48 3.12 80.11 ms 3.43 % 3.64
Load = Very Light
SuperTrak-100 RAID 5 w/ 4 Drives31.55 7.89 126.77 ms 1.34 % 23.54
Escalade 6400 RAID 5 w/ 4 Drives22.36 5.59 178.85 ms 7.06 % 3.17
Load = Light
SuperTrak-100 RAID 5 w/ 4 Drives31.53 7.88 507.29 ms 1.34 % 23.53
Escalade 6400 RAID 5 w/ 4 Drives21.51 5.38 743.58 ms 98.42 % 0.22
Load = Moderate
SuperTrak-100 RAID 5 w/ 4 Drives31.55 7.89 2028.69 ms 1.99 % 15.85
Escalade 6400 RAID 5 w/ 4 Drives21.58 5.39 2965.20 ms 98.75 % 0.22
Load = Heavy
SuperTrak-100 RAID 5 w/ 4 Drives30.65 7.66 7545.48 ms 1.74 % 17.61
Escalade 6400 RAID 5 w/ 4 Drives21.61 5.40 11725.58 ms 99.31 % 0.22

The SuperTrak's RAID 5 array performs significantly worse than a single drive. We're extremely disappointed with these numbers. It is fair to say at this point that the SuperTrak is not the card of choice for those with high performance in mind.

There's not much else to say on the matter - the SuperTrak's scores speak for themselves.

The Escalade fares better. Although the SuperTrak scores are better in the Workstation, File Server, and Database access patterns under Linear loads, the Escalade stakes out a commanding lead starting with Light loads and never looks back. The Escalade, on average, scores about 100% higher than the SuperTrak under Heavy loads.

The Escalade's write performance scores are nothing to write home about. Sequential writes clock in around 5MB/sec and random writes performance is much worse than that of even a single drive. (The SuperTrak's RAID 5 write performance isn't anything to brag about either, but remains better than the Escalade's nonetheless.)

Although its RAID 5 scores are much better than the SuperTrak's, the Escalade's 4-drive RAID 5 scores are barely better than its 2-drive RAID 0 scores, with scores actually worse in the Database, Sequential Write, and Random Write tests. While the "obvious" reason is the Escalade's lack of cache (which plays a big role in the performance of RAID levels that use parity), it's our opinion that this is simply the result of a larger issue: the Escalade was never meant for RAID 5 in the first place.

RAID 5 support for the Escalade likely came about for one reason: marketing. After the SuperTrak100's release, 3ware realized they had no RAID 5 card to market against the SuperTrak. We believe that 3ware decided to enable RAID 5 functionality on the Escalade 6400 and 6800 via firmware to solve this dilemma ASAP. Though its just a theory, the following points back it up:

  • It's hard to believe that anyone would design RAID 5 card without cache. Cache is crucial to the performance of RAID levels (such as 5) that use parity.
  • It's unlikely that the Escalade would relegate RAID 5 to a firmware-level if support had been planned all along. After all, the card implements RAID 0/1/10 at the hardware level, so RAID 5 would have been in the same boat had it been planned from the beginning.
  • If the Escalade was indeed meant for RAID 5 all along, support should have arrived much sooner, not six months after the controller's introduction.

Considering the firmware implementation, it should be no surprise that Escalade RAID 5 performs much worse than RAID 0. According to a 3ware engineer, all XOR calculations are done by the firmware itself. While the very nature of "firmware RAID" means that some potential performance is lost relative to "true" hardware RAID, one should note that the Escalade's firmware RAID 5 solidly trounces the SuperTrak's hardware implementation. This goes to show that generalizations such as "hardware RAID is superior to firmware RAID" aren't always true - performance depends mostly on the cards themselves.

 The SuperTrak`s RAID 3 WinBench 99 Performance...


HOME | ARTICLES | LEADERBOARD | PERFORMANCE DATABASE | REFERENCE GUIDE
COMMUNITY | RELIABILITY SURVEY | SUPPORT SR! | ABOUT SR |

Copyright © 1998-2005 StorageReview.com, Inc. All rights reserved.
Write: Webmaster