DRDB
2 x Intel Xeon E5606 testing with a Dell 00NH4P and Matrox MGA G200eW WPCM450 on Linux via the Phoronix Test Suite.


Using both nodes: 

	Processor: 2 x Intel Xeon E5606 @ 2.13GHz (8 Cores), Motherboard: Dell 00NH4P, Chipset: Intel 5520 I/O + ICH9, Memory: 24576MB, Disk: 67GB PERC H700 + 1933GB PERC H700, Graphics: Matrox MGA G200eW WPCM450, Network: Broadcom NetXtreme II BCM5709 Gigabit

	OS: Linux, Kernel: 2.6.32-5-amd64 (x86_64), Display Driver: matrox, Compiler: GCC 4.4.5, File-System: ext4

Failed to one node: 

	Processor: 2 x Intel Xeon E5606 @ 2.13GHz (8 Cores), Motherboard: Dell 00NH4P, Chipset: Intel 5520 I/O + ICH9, Memory: 24576MB, Disk: 67GB PERC H700 + 1933GB PERC H700, Graphics: Matrox MGA G200eW WPCM450, Network: Broadcom NetXtreme II BCM5709 Gigabit

	OS: Linux, Kernel: 2.6.32-5-amd64 (x86_64), Display Driver: matrox, Compiler: GCC 4.4.5, File-System: ext4


Gzip Compression
2GB File Compression
Seconds < Lower Is Better
Using both nodes ... 20.62 |===================================================
Failed to one node . 20.72 |===================================================


SQLite 3.7.3
12,500 INSERTs
Seconds < Lower Is Better
Using both nodes ... 45.68 |===================================================
Failed to one node . 8.10  |=========


Apache Benchmark 2.2.17
Static Web Page Serving
Requests Per Second > Higher Is Better
Using both nodes ... 15461.32 |================================================
Failed to one node . 15308.39 |================================================


PostgreSQL pgbench 9.0.4
TPC-B Transactions Per Second
TPS > Higher Is Better
Using both nodes ... 2424.24 |=============================================
Failed to one node . 2665.38 |=================================================


Compile Bench 0.6
Test: Initial Create
MB/s > Higher Is Better
Using both nodes ... 131.19 |================================================
Failed to one node . 136.72 |==================================================


Compile Bench 0.6
Test: Compile
MB/s > Higher Is Better
Using both nodes ... 581.72 |==============================================
Failed to one node . 637.73 |==================================================


Compile Bench 0.6
Test: Read Compiled Tree
MB/s > Higher Is Better
Using both nodes ... 851.59 |================================================
Failed to one node . 882.45 |==================================================


IOzone 3.347
8GB Write Performance
MB/s > Higher Is Better
Using both nodes ... 162.44 |========================
Failed to one node . 344.31 |==================================================


IOzone 3.347
8GB Read Performance
MB/s > Higher Is Better
Using both nodes ... 4350.31 |=================================================
Failed to one node . 4141.64 |===============================================


Dbench 4.0
1 Clients
MB/s > Higher Is Better
Using both nodes ... 138.20 |===================
Failed to one node . 366.02 |==================================================


Dbench 4.0
12 Clients
MB/s > Higher Is Better
Using both nodes ... 554.32  |===============
Failed to one node . 1828.30 |=================================================


Dbench 4.0
48 Clients
MB/s > Higher Is Better
Using both nodes ... 1004.65 |======================
Failed to one node . 2209.23 |=================================================


Dbench 4.0
128 Clients
MB/s > Higher Is Better
Using both nodes ... 1062.24 |==============================
Failed to one node . 1737.41 |=================================================


FS-Mark 3.3
1000 Files, 1MB Size
Files/s > Higher Is Better
Using both nodes ... 61.90  |===============
Failed to one node . 204.48 |==================================================


Flexible IO Tester 1.57
Intel IOMeter File Server Access Pattern
Seconds (Run Time) < Lower Is Better
Using both nodes ... 3673.70 |=================================================
Failed to one node . 3708.43 |=================================================


Threaded I/O Tester 0.3.3
64MB Random Read - 32 Threads
MB/s > Higher Is Better
Using both nodes ... 12636.76 |===============================================
Failed to one node . 12915.44 |================================================


Threaded I/O Tester 0.3.3
64MB Random Write - 32 Threads
MB/s > Higher Is Better
Using both nodes ... 2.10 |====================================================
Failed to one node . 2.11 |====================================================


PostMark 1.51
Disk Transaction Performance
TPS > Higher Is Better
Using both nodes ... 2812 |=================================================
Failed to one node . 2986 |====================================================


AIO-Stress 0.21
Random Write
MB/s > Higher Is Better
Using both nodes ... 1672.93 |=================================================
Failed to one node . 1677.64 |=================================================


Unpacking The Linux Kernel
linux-2.6.32.tar.bz2
Seconds < Lower Is Better
Using both nodes ... 17.03 |===================================================
Failed to one node . 16.88 |===================================================