New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
DataShack - Dual Xeon 5462 Benchmark
serverbear
Member
Hey guys, I know there's been a lot of argument about what constitutes a low end Dedi. As mentioned in previous posts I've been wanting to migrate a heap of stuff off Linode for ages, I've been keeping an eye on DataShack & found a pretty nice deal that I thought I'd grab.
Dual Intel Xeon 5462
8 Cores / 8 Threads
8GB DDR2 ECC RAM
500GB HDD
20TB Bandwidth
Order link: https://www.datashack.net/cart/?id=182
Use the coupon SAVE15 to get this config for $74/month
The benchmark below I replaced the main HDD for a 128GB SSD & am using the HDD as a storage drive (they seem to be out of stock of SSD's now though).
Intel(R) Xeon(R) CPU E5462 @ 2.80GHz
Benchmark Run: Fri Sep 28 2012 17:12:40 - 17:40:52 8 CPUs in system; running 8 parallel copies of tests Dhrystone 2 using register variables 220382276.2 lps (10.0 s, 7 samples) Double-Precision Whetstone 25872.9 MWIPS (9.9 s, 7 samples) Execl Throughput 19500.9 lps (30.0 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 619741.4 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 183077.5 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 1400791.0 KBps (30.0 s, 2 samples) Pipe Throughput 12119978.5 lps (10.0 s, 7 samples) Pipe-based Context Switching 2144836.4 lps (10.0 s, 7 samples) Process Creation 46361.9 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 41825.3 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 5910.4 lpm (60.0 s, 2 samples) System Call Overhead 2699487.0 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 220382276.2 18884.5 Double-Precision Whetstone 55.0 25872.9 4704.2 Execl Throughput 43.0 19500.9 4535.1 File Copy 1024 bufsize 2000 maxblocks 3960.0 619741.4 1565.0 File Copy 256 bufsize 500 maxblocks 1655.0 183077.5 1106.2 File Copy 4096 bufsize 8000 maxblocks 5800.0 1400791.0 2415.2 Pipe Throughput 12440.0 12119978.5 9742.7 Pipe-based Context Switching 4000.0 2144836.4 5362.1 Process Creation 126.0 46361.9 3679.5 Shell Scripts (1 concurrent) 42.4 41825.3 9864.5 Shell Scripts (8 concurrent) 6.0 5910.4 9850.6 System Call Overhead 15000.0 2699487.0 1799.7 ======== System Benchmarks Index Score 4426.7
ioping -c 10 request=1 time=0.2 ms request=2 time=0.2 ms request=3 time=0.2 ms request=4 time=0.2 ms request=5 time=0.2 ms request=6 time=0.2 ms request=7 time=0.2 ms request=8 time=0.2 ms request=9 time=0.2 ms request=10 time=0.2 ms 10 requests completed in 9003.0 ms, 4560 iops, 17.8 mb/s ioping -RD 4455 iops, 17.4 mb/s min/avg/max/mdev = 0.2/0.2/0.3/0.0 ms
dd if=/dev/zero of=sb-io-test bs=1M count=1k conv=fdatasync 6.00609 s, 179 MB/s dd if=/dev/zero of=sb-io-test bs=64k count=16k conv=fdatasync 7.60696 s, 141 MB/s
Cachefly 58.8 MB/s Linode, Atlanta, GA, USA 4.26 MB/s Linode, Dallas, TX, USA 17.9 MB/s Linode, Tokyo, JP 8.31 MB/s Linode, London, UK 6.12 MB/s OVH, Paris, France 11.7 MB/s SmartDC, Rotterdam, Netherlands 17.3 MB/s Hetzner, Nuremberg, Germany 14.2 MB/s iiNet, Perth, WA, Australia 7.79 MB/s Leaseweb, Haarlem, NL, USA 16.8 MB/s Softlayer, Singapore 7.87 MB/s Softlayer, Seattle, WA, USA 14.5 MB/s Softlayer, San Jose, CA, USA 30.8 MB/s Softlayer, Washington, DC, USA 27.3 MB/s
Pretty happy with the network too.
Comments
@serverbear Single HDD? No RAID1 at least?
I just noticed they have E3s, My day has just been completed but not sure how I would go about asking them to upgrade all nodes.
only 500GB HDD
Sounds like a pretty good deal.
BTW what does it mean by /29 /28 /27 ips etc etc.how many ips exactly are those?
/29 - 8 IPs, 5 usable
/28 - 16 IPs, 13 usable
/27 - 32 IPs, 29 usable
Thanks guys. So /26 - 64 ips, 61 usable?
@cosmicgate That's right. You need to loose 3 IPs in order to be able to use the block. The smaller the block, the bigger the waste.
/small rant: I find it ridiculous that some data centers still try to force a /29 block on you, despite the fact that a bigger single block is all you need. I actually like to be considerate about IPv4 usage / waste.