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.
Comments
the server is now being rsync-ed between two servers of online.net (80% so far), this is benchmark result:
I imagine running a download test will not even make one core sweat.
Both servers have hardware raid0 with 512mb cache?
because dd is stupid test that show which server got bigger BBUC/FBWC/Cachecade
if you do the test wit centos7 XFS will additionally shows better speeds (for what i see up to 600+ MB)
You should use old technology and disable raid controller cache if you want to relay dd (which sows how stupid is dd
difference between SAS and SATA is a lot more noticeable in possible iops especially when cache is full
P.S Is some one check models of the disks are they Constelation.3 ? If remember that what and sequential write if remeber correct of that drive is rated for 180MB/s so with 512MB FBWC it will be fast for the part of the test
Well, that's good for the download test. The test also involves a IO test. And there may be other benchmark tests people are interested in, unaware of the governor settings. My suggestion was, if you want to do benchmark tests, also pay attention to the governor and choose performance to minimize latency-related delays.
1215 is with 256 MB and he is doing dd were disk i suppose 3815 use is rated as fast as sas drives ... additionally constellation.3 has it own 128MB which is enabled (it a dd junkie dream )
So what's the one-liner (or similar) you suggest?
Just use a higher value for dd, like 4G or so, it will negate the effect of these small 128-256 MB caches.
Got 2 of the 2 x 2TB servers.
Plan is to replace my previous 2 x 600GB server (http://www.lowendtalk.com/discussion/48468/online-net-new-promo-e3-1240v3-32g-2x600sas-29-99eur-no-setup-fee), as far as I can tell, the only difference (besides the drives) is the 1230v3 instead of the 1240v3, and I don't think that will make much of a difference to me.
No much different, i have both server. And i love 2x2tb for video encoding and torrent
Thanks.
Would use this for backups and multiple VMs, but the additional space will really help.
Got two IDLE server as my friend cancelled the request. 55 eur for two. If somebody interested just PM
How much slower are HDDs vs SAS Drives? To this guys who have both the SAS 1240 and the HDD 1230 Version or others that can answer.
wow it took over 4.5 hours for the installation to complete ... but its working now
Mine just 30 minutes. and ready to go
How can I see SMART information for each disk under raid 1?
Try this: http://www.lowendtalk.com/discussion/comment/971754/#Comment_971754
That unfortunately does not show too much information:
Or maybe my smartmontools version is too old. (5.41)
SSD are very fast.
SATA is Old
@notgod: do you have some io results.
I am deeply impressed by your expertise. ;-)
Yes definitely try upgrading.
Maybe because 3815 is SATA3 and 1215 is not?
Harddisk quality changes as well as the interface.
Two 3915 tests I did (same server):
http://serverbear.com/benchmark/2015/09/30/EZR4g4goA04mfPaR
http://serverbear.com/benchmark/2015/09/30/g5sXxUI7gMb2wmAV
hdd raid 1
can someone do a benchmark please? download from http://www.primatelabs.com/geekbench/
Model: ATA MB2000GCWDA is an expensive drive
http://www.amazon.co.uk/MB2000GCWDA-2TB-7-2K-MDL-SATA/dp/B00V4BKXO2
http://www.discountmicrosales.com/mb2000gcwda.html
Unix Bench results (SSD version, RAID1)
Geekbench 3 64bit
http://browser.primatelabs.com/geekbench3/3634497
ServerBear: