scottbakertemp Posted February 11, 2011 Share Posted February 11, 2011 Any way you guys could do some tests comparing file copying speeds of WHS2003 VS WHS2011 with 5400 and 7200 hard drives? Link to comment Share on other sites More sharing options...
Guest no-control Posted February 11, 2011 Share Posted February 11, 2011 Need more info like why? what is the proposed question we can test against? Technically it would be the same as it's pretty much 95%? hardware dependent. If all variables are kept the same there should be only a minor difference. For hardware: across a single drive? across a RAID? what size caches? For software from WHS to what? a client machine? across a network (jumbo frames)? within the same WHS (disk to disk)? Large file transfers? small file transfers? We would really need to set some more specific parameters to do this. Link to comment Share on other sites More sharing options...
scottbakertemp Posted February 12, 2011 Author Share Posted February 12, 2011 I was under the impression that server 2008 was much faster when copying files to the server from a client and client to server as opposed to server 2003. Maybe I misunderstood. Is that completely false? Link to comment Share on other sites More sharing options...
pcdoc Posted February 12, 2011 Share Posted February 12, 2011 I have tested most of what you are asking for so here is a summary. Remember that there are a bunch of variables such as drive type (ie, WD Caviar), size (larger drives tend to be faster) and interface. In summary, given a 1T drive 5400 green vs 7200 Caviar, you can expect the the benchmarking to go from about 70-75 mmbs to roughly 90 mbs form either 2003 or 2011 as internal drive performance is about the same between comparable machines. Network performance is a bit faster with 2011 as there is no overhead form DE so you can expect about 10-15% difference between the two. Again many things can affect network performance. As an example, using WHS V1, I average 70mbs on the network but it can dip as low as 40 and peak at 80 depneding on what DE is doing at the time. Becasuse I am running raid on my 2011, I never see it below 105 mbs. I have not tested a single drive on 2011 yet so I will post when I get results. Hope this helps. Link to comment Share on other sites More sharing options...
scottbakertemp Posted February 12, 2011 Author Share Posted February 12, 2011 thanks for the reply. Looks like it's not the amazing difference I thought it was. Link to comment Share on other sites More sharing options...
pcdoc Posted February 12, 2011 Share Posted February 12, 2011 thanks for the reply. Looks like it's not the amazing difference I thought it was. Depending on hardware it could be but for the most part no. The most performance I got was going from V1 to 2011 using RAID. That is noticiable. Link to comment Share on other sites More sharing options...
kermi Posted February 12, 2011 Share Posted February 12, 2011 Depending on hardware it could be but for the most part no. The most performance I got was going from V1 to 2011 using RAID. That is noticiable. Actually that's not entirely true. There is signigicant improvements in SMB performance between 2003 and 2008. Link to comment Share on other sites More sharing options...
usacomp2k3 Posted February 13, 2011 Share Posted February 13, 2011 There is signigicant improvements in SMB performance between 2003 and 2008. That's what I was going to say. I think the BYOB guys mentioned something about that. SMB2 was released with Vista and Server 2008 and SMB2.1 for Win7 & Server 2008 R2. content... Might want to specify between MB/sec and mb/sec. Significant difference between the 2. Link to comment Share on other sites More sharing options...
pcdoc Posted February 14, 2011 Share Posted February 14, 2011 Actually that's not entirely true. There is signigicant improvements in SMB performance between 2003 and 2008. True but it it does not seem to manifest in eveyday file transfers. I realize that 2008 is technically superior but when I use standard windows file copy to perform my testing and that is the result I got. I still saw a 20+% gain from one to the other but I believe most was attributed to DE and there is an overhead penalty. If you have a more accurate way to measure the difference, let me know and I can reproduce it. Link to comment Share on other sites More sharing options...
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now