Search results

Do you want my "Imitation Atto" IOmeter .icf file to test with?

Gear:8 x Samsung Spinpoint F2EG HD154UI 1.5TB 5400 RPM 32MB cache Dell Perc 6/i PCI-E x8 SAS RAID controller with 256MB cache & battery 2 x 32pin SAS to 4 SATA cables The array is a single RAID-6 volume with a 512k size stripe. 8 x 1.5TB Perc 6/i RAID-6 Array IOmeter benchmark (ATTO...

I'm sure the water wasn't clean either... I'd say they're very likely toast unless you send them to a data recovery place, and even they might not be able to save them. Powering them on will probably eliminate the option of later data recovery by further damaging them, so unless professional...

Here's the ATTO style benchmark (from IOmeter) of my 8 x 1.5TB RAID-6 array on a Perc 6/i. It's slower than the 6 x 1.5TB RAID-5 array on a Perc 5/i with .5K, 1K, and 2K reads, but is faster everywhere else (look at the numbers, not the length of the bars). 8 x 1.5TB RAID-6 array (Perc 6/i)...

The CF to ExpressCard readers? I'd take a look at this article.

I realize it none of my business, that I don't know the nature of your relationship with Frodo, and you don't know if I know what I'm talking about, but... I think you're planning to come on a bit too strong. I'm not saying you should pull a full out Deacon on her, but I'd recommend keeping...

That's possibly an option... I tried to use larger files to avoid any sort of caching taking place. Two systems have 4GB of RAM, and the other 2GB of RAM. If you've got files that fit in a RAMdrive they might also be small enough to be mostly cached. I'm not really sure if Windows caches...

I didn't try that. It'll have to wait until my new RAID array is up and running before I can resume benchmarking though.

I'd try all the old stuff with the new motherboard you get from Gigabyte and file their idea of RMA'ing everything in the garbage can. I would Memtest86+ / Goldmemory the heck out of the system though. FWIW, I've found that Goldmemory is more effective than Memtest86+ at finding bad RAM though.

I'm still not so sure about that. Per Intel: Link Aggregation The combining of multiple adapters into a single channel to provide greater bandwidth. Bandwidth increase is only available when connecting to multiple destination addresses. ALB mode provides aggregation for transmission only while...

FWIW, the guys on the Hardforum tell me this won't work for host to host and that teaming / link aggregation / trunking is only useful for increasing BW in a one to many or a many to one situation.

I have to suffer at work on a regular basis trying to copy files over Windows network shares extended through a VPN over a WAN link. It can take over 1 hour to move 150MB of data with a 7Mbit/sec download speed. :cursin:

I looked at what that tool changes. It's mostly targeted at broadband optimization. It uses TCP window manipulation (which I did) and some other things to deal with latency (which I don't have on a gigabit switched network).

The main server has a RAID-5 array capable of reading and writing 300+ MB/sec. The other server had a RAID-5 array capable of 150+MB/sec reads and slower writes (but still faster than what was measured). My desktop PC used a mostly empty 1.5TB Seagate 7200.11's that can push >110MB/sec at the...

The posters on Hardforum all pushed Teracopy. I tried it and was underwhelmed. Windows Explorer Copy: (from before) Server2 push to Server1 - 59.14MB/sec Server2 pull from Server1 - 47.51MB/sec Teracopy 2.06beta: Server2 push to Server1 - 42.93MB/sec Server2 pull from Server1 - 32.78MB/sec

That's where ebay and working pulls come in handy. :sunny:

It's the latency that's the killer, not the speed. You'll find out soon enough. :nono:

Keep in mind SMB and WAN connections don't get along very well together, so windows file sharing will be horrifically slow (close to completely unusable) for the remote people.

Why didn't you go quad port? That solution doesn't really work for me. I don't have any free PCIe x4 or wider slots that I want to devote for a NIC in my server, though it has dual Realtek 8111C NiC's on-board. My backup server doesn't have any PCIe slots. I'm not sure what's out there in...

I tested with my desktop and my main server and got the following results: Baseline: Push to Server - 66.07MB/sec Pull from Desktop - 51.72MB/sec Pull from Server - 59.34MB/sec Push to Desktop - 22.73MB/sec Tweaked: Push to Server - 65.30MB/sec Pull from Desktop - 51.72MB/sec Pull from...

A lot of cars turn off the interior lights if you leave them on after say 30 minutes. I thought that was a standard feature since the mid 90's on most cars.

Well the results so far are, no you can't really speed up WFS with TCP tuning. I benchmarked a file copy between my two servers with and without the following registry tweaks. [HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Services\Tcpip\Parameters] "TcpWindowSize"=dword:00080000...

Judging from this morning's spam I guess no changes have been made yet.

Without any tweaks, here are the numbers back from iperf run this way: iperf.exe -c 192.168.1.151 -r -t 30 -w xxxxx 4k window: c: 352 gbit/sec s: 493 gbit/sec 8k window: c: 352 gbit/sec s: 493 gbit/sec 16k window: c: 401 gbit/sec s: 670 gbit/sec 32k window: c: 884 gbit/sec s: 926 gbit/sec...

I assume that's a joke... :scratch:

I see up to ~45MB/sec file transfers. My buddy who's really networking savvy tells me that's about the limit for Windows file sharing, and that a more efficient protocol is needed to get better speed. He tells me FTP is good for ~90MB/sec.

Does anyone know if these TCP tweaks for Windows XP and Server 2003 (aka XP x64) actually speed up file transfers using Windows file sharing? I can't find any benchmarks showing what improvement occurs by increasing the window size or any suggested values for gigabit ethernet. Am I wasting my...

Yeah, but there's a huge contingent looking for the look of their incandescent flashlights in there likely throwing off the results. The 5A bin is nice outside, but horrible inside IMHO.

It looks like some sort of DB cable.

Well, I bought a used Intel Pro/1000 PT Server Adapter off ebay and a new Intel Gigabit CT Desktop Adapter to do some testing with. I did a little experimenting with iPerf today and I was surprised at how high the CPU usage was with the on-board Realtek 8111C [PCIe] ~48% (server) / ~67%...

ExpressCard is just USB 2.0 + PCIe x1, so adding one to a desktop should be pretty straight forward. I found a few via Google. http://www.amtron.com/reader/pcie101.htm http://www.amtron.com/expresscard/exp54cdf.htm

I guess I will do some benchmarks with the Intel NAS Performance Toolkit and see what shakes out. I have some PCI Intel Pro/1000 MT cards I can benchmark against the PCIe Realtek's.

I think every gigabit NiC supports jumbo frames now days. However, I can't use them because I have a few 100Mbit/sec devices and one 10Mbit/sec device on the network that of course don't support jumbo frames. I tried using VLANs and creating a gigbit only jumbo frame supporting VLAN, but...

I have a 24 port 3com ProCurve 1800-24 (gigabit) in the basement and haven't had any issues with the Realtek 8111B / 8111C's on my mobos connecting at less than 1000Mbit/sec and based on the transfer speeds they really run at 1000Mbit/sec in real use. I did see a little quirkiness with one of...

Anyone have an opinion on PCIe x1 gigabit Ethernet cards? Some people on another forum swore that a good NiC like a gigabit Intel add in card (even an older PCI one) offer better performance than the cheapo Realtek stuff found soldered onto motherboards (even though the Realtek's are PCIe x1)...

Well, the Perc 5/i has been replaced by a Perc 6/i. :erm: I've also ordered two more 1.5TB 5400RPM Samsung drives. I will end up running 8 x 1.5GB + Perc 6/i + RAID-6. :bomb: I just don't know when to stop. :rotfl: However, without a port multiplier (which costs a lot more than the used Perc...

There's a guy with almost 33k in less than 3. :eekers:

You must not get out very much. :sunny: link

My wife and I bought a GE high efficiency top loader two years ago when we bought out house. I don't have any complaints.

You know the expression. If you have to ask...

FWIW, I compared the Non-recoverable Error Rate of various modern SATA drives. The WD Caviar Black drives are rated <1 in 10^14 bits read. Seagate's consumer drives are all rated 1 in 10^14 bits read. WD's Caviar Green drives are all rated <1 in 10^15 bits read as are their Caviar Blue...

Reportedly it's backwards compatible.

Can you boot from FC over IP?

The S90 looks better at high ISO than I would have expected, and worse at low ISO than I would have expected. There seems to be good detail, but the noise in flat areas at low ISO is somewhat surprising.

Maybe, but I wouldn't bet on it. Windows file sharing is a huge bottle neck on GigE. I shudder to think what it would do on 10 GigE. FC has no such bottleneck. Intel doesn't support XP for their 10 GigE cards (not sure about others). Ethernet and FC can do similar things, but FC has some...

I only suggested it. ;) FWIW, my buddy has a full FC setup in his house. He's running a SAN with 48 SAS 15k RPM drives on a Dell Perc 6/i using Server 2003. Apparently he bought all the FC stuff on ebay (used) pretty cheap. He gets insane performance and has no disks in any of his workstations.

Why didn't you use something like 4GB Fiber Channel instead? :-?

I'm pretty sure he said he used a 24 port Areca.

Slow down there. You're getting out of control man! :nono:

Good luck with the building code on that one. :aok: