More on CPU specs of the ReadyNAS Pro

[MikeMcr1]

Hmm, I notice Intel has confused matters by replacing the E6600 with another E6600 that runs at 3.06 GHz! It uses a smaller die size of 45 nm.

http://ark.intel.com/Compare.aspx?ids=42807,27250,

Since it shares the same name, would you expect it to be as compatible as the "old" 2.40 GHz E6600?

[super_poussin]

my unit with stock cpu

Skywalker:/Develop/CACTIv2# iperf -s
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
[ 4] local 192.168.101.21 port 5001 connected with 192.168.101.69 port 4890
[ 4] 0.0-10.0 sec 286 MBytes 239 Mbits/sec


Skywalker:/Develop/CACTIv2# hdparm -t -T /dev/c/c

/dev/c/c:
Timing cached reads: 2124 MB in 2.00 seconds = 1061.85 MB/sec
Timing buffered disk reads: 614 MB in 3.01 seconds = 204.26 MB/sec

[beisser1]

super-poussin wrote:

my unit with stock cpu Skywalker:/Develop/CACTIv2# iperf -s ------------------------------------------------------------ Server listening on TCP port 5001 TCP window size: 85.3 KByte (default) ------------------------------------------------------------ [ 4] local 192.168.101.21 port 5001 connected with 192.168.101.69 port 4890 [ 4] 0.0-10.0 sec 286 MBytes 239 Mbits/sec Skywalker:/Develop/CACTIv2# hdparm -t -T /dev/c/c /dev/c/c: Timing cached reads: 2124 MB in 2.00 seconds = 1061.85 MB/sec Timing buffered disk reads: 614 MB in 3.01 seconds = 204.26 MB/sec

thats like uber slow.

here are my results:

ReadyNAS-Pro:~# iperf -s
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
[  4] local 192.168.0.111 port 5001 connected with 192.168.0.91 port 49599
[  5] local 192.168.0.111 port 5001 connected with 192.168.0.91 port 49600
[  6] local 192.168.0.111 port 5001 connected with 192.168.0.91 port 49601
[  7] local 192.168.0.111 port 5001 connected with 192.168.0.91 port 49602
[  7]  0.0-10.0 sec    262 MBytes    220 Mbits/sec
[  4]  0.0-10.0 sec    283 MBytes    237 Mbits/sec
[  5]  0.0-10.0 sec    279 MBytes    234 Mbits/sec
[  6]  0.0-10.0 sec    280 MBytes    235 Mbits/sec
[SUM]  0.0-10.0 sec  1.08 GBytes    926 Mbits/sec

ReadyNAS-Pro:~# hdparm -t -T /dev/c/c

/dev/c/c:
 Timing cached reads:   1724 MB in  2.00 seconds = 862.13 MB/sec
 Timing buffered disk reads:  730 MB in  3.00 seconds = 243.30 MB/sec
ReadyNAS-Pro:~# hdparm -t -T /dev/c/c

my iperf is probably faster because i used the option -P4 which spawns 4 parallel streams instead of just one.

i havent got a clue why the hdparm speeds differ so much from yours though.

[super_poussin]

Hi Beisser

which teaming mode are you using ?

[super_poussin]

ftom nas to nas :

jedi:~# iperf -c 192.168.101.21 -P4
------------------------------------------------------------
Client connecting to 192.168.101.21, TCP port 5001
TCP window size: 73.0 KByte (default)
------------------------------------------------------------
[ 6] local 192.168.101.50 port 55057 connected with 192.168.101.21 port 5001
[ 4] local 192.168.101.50 port 55055 connected with 192.168.101.21 port 5001
[ 3] local 192.168.101.50 port 55054 connected with 192.168.101.21 port 5001
[ 5] local 192.168.101.50 port 55056 connected with 192.168.101.21 port 5001
[ 5] 0.0-10.0 sec 395 MBytes 331 Mbits/sec
[ 3] 0.0-10.0 sec 343 MBytes 287 Mbits/sec
[ 6] 0.0-10.0 sec 281 MBytes 235 Mbits/sec
[ 4] 0.0-10.1 sec 173 MBytes 145 Mbits/sec
[SUM] 0.0-10.1 sec 1.16 GBytes 994 Mbits/sec
jedi:~#

[super_poussin]

changing the cpu

jedi:~# iperf -c 192.168.101.21 -P4
------------------------------------------------------------
Client connecting to 192.168.101.21, TCP port 5001
TCP window size: 73.0 KByte (default)
------------------------------------------------------------
[ 6] local 192.168.101.50 port 43391 connected with 192.168.101.21 port 5001
[ 3] local 192.168.101.50 port 43388 connected with 192.168.101.21 port 5001
[ 4] local 192.168.101.50 port 43389 connected with 192.168.101.21 port 5001
[ 5] local 192.168.101.50 port 43390 connected with 192.168.101.21 port 5001
[ 5] 0.0-10.0 sec 476 MBytes 398 Mbits/sec
[ 4] 0.0-10.1 sec 52.3 MBytes 43.5 Mbits/sec
[ 6] 0.0-10.1 sec 454 MBytes 377 Mbits/sec
[ 3] 0.0-10.3 sec 251 MBytes 205 Mbits/sec
[SUM] 0.0-10.3 sec 1.20 GBytes 1.01 Gbits/sec

Skywalker:~# hdparm -t -T /dev/c/c

/dev/c/c:
Timing cached reads: 7370 MB in 2.00 seconds = 3690.37 MB/sec
Timing buffered disk reads: 710 MB in 3.00 seconds = 236.50 MB/sec
Skywalker:~#

Skywalker:~# cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 15
model name : Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz
stepping : 6
cpu MHz : 2394.000
cache size : 4096 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 2
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 10
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflus h dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_g ood pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm tpr_shadow
bogomips : 4788.16
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:

processor : 1
vendor_id : GenuineIntel
cpu family : 6
model : 15
model name : Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz
stepping : 6
cpu MHz : 2394.000
cache size : 4096 KB
physical id : 0
siblings : 2
core id : 1
cpu cores : 2
apicid : 1
initial apicid : 1
fpu : yes
fpu_exception : yes
cpuid level : 10
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflus h dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_g ood pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm tpr_shadow
bogomips : 8616.90
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:

[MacManiak]

Hello.

More info : http://processorfinder.intel.com/detail ... Spec=SL9S8 🙂

[mrwizardno2]

So I decided to upgrade my ReadyNAS Pro's CPU tonight and when I went to loosen the CPU heatsink, one of the screws snapped off in the mount. The mounts look permanent. Thoughts on how I can rectify this problem? I checked out those screw grabbers at Lowes, but they're huge and meant for large screws. The screw looks to have loc-tite or something similar around it! I thought that was strange. Anyway...

So, am I "screwed?"

[chirpa]

mrwizardno2 wrote:
So I decided to upgrade my ReadyNAS Pro's CPU tonight and when I went to loosen the CPU heatsink, one of the screws snapped off in the mount.

Can you take a picture of it?

Best I can do to help you, is get you a replacement heatsink, if that is all thats broken. I replaced a CPU the other day in a Pro, so I have a spare heatsink by lucky chance.

[mrwizardno2]

chirpa wrote:
Best I can do to help you, is get you a replacement heatsink, if that is all thats broken. I replaced a CPU the other day in a Pro, so I have a spare heatsink by lucky chance.

Chirpa, unfortunately it goes beyond the heatsink 😞

Here's the area beneath where the CPU is where the heatsink would mount over if the motherboard was in place


Here's the mounting standoff that has the broken screw (the same that sticks up in the picture you posted) inside. I tried slotting what was left of the screw, but it was so weak it twisted away to nothingness when I tried to turn it with a screwdriver.



This is baaaaad. The mount is pretty well useless with a screw stuck in it. Can't put the cooler back on the board at this point. Would you guys be willing to sell me a case with nothing in it? Just the bare metal - I don't know what else is going to work at this point because there is no way to replace the standoff / mount because it looks like it is part of the disk assembly below.

[chirpa]

I'll check into what spare parts we have and get back to you.

[chirpa]

Was able to source an empty chassis from one of the hardware guys. Checking into what the cost would be to send it to you, will update you shortly. Will be a fun weekend project swapping all the guts over 🙂

[mrwizardno2]

chirpa wrote:
Was able to source an empty chassis from one of the hardware guys. Checking into what the cost would be to send it to you, will update you shortly. Will be a fun weekend project swapping all the guts over 🙂

Not to sound like a scary internet stalker, but I LOVE YOU RIGHT NOW!!!! Hahaha.

I'll gladly pay for it along with shipping (assuming you're not going to charge me the price of a whole brand new readynas pro hehe.) Also, do you think it might also be possible to get a CPU cooler as well or just the screw assembly for the one leg that is broken? I was looking at the broken one and I wasn't sure if it was possible to repair it or if I would need a new one. Are there any parts that are compatible that I could pick up elsewhere? Either way is fine with me.

I owe you big! Thank you again! 😄

[chirpa]

Already one step ahead of you. See the white cardboard box in that picture above? It is a CPU heatsink 🙂

[chirpa]

I've logged a case for the issue (#11630617). I have passed the chassis to tech support, and asked them to contact you for follow up on payment and shipment. Will probably happen some time tomorrow.

[chirpa]

mrwizardno2, chassis has been shipped. Have fun swapping parts out 🙂

[mrwizardno2]

Chirpa, thank you so much! Wish I coulda bought you a green beer or a few tonight! Can't wait to see things back to normal... life just isn't the same with the RNP offline.

[chirpa]

Thank me after you get the parts swapped. It will be time consuming heh 🙂

[mrwizardno2]

Chirpa, I got the parts swapped but the box won't boot. I switched back to the old CPU thinking maybe the new one didn't work - but still got the same result. Fans go wild, but nothing happens.

I got this hairbrained idea to try hooking a monitor to the onboard VGA header. Luckily it worked! 🙂 Hehe...




I can see the board posts just fine. I poked around in the bios and everything looks ok, but I get the boot error. Could the onboard flash be corrupt? Where does that hook to the USB bus? I'm pretty sure swapping the cpu should not have caused this. I haven't tried booting up with the new CPU with the monitor attached yet. I just want to get the box booting first.

Any hints, oh master of ReadyNAS's?

Edit: I found the flash chip. It's on the IOExpander board. I tried booting from USB and that seems to work. I got it to boot a thumbdrive that I use to install windows. I obviously didn't install anything, but it did indeed work.

[chirpa]

Hook up a USB keyboard, press DEL on bootup to get into the BIOS. Check under Boot for the boot order.

Yes, the internal Flash is behind the LED screen.

[mrwizardno2]

chirpa wrote:
Hook up a USB keyboard, press DEL on bootup to get into the BIOS. Check under Boot for the boot order. Yes, the internal Flash is behind the LED screen.

Behind the LED screen? I removed the IOExpander and the flash was no longer listed during POST so I assumed it was on that board - I'll have to hunt for it when I get home from work. Anyway, I had already checked the BIOS and the flash disk is listed as the primary boot device, but fails to boot.

On a side note: I managed to boot the machine using a USB disk that I made (with windows 98 system files lol!) and ran some basic diagnostics. CPU and Memory both check out fine. Memtest ran three passes before I stopped it, all were clean. The fact that the machine can boot from USB just makes me wonder about that onboard flash. Is there a way to recover it if it has indeed gone on the blink? What else should I be looking at?

(also since this isn't really CPU Spec related, should I start a new thread? I feel like I'm taking this one off-topic now)

Edit: I created a new thread here: http://www.readynas.com/forum/viewtopic.php?f=64&t=40162

[dmross]

Has anyone tried plugging in a CPU that is not on the Intel compatibility list for the Q965 chipset? I'm very tempted to try this spare Celeron E3200...

[chirpa]

I tried an E7400 a few weeks back, wouldn't boot.

[dmross]

I tried the E3200 Celeron yesterday and it wouldn't POST.

[MrCyberdude]

MikeMcr wrote:
Hmm, I notice Intel has confused matters by replacing the E6600 with another E6600 that runs at 3.06 GHz! It uses a smaller die size of 45 nm. http://ark.intel.com/Compare.aspx?ids=42807,27250, Since it shares the same name, would you expect it to be as compatible as the "old" 2.40 GHz E6600?

Has anyone confirmed and used this E6600 3.06Ghz CPU as the 2.40Ghz CPU is hard to find locally?

When looking here http://ark.intel.com/Compare.aspx?ids=42807,27250, its interesting to note there are some significant differences.

Code Name..... Wolfdale ...vs... Conroe
Clock Speed..... 3.06 GHz ...vs... 2.4 GHz
Intel® Virtualization Technology for Directed I/O (VT-d)..... No ...vs... ?? It does have Intel® Virtualization Technology (VT-x)
Integrated Graphics No ...vs... ?? Is this needed if I want to use the 2x8pin header
Cache..... 2 MB Intel® Smart Cache ...vs... 4 MB L2 Cache How much difference will this make I wonder
Bus/Core Ratio 11.5 ...vs... 9
FSB Parity No ...vs... ??
VID Voltage Range 0.8500V – 1.3625V ...vs... 0.8500V-1.5V
TCASE 74.1°C ...vs... 60.1°C but the Max TDP of 65 is the same for both
Lithography 45 nm ...vs... 65 nm
Processing Die Size 82 mm2 ...vs... 143 mm2
# of Processing Die Transistors 228 million ...vs... 291 million
Sockets Supported LGA775 ...vs... PLGA775

EDIT: I have noticed that the 963/965 chipset are not listed as compatible here. http://ark.intel.com/Product.aspx?id=42807
Painfully Interesting that intel have re-used the E6600 name when they look to be quite different.
E6600 designations of SL9TZ, SL9S8 and SLGUG.
http://processorfinder.intel.com/details.aspx?sSpec=SL9S8 2.4 GHz
http://processorfinder.intel.com/details.aspx?sSpec=SL9ZL 2.4 GHz
http://processorfinder.intel.com/Details.aspx?sSpec=SLGUG 3.06 GHz