Fusion-io ioDrive 2 1.2TB Reference Page

Notice: Page may contain affiliate links for which we may earn a small commission through services like Amazon Affiliates or Skimlinks.

COROVICD

New Member
Oct 6, 2023
8
0
1
I have Dell PC, but I used Fusion-io drivers from Western Digital's site. Can that be a problem?

As well, does anybody maybe has Dell version of drivers, because all Dell links are broken / not working:

 
Last edited:

acquacow

Well-Known Member
Feb 15, 2017
787
439
63
42
No, only thing that matters is that the driver/firmware match up, and the card is in a proper slot.
 

COROVICD

New Member
Oct 6, 2023
8
0
1
PC - DP03.b__Fusion-io ioScale2 ioDrive2 1.6TB__P1030387__1024px.jpg

That's the offending card. New-Old stock, card was never used, fresh from wrappings.

I moved my card to more powerful x16 PCI-E v2.0 slot that is usually reserved for graphics cards and trumped up the Fusion-io card power settings to the full 75W. My BIOS is recognizing the card, but there are no settings in BIOS that can directly change card's behavior.

Please note that driver and firmware match perfectly.

In the Device Manager, in Win 10, device is registered and it is working properly. But its nowhere to be seen in the Disk Manager.

My Dell Precision T5400, with x2 CPUs, was manufactured in 2009 and card was made in 2012. Maybe that's where problem is?

These are the odd things:

- Device Manager is saying that Fusion-io card is in PCI slot #1, while actually it is physically in the slot #4. I did check these two directories for leftover of any unwanted configuration files or logs and these directories were absent ( before each re-installation ):

C:\Program Files\Fusion-io iomemory VSL\
C:\Windows\System32\config\systemprofile\AppData\fio-logs\

- since I moved card from PCI slot #1 to PCI-E 2.0 slot #4 card's name changed from "fct0" to "fct1",

- Fusion-io card is overheating to 84 degC ( although card is not even recognized by OS ), published limit is around 74 degC. Card was overheating even when card's power setting was down to only 25W.


Any suggestions as to what to try next?

This is how new fio-status report looks like:



C:\WINDOWS\system32>fio-status -a

Found 1 ioMemory device in this system
Driver version: 3.2.15 build 1699

Adapter: ioMono
Fusion-io 1.65TB ioScale2, Product Number:F11-003-1T65-CS-0001, SN:1412G0444, FIO SN:1412G0444
ioDrive2 Adapter Controller, PN:pA005004003
External Power Override: ON
External Power: NOT connected
PCIe Power limit threshold: 74.75W
PCIe slot available power: unavailable
Connected ioMemory modules:
fct1: Product Number:F11-003-1T65-CS-0001, SN:1412G0444

fct1 Status unknown: Driver is in MINIMAL MODE:
General channel initialization failure
ioDrive2 Adapter Controller, Product Number:F11-003-1T65-CS-0001, SN:1412G0444
!! ---> There are active errors or warnings on this device! Read below for details.
ioDrive2 Adapter Controller, PN:pA005004003
SMP(AVR) Versions: App Version: 1.0.19.0, Boot Version: 1.0.5.1
Powerloss protection: not available
PCI:01:00.0
Vendor:1aed, Device:2001, Sub vendor:1aed, Sub device:2001
Firmware v7.1.17, rev 116786 Public
Geometry and capacity information not available.
Format: not low-level formatted
PCIe slot available power: 150.00W
PCIe negotiated link: 2 lanes at 5.0 Gt/sec each, 1000.00 MBytes/sec total
Internal temperature: 84.65 degC, max 84.65 degC
Internal voltage: avg 1.01V, max 1.02V
Aux voltage: avg 2.49V, max 2.50V
Rated PBW: 8.00 PB
Lifetime data volumes:
Physical bytes written: 0
Physical bytes read : 0
RAM usage:
Current: 0 bytes
Peak : 0 bytes

ACTIVE WARNINGS:
The bandwidth of the PCI slot is not optimal for the ioMemory.
The ioMemory is currently running in a minimal state.



C:\WINDOWS\system32>fio-pci-check
This utility directly probes the pci configuration ports.
There are possible system stability risks in doing this.
Do you wish to continue [y/n]? y

Root Bridge PCIe 10250 MB/sec needed max
Memory Controller

Bridge 0000:00:01.00 (01-01) (8086:4021)
PCI-to-PCI Bridge
* Needed 2000 MB/sec Avail 1000 MB/sec

ioDrive 0000:01:00.0 (2001) Firmware 116786
Fusion ioMemory VSL Device
Slot Power limit: 150.0W (150000mw)
WARNING: All PCIe lanes are not in service.
 
Last edited:

acquacow

Well-Known Member
Feb 15, 2017
787
439
63
42
Check your bios settings and make sure nothing else is splitting lanes away from the x16 slot. Doesn't seem like the x16 slot is providing 4 lanes electrical for some reason.

That, or the card is damaged or missing some bits down near the pci-e connector that might have been knocked off by improper insertion.

Temp-wise, the card needs airflow, it's rated for 300LFM of airflow to keep cool even at idle, so find a single fan to point at the card.
 
  • Like
Reactions: COROVICD

COROVICD

New Member
Oct 6, 2023
8
0
1
Check your bios settings and make sure nothing else is splitting lanes away from the x16 slot. Doesn't seem like the x16 slot is providing 4 lanes electrical for some reason.

That, or the card is damaged or missing some bits down near the pci-e connector that might have been knocked off by improper insertion.

Temp-wise, the card needs airflow, it's rated for 300LFM of airflow to keep cool even at idle, so find a single fan to point at the card.
Card itself only has about four times less physical connectors then x16 slot. I guess that's why PC can't see enough lines.

I checked card around the PCIe connector and it seems there is nothing missing, and it seems that by design, manufacturer didn't put anything there. I compared my card to photos of other same cards and its all the same.

You are right about the airflow. I think card is internally limited to 74 deg. C, but I was getting 78 deg. C. Maybe card is cutting itself out, but then card is not even running?

I'm pretty sure its my PC, because its 14 years old, it precedes card by 4 years.

Thanks a lot for consideration.
 
Last edited:

COROVICD

New Member
Oct 6, 2023
8
0
1
Just an update to developments. I returned the above card to the seller.

Then I used "M.2 To PCI-E Adapter PCIE To Nvme M.2 Adapter PCIE V 2.0 and V1.0" with "Samsung SSD 512GB PM981a PCIe NVMe M.2 2280 MZ-VLB512B MZVLB512HBJQ-000H1" drive and that was immediately accepted by the Disk Management utility and I formatted it without any problems. I've placed it into x16 PCI-e v2.0 slot.
 

gb00s

Well-Known Member
Jul 25, 2018
1,190
602
113
Poland
What can go wrong on a Friday afternoon?

Fan, directed to the cards, failed. Worked as LOG drives for a zpool. Zpool failed .... Oooops. Server shut down by itself. Very bad smell in the server room.

01_Fusion_ioDrive2_785GB.png

02_Fusion_ioDrive2_785GB.png

03_Fusion_ioDrive2_785GB.png

04_Fusion_ioDrive2_785GB.png

05_Fusion_ioDrive2_785GB.png

06_Fusion_ioDrive2_785GB.png

07_Fusion_ioDrive2_785GB.png

Server case was hot as hell at the back. But cards are still working .. ;) Only plastic cover for the 3rd memory module (1.2TB version) was destroyed. But temps must have reached 90+C degrees.

root@kary-01:~# fio-status

Found 2 ioMemory devices in this system
Driver version: 3.2.16 build 1731

Adapter: Single Controller Adapter
Fusion-io ioDrive2 785GB MLC, Product Number:69RV8, SN:US069RV8760514CB0001
External Power: NOT connected
PCIe Power limit threshold: 24.75W
Connected ioMemory modules:
fct0: Product Number:69RV8, SN:1439D0711

fct0 Attached
ioDrive2 Adapter Controller, Product Number:69RV8, SN:1439D0711
Located in slot 0 Center of ioDrive2 Adapter Controller SN:1439D0711
PCI:41:00.0, Slot Number:2
Firmware v7.1.17, rev 116786 Public
785.00 GBytes device size
Internal temperature: 43.80 degC, max 62.51 degC
Reserve space status: Healthy; Reserves: 100.00%, warn at 10.00%
Contained VSUs:
fioa: ID:0, UUID:7de3f5f7-5601-fe49-a01a-dce5bd8f41c3

fioa State: Online, Type: block device
ID:0, UUID:7de3f5f7-5601-fe49-a01a-dce5bd8f41c3
785.00 GBytes device size

Adapter: Single Controller Adapter
Fusion-io ioDrive2 785GB, Product Number:F00-001-785G-CS-0001, SN:1239D2228, FIO SN:1239D2228
External Power: NOT connected
PCIe Power limit threshold: 24.75W
Connected ioMemory modules:
fct1: Product Number:F00-001-785G-CS-0001, SN:1239D2228

fct1 Attached
ioDrive2 Adapter Controller, Product Number:F00-001-785G-CS-0001, SN:1239D2228
Located in slot 0 Center of ioDrive2 Adapter Controller SN:1239D2228
PCI:61:00.0, Slot Number:3
Firmware v7.1.13, rev 109322 Public
785.00 GBytes device size
Internal temperature: 41.83 degC, max 47.25 degC
Reserve space status: Healthy; Reserves: 100.00%, warn at 10.00%
Contained VSUs:
fiob: ID:0, UUID:eab833f7-3958-480c-b2ad-8ba4017ece26

fiob State: Online, Type: block device
ID:0, UUID:eab833f7-3958-480c-b2ad-8ba4017ece26
785.00 GBytes device size

root@kary-01:~#
 

gb00s

Well-Known Member
Jul 25, 2018
1,190
602
113
Poland
Nope, Nutanix NX-8155-G6 (Supermicro 829) but airflow was concentrated to the Tesla cards. Therefore, I just mounted another 60mm Noctua to fit right behind the cards. This one failed. Lesson learned.
 

evansharp

New Member
Nov 3, 2023
6
0
1
Is there a known good source for old firmware files?

I have a Duo card that came to me at firmware 3.0.0 and will not complete a low-format or a secure-erase since I jumped it forward directly to 7.1.17; syslog says LEB map is unavailable and there is an EB error. @snuf and @bplein on the Discord have helped me a lot to determine that I probably need to back up and do FW upgrades: OG -> 5.0.1.42895 -> 5.0.7.107053 -> 7.1.17.

System is PVE 8 with a DKMS-hooked Remix 3.2.16 driver up and running with additional 3.2.11 fio-util binaries (thanks @snuf!).
 

acquacow

Well-Known Member
Feb 15, 2017
787
439
63
42
Is there a known good source for old firmware files?

I have a Duo card that came to me at firmware 3.0.0 and will not complete a low-format or a secure-erase since I jumped it forward directly to 7.1.17; syslog says LEB map is unavailable and there is an EB error. @snuf and @bplein on the Discord have helped me a lot to determine that I probably need to back up and do FW upgrades: OG -> 5.0.1.42895 -> 5.0.7.107053 -> 7.1.17.

System is PVE 8 with a DKMS-hooked Remix 3.2.16 driver up and running with additional 3.2.11 fio-util binaries (thanks @snuf!).
I have a few...
1699379926061.png

I have them up on my nextcloud instance at: ioDrive Stuff

-- Dave
 

evansharp

New Member
Nov 3, 2023
6
0
1
Oh, it's by driver version. I see.

Do you have older? I'm stuck looking for 2.3.10 or 11 ( fw 5.0.7.107053). The sandisk doc I have says 2.3.10/11 has to come after 2.1.0.

I have 2.3.10 (.fff extracted from the .rpm) from HP's KB, but its branded "ioaccelerator" and `fio-update-iodrive` won't apply it to my Duo card. @snuf I think told me crossflashing was ok, but it won't take it.
 
Last edited:

acquacow

Well-Known Member
Feb 15, 2017
787
439
63
42
No, I jumped everything I had to 3.x when it first came out for the adaptive flashback features and better performance. I didn't retain any 2.x.

If you don't need data on the card, I'd just jump to 3.1.1 and fio-sure-erase the card to get clean LEB maps, then update to the latest 3.2.16

You can crossflash, but you have to unzip the fff file and edit the INFO file inside and find the section that pertains to your card's PA# and duplicate it, adding your specific PA# on top

An entry looks like this:

[PA004137042]
version = 7.1.13.109322
file = gen2_49_salmon_fusion_7.1.13.109322.bin
format = bin
ecc = 49b
dpfile = gen2_49_salmon_dual_fusion_7.1.13.109322.bin
dpformat = bin
dpecc = 49b
cntrpdiversion = 1.0.23
cntrpdifile = carre_1.0.23.pdi
cntrpdiformat = pdi

I have other posts on this several pages back in this thread.