LSI SAS3008 HBA high temperature ?

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

Ustrel

New Member
Nov 29, 2020
3
0
1
Hi all,

I recently bought a SuperMicro AOC-S3008L-L8e HBA (LSI SAS3008 based with IT firmware) and plugged it in a home made NAS build with limited air cooling to keep everything quiet.

Monitoring the SAS3008 ROC (Raid On Chip) device using storcli utility shows a rather high 65 °C / 149 °F temperature under no I/O workload, i.e. when:
* no drive plugged into card;
* with 31 °C / 88 °F measured at case inlet air location ;
* with 35 °C / 95 °F measured at case outlet air location.

Using a straightforward I/O "intensive" workload:
* with 5 SSDs plugged into card
* with a formatting process running simultaneously onto each SSD (with read/write bad block scan and no discard operation)
* with 31 °C / 88 °F measured at case inlet air location ;
* with 35 °C / 95 °F measured at case outlet air location.
To my surprise, after more than 1 hour of continuous operation, measured temperature is still 65 °C / 149°F.

I'm considering giving the card more air flow through temperature driven fan control. However, I'm unable to find consistent documentation with respect to the ROC chip recommended temperature range itself... which makes it very difficult to enslave fan speed without knowing min / max temperature points at the very least.

Everything I could find so far was related to the recommended air flow ranging from 100 to 300 LFM (Linear Feet per Minute) which won't help me either given that my fan specifications are expressed as CFM (Cubic Feet per Minute) and I have no idea of the volume of air flowing around the chip.
This would not allow me to derive a process to drive fan speed as a function of chip temperature anyway.

  • Does anybody has experience / documentation / reference inputs related to this SAS3008 (or similar) chip ?
  • More specifically, what ROC max temperature shoud I never run over to preserve long term chip healthiness ?
  • I would also be interested in temperature measurements and / or experiments if anyone of you own such a HBA.

Many thanks in advance. Regards,
Greg.
 

Ustrel

New Member
Nov 29, 2020
3
0
1
If anyone's interested, here's Supermicro support answer:

What is the recommended mean ROC temperature under no I/O load ?
--> minimum of 200 linear feet per minute (LFM) airflow.

What ROC max temperature should I never run over to preserve long term chip healthiness ?
--> 55°C Max.

Regards,
Greg.
 

i386

Well-Known Member
Mar 18, 2016
4,526
1,696
113
35
Germany
What ROC max temperature should I never run over to preserve long term chip healthiness ?
--> 55°C Max.
This is the max. ambient temperature. The asic/cpu can get up to 80-90°C before sensors and alarms goes off.

Raid.JPG
 
  • Like
Reactions: exxr and mattlach

Ustrel

New Member
Nov 29, 2020
3
0
1
Thanks for the input.

However, the SAS9361 is based upon the SAS3108 ROC (dual PPC 476 core + additional cache mem).
The SM AOC-S3008L-L8e is based upon the SAS3008 one (single PPC 476 core, no additional cache mem).

Note that LSI / Broadcom cards comparable to the SM (such as SAS9300-8i) are also given for 55°C max ambient temperature as stated into SAS 9300 12Gb/s SAS Host Bus Adapter Family Product Brief.

Quite oddly enough, SM website stated AOC-S3008L-L8e max ambient temperature at 35°C 2 days ago.
Checked back a few minutes ago: it has changed to 55 °C...
See here: Add-on Card AOC-S3008L-L8e / AOC-S3008L-L8e+.

So you're very likely right. It seems these kind of chip internal temperature sensor can go really hot (up to 115°C max operating at junction level as stated in this old application note).

Which leaves me rather confused and still unable to figure out an acceptable max operating temperature to prevent my card from frying after 3 years of uninterrupted operation...
 

Whaaat

Active Member
Jan 31, 2020
376
203
43
65°C is cool, my perc h330 has been running at 75-80°C for years. That temp is perfectly normal for sas cards for constant operation. If you turn off your pc daily than it's a different story and it would be better to cut 10 or more degrees off the max
 

mattlach

Active Member
Aug 1, 2014
406
165
43
This is the max. ambient temperature. The asic/cpu can get up to 80-90°C before sensors and alarms goes off.

View attachment 16500
65°C is cool, my perc h330 has been running at 75-80°C for years. That temp is perfectly normal for sas cards for constant operation. If you turn off your pc daily than it's a different story and it would be better to cut 10 or more degrees off the max
Thanks for this. Between these two posts, this was the answer I came here looking for.

I had seen the 55°C figure bandied about, and thought it sounded awfully low for a silicon chip, but I didn't know for sure. Makes perfect sense that it is ambient.

I currently have two active systems with LSI/Avago/Broadcom/Whatever HBA's (both currently happen to be SAS9305-24i cards, through I have a currently non-booting remote backup server box with two SAS9300-8i's due to an errant "zpool upgrade" and a "spare parts" box full of various others I no longer use, including several SAS9300-8i's a SAS9300-16i, a SAS9400-16i and several old SAS9200 series cards)

I had always been somewhat concerned at just how hot these things get to the touch. Even after over a decade of using these things. (I started out with a couple of IBM M1015 cards cross-flashed to HBA's back in 2014) I only just heard of the "storcli" program last week :oops:

The primary box is my all-in-wonder VM/Container host and NAS server utilizing a Supermicro H12SSL-NT board with an EPYC 7543. It is in a custom modded Supermicro SC-846 case with the direct BP846A backplane (no SAS expander). I took out the fan wall, and replaced it with three 3000rpm 120mm Noctua Industrial Fans, and custom crafted a piece of wood to block the airflow on top of them:

H12SSL-NT.jpg

The 3000rpm Noctua fans provide lots of airflow at ~110CFM each at max speed, (though I have no way of measuring if it meets the 200 linear feet spec, I could probably divide the total airflow by the swept area, which gives me about 710 linear feet per minute, but that does not account for the fact that 110 cfm is an unrestricted specification, and is decidedly less when static pressure is factored in. I don't have the proper metrology device to measure what kind of airflow I am actually seeing, though I figure that is plenty of safety margin.

Either way, this results in much quieter operation, which is important for a home setup, as the little high RPM 80mm screamers are audible two rooms over with all doors closed. Despite pushing more air, the 120mm fans are quieter due to their size. All else being equal (same airflow) generally larger fan = quieter. (Also, more fans at lower speeds are generally quieter than fewer fans at higher speeds)

In this configuration, the SAS9305-24i with 12x 16TB 7200rpm Seagate Exos x18 drives attached sits at ~80°C at idle in a 24°C room, which is slightly alarming to me, but the temperature warning LED has never gone off, so I guess I am OK.

I think the 6 semi-bulky SAS cables coming off of the 24i variant get in the way of direct airflow. I might mount another fan blowing at the HBA if my concern grows.

The second system uses my (very old but still surprisingly still usable) decommed server board (Supermicro X9DRI-F with dual Xeon E5-2697 V2's) in a pedestal workstation case (OG Phanteks Enthoo Pro) with a 200mm fan upfront blowing air across the hard drives and into the case.

Enthoo.jpg

In this case, the Medusas hair of SAS cables block airflow to the HBA even more, and there is less airflow, so I added a fan blowing down on the HBA (and NIC, both sandwiched between the old Titan GPU and the 16x four way NVMe riser card) to help remediate it. It doesn't blow in the same direction as the heatsink fins, but at least it helps a little bit.

In this case and configuration the same HBA runs significantly cooler, only registering about 60°C, but the office it is in is a degree or two cooler, and the load on the workstation is lower, with fewer drives attached (only 6x 4TB HGST SAS drives, the rest of the SAS connectors go to various 3.5" and 2.5" hot swap bays for imaging and other maintenance purposes)

Interestingly, I have never seen more than a 1°C-2°C difference in SAS HBA temperature (as reported by storcli) between idle and full load on any system. It sounds to me like LSI/Avago/Broadcom/Whatever have little to no power management in their designs. I'm guessing they just run full power all the time whether full load or idle, which is kind of wasteful :/

My guess would be that the tiny difference in temperature I see between idle and load is a result not of the HBA silicon itself, but rather the heat coming off other devices that also see more load when the drive load goes up (hard drives themselves, CPU's calculating ZFS checksums, etc.)

The hottest LSI HBA's I have ever used despite its massive heatsink (judging by touch, this was before I discovered "storcli" and I haven't had it installed to test it since then) has been the SAS9300-16i. I presume this is because this board was simply two SAS9300-8i chips glued together on the same card using a PCIe (PLX) switch, and the PCIe switch uses a non insignificant amount of power itself, in addition to there being two SAS controller chips instead of just one. Notably this is also the only HBA I have ever used that required it's own supplemental PCIe power cable to power it. Apparently the power the slot could provide was insufficient. The temperature of this heatsink definitely was above the pain threashold when I touched it. I'm actually surprised I didn't get a blister.

To address this I ziptied a 92mm slim Noctua fan directly to the heatsink.

1731441006820.png

This worked very well to control the temperature of the thing, but it did block the abutting PCIe slot, which is why I eventually replaced it, as I needed that slot. Starting with the SAS9305-16i, they had a new cooler chip with all 16 lanes on the same chip, which ran much cooler, so that is w3hat I went shopping for, but when I did I found a decommed SAS9400-16i for almost the same price, so I just bought that instead.

It worked well, and I used it in this workstation up until just a few months ago, when I wanted to add the six hard drives to create a ZFS send/recv backup pool in the workstation (to do backups off of my main NAS, until I could figure out and fix why my offsite backup server wasn't booting, and this was going to take a while as it is in a location I rarely have time to visit).

When adding the 6 hard drives, I ran into the issue that while I only needed 15 connections, 6 of them needed to be SAS (for the hard drives), and 9 of them needed to be SATA (for the hot swap bays). I initially considered pulling one of the old Intel or HP SAS expander cards I have in the spare parts bin for this, but I decided to rather than deal with a hodgepodge of adapters or expanders (I hate troubleshooting intermittent adapter connections) I noticed that the 9305-24i's which initially where rather pricy when I bought the one for my NAS are now quite affordable on the used server pull market, so I just got another one. This way I can have two breakout cables that are SAS (no backplane here, unlike the Supermicro case), and three breakout cables that are SATA, and make things cleaner.

I think the 9305-24i might just run a little cooler than the 9400-16i did. This might have something to do with the fact that the 9400 series were the first to support NVMe drives using what they call Tri-Mode "SerDes" technology. Some part of that "SerDes" stuff must consume power and create heat even when not in use.

At first I thought it had some sort of integral PCIe (PLX) switch that handled this, but I ahve since learned that the Tri-Mode SerDes HBA's actually present NVMe drives to the host as SCSI devices, not as native PCIe devices, so there is probably something else going on here.

I haven't tested this myself yet though, I am just going off of what I have read.

I have also read that its not worth bothering with the NVMe capability of the SAS9400 and SAS9500 series HBA's, as they really neuter the performance of attached NVMe drives. The SAS9600 series - however - apparently work at near native NVMe speeds (or so I am told) but these are way too new to be in my hobbyists budget. Maybe I'll get one down the road when server pulls start showing up.

The 9400 and 9500 might be OK if you just need to access NVMe drives though, and don't need their high native PCIe performance.

Anyway, sorry for the TLDR brain dump. I started writing this to share my temperature experiences if anyone else was interested, and like always I went off the rails. I hope someone (other than a cursed thieving data mining AI language model) finds this post useful.
 
Last edited:
  • Like
Reactions: Pakna

trumee

Member
Jan 31, 2016
245
16
18
55
I am using an Inspur 9311-8i card based which is based on LSI SAS 3008 chipset. It is also enclosed in an SC846 chassis with a fan wall similar to @mattlach

I looked up the temperature,
Code:
# storcli /c0 show temperature
CLI Version = 007.3103.0000.0000 Aug 22, 2024
Operating system = Linux 6.6.62-1-lts
Controller = 0
Status = Success
Description = None


Controller Properties :
=====================

--------------------------------------
Ctrl_Prop Value
--------------------------------------
ROC temperature(Degree Celsius) 117
--------------------------------------

# storcli /c0 show  

Product Name = INSPUR 3008IT
FW Package Build = 00.00.00.00
FW Version = 16.00.10.00
BIOS Version = 08.37.02.00_18.00.00.00
NVDATA Version = 14.01.00.07
Driver Name = mpt3sas
Driver Version = 43.100.00.00
Bus Number = 3
Device Number = 0
Function Number = 0
Domain ID = 0
Vendor Id = 0x1000
Device Id = 0x97
SubVendor Id = 0x1BD4
SubDevice Id = 0xC
Board Name = INSPUR 3008IT
Board Assembly = INSPUR
Board Tracer Number = N/A
Security Protocol = None
Physical Drives = 24
Am i in trouble?
 

Stephan

Well-Known Member
Apr 21, 2017
1,047
808
113
Germany
117 degC is way too high imho, controller will throttle or throw errors or reboot. Check with an IR camera, or zip-tie an 80x80 fan with 1000 rpm blowing right at the chip's heatsink to test. Temps should retreat at idle to 60 or 70 degC.
 

mattlach

Active Member
Aug 1, 2014
406
165
43
I am using an Inspur 9311-8i card based which is based on LSI SAS 3008 chipset. It is also enclosed in an SC846 chassis with a fan wall similar to @mattlach

Am i in trouble?
Yikes, yeah that is high.

Is the thermal warning LED activating on it? They have two LED's, one just to indicate power, and the other to indicate overheating. I have never seen the latter, so I don't know what it looks like or if it is the same color, or if it flashes or anything like that. But if you see two LED's light up on the board (usually towards the back so you can see them through the PCIe slot ventilation holes) thats one way to confirm you have a problem.

I can't imagine it wouldn't be lit up at that temperature though.

(I wish I could find a spec that tells us at what temp it lights up. Because that, the actual silicone max temp would be more useful to me than knowing the ambient temp max as the effect of ambient on the temp of the board has way too many variables based on air flow and such.)

Generally you don't want to see silicon go over ~85-90°C in most cases. Some parts designed to get really hot (CPU's, GPU's) can handle a little more due to use of specialized solder, etc.

The saving grace (which is probably why it is still working at all) is that these LSI controllers seem to output a fixed amount of power whether they are loaded up or not, which means that you likely don't have frequent hot/cold temperature cycles. This is what can often result in hardware failure, when too many hot/cold cycles result in repeated thermal expansion and contraction eventually cracking solder joints.

That said, I wouldn't leave it like that. I would try to strap a little fan blowing at it or something. There is more than one way to do it. A PCI slot fan could do the trick, or you can custom strap a fan directly to the card and heatsink using zipties, or place one elsewhere blowing at it.

Since these cards only put out between 5w and 15w (depending on the model) it doesn't take a huge amount of direct airflow to significantly lower those temps, so if noise is a concern in your environment, you can probably use 4pin pwm fans, inline resistor/silencer adapters or other fan controllers to really slow down the fan to keep it silent, and still be rather effective.

But yeah, I'd do something. Probably sooner rather than later.
 

trumee

Member
Jan 31, 2016
245
16
18
55
@mattlach Thanks for pointing out the urgency of the situation. I slapped a Noctua A4x10 on top of the heat sink, and the temperature dropped.

Code:
# storcli /c0 show temperature
CLI Version = 007.3103.0000.0000 Aug 22, 2024
Operating system = Linux 6.6.62-1-lts
Controller = 0
Status = Success
Description = None


Controller Properties :
=====================

--------------------------------------
Ctrl_Prop Value
--------------------------------------
ROC temperature(Degree Celsius) 81
 
  • Like
Reactions: mattlach

Shonk

Member
Nov 25, 2016
63
35
18
74
I have an 80mm fan above my 9305-24i and its 63-70°C i moved the fan directly ontop of the heatsink and it only dropped about 2-3°C
The case also has 6 x 140mm fans 3 push 3 pull
I think lsi cards just run hot af














 
Last edited:
  • Like
Reactions: Eta_Carinae

mattlach

Active Member
Aug 1, 2014
406
165
43
I have an 80mm fan above my 9305-24i and its 63-70°C i moved the fan directly ontop of the heatsink and it only dropped about 2-3°C
The case also has 6 x 140mm fans 3 push 3 pull
I think lsi cards just run hot af
You'd probably be better served by an actual server case than trying to jam everything into a workstation/desktop case.

Also, you are sacrificing one of the biggest reasons for having those Optane drives (low latency & 4k random performance) by putting them behind a PCIe switch which introduces lots of latency.
 
  • Like
Reactions: nexox

Shonk

Member
Nov 25, 2016
63
35
18
74
It doesnt really matter what case i have i will always put as much as i can in it
its the way i am and i prefer desktop cases over rackmount cases anyway

With regards to the the PCIe switch its only 100ns of latency added
Asmedia Spec 100ns average 150ns worstcase for the switch
Optane Drives are what 0.5ms (from a quick 2 second google) which is 500000ns oh no its 500100ns now

its a PCIe x8 to 16 lane switch exactly the same as a Z690/Z790/Z890 PCH which is a PCIe x8 to 28 lane switch
I am using the drives as NVMe storage not Optane Persistent Memory (where you get the large latency gain with Optane)
100ns added is hardly anything and doesnt detract anything from the drive

I used to run one P1600X in the 8x Slot (CPU Lanes) before i got the ASM2824 to use the other 4 unused lanes
they benchmark faster in every regard in the ASM2824 due to pipelining and cacheing by the PCIe switch

I also have 3 more Optane drives in the Z390 PCH M.2 slots which is 4 lanes of PCIe x4 3.0 split out over 3 M.2 slots + PCIe + USB + everything else supplied by the PCH

If you had just seen the Optane drives in the motherboard PCH M.2 Slots you wouldnt have said a thing
due to your inaccurate and very subjective opinion
the ASM2824 with 8 CPU lanes is superior in every regard

The ASM2824 is a significant step up in regards to adding capability to the device and is far less bottlenecked than the 9900KS's Z390 PCH

another example my main PC 14900KS + Z690
CPU Lanes = Intel Optane 900P 480GB
PCH Lanes = Intel Optane 900P 280GB
the one on the PCH lanes consistently benchmarks faster in all regards and about 70MB/s in overall bandwidth

next you will be saying never to use your PCH lanes on a motherboard

I use optane for the write endurance not for the latency
its something i have never been happy with since we went from SLC to MLC to TLC to QLC
SLC is the only nand that i consdered acceptable

the latency is a nice bonus and makes the OS super snappy
which is nice ofc but its not my main reason for using Optane

MY 12900K PC also has an Optane 900P 480GB as its OS drive and a P1600X 118GB as its Scratch drive
My 11950H Laptop has an Optane 800P 118GB as its Scratch drive

Your usecase is not my usecase i am not running Linux/ZFS i am running Windows 10 Pro I have a Server 2022 License but it prevents me spinning drives down on LSI controllers by adding the required registry keys for spindown i can add them but its bugged in the build of Server 2022 that i used at the time it may be fixed now but i cant be bothered testing and ended up using Windows 10 Pro as i have zero need to have 24 3.5" Drives Spinning 24/7 and with the cost of electricity being something like 35p (50¢) a kWh in the UK i cant really afford to have them spinning 24/7
 
Last edited:

mattlach

Active Member
Aug 1, 2014
406
165
43
It doesnt really matter what case i have i will always put as much as i can in it
its the way i am and i prefer desktop cases over rackmount cases anyway

With regards to the the PCIe switch its only 100ns of latency added
Asmedia Spec 100ns average 150ns worstcase for the switch
Optane Drives are what 0.5ms (from a quick 2 second google) which is 500000ns oh no its 500100ns now

its a PCIe x8 to 16 lane switch exactly the same as a Z690/Z790/Z890 PCH which is a PCIe x8 to 28 lane switch
I am using the drives as NVMe storage not Optane Persistent Memory (where you get the large latency gain with Optane)
100ns added is hardly anything and doesnt detract anything from the drive

I used to run one P1600X in the 8x Slot (CPU Lanes) before i got the ASM2824 to use the other 4 unused lanes
they benchmark faster in every regard in the ASM2824 due to pipelining and cacheing by the PCIe switch

I also have 3 more Optane drives in the Z390 PCH M.2 slots which is 4 lanes of PCIe x4 3.0 split out over 3 M.2 slots + PCIe + USB + everything else supplied by the PCH

If you had just seen the Optane drives in the motherboard PCH M.2 Slots you wouldnt have said a thing
due to your inaccurate and very subjective opinion
the ASM2824 with 8 CPU lanes is superior in every regard

The ASM2824 is a significant step up in regards to adding capability to the device and is far less bottlenecked than the 9900KS's Z390 PCH

another example my main PC 14900KS + Z690
CPU Lanes = Intel Optane 900P 480GB
PCH Lanes = Intel Optane 900P 280GB
the one on the PCH lanes consistently benchmarks faster in all regards and about 70MB/s in overall bandwidth

next you will be saying never to use your PCH lanes on a motherboard

I use optane for the write endurance not for the latency
its something i have never been happy with since we went from SLC to MLC to TLC to QLC
SLC is the only nand that i consdered acceptable

the latency is a nice bonus and makes the OS super snappy
which is nice ofc but its not my main reason for using Optane

MY 12900K PC also has an Optane 900P 480GB as its OS drive and a P1600X 118GB as its Scratch drive
My 11950H Laptop has an Optane 800P 118GB as its Scratch drive

Your usecase is not my usecase i am not running Linux/ZFS i am running Windows 10 Pro I have a Server 2022 License but it prevents me spinning drives down on LSI controllers by adding the required registry keys for spindown i can add them but its bugged in the build of Server 2022 that i used at the time it may be fixed now but i cant be bothered testing and ended up using Windows 10 Pro as i have zero need to have 24 3.5" Drives Spinning 24/7 and with the cost of electricity being something like 35p (50¢) a kWh in the UK i cant really afford to have them spinning 24/7
Sorry, I realize in retrospect that my comment sounded a little bit more negative/criticizing/harsh than I intended.

That said, I have noticed a significant difference in Optane drives IOPS and low queue depth random performance when on chipset lanes or behind PLX/PCIe Switch type devices.

Yes, the actual latency from the chipset and/or PLX/PCIe switch is small, but the impact to drive performance is often very large in my experience.

This is one of the many reasons I am a bit of a "enterprise/server hardware" purist for anything that involves data storage. You get a shit ton of PCIe lanes going straight to the CPU, Bifurcation is usually supported, and you get well validated ECC and CPU support
 

molnart

Member
Feb 5, 2023
43
0
6
I was trying to check the temperatures of my LSI SAS3008, but storcli does not seem to detect the card:

Code:
$ sudo lspci | grep -i LSI
03:00.0 Serial Attached SCSI controller: Broadcom / LSI SAS3008 PCI-Express Fusion-MPT SAS-3 (rev 02)
Code:
$ sudo ./sas3flash -list
Avago Technologies SAS3 Flash Utility
Version 16.00.00.00 (2017.05.02)
Copyright 2008-2017 Avago Technologies. All rights reserved.

        Adapter Selected is a Avago SAS: SAS3008(C0)

        Controller Number              : 0
        Controller                     : SAS3008(C0)
        PCI Address                    : 00:03:00:00
        SAS Address                    : 5003048-0-2516-d400
        NVDATA Version (Default)       : 0e.01.30.28
        NVDATA Version (Persistent)    : 0e.01.30.28
        Firmware Product ID            : 0x2221 (IT)
        Firmware Version               : 16.00.14.00
        NVDATA Vendor                  : LSI
        NVDATA Product ID              : LSI3008-IT
        BIOS Version                   : 08.27.00.00
        UEFI BSD Version               : 13.07.00.00
        FCODE Version                  : N/A
        Board Name                     : LSI3008-IR
        Board Assembly                 : N/A
        Board Tracer Number            : N/A

        Finished Processing Commands Successfully.
        Exiting SAS3Flash.
Code:
  sudo ./storcli64 show
CLI Version = 007.3205.0000.0000 Oct 09, 2024
Operating system = Linux 6.1.0-28-amd64
Status Code = 0
Status = Success
Description = None

Number of Controllers = 0
Host Name = OMV-DL80
Operating System  = Linux 6.1.0-28-amd64
StoreLib IT Version = 07.3205.0200.0000
Any idea how to get the temperature info?
 

mattlach

Active Member
Aug 1, 2014
406
165
43
I was trying to check the temperatures of my LSI SAS3008, but storcli does not seem to detect the card:

Code:
$ sudo lspci | grep -i LSI
03:00.0 Serial Attached SCSI controller: Broadcom / LSI SAS3008 PCI-Express Fusion-MPT SAS-3 (rev 02)
Code:
$ sudo ./sas3flash -list
Avago Technologies SAS3 Flash Utility
Version 16.00.00.00 (2017.05.02)
Copyright 2008-2017 Avago Technologies. All rights reserved.

        Adapter Selected is a Avago SAS: SAS3008(C0)

        Controller Number              : 0
        Controller                     : SAS3008(C0)
        PCI Address                    : 00:03:00:00
        SAS Address                    : 5003048-0-2516-d400
        NVDATA Version (Default)       : 0e.01.30.28
        NVDATA Version (Persistent)    : 0e.01.30.28
        Firmware Product ID            : 0x2221 (IT)
        Firmware Version               : 16.00.14.00
        NVDATA Vendor                  : LSI
        NVDATA Product ID              : LSI3008-IT
        BIOS Version                   : 08.27.00.00
        UEFI BSD Version               : 13.07.00.00
        FCODE Version                  : N/A
        Board Name                     : LSI3008-IR
        Board Assembly                 : N/A
        Board Tracer Number            : N/A

        Finished Processing Commands Successfully.
        Exiting SAS3Flash.
Code:
  sudo ./storcli64 show
CLI Version = 007.3205.0000.0000 Oct 09, 2024
Operating system = Linux 6.1.0-28-amd64
Status Code = 0
Status = Success
Description = None

Number of Controllers = 0
Host Name = OMV-DL80
Operating System  = Linux 6.1.0-28-amd64
StoreLib IT Version = 07.3205.0200.0000
Any idea how to get the temperature info?
Agreed, it looks like it can't find your controller.

My first suspicion was your firmware revision, but it seems up to date.

Your firmware 16.00.14.00 is actually a slightly newer revision than I am used to seeing (all of mine have 16.00.12.00).

That is a little odd, because I don't see any updates to the 9300 firmware package since 2018, so I would have expected all the most recent versions to be the same. Maybe the slightly different revisions are board specific differences? Which board do you have? Is it a 9300 or 9305?

It is seemingly impossible to find the latest firmware on Broadcoms nightmare of a website, so I always get confused regarding their firmware.

One thing that does stand out to me though is that your Linux kernel (6.1.0-28) is a bit on the old side. The driver (mpt3sas) is included with the kernel. I wonder if the driver in the 6.1 kernel just doesn't fully support this feature? Can you try with a more recent kernel?

If you don't want to mess with whatever system it is in just to test, maybe try booting a live Linux image from something newer and test from there?
 
Last edited:

kapone

Well-Known Member
May 23, 2015
1,283
737
113
I have had the pleasure...of dealing with SAS cards for a LONG time... :)

1. Yes, they run hot.
2. Do they run hot? Look at #1.

They almost always run full throttle, because...well, if you think about it, do you really want your SAS HBA to add latency when your disks/arrays are accessed, because it was in a lower power state? I presume not...

I've had LSI cards, Adaptec cards, some even more exotic cards and almost all of them have run hot. I define hot as anything over 50c. The limited success I've had in cooling them down (in order):

1. Repaste. Generally speaking these cards are >8-10 yrs old at this point. They benefit from taking the heatsink off, a good clean and repaste.
2. Various fans hanging off the cards/on the cards/in front of the cards. The most optimal effect is of course slapping a fan right on the heatsink (using various DIY concoctions...mostly just finding the right screws that wedge themselves in the heatsink), but you lose a slot that way. Sometimes that's acceptable, sometimes it's not.

I've made peace with it. :) They're cheap enough that if they do die, getting another one is not a big deal. Right now, I'm running a bunch of Adaptecs (and they generally run hotter than LSIs) in various DIY concoctions to cool them down, and the lowest I've had them down to is ~55C at idle.
 

molnart

Member
Feb 5, 2023
43
0
6
Your firmware 16.00.14.00 is actually a slightly newer revision than I am used to seeing (all of mine have 16.00.12.00).
This is the firmware I have installed www.supermicro.com - /wdl/driver/SAS/Broadcom/3008/Firmware/

Which board do you have? Is it a 9300 or 9305?
Honestly I have no idea. This is the card AOC-S3008L-L8e / AOC-S3008L-L8e+ | Add-on Cards | Accessories | Products - Super Micro Computer, Inc.

One thing that does stand out to me though is that your Linux kernel (6.1.0-28) is a bit on the old side.
The kernel is 6.8.12-5-pve as reported by uname -a, not sure were that 6.1.0-28 is coming from