Two identical disks, two different SATA speeds?

oscar

oscar

Hi,

I have just noted this in my dmesg:

Code: 
ada0 at ata2 bus 0 scbus0 target 0 lun 0
[B]ada0: <ST3000VN007-2E4166 SC60> ACS-2 ATA SATA 3.x device[/B]
ada0: Serial Number Z6A06CDP
[B]ada0: 600.000MB/s transfers (SATA 3.x, UDMA5, PIO 8192bytes)[/B]
ada0: 2861588MB (5860533168 512 byte sectors)
ada1 at ata3 bus 0 scbus1 target 1 lun 0
[B]ada1: <ST3000VN007-2E4166 SC60> ACS-2 ATA SATA 3.x device[/B]
ada1: Serial Number Z6A06LWX
[B]ada1: 300.000MB/s transfers (SATA 2.x, UDMA5, PIO 8192bytes)[/B]
ada1: 2861588MB (5860533168 512 byte sectors)
ada2 at ata5 bus 0 scbus3 target 0 lun 0
[I]ada2: <Samsung SSD 850 EVO 250GB EMT02B6Q> ACS-2 ATA SATA 3.x device[/I]
ada2: Serial Number S2R6NX0J411143Y
[I]ada2: 300.000MB/s transfers (SATA 2.x, UDMA5, PIO 512bytes)[/I]
ada2: 238475MB (488397168 512 byte sectors)
ada2: quirks=0x3<4K,NCQ_TRIM_BROKEN>

ada0 and ada1 are identical but one is apparently SATA 2 while the other is SATA 3? Also, the Samsung SSD 850 EVO at the bottom is also SATA 2, what is going on here?

The hardware is an old HP ML110 Gen7. The plan is to mirror ada0 and ada1 with ZFS, no hardware RAID. The larger disks are both Seagate IronWolf 3TB 3.5" SATA-600 which are bought this year without much use.
 
oscar said:
Code: 
ada0 at ata2 bus 0 [b]scbus0[/b] target 0 lun 0
[...]
ada1 at ata3 bus 0 [b]scbus1[/b] target 1 lun 0
Click to expand...

The drives seem to be connected to different controllers (or different buses at the same controller) and the second (and third) is/are most likely only SATA2 capable/configured.
Have a look at the output of lspci (part of the pcitools package) or grep for SATA in your dmesg output to see what controllers are present.
IIRC (some) HP servers have lower-spec connectors for CDROM/DVD drives. You might also have a look at the BIOS settings for the onboard connectors; these usually can be configured to lower speeds.

Cheap SATA cables are also a common reason for decreased link speeds.
 
My take on you're situations that one drive is a third generation ssd and you;re primary ora ada0 devjuce is sata 2.3 high spindle speed conventional (magnetic platter based drive)/
 
My take on you're situations that one drive is a third generation ssd and you;re primary ora ada0 devjuce is sata 2.3 high spindle speed conventional (magnetic platter based drive)/
Click to expand...

Can't really understand what you mean. All 3 devices are listed as SATA 3 capable, but only one is actually running at SATA 3 speed. The SSD is actually one of the devices running at SATA 2 and one of the Platter disks is running at SATA 3. The most confusing thing, and the main point of the post is that the two conventional disks are identical spec, but one is running at SATA 3 and the other SATA 2.

As mentioned by sko, the most likely reason is that some of the ports are only SATA 2. If there's any SATA3 ports at all (which there obviously is), I'd expect there to be at least 2 though.

In this instance it may be worth trying the SSD in the port ada0 is in. The Seagate drives probably won't hit the limit of SATA2 anyway so it may be reasonable to settle for having the SSD at SATA3 and the other disks at SATA2 if you can get it running like that.
 
Try some other cables too. There should be no difference between SATA 2 or 3 cables (they're all the same) but if a cable is a bit dodgy it may not be able to run at the full SATA 3 speeds. They're easy enough to replace and test.
 
To debug this remotely, we would need more information, like all lines from dmesg (or /var/log/messages) that pertain to the SATA controllers. Or you debug it yourself, for example using lspci or dmesg or the BIOS, to figure out who is who.

In practice, there is probably no reason to care anyhow. The Seagate ST3000VN007 drive is a consumer-grade slow spinning drive, with a maximum data rate of 180 MByte/sec; the 300 MByte/sec throughput of SATA-2 is already sufficient for those. But I can completely understand trying to figure out *why* that one drive isn't getting SATA-3 speeds, given that it maybe ought to (following the example of its twin brother).
 
Hi,

Sorry for my late reply. The first two discs are mounted in the same disk cabinet in the chassis, the third one to a stray cable which probably is only made for connecting an optical drive or similar. I can try to rearrange the disks in the cabinet (four slots in total) and see if it matters, and I will post more details in this thread once I have done so. At work at the moment.

Thanks,
Oscar
 
So, first output from lspci


00:00.0 Host bridge: Intel Corporation Xeon E3-1200 Processor Family DRAM Controller (rev 09)
00:01.0 PCI bridge: Intel Corporation Xeon E3-1200/2nd Generation Core Processor Family PCI Express Root Port (rev 09)
00:06.0 PCI bridge: Intel Corporation Xeon E3-1200/2nd Generation Core Processor Family PCI Express Root Port (rev 09)
00:1a.0 USB controller: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #2 (rev 05)
00:1c.0 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 1 (rev b5)
00:1c.4 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 5 (rev b5)
00:1c.5 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 6 (rev b5)
00:1c.6 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 7 (rev b5)
00:1c.7 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 8 (rev b5)
00:1d.0 USB controller: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #1 (rev 05)
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev a5)
00:1f.0 ISA bridge: Intel Corporation C204 Chipset Family LPC Controller (rev 05)
00:1f.2 IDE interface: Intel Corporation 6 Series/C200 Series Chipset Family Desktop SATA Controller (IDE mode, ports 0-3) (rev 05)
00:1f.5 IDE interface: Intel Corporation 6 Series/C200 Series Chipset Family Desktop SATA Controller (IDE mode, ports 4-5) (rev 05)
01:00.0 System peripheral: Hewlett-Packard Company Integrated Lights-Out Standard Slave Instrumentation & System Support (rev 05)
01:00.1 VGA compatible controller: Matrox Electronics Systems Ltd. MGA G200EH
01:00.2 System peripheral: Hewlett-Packard Company Integrated Lights-Out Standard Management Processor Support and Messaging (rev 05)
01:00.4 USB controller: Hewlett-Packard Company Integrated Lights-Out Standard Virtual USB Controller (rev 02)
02:00.0 Ethernet controller: Intel Corporation 82574L Gigabit Network Connection
03:00.0 Ethernet controller: Intel Corporation 82574L Gigabit Network Connection


And relevant parts from dmesg:


atapci0: <Intel Cougar Point SATA600 controller> port 0x1400-0x1407,0x1408-0x140b,0x1410-0x1417,0x1418-0x141b,0x1420-0x142f,0x1430-0x143f irq 17 at device 31.2 on pci0
ata2: <ATA channel> at channel 0 on atapci0
ata3: <ATA channel> at channel 1 on atapci0
atapci1: <Intel Cougar Point SATA300 controller> port 0x1440-0x1447,0x1448-0x144b,0x1450-0x1457,0x1458-0x145b,0x1460-0x146f,0x1470-0x147f irq 17 at device 31.5 on pci0
ata4: <ATA channel> at channel 0 on atapci1
ata5: <ATA channel> at channel 1 on atapci1


I couldn't find much more relevant in dmesg, should I simply post a full log somewhere? No exciting things found in /var/log/messages either.

Next up is switching places in the cabinet.
 
Wow, this is interesting.


ada0 at ata2 bus 0 scbus0 target 0 lun 0
ada0: <ST3000VN007-2E4166 SC60> ACS-2 ATA SATA 3.x device
ada0: Serial Number Z6A06CDP
ada0: 600.000MB/s transfers (SATA 3.x, UDMA5, PIO 8192bytes)
ada0: 2861588MB (5860533168 512 byte sectors)
ada1 at ata2 bus 0 scbus0 target 1 lun 0
ada1: <Samsung SSD 850 EVO 250GB EMT02B6Q> ACS-2 ATA SATA 3.x device
ada1: Serial Number S2R6NX0J411143Y
ada1: 300.000MB/s transfers (SATA 2.x, UDMA5, PIO 512bytes)
ada1: 238475MB (488397168 512 byte sectors)
ada1: quirks=0x3<4K,NCQ_TRIM_BROKEN>
ada2 at ata3 bus 0 scbus1 target 0 lun 0
ada2: <ST3000VN007-2E4166 SC60> ACS-2 ATA SATA 3.x device
ada2: Serial Number Z6A06LWX
ada2: 600.000MB/s transfers (SATA 3.x, UDMA5, PIO 8192bytes)
ada2: 2861588MB (5860533168 512 byte sectors)


ada0 has not been moved, but ada2 and ada1 has both been moved. Order in the cabinet is now ada0, ada2 and ada1 which makes me confused but probably has some explanation. It seems that the SSD is also reporting a pretty high temperature so all fans are working like crazy.
 
So the SSD is a SATA2 device which is now plugged into a SATA2 controller. Previously, it was plugged into a SATA3 controller, but the device limited it to SATA2 speeds.

The second Seagate drive is a SATA3 device that was plugged into a SATA2 controller, thus limiting it SATA2 speeds. Now it's plugged into a SATA3 controller.

IOW, you have now found the optimal configuration, with the SSD on a SATA2 controller, and the two Seagate drives connected to a SATA3 controller. :)
 
phoenix said:
So the SSD is a SATA2 device which is now plugged into a SATA2 controller.
Click to expand...

I'm 100% certain that that SSD has a SATA-3 interface and so does samsung if you check the datasheet. :)

oscar, your config will be optimal with the disks running at SATA-2 link speed and your SSD at SATA-3.

As ralphbsz and usdmatt said, your HDD's wont benefit from SATA-3 link speeds.

You should try to get your SSD to operate at SATA-3 link speed.
 
oscar said:
It seems that the SSD is also reporting a pretty high temperature so all fans are working like crazy.
Click to expand...
To me, that would be way more important than link speed. Most systems are not able to exploit the difference between 300 and 600 MByte/sec on a disk interface; but frying your hardware is not a good idea.
 
(IDE mode, ports 0-3)
Click to expand...

Might not make any difference to this issue but is there a BIOS setting for the SATA controller(s) that's set to legacy/ide mode? You're better off set to AHCI really if it has the option.
 
You must log in or register to reply here.
Back
Top