Skip to contentSkip to conversation

Disk speed comparison

DISCUSSION Roy Sigurd Karlsbakk 3 participants 9 messages Dec 22, 2012 – Dec 23, 2012 MD RAID

lore
Share & tools
lore
#0 lore raw

Hi all

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

Anyone seen something similar?

Vennlige hilsener / Best regards

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. --
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#1 lore raw
Quoted 8 lines · Roy Sigurd Karlsbakk

Hi all

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

Anyone seen something similar?

Vennlige hilsener / Best regards

Quoted 10 lines

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. --

Go the the manufacturers web sites and find the spec sheets for the drivers.

They will likely list a min speed and a max speed for how fast data is passing under the head depending on if it is the inner or outer track.

It basically comes down to if all is working exactly right, the number of bytes passing under the head times rpm, so if one disk has a higher bit density the rate will be larger, and this varies quite a bit from disk to disk.
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#2 lore raw
Quoted 14 lines
Quoted 10 lines

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at
http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html
that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

Anyone seen something similar?

Go the the manufacturers web sites and find the spec sheets for the drivers.

Quoted 7 lines

They will likely list a min speed and a max speed for how fast data is passing under the head depending on if it is the inner or outer track.

It basically comes down to if all is working exactly right, the number of bytes passing under the head times rpm, so if one disk has a higher bit density the rate will be larger, and this varies quite a bit from disk to disk.

Thanks for the replay

WD2001FASS: 4x500GB platters
HDS723020BLA642: 3x667GB platters

- Shouldn't higher density normally mean higher speed?

Vennlige hilsener / Best regards

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. --
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#3 lore raw
Quoted 31 lines · Roy Sigurd Karlsbakk
Quoted 14 lines
Quoted 10 lines

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at
http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html
that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

Anyone seen something similar?

Go the the manufacturers web sites and find the spec sheets for the drivers.

Quoted 7 lines

They will likely list a min speed and a max speed for how fast data is passing under the head depending on if it is the inner or outer track.

It basically comes down to if all is working exactly right, the number of bytes passing under the head times rpm, so if one disk has a higher bit density the rate will be larger, and this varies quite a bit from disk to disk.

Thanks for the replay

WD2001FASS: 4x500GB platters
HDS723020BLA642: 3x667GB platters

- Shouldn't higher density normally mean higher speed?

Vennlige hilsener / Best regards

Quoted 9 lines

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk.

Depends...that assumes that the tracks on each manufacturers disks is the same...the higher density platters could have more tracks and because of that lower date per track and lower bit rates per track.

Check what the manufacturer says on bit rates under the head. --
To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#4 lore raw
Quoted 10 lines
Quoted 4 lines

WD2001FASS: 4x500GB platters
HDS723020BLA642: 3x667GB platters

- Shouldn't higher density normally mean higher speed?

Depends...that assumes that the tracks on each manufacturers disks is the same...the higher density platters could have more tracks and because of that lower date per track and lower bit rates per track.

Check what the manufacturer says on bit rates under the head.

hrmf - can't find any data on that from WD - Hitachi is quite clear on that part, though… http://www.hgst.com/internal-drives/desktop/deskstar/deskstar-7k3000

Signature · 15 lines
Vennlige hilsener / Best regards

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk.
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
#5 lore raw
Quoted 1 line · Roy Sigurd Karlsbakk

WD2001FASS

From the stuff the wd runs max 138 and the hds runs max 163...assuming you are using
the outside tracks on both, inside tracks can be 2x slower (less data).

I would make sure they are both running the same sata speed, if a sata/ide port gets errors sometimes
it drops the speed and retries at the slower speed, and generally once it throttles down a reboot is
required to undo it.

look at hdparm/sdparm (which works depends on distro) and smartctl to see what you can pull about
the disks.

#6 lore raw
In reply to Roy Sigurd Karlsbakk
Quoted 1 line · Roy Sigurd Karlsbakk

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

You've provided zero information about the controllers or the configuration of the drives. If the SATA ASIC to which the Black drives are connected is AHCI and the other is not, then NCQ may account for the difference in performance. Or, both may currently be AHCI, but possibly the Hitachi drives perform better with NCQ disabled. This would not be rare. If you laid partitions on the Hitachi drives and misaligned them, this could easily cause a 30% deficit. Etc, etc.

I doubt there is a 30% overall performance difference between these two drive models. The Black models are "enthusiast" class drives, and do have some additional performance features, but not that I'd think would yield a 30% advantage.

You need to dig deeper into the details.

Signature · 1 line
Stan
#7 lore raw
Quoted 21 lines
Quoted 8 lines

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at
http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html
that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

You've provided zero information about the controllers or the configuration of the drives. If the SATA ASIC to which the Black drives
are connected is AHCI and the other is not, then NCQ may account for the
difference in performance. Or, both may currently be AHCI, but possibly
the Hitachi drives perform better with NCQ disabled. This would not be rare. If you laid partitions on the Hitachi drives and misaligned them,
this could easily cause a 30% deficit. Etc, etc.

Quoted 8 lines

I doubt there is a 30% overall performance difference between these two
drive models. The Black models are "enthusiast" class drives, and do have some additional performance features, but not that I'd think would
yield a 30% advantage.

You need to dig deeper into the details.

no partitions on this setup, just plain drives. what munin tells me is those WD drives are rather faster than the hitachis. As noted, all drives are on a mixed controller setup, the hitachis and wd drives share controllers for some. the only known common factor for the slow and fast drives are their label.

Signature · 15 lines
Vennlige hilsener / Best regards

roy
--
Roy Sigurd Karlsbakk
(+47) 98013356
[email protected]
http://blogg.karlsbakk.net/
GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt
--
I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk.
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
#8 lore raw
Quoted 28 lines · Roy Sigurd Karlsbakk
Quoted 28 lines
Quoted 8 lines

I have an array with 6 2TB drives plus a spare. While this works well, I can from the munin graphs at
http://munin.karlsbakk.net/munin/karlsbakk.net/smilla.karlsbakk.net/index.html
that the WD2001FASS drives (sd[bcfg]) perform some 30% better than the Hitachi HDS723020BLA642 drives (sd[eh]). The drives are on a mixed set of controllers, so this shouldn't be relevant. Since they all are specified to spin on 7200RPM, I find it wierd that the performance difference shown by the Munin graph is so big.

You've provided zero information about the controllers or the configuration of the drives. If the SATA ASIC to which the Black drives
are connected is AHCI and the other is not, then NCQ may account for the
difference in performance. Or, both may currently be AHCI, but possibly
the Hitachi drives perform better with NCQ disabled. This would not be rare. If you laid partitions on the Hitachi drives and misaligned them,
this could easily cause a 30% deficit. Etc, etc.

I doubt there is a 30% overall performance difference between these two
drive models. The Black models are "enthusiast" class drives, and do have some additional performance features, but not that I'd think would
yield a 30% advantage.

Quoted 3 lines
Quoted 1 line

You need to dig deeper into the details.

no partitions on this setup, just plain drives. what munin tells me is those WD drives are rather faster than the hitachis. As noted, all drives are on a mixed controller setup, the hitachis and wd drives share controllers for some. the only known common factor for the slow and fast drives are their label.

I just looked at your Munin graphs more closely. Your interpretation of 30% difference in performance doesn't seem to be accurate. All 6 drives have nearly identical daily and weekly avg IOs and throughput. The avg latency of the Hitachi drives is a few milliseconds higher, but this doesn't seem to be negatively affecting IOPS or throughput.

How are you determining your claimed 30% performance deficit? I don't see it.

Signature · 1 line
Stan