* very slow write to AHCI device
@ 2012-05-07 16:16 Daniel Pocock
2012-05-07 18:10 ` Martin Mokrejs
0 siblings, 1 reply; 6+ messages in thread
From: Daniel Pocock @ 2012-05-07 16:16 UTC (permalink / raw)
To: linux-ide
Hi,
I'm testing a problem with the following combination:
- SB700/SB800 type controller in AHCI mode (in a HP Microserver N36L)
- Seagate Barracuda 1TB 7k2 drive with NCQ
I've got a fresh 256MB partition, formatted ext4, mounted
barrier=1,data=ordered, write-cache enabled (hdparm -W 1 /dev/sdb) and
shared over NFS.
When the NFS client writes,
- unpacking a source tarball, many small files, iostat reports speeds
under 500kBytes/sec
- dd conv=fsync, iostat reports about 50MB/sec
If I set up a USB disk on the same box, with a partition formatted
exactly the same way, the iostat reports the write speed (unpacking the
same tarball) is over 5MBytes/sec - not so fast, but 10 times faster
than the AHCI device.
Is there anything I can do to troubleshoot this issue?
Or should I just stop using this onboard SATA and go to something like
an Adaptec 1405?
Regards,
Daniel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: very slow write to AHCI device
2012-05-07 16:16 very slow write to AHCI device Daniel Pocock
@ 2012-05-07 18:10 ` Martin Mokrejs
2012-05-07 18:11 ` Daniel Pocock
0 siblings, 1 reply; 6+ messages in thread
From: Martin Mokrejs @ 2012-05-07 18:10 UTC (permalink / raw)
To: Daniel Pocock; +Cc: linux-ide
Hi Daniel,
Daniel Pocock wrote:
>
>
> Hi,
>
> I'm testing a problem with the following combination:
> - SB700/SB800 type controller in AHCI mode (in a HP Microserver N36L)
> - Seagate Barracuda 1TB 7k2 drive with NCQ
Is that a disk with 4k hardware sectors (Advanced Format)? Where does
you partition start? At sector 63 or 2048? ;-)
>
> I've got a fresh 256MB partition, formatted ext4, mounted
> barrier=1,data=ordered, write-cache enabled (hdparm -W 1 /dev/sdb) and
> shared over NFS.
>
> When the NFS client writes,
> - unpacking a source tarball, many small files, iostat reports speeds
> under 500kBytes/sec
> - dd conv=fsync, iostat reports about 50MB/sec
>
> If I set up a USB disk on the same box, with a partition formatted
> exactly the same way, the iostat reports the write speed (unpacking the
> same tarball) is over 5MBytes/sec - not so fast, but 10 times faster
> than the AHCI device.
So USB is at speed 10 times less, right?
Martin
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: very slow write to AHCI device
2012-05-07 18:10 ` Martin Mokrejs
@ 2012-05-07 18:11 ` Daniel Pocock
2012-05-07 18:27 ` Martin Mokrejs
0 siblings, 1 reply; 6+ messages in thread
From: Daniel Pocock @ 2012-05-07 18:11 UTC (permalink / raw)
To: Martin Mokrejs; +Cc: linux-ide
On 07/05/12 20:10, Martin Mokrejs wrote:
> Hi Daniel,
>
> Daniel Pocock wrote:
>
>>
>> Hi,
>>
>> I'm testing a problem with the following combination:
>> - SB700/SB800 type controller in AHCI mode (in a HP Microserver N36L)
>> - Seagate Barracuda 1TB 7k2 drive with NCQ
>>
> Is that a disk with 4k hardware sectors (Advanced Format)? Where does
> you partition start? At sector 63 or 2048? ;-)
>
>
At 2048:
Disk /dev/sdb: 1000.2 GB, 1000204886016 bytes
255 heads, 63 sectors/track, 121601 cylinders, total 1953525168 sectors
Units = sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disk identifier: 0x484d5754
Device Boot Start End Blocks Id System
/dev/sdb1 * 2048 499711 248832 83 Linux
Partition 1 does not end on cylinder boundary.
/dev/sdb2 499712 1953523711 976512000 fd Linux raid
autodetect
>> I've got a fresh 256MB partition, formatted ext4, mounted
>> barrier=1,data=ordered, write-cache enabled (hdparm -W 1 /dev/sdb) and
>> shared over NFS.
>>
>> When the NFS client writes,
>> - unpacking a source tarball, many small files, iostat reports speeds
>> under 500kBytes/sec
>> - dd conv=fsync, iostat reports about 50MB/sec
>>
>> If I set up a USB disk on the same box, with a partition formatted
>> exactly the same way, the iostat reports the write speed (unpacking the
>> same tarball) is over 5MBytes/sec - not so fast, but 10 times faster
>> than the AHCI device.
>>
> So USB is at speed 10 times less, right?
>
>
No - the USB is 10x faster, 5MBytes/sec, the SATA disk is giving me
barely 500kBytes/sec for the same write over NFS
> Martin
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ide" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: very slow write to AHCI device
2012-05-07 18:11 ` Daniel Pocock
@ 2012-05-07 18:27 ` Martin Mokrejs
2012-05-07 23:30 ` Daniel Pocock
0 siblings, 1 reply; 6+ messages in thread
From: Martin Mokrejs @ 2012-05-07 18:27 UTC (permalink / raw)
To: Daniel Pocock; +Cc: linux-ide
Daniel Pocock wrote:
> On 07/05/12 20:10, Martin Mokrejs wrote:
>> Hi Daniel,
>>
>> Daniel Pocock wrote:
>>
>>>
>>> Hi,
>>>
>>> I'm testing a problem with the following combination:
>>> - SB700/SB800 type controller in AHCI mode (in a HP Microserver N36L)
>>> - Seagate Barracuda 1TB 7k2 drive with NCQ
>>>
>> Is that a disk with 4k hardware sectors (Advanced Format)? Where does
>> you partition start? At sector 63 or 2048? ;-)
>>
>>
> At 2048:
So you you safe if it would be 4k sector drive.
>
> Disk /dev/sdb: 1000.2 GB, 1000204886016 bytes
> 255 heads, 63 sectors/track, 121601 cylinders, total 1953525168 sectors
> Units = sectors of 1 * 512 = 512 bytes
> Sector size (logical/physical): 512 bytes / 512 bytes
> I/O size (minimum/optimal): 512 bytes / 512 bytes
> Disk identifier: 0x484d5754
>
> Device Boot Start End Blocks Id System
> /dev/sdb1 * 2048 499711 248832 83 Linux
> Partition 1 does not end on cylinder boundary.
> /dev/sdb2 499712 1953523711 976512000 fd Linux raid
> autodetect
I caught myself:
# lsscsi
[0:0:0:0] disk ATA ST380815AS 3.AA /dev/sda
[1:0:0:0] disk ATA WDC WD2502ABYS-0 02.0 /dev/sdb
[2:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdc
[3:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdd
[4:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sde
[5:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdf
# fdisk /dev/sdc
Command (m for help): p
Disk /dev/sdc: 1000.2 GB, 1000204886016 bytes
255 heads, 63 sectors/track, 121601 cylinders, total 1953525168 sectors
Units = sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disk identifier: 0xe997c4dd
Device Boot Start End Blocks Id System
/dev/sdc1 63 1953520064 976760001 fd Linux raid autodetect
Command (m for help): q
# smartctl -a /dev/sdc
smartctl 5.42 2011-10-20 r3458 [x86_64-linux-3.3.2-default] (local build)
Copyright (C) 2002-11 by Bruce Allen, http://smartmontools.sourceforge.net
=== START OF INFORMATION SECTION ===
Model Family: Western Digital RE2-GP
Device Model: WDC WD1000FYPS-01ZKB0
Serial Number: WD-WCASJ1253793
LU WWN Device Id: 5 0014ee 256812a2d
Firmware Version: 02.01B01
User Capacity: 1,000,204,886,016 bytes [1.00 TB]
Sector Size: 512 bytes logical/physical
Device is: In smartctl database [for details use: -P show]
ATA Version is: 8
ATA Standard is: Exact ATA specification draft version not indicated
Local Time is: Mon May 7 20:21:35 2012 MEST
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
[cut]
Do you have same model?
My disk catch up at 3Gbps:
ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
ata3.00: ATA-8: WDC WD1000FYPS-01ZKB0, 02.01B01, max UDMA/133
ata3.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA
ata3.00: configured for UDMA/133
scsi 2:0:0:0: Direct-Access ATA WDC WD1000FYPS-0 02.0 PQ: 0 ANSI: 5
sd 2:0:0:0: [sdc] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
sd 2:0:0:0: Attached scsi generic sg2 type 0
sd 2:0:0:0: [sdc] Write Protect is off
sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sdc: sdc1
sd 2:0:0:0: [sdc] Attached SCSI disk
Martin
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: very slow write to AHCI device
2012-05-07 18:27 ` Martin Mokrejs
@ 2012-05-07 23:30 ` Daniel Pocock
2012-05-08 8:21 ` Martin Mokrejs
0 siblings, 1 reply; 6+ messages in thread
From: Daniel Pocock @ 2012-05-07 23:30 UTC (permalink / raw)
To: Martin Mokrejs; +Cc: linux-ide
>> Disk /dev/sdb: 1000.2 GB, 1000204886016 bytes
>> 255 heads, 63 sectors/track, 121601 cylinders, total 1953525168 sectors
>> Units = sectors of 1 * 512 = 512 bytes
>> Sector size (logical/physical): 512 bytes / 512 bytes
>> I/O size (minimum/optimal): 512 bytes / 512 bytes
>> Disk identifier: 0x484d5754
>>
>> Device Boot Start End Blocks Id System
>> /dev/sdb1 * 2048 499711 248832 83 Linux
>> Partition 1 does not end on cylinder boundary.
>> /dev/sdb2 499712 1953523711 976512000 fd Linux raid
>> autodetect
>>
> I caught myself:
>
> # lsscsi
> [0:0:0:0] disk ATA ST380815AS 3.AA /dev/sda
> [1:0:0:0] disk ATA WDC WD2502ABYS-0 02.0 /dev/sdb
> [2:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdc
> [3:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdd
> [4:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sde
> [5:0:0:0] disk ATA WDC WD1000FYPS-0 02.0 /dev/sdf
> # fdisk /dev/sdc
>
> Command (m for help): p
>
> Disk /dev/sdc: 1000.2 GB, 1000204886016 bytes
> 255 heads, 63 sectors/track, 121601 cylinders, total 1953525168 sectors
> Units = sectors of 1 * 512 = 512 bytes
> Sector size (logical/physical): 512 bytes / 512 bytes
> I/O size (minimum/optimal): 512 bytes / 512 bytes
> Disk identifier: 0xe997c4dd
>
> Device Boot Start End Blocks Id System
> /dev/sdc1 63 1953520064 976760001 fd Linux raid autodetect
>
> Command (m for help): q
>
> # smartctl -a /dev/sdc
> smartctl 5.42 2011-10-20 r3458 [x86_64-linux-3.3.2-default] (local build)
> Copyright (C) 2002-11 by Bruce Allen, http://smartmontools.sourceforge.net
>
> === START OF INFORMATION SECTION ===
> Model Family: Western Digital RE2-GP
> Device Model: WDC WD1000FYPS-01ZKB0
> Serial Number: WD-WCASJ1253793
> LU WWN Device Id: 5 0014ee 256812a2d
> Firmware Version: 02.01B01
> User Capacity: 1,000,204,886,016 bytes [1.00 TB]
> Sector Size: 512 bytes logical/physical
> Device is: In smartctl database [for details use: -P show]
> ATA Version is: 8
> ATA Standard is: Exact ATA specification draft version not indicated
> Local Time is: Mon May 7 20:21:35 2012 MEST
> SMART support is: Available - device has SMART capability.
> SMART support is: Enabled
>
> [cut]
>
> Do you have same model?
>
>
Not quite:
# smartctl -a /dev/sda
smartctl 5.40 2010-07-12 r3124 [x86_64-unknown-linux-gnu] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
=== START OF INFORMATION SECTION ===
Model Family: Seagate Barracuda 7200.12 family
Device Model: ST31000528AS
Serial Number: 6VP0KWSF
Firmware Version: CC49
User Capacity: 1,000,204,886,016 bytes
Device is: In smartctl database [for details use: -P show]
ATA Version is: 8
ATA Standard is: ATA-8-ACS revision 4
Local Time is: Tue May 8 01:26:06 2012 CEST
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
> My disk catch up at 3Gbps:
>
> ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> ata3.00: ATA-8: WDC WD1000FYPS-01ZKB0, 02.01B01, max UDMA/133
> ata3.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA
> ata3.00: configured for UDMA/133
> scsi 2:0:0:0: Direct-Access ATA WDC WD1000FYPS-0 02.0 PQ: 0 ANSI: 5
> sd 2:0:0:0: [sdc] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
> sd 2:0:0:0: Attached scsi generic sg2 type 0
> sd 2:0:0:0: [sdc] Write Protect is off
> sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
> sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
> sdc: sdc1
> sd 2:0:0:0: [sdc] Attached SCSI disk
>
>
One of mine died as soon as I upgraded to the CC49 firmware today:
[ 2905.173593] sd 0:0:0:0: [sda] Unhandled error code
[ 2905.173599] sd 0:0:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
driverbyte=DRIVER_OK
[ 2905.173608] sd 0:0:0:0: [sda] CDB: Write(10): 2a 00 18 f7 aa c8 00 00
10 00
[ 2905.173628] end_request: I/O error, dev sda, sector 418884296
[ 2905.180214] sd 0:0:0:0: [sda] Unhandled error code
[ 2905.180220] sd 0:0:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
driverbyte=DRIVER_OK
[ 2905.180234] sd 0:0:0:0: [sda] CDB: Write(10): 2a 00 18 f7 aa b8 00 00
08 00
[ 2905.180286] end_request: I/O error, dev sda, sector 418884280
[ 2905.180496] md/raid1:md2: Disk failure on sda2, disabling device.
[ 2905.180501] md/raid1:md2: Operation continuing on 1 devices.
[ 2905.199738] sd 0:0:0:0: [sda] Unhandled error code
Lucky I'm using md
I thought maybe the firmware had just exposed a pre-existing problem and
that maybe the bad drive had already been making my AHCI controller slow
down - but removing the drive completely hasn't made operations any
faster on the remaining drive.
I'm now looking to replace them with something like the Seagate
Constellation or another slightly more robust enterprise drive, maybe
even SAS
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: very slow write to AHCI device
2012-05-07 23:30 ` Daniel Pocock
@ 2012-05-08 8:21 ` Martin Mokrejs
0 siblings, 0 replies; 6+ messages in thread
From: Martin Mokrejs @ 2012-05-08 8:21 UTC (permalink / raw)
To: Daniel Pocock; +Cc: linux-ide
Daniel Pocock wrote:
> Not quite:
>
> # smartctl -a /dev/sda
> smartctl 5.40 2010-07-12 r3124 [x86_64-unknown-linux-gnu] (local build)
> Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
>
> === START OF INFORMATION SECTION ===
> Model Family: Seagate Barracuda 7200.12 family
> Device Model: ST31000528AS
> Serial Number: 6VP0KWSF
> Firmware Version: CC49
> User Capacity: 1,000,204,886,016 bytes
> Device is: In smartctl database [for details use: -P show]
> ATA Version is: 8
> ATA Standard is: ATA-8-ACS revision 4
> Local Time is: Tue May 8 01:26:06 2012 CEST
> SMART support is: Available - device has SMART capability.
> SMART support is: Enabled
>
>
>> My disk catch up at 3Gbps:
>>
>> ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
>> ata3.00: ATA-8: WDC WD1000FYPS-01ZKB0, 02.01B01, max UDMA/133
>> ata3.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA
>> ata3.00: configured for UDMA/133
>> scsi 2:0:0:0: Direct-Access ATA WDC WD1000FYPS-0 02.0 PQ: 0 ANSI: 5
>> sd 2:0:0:0: [sdc] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
>> sd 2:0:0:0: Attached scsi generic sg2 type 0
>> sd 2:0:0:0: [sdc] Write Protect is off
>> sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
>> sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
>> sdc: sdc1
>> sd 2:0:0:0: [sdc] Attached SCSI disk
>>
>>
>
>
> One of mine died as soon as I upgraded to the CC49 firmware today:
>
> [ 2905.173593] sd 0:0:0:0: [sda] Unhandled error code
> [ 2905.173599] sd 0:0:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
> driverbyte=DRIVER_OK
> [ 2905.173608] sd 0:0:0:0: [sda] CDB: Write(10): 2a 00 18 f7 aa c8 00 00
> 10 00
> [ 2905.173628] end_request: I/O error, dev sda, sector 418884296
> [ 2905.180214] sd 0:0:0:0: [sda] Unhandled error code
> [ 2905.180220] sd 0:0:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
> driverbyte=DRIVER_OK
> [ 2905.180234] sd 0:0:0:0: [sda] CDB: Write(10): 2a 00 18 f7 aa b8 00 00
> 08 00
> [ 2905.180286] end_request: I/O error, dev sda, sector 418884280
> [ 2905.180496] md/raid1:md2: Disk failure on sda2, disabling device.
> [ 2905.180501] md/raid1:md2: Operation continuing on 1 devices.
> [ 2905.199738] sd 0:0:0:0: [sda] Unhandled error code
>
>
I use CC4C in my 3TB Seagates (ST3000DM001 disk, 4k sectors). Do you wnat to downgrade? ;-)
Martin
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2012-05-08 8:18 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-05-07 16:16 very slow write to AHCI device Daniel Pocock
2012-05-07 18:10 ` Martin Mokrejs
2012-05-07 18:11 ` Daniel Pocock
2012-05-07 18:27 ` Martin Mokrejs
2012-05-07 23:30 ` Daniel Pocock
2012-05-08 8:21 ` Martin Mokrejs
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).