View previous topic :: View next topic |
Author |
Message |
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Sun Oct 07, 2012 2:06 pm Post subject: What's wrong with my drive setup? |
|
|
I recently had a hard drive failure on my root drive. I replaced it with a SATA3 1TB drive. Thanks to some folks here, I found out I had to jumper the drive so it would show up as max SATA2 before my motherboard could use it.
I have four partitions on the drive:
Code: | 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: 0x47b8944d
Device Boot Start End Blocks Id System
/dev/sdc1 * 2048 67583 32768 83 Linux
/dev/sdc2 67584 2164735 1048576 82 Linux swap / Solaris
/dev/sdc3 2164736 631310335 314572800 83 Linux
/dev/sdc4 631310336 1953525167 661107416 83 Linux |
1 is my boot partition (EXT2), 2 is obviously swap, 3 is root (EXT3), and 4 is a media partition (XFS).
Here's my problem - I transfer large files from my video editing to partition 4 all the time, but the file transfers to or from this drive take forever. For instance, a 10GB file will transfer to another drive on the same system in a couple of minutes, but will take about 20 minutes if I'm transferring to SDC.
In addition, since my root partition is on this drive, even pulling directory listings while a file is transferring takes forever.
Any suggestions? |
|
Back to top |
|
|
eccerr0r Watchman
Joined: 01 Jul 2004 Posts: 9712 Location: almost Mile High in the USA
|
Posted: Sun Oct 07, 2012 6:10 pm Post subject: |
|
|
The first guess most people would assume is probably not it - it looks like your partitions are indeed on 4K boundaries so it should be fine.
The next question is how did you mke2fs the drives? Did you use special options like decrease block sizes?
Then after that, do you see SMART issues (using smartmontools) or see any issues in your dmesg log indicating the disk having problems?
What brand/model of disk is it? I thought "the jumper" usually makes it go back to SATA 1.5Gbps... I haven't seen enough sata 6Gbit disks to know (only two sata 6Gbit disks I have are SSDs and they don't appear to have jumpers.) _________________ Intel Core i7 2700K/Radeon R7 250/24GB DDR3/256GB SSD
What am I supposed watching? |
|
Back to top |
|
|
kimmie Guru
Joined: 08 Sep 2004 Posts: 531 Location: Australia
|
Posted: Mon Oct 08, 2012 9:25 am Post subject: |
|
|
Does this happen with both sdc3 and sdc4, or does it depend on the filesystem?
What is the output of "xfs_info /dev/sdc4 ; grep sdc4 /proc/mounts"? |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Mon Oct 08, 2012 7:29 pm Post subject: |
|
|
eccerr0r wrote: | The first guess most people would assume is probably not it - it looks like your partitions are indeed on 4K boundaries so it should be fine.
The next question is how did you mke2fs the drives? Did you use special options like decrease block sizes?
Then after that, do you see SMART issues (using smartmontools) or see any issues in your dmesg log indicating the disk having problems?
What brand/model of disk is it? I thought "the jumper" usually makes it go back to SATA 1.5Gbps... I haven't seen enough sata 6Gbit disks to know (only two sata 6Gbit disks I have are SSDs and they don't appear to have jumpers.) |
I just did standard mkfs's when I made the filesystems. smartctl lists no errors, nor does the message log.
The drive info:
Code: | Model Family: Western Digital Caviar Blue Serial ATA
Device Model: WDC WD10EALX-009BA0
|
|
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Mon Oct 08, 2012 7:30 pm Post subject: |
|
|
kimmie wrote: | Does this happen with both sdc3 and sdc4, or does it depend on the filesystem?
What is the output of "xfs_info /dev/sdc4 ; grep sdc4 /proc/mounts"? |
Good question - I'll try to copy a big file to sdc3 to see what happens.
Code: | log # xfs_info /dev/sdc4 ; grep sdc4 /proc/mounts
meta-data=/dev/sdc4 isize=256 agcount=4, agsize=41319214 blks
= sectsz=512 attr=2
data = bsize=4096 blocks=165276854, imaxpct=25
= sunit=0 swidth=0 blks
naming =version 2 bsize=4096 ascii-ci=0
log =internal bsize=4096 blocks=80701, version=2
= sectsz=512 sunit=0 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
/dev/sdc4 /var/video3 xfs rw,noatime,attr2,allocsize=524288k,noquota 0 0 |
|
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Mon Oct 08, 2012 7:45 pm Post subject: |
|
|
I've set up an additional Samba mount, and I'm currently copying a file to sdc3 from my Windows PC using teracopy, which gives me the transfer rate. It looks like it will go quickly (~15MB/s), and then drop down to 2MB/s or so.
After I've copied the file to this partition, I'll also copy it to another (working) partition on this machine, and to the original bad partition, and post the transfer times of the three for comparison. |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Mon Oct 08, 2012 8:55 pm Post subject: |
|
|
Copying to sdc3 (the ext3 root partition): 6.75 GB, 22:38, 5.1MB/s
Copying to sdc4 (XFS): 6.75 GB, 27:45, 4.1MB/s
Copying to another XFS partition on the same machine: 6.75GB, 2:24, 48MB/s
Looks like it's an issue with the way the drive is set up, as opposed to the partitions. |
|
Back to top |
|
|
eccerr0r Watchman
Joined: 01 Jul 2004 Posts: 9712 Location: almost Mile High in the USA
|
Posted: Mon Oct 08, 2012 10:31 pm Post subject: |
|
|
Did you use the same port as the old drive it replaced?
What disk driver is the port you're using...using? _________________ Intel Core i7 2700K/Radeon R7 250/24GB DDR3/256GB SSD
What am I supposed watching? |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Tue Oct 09, 2012 2:09 am Post subject: |
|
|
eccerr0r wrote: | Did you use the same port as the old drive it replaced?
What disk driver is the port you're using...using? |
Nah - it's a new install, since my root drive died. The old root drive was on an IDE port.
I'm using in-kernel sata_nv for all of my drives. |
|
Back to top |
|
|
kimmie Guru
Joined: 08 Sep 2004 Posts: 531 Location: Australia
|
Posted: Tue Oct 09, 2012 5:24 am Post subject: |
|
|
What does /var/log/dmesg say about the drive? |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Tue Oct 09, 2012 2:20 pm Post subject: |
|
|
kimmie wrote: | What does /var/log/dmesg say about the drive? |
Code: | linux # dmesg|grep sdc
[ 0.000000] Command line: root=/dev/sdc3
[ 0.000000] Kernel command line: root=/dev/sdc3
[ 2.537675] sd 2:0:0:0: [sdc] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
[ 2.538101] sd 2:0:0:0: [sdc] Write Protect is off
[ 2.538332] sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
[ 2.538371] sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 2.567312] sdc: sdc1 sdc2 sdc3 sdc4
[ 2.568145] sd 2:0:0:0: [sdc] Attached SCSI disk
[ 4.116834] EXT3-fs (sdc3): mounted filesystem with writeback data mode
[ 10.533862] EXT3-fs (sdc3): using internal journal
[ 10.985718] XFS (sdc4): Mounting Filesystem
[ 11.318844] XFS (sdc4): Ending clean mount
[ 12.468753] Adding 1048572k swap on /dev/sdc2. Priority:-1 extents:1 across:1048572k
|
|
|
Back to top |
|
|
kimmie Guru
Joined: 08 Sep 2004 Posts: 531 Location: Australia
|
Posted: Wed Oct 10, 2012 7:54 am Post subject: |
|
|
It's a bit hard coming up with a theory, hey? I thought perhaps the write cache was off, but that's not it. There used to be an issue with certain WD green drives and head unloading; this can cause a throughput issue depending on your power management config. Maybe it's sata_nv not liking the drive, or the jumpered drive? Anyway, might as well see what there is to see...
That grep of dmesg didn't show the controller info, so how about: egrep -i 'ata|sd' /var/log/dmesg
Also, what is SMART telling us: smartctl -a /dev/sdc ?
What kernel are you using? I found a report of someone using a jumpered SATA3 drive with nForce under windows going slow until they updated their chipset driver...
Sorry about the turnaround, timezones, y'know. |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Wed Oct 10, 2012 1:13 pm Post subject: |
|
|
Code: | # egrep -i 'ata|sd' /var/log/dmesg
[ 0.000000] Command line: root=/dev/sdc3
[ 0.000000] BIOS-e820: 000000007ffd0000 - 000000007ffde000 (ACPI data)
[ 0.000000] modified: 000000007ffd0000 - 000000007ffde000 (ACPI data)
[ 0.000000] ACPI: RSDP 00000000000f88a0 00014 (v00 ACPIAM)
[ 0.000000] ACPI: RSDT 000000007ffd0000 00034 (v01 A M I OEMRSDT 04000607 MSFT 00000097)
[ 0.000000] ACPI: DSDT 000000007ffd0410 057C8 (v01 1ACAI 1ACAI003 00000003 INTL 02002026)
[ 0.000000] NODE_DATA [0000000135ffb000 - 0000000135ffffff]
[ 0.000000] Kernel command line: root=/dev/sdc3
[ 0.000000] Memory: 2787396k/5079040k available (7704k kernel code, 2097796k absent, 193848k reserved, 5287k data, 580k init)
[ 0.259604] ACPI: EC: Look up EC in DSDT
[ 0.331429] ACPI: PCI Interrupt Link [LATA] (IRQs 20 21 22) *14
[ 0.335252] libata version 3.00 loaded.
[ 1.003891] Installing knfsd (copyright (C) 1996 okir@monad.swb.de).
[ 1.593212] sata_nv 0000:00:07.0: version 3.5
[ 1.593627] sata_nv 0000:00:07.0: setting latency timer to 64
[ 1.594241] scsi0 : sata_nv
[ 1.594553] scsi1 : sata_nv
[ 1.594897] ata1: SATA max UDMA/133 cmd 0xc800 ctl 0xc400 bmdma 0xb800 irq 20
[ 1.594997] ata2: SATA max UDMA/133 cmd 0xc000 ctl 0xbc00 bmdma 0xb808 irq 20
[ 1.595510] sata_nv 0000:00:08.0: setting latency timer to 64
[ 1.596212] scsi2 : sata_nv
[ 1.596522] scsi3 : sata_nv
[ 1.596861] ata3: SATA max UDMA/133 cmd 0xb400 ctl 0xb000 bmdma 0xa400 irq 22
[ 1.596959] ata4: SATA max UDMA/133 cmd 0xac00 ctl 0xa800 bmdma 0xa408 irq 22
[ 1.597567] sata_nv 0000:80:07.0: setting latency timer to 64
[ 1.598232] scsi4 : sata_nv
[ 1.598537] scsi5 : sata_nv
[ 1.598875] ata5: SATA max UDMA/133 cmd 0xf800 ctl 0xf400 bmdma 0xe800 irq 47
[ 1.598975] ata6: SATA max UDMA/133 cmd 0xf000 ctl 0xec00 bmdma 0xe808 irq 47
[ 1.599525] sata_nv 0000:80:08.0: setting latency timer to 64
[ 1.600226] scsi6 : sata_nv
[ 1.600534] scsi7 : sata_nv
[ 1.600878] ata7: SATA max UDMA/133 cmd 0xe400 ctl 0xe000 bmdma 0xd400 irq 46
[ 1.600976] ata8: SATA max UDMA/133 cmd 0xdc00 ctl 0xd800 bmdma 0xd408 irq 46
[ 1.601364] pata_amd 0000:00:06.0: version 0.4.1
[ 1.601401] pata_amd 0000:00:06.0: setting latency timer to 64
[ 1.602229] scsi8 : pata_amd
[ 1.602539] scsi9 : pata_amd
[ 1.604104] ata9: PATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0x3000 irq 14
[ 1.604203] ata10: PATA max UDMA/133 cmd 0x170 ctl 0x376 bmdma 0x3008 irq 15
[ 1.902025] ata5: SATA link down (SStatus 0 SControl 300)
[ 1.904024] ata7: SATA link down (SStatus 0 SControl 300)
[ 2.049035] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 2.052302] ata1.00: ATA-8: ST3000DM001-9YN166, CC9D, max UDMA/133
[ 2.052407] ata1.00: 5860533168 sectors, multi 16: LBA48 NCQ (depth 0/32)
[ 2.074282] ata1.00: configured for UDMA/133
[ 2.074596] scsi 0:0:0:0: Direct-Access ATA ST3000DM001-9YN1 CC9D PQ: 0 ANSI: 5
[ 2.075135] sd 0:0:0:0: [sda] 5860533168 512-byte logical blocks: (3.00 TB/2.72 TiB)
[ 2.075331] sd 0:0:0:0: [sda] 4096-byte physical blocks
[ 2.075352] sd 0:0:0:0: Attached scsi generic sg0 type 0
[ 2.075605] sd 0:0:0:0: [sda] Write Protect is off
[ 2.075700] sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
[ 2.075722] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 2.102030] ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 2.106110] ata3.00: ATA-8: WDC WD10EALX-009BA0, 15.01H15, max UDMA/133
[ 2.106212] ata3.00: 1953525168 sectors, multi 16: LBA48 NCQ (depth 0/32)
[ 2.112266] ata3.00: configured for UDMA/133
[ 2.369622] sda: sda1
[ 2.370120] sd 0:0:0:0: [sda] Attached SCSI disk
[ 2.529031] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 2.532198] ata2.00: ATA-8: INTEL SSDSA2CW080G3, 4PC10362, max UDMA/133
[ 2.532299] ata2.00: 156301488 sectors, multi 16: LBA48 NCQ (depth 0/32)
[ 2.535202] ata2.00: configured for UDMA/133
[ 2.535532] scsi 1:0:0:0: Direct-Access ATA INTEL SSDSA2CW08 4PC1 PQ: 0 ANSI: 5
[ 2.536056] sd 1:0:0:0: [sdb] 156301488 512-byte logical blocks: (80.0 GB/74.5 GiB)
[ 2.536275] sd 1:0:0:0: Attached scsi generic sg1 type 0
[ 2.536314] sd 1:0:0:0: [sdb] Write Protect is off
[ 2.536317] sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
[ 2.536337] sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 2.536932] scsi 2:0:0:0: Direct-Access ATA WDC WD10EALX-009 15.0 PQ: 0 ANSI: 5
[ 2.537105] sdb: sdb1
[ 2.537675] sd 2:0:0:0: [sdc] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
[ 2.537732] sd 1:0:0:0: [sdb] Attached SCSI disk
[ 2.538101] sd 2:0:0:0: [sdc] Write Protect is off
[ 2.538129] sd 2:0:0:0: Attached scsi generic sg2 type 0
[ 2.538332] sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
[ 2.538371] sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 2.567312] sdc: sdc1 sdc2 sdc3 sdc4
[ 2.568145] sd 2:0:0:0: [sdc] Attached SCSI disk
[ 2.992038] ata4: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 3.272822] ata4.00: ATA-8: WDC WD10EACS-00ZJB0, 01.01B01, max UDMA/133
[ 3.272924] ata4.00: 1953525168 sectors, multi 16: LBA48 NCQ (depth 0/32)
[ 3.279689] ata4.00: configured for UDMA/133
[ 3.279943] scsi 3:0:0:0: Direct-Access ATA WDC WD10EACS-00Z 01.0 PQ: 0 ANSI: 5
[ 3.280475] sd 3:0:0:0: [sdd] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB)
[ 3.280603] sd 3:0:0:0: Attached scsi generic sg3 type 0
[ 3.280849] sd 3:0:0:0: [sdd] Write Protect is off
[ 3.280948] sd 3:0:0:0: [sdd] Mode Sense: 00 3a 00 00
[ 3.280970] sd 3:0:0:0: [sdd] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 3.289249] sdd: sdd1
[ 3.289735] sd 3:0:0:0: [sdd] Attached SCSI disk
[ 3.583027] ata6: SATA link down (SStatus 0 SControl 300)
[ 3.886022] ata8: SATA link down (SStatus 0 SControl 300)
[ 4.051794] ata10.01: ATAPI: SONY CDU4811, PY09, max UDMA/33, CDB intr
[ 4.051906] ata10: nv_mode_filter: 0x739f&0x739f->0x739f, BIOS=0x7000 (0xc0) ACPI=0x701f (900:54:0x14)
[ 4.059816] ata10.01: configured for UDMA/33
[ 4.116834] EXT3-fs (sdc3): mounted filesystem with writeback data mode
[ 4.118818] Write protecting the kernel read-only data: 12288k
[ 10.533862] EXT3-fs (sdc3): using internal journal
[ 10.661462] XFS (sda1): Mounting Filesystem
[ 10.809709] XFS (sda1): Ending clean mount
[ 10.825655] XFS (sdd1): Mounting Filesystem
[ 10.957178] XFS (sdd1): Ending clean mount
[ 10.960086] EXT3-fs (sdb1): using internal journal
[ 10.960090] EXT3-fs (sdb1): mounted filesystem with writeback data mode
[ 10.985718] XFS (sdc4): Mounting Filesystem
[ 11.318844] XFS (sdc4): Ending clean mount
|
Code: | # smartctl -a /dev/sdc
smartctl 5.42 2011-10-20 r3458 [x86_64-linux-3.3.8-gentoo] (local build)
Copyright (C) 2002-11 by Bruce Allen, http://smartmontools.sourceforge.net
=== START OF INFORMATION SECTION ===
Model Family: Western Digital Caviar Blue Serial ATA
Device Model: WDC WD10EALX-009BA0
Serial Number: WD-WMATR1376127
LU WWN Device Id: 5 0014ee 2b1d8a021
Firmware Version: 15.01H15
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: Wed Oct 10 09:10:56 2012 EDT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
General SMART Values:
Offline data collection status: (0x82) Offline data collection activity
was completed without error.
Auto Offline Data Collection: Enabled.
Self-test execution status: ( 0) The previous self-test routine completed
without error or no self-test has ever
been run.
Total time to complete Offline
data collection: (16800) seconds.
Offline data collection
capabilities: (0x7b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
Offline surface scan supported.
Self-test supported.
Conveyance Self-test supported.
Selective Self-test supported.
SMART capabilities: (0x0003) Saves SMART data before entering
power-saving mode.
Supports SMART auto save timer.
Error logging capability: (0x01) Error logging supported.
General Purpose Logging supported.
Short self-test routine
recommended polling time: ( 2) minutes.
Extended self-test routine
recommended polling time: ( 194) minutes.
Conveyance self-test routine
recommended polling time: ( 5) minutes.
SCT capabilities: (0x3037) SCT Status supported.
SCT Feature Control supported.
SCT Data Table supported.
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x002f 200 200 051 Pre-fail Always - 0
3 Spin_Up_Time 0x0027 172 172 021 Pre-fail Always - 4375
4 Start_Stop_Count 0x0032 100 100 000 Old_age Always - 11
5 Reallocated_Sector_Ct 0x0033 200 200 140 Pre-fail Always - 0
7 Seek_Error_Rate 0x002e 200 200 000 Old_age Always - 0
9 Power_On_Hours 0x0032 099 099 000 Old_age Always - 1251
10 Spin_Retry_Count 0x0032 100 253 000 Old_age Always - 0
11 Calibration_Retry_Count 0x0032 100 253 000 Old_age Always - 0
12 Power_Cycle_Count 0x0032 100 100 000 Old_age Always - 9
192 Power-Off_Retract_Count 0x0032 200 200 000 Old_age Always - 7
193 Load_Cycle_Count 0x0032 200 200 000 Old_age Always - 3
194 Temperature_Celsius 0x0022 120 111 000 Old_age Always - 27
196 Reallocated_Event_Count 0x0032 200 200 000 Old_age Always - 0
197 Current_Pending_Sector 0x0032 200 200 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0030 200 200 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x0032 200 200 000 Old_age Always - 0
200 Multi_Zone_Error_Rate 0x0008 200 200 000 Old_age Offline - 0
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
No self-tests have been logged. [To run self-tests, use: smartctl -t]
SMART Selective self-test log data structure revision number 1
SPAN MIN_LBA MAX_LBA CURRENT_TEST_STATUS
1 0 0 Not_testing
2 0 0 Not_testing
3 0 0 Not_testing
4 0 0 Not_testing
5 0 0 Not_testing
Selective self-test flags (0x0):
After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.
|
Code: | # uname -r
3.3.8-gentoo
|
No worries about the turnaround - I appreciate the help! |
|
Back to top |
|
|
kimmie Guru
Joined: 08 Sep 2004 Posts: 531 Location: Australia
|
Posted: Wed Oct 10, 2012 4:20 pm Post subject: |
|
|
I can't see any issues
Just to check your benchmarks, what sort of rate do you get when you write a 512M file using dd? dd if=/dev/zero of=<some file somewhere on sdcx> bs=1M count=512. From hdparm -Tt /dev/sdc4 ?
If those look bad, I'm not really sure where to go next, I'd be trying:
- Different SATA ports / BIOS settings.
- Checking that there's nothing else thrashing the disk (benchmark from single user mode, or use sys-process/iotop.
- Upgrading kernel.
- Checking the drive using another OS.
- Yodelling. Subjective time speeds up when you yodel, so the drive will at least seem faster.
|
|
Back to top |
|
|
krinn Watchman
Joined: 02 May 2003 Posts: 7470
|
Posted: Wed Oct 10, 2012 7:28 pm Post subject: |
|
|
Code: | [ 3.272924] ata4.00: 1953525168 sectors, multi 16: LBA48 NCQ (depth 0/32) |
try do that, right now, your ncq is disable for your drive
Code: | echo 31 > /sys/block/sdc/device/queue_depth |
If it fail your controller driver cannot manage ncq, and your drive will always be poor, specially for its size, at handling multi-read/write on itself. |
|
Back to top |
|
|
eccerr0r Watchman
Joined: 01 Jul 2004 Posts: 9712 Location: almost Mile High in the USA
|
Posted: Thu Oct 11, 2012 12:31 am Post subject: |
|
|
I don't know about that, I have many controller/disk combos that have NCQ disabled and they are well past 40MB/sec. Something else very sinister is going on here...
What if you swap the ports for the working disk and the non-working disk, does the problem move with the disk or the port?
Are all the ports physically right next to each other on the board? Anything interesting about the ports?
I've never worked with nvidia sata ports before, just ICH ports... they should be about symmetric for each port... Though I just got a broken board that has master/slave for the SATA 1.5Gb ports, need to experiment with them... if I can get the rest of the board to work... _________________ Intel Core i7 2700K/Radeon R7 250/24GB DDR3/256GB SSD
What am I supposed watching? |
|
Back to top |
|
|
kimmie Guru
Joined: 08 Sep 2004 Posts: 531 Location: Australia
|
Posted: Thu Oct 11, 2012 12:37 pm Post subject: |
|
|
krinn wrote: | Code: | [ 3.272924] ata4.00: 1953525168 sectors, multi 16: LBA48 NCQ (depth 0/32) |
try do that, right now, your ncq is disable for your drive |
True, but it's the same for his other drives as well, so it's probably not the cause of the speed issue. |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Fri Oct 12, 2012 11:41 am Post subject: |
|
|
eccerr0r wrote: | I don't know about that, I have many controller/disk combos that have NCQ disabled and they are well past 40MB/sec. Something else very sinister is going on here...
What if you swap the ports for the working disk and the non-working disk, does the problem move with the disk or the port?
Are all the ports physically right next to each other on the board? Anything interesting about the ports?
I've never worked with nvidia sata ports before, just ICH ports... they should be about symmetric for each port... Though I just got a broken board that has master/slave for the SATA 1.5Gb ports, need to experiment with them... if I can get the rest of the board to work... |
Hmmm - I haven't looked at the motherboard yet. I have a Supermicro MBD-H8DCE-O. All of the SATA drives I'm using are using the same block of ports (should be the master set, but I'll check), so I'll have to try to move things around when I can power the computer off. |
|
Back to top |
|
|
eccerr0r Watchman
Joined: 01 Jul 2004 Posts: 9712 Location: almost Mile High in the USA
|
Posted: Fri Oct 12, 2012 2:46 pm Post subject: |
|
|
According to supermicro it seems there's three controllers - IDE, SATA2 and SATA3. I wonder if one of them doesn't have the right driver and going to some default driver. what kernel are you using?
And yes, might want to try another distribution and see if it also suffers the same problem or not... _________________ Intel Core i7 2700K/Radeon R7 250/24GB DDR3/256GB SSD
What am I supposed watching? |
|
Back to top |
|
|
fuzzybee Apprentice
Joined: 09 May 2005 Posts: 159
|
Posted: Fri Oct 12, 2012 2:55 pm Post subject: |
|
|
eccerr0r wrote: | According to supermicro it seems there's three controllers - IDE, SATA2 and SATA3. I wonder if one of them doesn't have the right driver and going to some default driver. what kernel are you using?
And yes, might want to try another distribution and see if it also suffers the same problem or not... |
Hmm - may be worth moving over to one of the other SATA ports and un-jumpering the transfer speed limiter. The manual (http://www.supermicro.com/manuals/motherboard/nForce2200/MNL-H8DCE.pdf) doesn't seem to distinguish between the sets of SATA ports, other than listing four as "Master" and the other four as "slave". |
|
Back to top |
|
|
eccerr0r Watchman
Joined: 01 Jul 2004 Posts: 9712 Location: almost Mile High in the USA
|
Posted: Sat Oct 13, 2012 8:42 am Post subject: |
|
|
It's kind of strange, most modern motherboards usually don't even discern between master and slave for SATA disks, they're basically all "master" if all things are good.
The thing that does however stick out is that four of the ports are associated with one southbridge and the other four to the other southbridge, but it doesn't make it clear which belong to which... Definitely worth trying swapping ports. _________________ Intel Core i7 2700K/Radeon R7 250/24GB DDR3/256GB SSD
What am I supposed watching? |
|
Back to top |
|
|
|