Skip to contentSkip to conversation

New: Write cache: disabled, read cache: enabled, supports DPO and FUA? it's bug???

Bug 13499 [email protected] 2 participants 5 messages Jun 10, 2009 SCSI

lore
Share & tools
lore
#0 lore raw

http://bugzilla.kernel.org/show_bug.cgi?id=13499

Summary: Write cache: disabled, read cache: enabled, supports
DPO and FUA? it's bug???
Product: SCSI Drivers
Version: 2.5
Kernel Version: 2.6.22 - 2.6.30
Platform: All
OS/Version: Linux
Tree: Mainline
Status: NEW
Severity: normal
Priority: P1
Component: Other
AssignedTo: [email protected]
ReportedBy: [email protected]
Regression: No

scsi0 : LSI Logic SAS based MegaRAID driver
scsi 0:0:0:0: Direct-Access SEAGATE ST9146852SS HT03 PQ: 0 ANSI: 5
done.
Begin: Running /scripts/init-premount ... scsi 0:0:1:0: Direct-Access
SEAGATE ST9146852SS HT03 PQ: 0 ANSI: 5

scsi 0:0:2:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5
scsi 0:0:3:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5
scsi 0:0:4:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5
scsi 0:0:5:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5
scsi 0:0:6:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5
scsi 0:0:7:0: Direct-Access     SEAGATE  ST9146852SS      HT03 PQ: 0 ANSI: 5

scsi 0:0:32:0: Enclosure DP BACKPLANE 1.07 PQ: 0 ANSI: 5
scsi 0:2:0:0: Direct-Access DELL PERC 6/i 1.21 PQ: 0 ANSI: 5
scsi 0:0:32:0: Attached scsi generic sg0 type 13
sd 0:2:0:0: [sda] 1998323712 512-byte hardware sectors (1023142 MB) sd 0:2:0:0: [sda] Write Protect is off
sd 0:2:0:0: [sda] Write cache: disabled, read cache: enabled, supports DPO and FUA
sd 0:2:0:0: [sda] 1998323712 512-byte hardware sectors (1023142 MB) sd 0:2:0:0: [sda] Write Protect is off
sd 0:2:0:0: [sda] Write cache: disabled, read cache: enabled, supports DPO and FUA
sda: sda1 sda4 < sda5 sda6 sda7 sda8 sda9 >

Signature · 3 lines
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
#1 lore raw

[Bug 13499] Write cache: disabled, read cache: enabled, supports DPO and FUA? it's bug???

http://bugzilla.kernel.org/show_bug.cgi?id=13499

--- Comment #1 from ping.li <[email protected]> 2009-06-10 14:00:53 --- Write cache: disabled, read cache: enabled,

why Write cache: disabled??

Signature · 3 lines
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
maintainer
#2 lore raw

Re: [Bug 13499] Write cache: disabled, read cache: enabled, supports DPO and FUA? it's bug???

Quoted 1 line · On Wed, 2009-06-10 at 14:00 +0000, [email protected] wrote:

why Write cache: disabled??

The SCSI mid layer is merely reporting what your array is telling it. For arrays without a battery backed cache, write through configuration (i.e. read cache enabled, write cache disabled) is the usual safe default.

You can alter your write cache settings using Doug Gilbert's sg3-utils ... but be warned, enabling the write cache without battery backing in an array is a dangerous thing to do since most arrays have huge caches, they either ignore SYNCHRONIZE CACHE (which would leave you vulnerable to data loss on power failure) or take such a long time, it would kill performance.

James

#3 lore raw

[Bug 13499] Write cache: disabled, read cache: enabled, supports DPO and FUA? it's bug???

In reply to [email protected]

http://bugzilla.kernel.org/show_bug.cgi?id=13499

--- Comment #2 from Anonymous Emailer <[email protected]> 2009-06-10 14:14:13 ---
Reply-To: [email protected]

Quoted 1 line · On Wed, 2009-06-10 at 14:00 +0000, [email protected] wrote:

why Write cache: disabled??

The SCSI mid layer is merely reporting what your array is telling it. For arrays without a battery backed cache, write through configuration (i.e. read cache enabled, write cache disabled) is the usual safe default.

You can alter your write cache settings using Doug Gilbert's sg3-utils ... but be warned, enabling the write cache without battery backing in an array is a dangerous thing to do since most arrays have huge caches, they either ignore SYNCHRONIZE CACHE (which would leave you vulnerable to data loss on power failure) or take such a long time, it would kill performance.

James

Signature · 3 lines
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
#4 lore raw

[Bug 13499] Write cache: disabled, read cache: enabled, supports DPO and FUA? it's bug???

In reply to [email protected]

http://bugzilla.kernel.org/show_bug.cgi?id=13499

--- Comment #3 from ping.li <[email protected]> 2009-06-10 17:04:29 ---
1. BBU status is ok
./MegaCli64 -AdpBbuCmd -GetBbuStatus -a0

BBU status for Adapter: 0

BatteryType: BBU
Voltage: 4058 mV
Current: 0 mA
Temperature: 19 C
Firmware Status: 00000000

Battery state:

GasGuageStatus:

  Fully Discharged        : No
  Fully Charged           : Yes
  Discharging             : Yes
  Initialized             : Yes
  Remaining Time Alarm    : No
  Remaining Capacity Alarm: No
  Discharge Terminated    : No
  Over Temperature        : No
  Charging Terminated     : Yes
  Over Charged            : No

Relative State of Charge: 98 %
Charger Status: Complete
Remaining Capacity: 1634 mAh
Full Charge Capacity: 1662 mAh
isSOHGood: Yes

2. Cache Policy is default,and try change setting but problem still.

./MegaCli64 -LDinfo -L0 -a0
Adapter 0 -- Virtual Drive Information:
Virtual Disk: 0 (target id: 0)
Name:
RAID Level: Primary-5, Secondary-0, RAID Level Qualifier-3 Size:975744MB
State: Optimal
Stripe Size: 64kB
Number Of Drives:8
Span Depth:1
Default Cache Policy: WriteBack, ReadAheadNone, Direct, Write Cache OK if Bad BBU
Current Cache Policy: WriteBack, ReadAheadNone, Direct, Write Cache OK if Bad BBU
Access Policy: Read/Write
Disk Cache Policy: Enabled

Signature · 3 lines
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.