- Community Home
- >
- Storage
- >
- Midrange and Enterprise Storage
- >
- HPE EVA Storage
- >
- Re: VAAI ScsiDeviceIO H:0x7 failure with HP FC HBA...
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Forums
Discussions
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Community
Resources
Forums
Blogs
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
07-04-2013 01:04 AM
07-04-2013 01:04 AM
VAAI ScsiDeviceIO H:0x7 failure with HP FC HBA / Fujitsu storage
It appears that only with Firmware Version V10L47-0000, a Fujitsu
Eternus DX90 S2 will fully utilize VAAI (Details available in Fujitsu
Support document SB-STO-13023).
After upgrading to that firmware version we are observing enjoyable
high throughput with VAAI operations (up to 900 MB/s).
We are only somewhat bothered that vmkernel.log on the ESXi 5.1 server
reports about 2500 lines of Warnings, some even Errors, e.g.
...NMP: nmp_ThrottleLogForDevice:2319: Cmd 0x83 (0x4124801cbe80, 17670) to dev "naa.6000000d10e100000112105c00000000" on path "vmhba4:C0:T0:L1" Failed: H:0x7 D:0x0 P:0x0 Possible sense data: 0x0 0x0 0x0. Act:EVAL
...WARNING: NMP: nmp_DeviceRequestFastDeviceProbe:237:NMP device "naa.6000000d10e100000112105c00000000" state in doubt; requested fast path state update...
...ScsiDeviceIO: 2331: Cmd(0x4124801cbe80) 0x83, CmdSN 0x7bd from world 17670 to dev "naa.6000000d10e100000112105c00000000" failed H:0x7 D:0x0 P:0x0 Possible sense data: 0x0 0x0 0x0.
...<3>lpfc820 0000:0c:00.1: 1:(0):0717 FCP command x83 residual underrun converted to error Data: x6c x6c x6c
Can we savely errors like H:0x7 ()
Now VMWare support says this is a HBA issue:
...
We can see here from the analysis of one of the error codes (this one
came direct from storage, as it was a D:0x2):
H:0x0 D:0x2 P:0x0 Valid sense data: 0xa 0xd 0x1
This means, basically:
Indicates an EXTENDED COPY command was aborted due to an error
condition on the source device. the destination device. or both.
However, there are H:0x7 failures, which usually definitely indicate a
host adapter issue.
...
HP support says they do not check HP adapter / Fujitsu storage
interoperability, and Fujitsu should be asked.
Fujitsu support says it is not an issue with their storage.
betwixed and between ...
Has someone made similar observations?
Regards, Thomas
Here is an abstract of the environment:
ESXi Server
HP DL385 G7
System ROM A18 12/08/2012
FC2242SR HBA
Firmware 2012.02.01a
ESXi Version
VMware ESXi 5.1.0 build-1065491
driver: scsi-lpfc820 8.2.4.151.65-1OEM.500.0.0.472560, Emulex (VMwareCertified)
Storage: Fujitsu Eternus DX90 S2
Firmware Version V10L47-0000
also posted this here
and here
- Tags:
- HBA
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
07-24-2013 12:16 PM
07-24-2013 12:16 PM
Re: VAAI ScsiDeviceIO H:0x7 failure with HP FC HBA / Fujitsu storage
Hi Thomas,
FCP command x83 residual underrun converted to error Data: x6c x6c x6c
The above error message is reported by HBA and is documented as follows.
printk "%sFCP command x%x residual underrun converted to error Data: x%x x%x x%x";
Probable Causes:
- "The driver convert this underrun condition to an error based on the underflow field in the SCSI cmnd."
Actions:
- "No action needed, informational."
Following known issue is documented in Eternus VAAI guide,
Following message may appear many times to /var/log/vmkernel* log files while “Full Copy”. This
message can be safely ignored because it simply indicates that the submission queue for the
ETERNUS copy engine is full and therefore it cannot accept any more copy jobs. The copy jobs
are resubmitted automatically though retry mechanism so no action is required by the user.
NMP: nmp_ThrottleLogForDevice:2318: Cmd 0xe9 (0x412440c414c0) to dev
"naa.600000e00d1000000010011000210000" on path "vmhba4:C0:T0:L0" Failed: H:0x0 D:0x2
P:0x0 Valid sense data: 0x5 0x26 0x92.Act:NONE
Looks like there is an underrun condition caused by Array which is converted to error message by HBA.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
07-24-2013 12:28 PM
07-24-2013 12:28 PM
Re: VAAI ScsiDeviceIO H:0x7 failure with HP FC HBA / Fujitsu storage
Supplemental link to Fujitsu document - refer to page 5:
http://www.fujitsu.com/downloads/STRSYS/system/evaai5_user_en.pdf