Note: This is a beta release of Red Hat Bugzilla 5.0. The data contained within is a snapshot of the live data so any changes you make will not be reflected in the production Bugzilla. Also email is disabled so feel free to test any aspect of the site that you want. File any problems you find or give feedback here.
Bug 154439 - kernel dm-multipath: Path testing needs FAILFAST
Summary: kernel dm-multipath: Path testing needs FAILFAST
Keywords:
Status: ASSIGNED
Alias: None
Product: Fedora
Classification: Fedora
Component: device-mapper-multipath
Version: rawhide
Hardware: All
OS: Linux
medium
medium
Target Milestone: ---
Assignee: Mike Christie
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2005-04-11 18:00 UTC by Alasdair Kergon
Modified: 2012-05-29 13:29 UTC (History)
8 users (show)

Fixed In Version:
Doc Type: Enhancement
Doc Text:
Clone Of:
Environment:
Last Closed:


Attachments (Terms of Use)

Description Alasdair Kergon 2005-04-11 18:00:29 UTC
In the interest of reducing delay time when testing either good or
failed paths, could we prevent SCSI mid-layer initiated i/o
retry of these requests?  
                                                                               
                                                     
Currently the scsi_cmd_ioctl->sg_io->blk_execute_rq code
path for a multipath test i/o does not set the REQ_FAILFAST
bit in the flags field of the request structure.
                                                                               
                                                     
Possibly the desire for each of this attribute could be
passed as a flag bit setting in the flag field of the sg_io_hdr
structure passed into the kernel as part of the test path ioctl(2).

[Ed Goggin, EMC]

Comment 1 Lars Marowsky-Bree 2005-04-21 20:16:51 UTC
Is this not essentially a dup of #154436?

Comment 2 John Poelstra 2008-07-08 03:39:02 UTC
Question in comment #1

Comment 3 Alasdair Kergon 2008-09-27 07:10:11 UTC
John - work is progressing upstream in the scsi layer.

If we had a long-term category where we could park bugs while waiting for other development work, this one would have been in it.

Comment 4 Alasdair Kergon 2011-02-11 17:56:49 UTC
Do you think this is still relevant?


Note You need to log in before you can comment on or make changes to this bug.