Bug 820922

Summary: Replace-brick start results in iozone termination with error.
Product: [Community] GlusterFS Reporter: Vijaykumar Koppad <vkoppad>
Component: glusterdAssignee: krishnan parthasarathi <kparthas>
Status: CLOSED DEFERRED QA Contact:
Severity: high Docs Contact:
Priority: unspecified    
Version: mainlineCC: bbandari, gluster-bugs, nsathyan
Target Milestone: ---   
Target Release: ---   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2012-05-14 11:27:02 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description Vijaykumar Koppad 2012-05-11 10:56:25 UTC
Description of problem:While running iozone , if replace-brick is started, the iozone exits with an error saying 
 
Error writing block 772, fd= 3
write: Transport endpoint is not connected

iozone: interrupted

exiting iozone


Version-Release number of selected component (if applicable):3.3.0qa40


How reproducible: Always. 


Steps to Reproduce:
1.Create a distributed-stripe volume.
2.Run "iozone -a" on the mount-point 
3.While its running, do replace-brick of the first sub-volume.
  
Actual results:


Expected results:


Additional info:

Comment 1 krishnan parthasarathi 2012-05-14 11:27:02 UTC
Volume type such as stripe and distributed stripe, may fail operations on the mount point with EIO if the first subvolume is "down". During a replace-brick operation, src brick is stopped and restarted with pump xlator inserted into the server graph. During which operations running on the mount can fail. This is a known limitation of replace-brick with stripe, distributed stripe type volumes.