Re: [Gluster-devel] glusterfs(3.2.7) hang when making the same dir at the same time

[Song]

I have compared the source code of features/locks between 3.2.7 and 3.3.1. I find  mutex lock is added in various functions, such as get_domain function.

Are these changes updated to 3.2.7 branch?

 

From: Anand Avati [mailto:address@hidden
Sent: Friday, February 01, 2013 4:18 AM
To: Song
Cc: address@hidden
Subject: Re: [Gluster-devel] glusterfs(3.2.7) hang when making the same dir at the same time

 

Can you please verify if this issue exists in the master HEAD? There have been quite a few locking changes/fixes recently and this may be a specific case of those issues.

 

Avati

On Thu, Jan 24, 2013 at 12:02 AM, Song <address@hidden> wrote:

Hi,

 

Recently, glusterfs will hang when we do stress testing. To find the reason, we write a test shell script.

 

We run the test shell on 5 servers at the same time. For a moment, all test programming is hang.

When execute command “cd /xmail/gfs1/scl_test/001”, also hang.

 

The test shell script:

 

for((i=1;i<=100;i++));

do

rmdir /xmail/gfs1/scl_test/001

if [ "$?" == "0" ];

then

echo "delete dir success"

fi

 

mkdir /xmail/gfs1/scl_test/001

if [ "$?" == "0" ];

then

echo "create dir success"

fi

 

echo "1111" >>/xmail/gfs1/scl_test/001/001.txt

echo "2222" >>/xmail/gfs1/scl_test/001/002.txt

echo "3333" >>/xmail/gfs1/scl_test/001/003.txt

 

rm -rf /xmail/gfs1/scl_test/001/001.txt

rm -ff /xmail/gfs1/scl_test/001/002.txt

rm -rf /xmail/gfs1/scl_test/001/003.txt

done

 

“/xmail/gfs1” is native mount point of gluster volume gfs1.

 

Gluster volume info is as below:

address@hidden glusterfs]# gluster volume info

 

Volume Name: gfs1

Type: Distributed-Replicate

Status: Started

Number of Bricks: 30 x 3 = 90

Transport-type: tcp

 

 

Please help me, Thanks!

 

_______________________________________________
Gluster-devel mailing list
address@hidden
https://lists.nongnu.org/mailman/listinfo/gluster-devel