craig,
A) stat on server that generated the file:
j...@riff:/mnt/gluster$ stat y.out
File: `y.out'
Size: 214574579712 Blocks: 291441832 IO Block: 65536 regular file
Device: 16h/22d Inode: 14213316644377695875 Links: 1
Access: (0777/-rwxrwxrwx) Uid: ( 0/ root) Gid: ( 0/ root)
Access: 2010-11-09 10:32:16.000000000 -0800
Modify: 2010-11-09 13:57:05.000000000 -0800
Change: 2010-11-09 13:57:05.000000000 -0800
B) stat on gluster brick (brick2) that is housing the file:
[r...@brick2 ~]# stat /exp2/y.out
File: `/exp2/y.out'
Size: 214574579712 Blocks: 291441832 IO Block: 4096 regular file
Device: fd00h/64768d Inode: 655412 Links: 1
Access: (0777/-rwxrwxrwx) Uid: ( 0/ root) Gid: ( 0/ root)
Access: 2010-11-09 10:32:16.000000000 -0800
Modify: 2010-11-09 13:57:05.000000000 -0800
Change: 2010-11-09 13:57:05.000000000 -0800
c) df on brick 2
[r...@brick2 ~]# df -h
Filesystem Size Used Avail Use% Mounted on
/dev/mapper/VolGroup00-LogVol00
143G 143G 0 100% /
/dev/hda1 99M 13M 82M 13% /boot
tmpfs 470M 0 470M 0% /dev/shm
172.16.1.76:/gs-test 283G 158G 119G 58% /mnt/gluster
interesting that block size is different depending on who you ask.
[r...@brick2 ~]# dumpe2fs /dev/hda1 | grep -i 'Block size'
dumpe2fs 1.39 (29-May-2006)
Block size: 1024
-Matt
On Nov 11, 2010, at 9:44 PM, Craig Carl wrote:
Matt,
Based on your Gluster servers configs that file is bigger than the
available disk space, obviously that isn't right.
Can you send us the output of `stat y.out` taken from the Gluster
mount point and from the back end of the server Gluster created the
file on
I'm also going to try and reproduce the problem here on 3.1 and
3.1.1qa5.
Thanks,
Craig
-->
Craig Carl
Gluster, Inc.
Cell - (408) 829-9953 (California, USA)
Gtalk - [email protected]
From: "Matt Hodson" <[email protected]>
To: "Craig Carl" <[email protected]>
Cc: "Jeff Kozlowski" <[email protected]>, [email protected]
Sent: Wednesday, November 10, 2010 9:21:40 AM
Subject: Re: [Gluster-users] filling gluster cluster with large file
doesn't crash the system?!
Craig,
inline...
On Nov 10, 2010, at 7:17 AM, Craig Carl wrote:
Matt -
A couple of questions -
What is your volume config? (`gluster volume info all`)
gluster> volume info all
Volume Name: gs-test
Type: Distribute
Status: Started
Number of Bricks: 2
Transport-type: tcp
Bricks:
Brick1: 172.16.1.76:/exp1
Brick2: 172.16.2.117:/exp2
What is the hardware config for each storage server?
brick 1 = 141GB
brick 2 = 143GB
What command did you run to create the test data?
#perl -e 'print rand while 1' > y.out &
What process is still writing to the file?
same one as above.
Thanks,
Craig
-->
Craig Carl
Gluster, Inc.
Cell - (408) 829-9953 (California, USA)
Gtalk - [email protected]
From: "Matt Hodson" <[email protected]>
To: [email protected]
Cc: "Jeff Kozlowski" <[email protected]>
Sent: Tuesday, November 9, 2010 10:46:04 AM
Subject: Re: [Gluster-users] filling gluster cluster with large file
doesn't crash the system?!
I should also note that on this non-production test rig the block size
on both bricks is 1KB (1024) so the theoretical file size limit is
16GB. so how then did i get a file of 200GB?
-matt
On Nov 9, 2010, at 10:34 AM, Matt Hodson wrote:
> craig et al,
>
> I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we
> nfs mounted the cluster from a 3rd machine and wrote random junk to
> a file. i watched the file grow to 200GB on the cluster when it
> appeared to stop. however the machine writing to the file still
> lists the file as growing. it's now at over 320GB. what's going on?
>
> -matt
>
> -------
> Matt Hodson
> Scientific Customer Support, Geospiza
> (206) 633-4403, Ext. 111
> http://www.geospiza.com
>
>
>
>
_______________________________________________
Gluster-users mailing list
[email protected]
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
_______________________________________________
Gluster-users mailing list
[email protected]
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
