Michael Bachmor
2014-Apr-24 14:27 UTC
[Gluster-users] ping_pong test failes with gluster 3.4.3-3
Hello, i have a replica gluster with to node ( centos 6.5 ) create gluster with: gluster volume create testgl replica 2 transport tcp node1:/gluster/testgl/brick/ node2:/glusterfs/testgl/brick/ info: gluster volume info Volume Name: testgl Type: Replicate Volume ID: 5c820047-76d2-46c9-908b-520df0c8ba8c Status: Started Number of Bricks: 1 x 2 = 2 Transport-type: tcp Bricks: Brick1: node1:/gluster/testgl/brick Brick2: node2:/gluster/testgl/brick mount gluster: node1: mount -t glusterfs node1:testgl /mnt/ node2: mount -t glusterfs node2:testgl /mnt/ ping_pong test: node1: start: ping_pong -rw /mnt/test 3 data increment = 1 930 locks/sec start node2: nothing / hang - as long as is terminated on node1 filesytem: test ext4 and xfs /dev/xvdb1 on /gluster/testgl type ext4 what es wrong? what information you need yet? thanks Michael Bachmor
Pranith Kumar Karampuri
2014-Apr-25 06:34 UTC
[Gluster-users] ping_pong test failes with gluster 3.4.3-3
Michael, Could you try the test with "gluster volume set testgl cluster.eager-lock off". If you confirm, we may have to backport the following patch from master/3.5 commit 36b102645ab66d141dcc831e67caa78966d45419 Author: Pranith Kumar K <pkarampu at redhat.com> Date: Tue Jul 30 18:29:15 2013 +0530 cluster/afr: Disable eager-lock if open-fd-count > 1 Lets say mount1 has eager-lock(full-lock) and after the eager-lock is taken mount2 opened the same file, it won't be able to perform any data operations until mount1 releases eager-lock. To avoid such scenario do not enable eager-lock for transaction if open-fd-count is > 1. Delaying of changelog piggybacking is avoided in this situation. Change-Id: I51b45d6a7c216a78860aff0265a0b8dabc6423a5 BUG: 910217 Signed-off-by: Pranith Kumar K <pkarampu at redhat.com> Reviewed-on: http://review.gluster.org/5432 Tested-by: Gluster Build System <jenkins at build.gluster.com> Reviewed-by: venkatesh somyajulu <vsomyaju at redhat.com> Reviewed-by: Vijay Bellur <vbellur at redhat.com> Pranith ----- Original Message -----> From: "Michael Bachmor" <spam500 at gmx.de> > To: gluster-users at gluster.org > Sent: Thursday, April 24, 2014 7:57:46 PM > Subject: [Gluster-users] ping_pong test failes with gluster 3.4.3-3 > > Hello, > > i have a replica gluster with to node ( centos 6.5 ) > > create gluster with: > gluster volume create testgl replica 2 transport tcp > node1:/gluster/testgl/brick/ node2:/glusterfs/testgl/brick/ > > > info: > gluster volume info > > Volume Name: testgl > Type: Replicate > Volume ID: 5c820047-76d2-46c9-908b-520df0c8ba8c > Status: Started > Number of Bricks: 1 x 2 = 2 > Transport-type: tcp > Bricks: > Brick1: node1:/gluster/testgl/brick > Brick2: node2:/gluster/testgl/brick > > > mount gluster: > node1: > mount -t glusterfs node1:testgl /mnt/ > node2: > mount -t glusterfs node2:testgl /mnt/ > > > ping_pong test: > node1: > start: > ping_pong -rw /mnt/test 3 > data increment = 1 > 930 locks/sec > > start node2: > nothing / hang - as long as is terminated on node1 > > > filesytem: test ext4 and xfs > /dev/xvdb1 on /gluster/testgl type ext4 > > what es wrong? > > what information you need yet? > > thanks > > Michael Bachmor > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users >
Joe Julian
2014-Apr-25 07:54 UTC
[Gluster-users] ping_pong test failes with gluster 3.4.3-3
Make sure you're using the latest ping-pong, not the older broken one. On 4/24/2014 7:27 AM, Michael Bachmor wrote:> Hello, > > i have a replica gluster with to node ( centos 6.5 ) > > create gluster with: > gluster volume create testgl replica 2 transport tcp node1:/gluster/testgl/brick/ node2:/glusterfs/testgl/brick/ > > > info: > gluster volume info > > Volume Name: testgl > Type: Replicate > Volume ID: 5c820047-76d2-46c9-908b-520df0c8ba8c > Status: Started > Number of Bricks: 1 x 2 = 2 > Transport-type: tcp > Bricks: > Brick1: node1:/gluster/testgl/brick > Brick2: node2:/gluster/testgl/brick > > > mount gluster: > node1: > mount -t glusterfs node1:testgl /mnt/ > node2: > mount -t glusterfs node2:testgl /mnt/ > > > ping_pong test: > node1: > start: > ping_pong -rw /mnt/test 3 > data increment = 1 > 930 locks/sec > > start node2: > nothing / hang - as long as is terminated on node1 > > > filesytem: test ext4 and xfs > /dev/xvdb1 on /gluster/testgl type ext4 > > what es wrong? > > what information you need yet? > > thanks > > Michael Bachmor > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users