<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">Hi Rafi,<div><br></div><div>It’s what I do. But I note particularly this kind of trouble when I mount my volumes manually.</div><div><br></div><div>In addition, when I changed my transport-type from tcp or rdma to tcp,rdma, I have had to restart my volume in order they can took effect. </div><div><br></div><div>I wonder if these trouble are not due to RDMA protocol… because it looks like more stable with TCP one.</div><div><br></div><div>Another idea?</div><div>Thanks for replying and by advance,</div><div>Geoffrey</div><div apple-content-edited="true">
------------------------------------------------------<br>Geoffrey Letessier<br>Responsable informatique & ingénieur système<br>UPR 9080 - CNRS - Laboratoire de Biochimie Théorique<br>Institut de Biologie Physico-Chimique<br>13, rue Pierre et Marie Curie - 75005 Paris<br>Tel: 01 58 41 50 93 - eMail: <a href="mailto:geoffrey.letessier@ibpc.fr">geoffrey.letessier@ibpc.fr</a>
</div>
<br><div><div>Le 22 juil. 2015 à 07:33, Mohammed Rafi K C <<a href="mailto:rkavunga@redhat.com">rkavunga@redhat.com</a>> a écrit :</div><br class="Apple-interchange-newline"><blockquote type="cite">
<meta content="text/html; charset=windows-1252" http-equiv="Content-Type">
<div bgcolor="#FFFFFF" text="#000000">
<br>
<br>
<div class="moz-cite-prefix">On 07/22/2015 04:51 AM, Geoffrey
Letessier wrote:<br>
</div>
<blockquote cite="mid:AE01B7C4-7319-4F71-8912-AD5C775F956F@cnrs.fr" type="cite">
<meta http-equiv="Content-Type" content="text/html;
charset=windows-1252">
Hi Niels,
<div><br>
</div>
<div>Thanks for replying. </div>
<div><br>
</div>
<div>In fact, after having checked the log, I've discovered
GlusterFS tried to connect a brick with a TCP (or RDMA) port
allocated to another volume… (bug?)</div>
<div>For example, here is a extract of my workdir.log file :</div>
<div>
<div style="margin: 0px; font-size: 11px; font-family: Menlo;
color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);
position: static; z-index: auto;">[2015-07-21 21:34:01.820188]
E [socket.c:2332:socket_connect_finish]
0-vol_workdir_amd-client-0: connection to 10.0.4.1:49161
failed (Connexion refusée)</div>
<div style="margin: 0px; font-size: 11px; font-family: Menlo;
color: rgb(255, 255, 255); background-color: rgb(0, 0, 0);
position: static; z-index: auto;">[2015-07-21 21:34:01.822563]
E [socket.c:2332:socket_connect_finish]
0-vol_workdir_amd-client-2: connection to 10.0.4.1:49162
failed (Connexion refusée)</div>
<div><br>
</div>
<div>But the 2 ports (49161 and 49162) concerned only my
vol_home volume, not the vol_workdir_amd one.</div>
<div><br>
</div>
<div>Now, after having restart all glusterd synchronously (pdsh
-w cl-storage[1-4] service glusterd restart), all seems to be
back into a normal situation (size, write permission, etc.)</div>
<div><br>
</div>
<div>But, a few minutes later, i note a strange thing I notice
since i’ve upgraded my cluster storage from 3.5.3 to 3.7.2-3:
when I try to mount some volume (particularly my vol_shared
volume (replicated volume)) my system can hang… And, because I
use it in my bashrc file for my environment modules, i need to
restart my node. Idem if I try to do a DF on my mounted volume
(if it doesn’t hang during the mount).</div>
<div><br>
</div>
<div>With TCP transport-type, the situation seems to be more
stable..</div>
<div><br>
</div>
<div>In addition: If I restart a storage node, I can’t use
Gluster CLI (it also hang).</div>
<div><br>
</div>
<div>Do you have an idea?</div>
</div>
</blockquote>
<br>
Are you using bash script to start/mount the volume ? If so, add a
sleep after volume start and mount, to allow all the process to
start properly. Because RDMA protocol will take some time to init
the resources.<br>
<br>
Regards<br>
Rafi KC<br>
<br>
<br>
<br>
<blockquote cite="mid:AE01B7C4-7319-4F71-8912-AD5C775F956F@cnrs.fr" type="cite">
<div>
<div><br>
</div>
<div>One more time, thanks a lot for your help,</div>
<div>Geoffrey</div>
</div>
<div><br>
</div>
<div apple-content-edited="true">
------------------------------------------------------<br>
Geoffrey Letessier<br>
Responsable informatique & ingénieur système<br>
UPR 9080 - CNRS - Laboratoire de Biochimie Théorique<br>
Institut de Biologie Physico-Chimique<br>
13, rue Pierre et Marie Curie - 75005 Paris<br>
Tel: 01 58 41 50 93 - eMail: <a moz-do-not-send="true" href="mailto:geoffrey.letessier@ibpc.fr">geoffrey.letessier@ibpc.fr</a>
</div>
<br>
<div style="">
<div>Le 21 juil. 2015 à 23:49, Niels de Vos <<a moz-do-not-send="true" href="mailto:ndevos@redhat.com">ndevos@redhat.com</a>>
a écrit :</div>
<br class="Apple-interchange-newline">
<blockquote type="cite">On Tue, Jul 21, 2015 at 11:20:20PM
+0200, Geoffrey Letessier wrote:<br>
<blockquote type="cite">Hello Soumya, Hello everybody,<br>
<br>
network.ping-timeout was set to 42 seconds. I set it to 0
but no<br>
difference. The problem was, after having re-set le
transport-type to<br>
rdma,tcp some brick down after a few minutes.. Despite of
restarting<br>
volumes, after a few minutes, some [other/different] bricks
down<br>
again.<br>
</blockquote>
<br>
I'm not sure how if the ping-timeout is differently handled
when RDMA is<br>
used. Adding two of the guys that know RDMA well on CC.<br>
<br>
<blockquote type="cite">Now, after re-creation of my volume,
bricks keep alive but, oddly, i’m<br>
not able to write on my volume. In addition, I defined a
distributed<br>
volume with 2 servers, 4 bricks of 250GB each and my final
volume<br>
seems to be only sized to 500GB… It’s amazing.. <br>
</blockquote>
<br>
As seen further below, the 500GB volume is caused by two
unreachable<br>
bricks. When the bricks are not reachable, the size of the
bricks can<br>
not be detected by the client and therefore 2x 250 GB is
missing.<br>
<br>
It is unclear to me why writing to a pure distributed volume
fails. When<br>
a brick is not reachable, and the file should be created
there, it<br>
would normally get created on an other brick. When the brick
that should<br>
have the file gets online, and a new lookup for the file is
done, a so<br>
called "link file" is created, which points to the file on the
other<br>
brick. I guess the failure has to do with the connection
issues, and I<br>
would suggest to get that solved first.<br>
<br>
HTH,<br>
Niels<br>
<br>
<br>
<blockquote type="cite">Here you can find some information:<br>
# gluster volume status vol_workdir_amd<br>
Status of volume: vol_workdir_amd<br>
Gluster process TCP Port RDMA
Port Online Pid<br>
------------------------------------------------------------------------------<br>
Brick ib-storage1:/export/brick_workdir/bri<br>
ck1/data 49185 49186
Y 23098<br>
Brick ib-storage3:/export/brick_workdir/bri<br>
ck1/data 49158 49159
Y 3886 <br>
Brick ib-storage1:/export/brick_workdir/bri<br>
ck2/data 49187 49188
Y 23117<br>
Brick ib-storage3:/export/brick_workdir/bri<br>
ck2/data 49160 49161
Y 3905 <br>
<br>
# gluster volume info vol_workdir_amd<br>
<br>
Volume Name: vol_workdir_amd<br>
Type: Distribute<br>
Volume ID: 087d26ea-c6df-4cbe-94af-ecd87b59aedb<br>
Status: Started<br>
Number of Bricks: 4<br>
Transport-type: tcp,rdma<br>
Bricks:<br>
Brick1: ib-storage1:/export/brick_workdir/brick1/data<br>
Brick2: ib-storage3:/export/brick_workdir/brick1/data<br>
Brick3: ib-storage1:/export/brick_workdir/brick2/data<br>
Brick4: ib-storage3:/export/brick_workdir/brick2/data<br>
Options Reconfigured:<br>
performance.readdir-ahead: on<br>
<br>
# pdsh -w storage[1,3] df -h
/export/brick_workdir/brick{1,2}<br>
storage3: Filesystem Size Used Avail Use%
Mounted on<br>
storage3: /dev/mapper/st--block1-blk1--workdir<br>
storage3: 250G 34M 250G 1%
/export/brick_workdir/brick1<br>
storage3: /dev/mapper/st--block2-blk2--workdir<br>
storage3: 250G 34M 250G 1%
/export/brick_workdir/brick2<br>
storage1: Filesystem Size Used Avail Use%
Mounted on<br>
storage1: /dev/mapper/st--block1-blk1--workdir<br>
storage1: 250G 33M 250G 1%
/export/brick_workdir/brick1<br>
storage1: /dev/mapper/st--block2-blk2--workdir<br>
storage1: 250G 33M 250G 1%
/export/brick_workdir/brick2<br>
<br>
# df -h /workdir/<br>
Filesystem Size Used Avail Use% Mounted on<br>
localhost:vol_workdir_amd.rdma<br>
500G 67M 500G 1% /workdir<br>
<br>
# touch /workdir/test<br>
touch: impossible de faire un touch « /workdir/test »: Aucun
fichier ou dossier de ce type<br>
<br>
# tail -30l /var/log/glusterfs/workdir.log <br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:33.927673] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-2: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1020
peer:10.0.4.1:49174)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:37.877231] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-0: changing port to 49173 (from 0)<br>
[2015-07-21 21:10:37.880556] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-2: changing port to 49174 (from 0)<br>
[2015-07-21 21:10:37.914661] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-0: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1021
peer:10.0.4.1:49173)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:37.923535] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-2: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1020
peer:10.0.4.1:49174)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:41.883925] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-0: changing port to 49173 (from 0)<br>
[2015-07-21 21:10:41.887085] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-2: changing port to 49174 (from 0)<br>
[2015-07-21 21:10:41.919394] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-0: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1021
peer:10.0.4.1:49173)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:41.932622] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-2: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1020
peer:10.0.4.1:49174)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:44.682636] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:44.682947] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:44.683240] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:44.683472] W
[dht-diskusage.c:48:dht_du_info_cbk] 0-vol_workdir_amd-dht:
failed to get disk info from vol_workdir_amd-client-0<br>
[2015-07-21 21:10:44.683506] W
[dht-diskusage.c:48:dht_du_info_cbk] 0-vol_workdir_amd-dht:
failed to get disk info from vol_workdir_amd-client-2<br>
[2015-07-21 21:10:44.683532] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:44.683551] W
[fuse-bridge.c:1970:fuse_create_cbk] 0-glusterfs-fuse: 18:
/test => -1 (Aucun fichier ou dossier de ce type)<br>
[2015-07-21 21:10:44.683619] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:44.683846] W
[dht-layout.c:189:dht_layout_search] 0-vol_workdir_amd-dht:
no subvolume for hash (value) = 1072520554<br>
[2015-07-21 21:10:45.886807] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-0: changing port to 49173 (from 0)<br>
[2015-07-21 21:10:45.893059] I
[rpc-clnt.c:1819:rpc_clnt_reconfig]
0-vol_workdir_amd-client-2: changing port to 49174 (from 0)<br>
[2015-07-21 21:10:45.920434] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-0: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1021
peer:10.0.4.1:49173)<br>
Host Unreachable, Check your connection with IPoIB<br>
[2015-07-21 21:10:45.925292] W
[rdma.c:1263:gf_rdma_cm_event_handler]
0-vol_workdir_amd-client-2: cma event
RDMA_CM_EVENT_REJECTED, error 8 (me:10.0.4.1:1020
peer:10.0.4.1:49174)<br>
Host Unreachable, Check your connection with IPoIB<br>
<br>
I use GlusterFS in production since around 3 years without
any block<br>
problem but now the situation is awesome since more than 3
weeks…<br>
Indeed, our production are down since roughly 3.5 weeks
(with a lot<br>
and different problems with GlusterFS v3.5.3 and now with
3.7.2-3) and<br>
i need to restart it… <br>
<br>
Thanks in advance,<br>
Geoffrey<br>
------------------------------------------------------<br>
Geoffrey Letessier<br>
Responsable informatique & ingénieur système<br>
UPR 9080 - CNRS - Laboratoire de Biochimie Théorique<br>
Institut de Biologie Physico-Chimique<br>
13, rue Pierre et Marie Curie - 75005 Paris<br>
Tel: 01 58 41 50 93 - eMail: <a moz-do-not-send="true" href="mailto:geoffrey.letessier@ibpc.fr">geoffrey.letessier@ibpc.fr</a><br>
<br>
Le 21 juil. 2015 à 19:36, Soumya Koduri <<a moz-do-not-send="true" href="mailto:skoduri@redhat.com">skoduri@redhat.com</a>>
a écrit :<br>
<br>
<blockquote type="cite">From the following errors,<br>
<br>
[2015-07-21 14:36:30.495321] I [MSGID: 114020]
[client.c:2118:notify] 0-vol_shared-client-0: parent
translators are ready, attempting connect on transport<br>
[2015-07-21 14:36:30.498989] W
[socket.c:923:__socket_keepalive] 0-socket: failed to set
TCP_USER_TIMEOUT 0 on socket 12, Protocole non disponible<br>
[2015-07-21 14:36:30.499004] E
[socket.c:3015:socket_connect] 0-vol_shared-client-0:
Failed to set keep-alive: Protocole non disponible<br>
<br>
looks like setting TCP_USER_TIMEOUT value to 0 on the
socket failed with error (IIUC) "Protocol not available".<br>
Could you check if 'network.ping-timeout' is set to zero
for that volume using 'gluster volume info'? Anyways from
the code looks like 'TCP_USER_TIMEOUT' can take value
zero. Not sure why it has failed.<br>
<br>
Niels, any thoughts?<br>
<br>
Thanks,<br>
Soumya<br>
<br>
On 07/21/2015 08:15 PM, Geoffrey Letessier wrote:<br>
<blockquote type="cite">[2015-07-21 14:36:30.495321] I
[MSGID: 114020] [client.c:2118:notify]<br>
0-vol_shared-client-0: parent translators are ready,
attempting connect<br>
on transport<br>
[2015-07-21 14:36:30.498989] W
[socket.c:923:__socket_keepalive]<br>
0-socket: failed to set TCP_USER_TIMEOUT 0 on socket 12,
Protocole non<br>
disponible<br>
[2015-07-21 14:36:30.499004] E
[socket.c:3015:socket_connect]<br>
0-vol_shared-client-0: Failed to set keep-alive:
Protocole non disponible<br>
</blockquote>
</blockquote>
<br>
</blockquote>
</blockquote>
</div>
<br>
</blockquote>
<br>
</div>
</blockquote></div><br></body></html>