<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Jan 23, 2019 at 1:59 AM Lindolfo Meira <<a href="mailto:meira@cesup.ufrgs.br">meira@cesup.ufrgs.br</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Dear all,<br>
<br>
I've been trying to benchmark a gluster file system using the MPIIO API of <br>
IOR. Almost all of the times I try to run the application with more than 6 <br>
tasks performing I/O (mpirun -n N, for N > 6) I get the error: "writev: <br>
Transport endpoint is not connected". And then each one of the N tasks <br>
returns "ERROR: cannot open file to get file size, MPI MPI_ERR_FILE: <br>
invalid file, (aiori-MPIIO.c:488)".<br>
<br>
Does anyone have any idea what's going on?<br>
<br>
I'm writing from a single node, to a system configured for stripe over 6 <br>
bricks. The volume is mounted with the options _netdev and transport=rdma. <br>
I'm using OpenMPI 2.1.2 (I tested version 4.0.0 and nothing changed). IOR <br>
arguments used: -B -E -F -q -w -k -z -i=1 -t=2m -b=1g -a=MPIIO. Running <br>
OpenSUSE Leap 15.0 and GlusterFS 5.3. Output of "gluster volume info" <br>
follows bellow:<br>
<br>
Volume Name: gfs<br>
Type: Stripe<br></blockquote><div><br><a class="gmail_plusreply" id="plusReplyChip-0" href="mailto:kdhananj@redhat.com" tabindex="-1">+Dhananjay, Krutika</a> <br></div><div>stripe has been deprecated. You can use sharded volumes.<br> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
Volume ID: ea159033-5f7f-40ac-bad0-6f46613a336b<br>
Status: Started<br>
Snapshot Count: 0<br>
Number of Bricks: 1 x 6 = 6<br>
Transport-type: rdma<br>
Bricks:<br>
Brick1: pfs01-ib:/mnt/data/gfs<br>
Brick2: pfs02-ib:/mnt/data/gfs<br>
Brick3: pfs03-ib:/mnt/data/gfs<br>
Brick4: pfs04-ib:/mnt/data/gfs<br>
Brick5: pfs05-ib:/mnt/data/gfs<br>
Brick6: pfs06-ib:/mnt/data/gfs<br>
Options Reconfigured:<br>
nfs.disable: on<br>
<br>
<br>
Thanks in advance,<br>
<br>
Lindolfo Meira, MSc<br>
Diretor Geral, Centro Nacional de Supercomputação<br>
Universidade Federal do Rio Grande do Sul<br>
+55 (51) 3308-3139_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="https://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">https://lists.gluster.org/mailman/listinfo/gluster-users</a></blockquote></div></div>