+++ This bug was initially created as a clone of Bug #1065296 +++ Description of problem: glusterd performs synchronous RPCs to brick, gluster-nfs and Self-heal daemon, for eg., during a volume-status command invocation. This serial execution of RPCs will not scale as the no. of bricks per node increases. Version-Release number of selected component (if applicable): How reproducible: Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info: --- Additional comment from Anand Avati on 2014-02-14 04:58:26 EST --- REVIEW: http://review.gluster.org/6953 (glusterd: make brick/node RPCs 'batched'/'parallel') posted (#2) for review on master by Krishnan Parthasarathi (kparthas) --- Additional comment from Anand Avati on 2014-02-14 06:51:46 EST --- REVIEW: http://review.gluster.org/6953 (glusterd: make brick/node RPCs 'batched'/'parallel') posted (#3) for review on master by Krishnan Parthasarathi (kparthas) --- Additional comment from Anand Avati on 2014-02-17 04:17:40 EST --- REVIEW: http://review.gluster.org/6953 (glusterd: make brick/node RPCs 'batched'/'parallel') posted (#4) for review on master by Krishnan Parthasarathi (kparthas) --- Additional comment from Anand Avati on 2014-04-01 03:39:51 EDT --- REVIEW: http://review.gluster.org/6953 (glusterd: make brick/node RPCs 'batched'/'parallel') posted (#5) for review on master by Krishnan Parthasarathi (kparthas) --- Additional comment from Anand Avati on 2014-04-25 05:59:28 EDT --- REVIEW: http://review.gluster.org/6953 (glusterd: make brick/node RPCs 'batched'/'parallel') posted (#6) for review on master by Krishnan Parthasarathi (kparthas)
We don't have any future plan to fix this in glusterd. In GlusterD2 development phase the same factor will be considered.