Description of problem: ================= Memory leak is happening during the re-balance process Version-Release number of selected component (if applicable): ======================= glusterfs-cli-3.7.1-16 How reproducible: Steps to Reproduce: ================= 1.Create volume with one brick and mount it on client using FUSE and create 5 Million files 2.Add one more brick to the volume and do rebalance with force option 3.Rebalance process started with 0.3 % of total memory and to migrate 1.5 M files it took 16 % of total memory so looks there is memory leak Actual results: Expected results: ============= Memeory leak should not be there during the rebalance Additional info: ============== [root@rhs-client21 ~]# gluster vol status dht_mem2 Status of volume: dht_mem2 Gluster process TCP Port RDMA Port Online Pid ------------------------------------------------------------------------------ Brick rhs-client21.lab.eng.blr.redhat.com:/ rhs/brick6/dht_mem2 49161 0 Y 31030 Brick rhs-client21.lab.eng.blr.redhat.com:/ rhs/brick7/dht_mem2 49162 0 Y 32498 NFS Server on localhost N/A N/A N N/A NFS Server on rhs-client39.lab.eng.blr.redh at.com N/A N/A N N/A NFS Server on rhs-client9.lab.eng.blr.redha t.com N/A N/A N N/A Task Status of Volume dht_mem2 ------------------------------------------------------------------------------ Task : Rebalance ID : 6c1bf2c3-6660-4708-829f-9bd6e00e280c Status : in progress [root@rhs-client21 ~]# gluster vol rebalance dht_mem2 status Node Rebalanced-files size scanned failures skipped status run time in secs --------- ----------- ----------- ----------- ----------- ----------- ------------ -------------- localhost 1494440 10.9MB 3289806 0 0 in progress 80441.00 volume rebalance: dht_mem2: success: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 32557 root 20 0 4468440 2.341g 3260 S 34.2 15.1 449:51.34 glusterfs