Description of problem: ======================== I/O error on calculating are equal check sum on mount point , while trying to create files which are greater than the brick size Version-Release number of selected component (if applicable): ============================================================= 3.4.0.14rhs-1.el6rhs.x86_64 How reproducible: ================= always Steps to Reproduce: =================== 1.Create a distribute volume with 2 bricks (each brick is 1GB in size) 2.Fuse mount the volume and create files which are greater than the brick size for i in {1..500} ; do dd if=/dev/urandom of=f"$i" bs=10M count=1; done Files are created and after some time , we get 'No Space left on device' 3.[root@RHEL6 sample]# du -sh 1.9G 4. Are equal check sum on the mount point fails with short read : /opt/qa/tools/arequal-checksum /mnt/sample/ md5sum: /mnt/sample/f164: No such file or directory /mnt/sample/f164: short read ftw (/mnt/sample/) returned -1 (Success), terminating Are equal check sum fails with short read for /f164 . As per our understanding , f164 was being created when the first brick was full and it creates a link file on the other brick for creation of file f164 and then continues with the creation of other files and so are equal fails with short read . Please correct me if I am wrong . -------------------------Part of the Log---------------------------- [2013-08-01 06:38:28.874289] W [fuse-bridge.c:2384:fuse_create_cbk] 0-glusterfs-fuse: 17599: /f500 => -1 (No space left on device) [2013-08-01 06:38:28.874375] W [defaults.c:1291:default_release] (-->/usr/lib64/glusterfs/3.4.0.14rhs/xlator/protocol/client.so(client3_3_create_cbk+0xa01) [0x7f662567fe51] (-->/usr/lib64/glusterfs/3.4.0.14rhs/xlator/protocol/client.so(client_local_wipe+0x28) [0x7f662566ec98] (-->/usr/lib64/libglusterfs.so.0(fd_unref+0x13b) [0x3ee5a3975b]))) 0-fuse: xlator does not implement release_cbk [2013-08-01 06:58:46.387644] W [client-rpc-fops.c:1170:client3_3_fgetxattr_cbk] 0-sample-client-0: remote operation failed: No data available [2013-08-01 06:58:46.387704] E [dht-helper.c:761:dht_migration_complete_check_task] 0-sample-dht: (null): failed to get the 'linkto' xattr No data available [2013-08-01 06:58:46.387960] W [page.c:991:__ioc_page_error] 0-sample-io-cache: page error for page = 0x7f6618021900 & waitq = 0x7f661802dbe0 [2013-08-01 06:58:46.388191] W [fuse-bridge.c:2603:fuse_readv_cbk] 0-glusterfs-fuse: 26162: READ => -1 (No such file or directory) [2013-08-01 07:26:23.319505] E [dht-helper.c:761:dht_migration_complete_check_task] 0-sample-dht: /f164: failed to get the 'linkto' xattr No data available Actual results: ================ Are equal check sum on the mount point fails with short read Expected results: Additional info:
Volume info : ============ [root@jay tmp]# gluster v i sample Volume Name: sample Type: Distribute Volume ID: 1895ec09-a451-4182-acd6-b258519c8c8e Status: Started Number of Bricks: 2 Transport-type: tcp Bricks: Brick1: 10.70.34.86:/BRICK1/b1 Brick2: 10.70.34.87:/BRICK1/b2 ===================================================================== sosreports at : http://rhsqe-repo.lab.eng.blr.redhat.com/bugs_necessary_info/990897/