Rebalance and EPERM, looks like you are hitting http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2369 Pranith. ----- Original Message ----- From: "John Lao" <jlao at cloud9analytics.com> To: gluster-users at gluster.org Sent: Thursday, February 24, 2011 11:55:52 PM Subject: Experiencing errors after adding new nodes Hi, I had a 2 node distributed cluster running on 3.1.1 and I added 2 more nodes. I then ran a rebalance on the cluster. Now I am getting permission denied errors and I see the following in the client logs: [2011-02-24 09:59:10.210166] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:59:11.851656] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [root at qe-loader1 glusterfs]# tail -100 mnt-qe-filer01.log [2011-02-24 09:32:50.844211] I [dht-common.c:415:dht_revalidate_cbk] loader-dht: mismatching layouts for / [2011-02-24 09:32:50.845312] I [dht-layout.c:588:dht_layout_normalize] loader-dht: found anomalies in /. holes=1 overlaps=0 [2011-02-24 09:32:50.846417] I [dht-layout.c:689:dht_layout_dir_mismatch] loader-dht: subvol: loader-client-0; inode layout - 0 - 2147483646; disk layout - 2147483646 - 3221225468 [2011-02-24 09:32:50.846434] I [dht-common.c:415:dht_revalidate_cbk] loader-dht: mismatching layouts for / [2011-02-24 09:32:50.846561] I [dht-layout.c:689:dht_layout_dir_mismatch] loader-dht: subvol: loader-client-1; inode layout - 2147483647 - 4294967295; disk layout - 3221225469 - 4294967295 [2011-02-24 09:32:50.846577] I [dht-common.c:415:dht_revalidate_cbk] loader-dht: mismatching layouts for / [2011-02-24 09:32:50.847650] I [dht-layout.c:588:dht_layout_normalize] loader-dht: found anomalies in /. holes=1 overlaps=0 [2011-02-24 09:39:08.159175] I [fuse-bridge.c:3138:fuse_thread_proc] fuse: unmounting /mnt/qe-filer01 [2011-02-24 09:39:08.160180] I [glusterfsd.c:672:cleanup_and_exit] glusterfsd: shutting down [2011-02-24 09:39:14.184554] W [io-stats.c:1644:init] loader: dangling volume. check volfile [2011-02-24 09:39:14.184599] W [dict.c:1204:data_to_str] dict: @data=(nil) [2011-02-24 09:39:14.184614] W [dict.c:1204:data_to_str] dict: @data=(nil) Given volfile: +------------------------------------------------------------------------------+ 1: volume loader-client-0 2: type protocol/client 3: option remote-host qe-filer03 4: option remote-subvolume /data1 5: option transport-type tcp 6: end-volume 7: 8: volume loader-client-1 9: type protocol/client 10: option remote-host qe-filer04 11: option remote-subvolume /data1 12: option transport-type tcp 13: end-volume 14: 15: volume loader-client-2 16: type protocol/client 17: option remote-host 172.24.8.25 18: option remote-subvolume /data1 19: option transport-type tcp 20: end-volume 21: 22: volume loader-client-3 23: type protocol/client 24: option remote-host qe-filer02 25: option remote-subvolume /data1 26: option transport-type tcp 27: end-volume 28: 29: volume loader-dht 30: type cluster/distribute 31: subvolumes loader-client-0 loader-client-1 loader-client-2 loader-client-3 32: end-volume 33: 34: volume loader-write-behind 35: type performance/write-behind 36: subvolumes loader-dht 37: end-volume 38: 39: volume loader-read-ahead 40: type performance/read-ahead 41: subvolumes loader-write-behind 42: end-volume 43: 44: volume loader-io-cache 45: type performance/io-cache 46: subvolumes loader-read-ahead 47: end-volume 48: 49: volume loader-quick-read 50: type performance/quick-read 51: subvolumes loader-io-cache 52: end-volume 53: 54: volume loader-stat-prefetch 55: type performance/stat-prefetch 56: subvolumes loader-quick-read 57: end-volume 58: 59: volume loader 60: type debug/io-stats 61: subvolumes loader-stat-prefetch 62: end-volume +------------------------------------------------------------------------------+ [2011-02-24 09:39:18.132954] I [client-handshake.c:993:select_server_supported_programs] loader-client-2: Using Program GlusterFS-3.1.0, Num (1298437), Version (310) [2011-02-24 09:39:18.136077] I [client-handshake.c:829:client_setvolume_cbk] loader-client-2: Connected to 172.24.8.25:24009, attached to remote volume '/data1'. [2011-02-24 09:39:18.136498] I [client-handshake.c:993:select_server_supported_programs] loader-client-1: Using Program GlusterFS-3.1.0, Num (1298437), Version (310) [2011-02-24 09:39:18.137083] I [client-handshake.c:829:client_setvolume_cbk] loader-client-1: Connected to 172.24.8.222:24009, attached to remote volume '/data1'. [2011-02-24 09:39:18.140002] I [client-handshake.c:993:select_server_supported_programs] loader-client-0: Using Program GlusterFS-3.1.0, Num (1298437), Version (310) [2011-02-24 09:39:18.140599] I [client-handshake.c:829:client_setvolume_cbk] loader-client-0: Connected to 172.24.8.221:24009, attached to remote volume '/data1'. [2011-02-24 09:39:18.144060] I [client-handshake.c:993:select_server_supported_programs] loader-client-3: Using Program GlusterFS-3.1.0, Num (1298437), Version (310) [2011-02-24 09:39:18.144689] I [client-handshake.c:829:client_setvolume_cbk] loader-client-3: Connected to 172.24.8.220:24009, attached to remote volume '/data1'. [2011-02-24 09:39:18.150335] I [fuse-bridge.c:2817:fuse_init] glusterfs-fuse: FUSE inited with protocol versions: glusterfs 7.13 kernel 7.10 [2011-02-24 09:54:12.904354] W [fuse-bridge.c:888:fuse_unlink_cbk] glusterfs-fuse: 4094: UNLINK() / c9.lock => -1 (Permission denied) [2011-02-24 09:54:34.716535] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:54:36.470275] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:55:24.588912] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:55:26.180690] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:55:57.816431] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:55:59.242725] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:56:54.92112] W [fuse-bridge.c:1510:fuse_create_cbk] glusterfs-fuse: 23558: / c9_refresh.lock => -1 (Permission denied) [2011-02-24 09:57:01.792819] W [fuse-bridge.c:1510:fuse_create_cbk] glusterfs-fuse: 23564: /Cloud9c9_refresh.lock => -1 (Permission denied) [2011-02-24 09:57:31.812728] W [fuse-bridge.c:1510:fuse_create_cbk] glusterfs-fuse: 23570: / c9_refresh.lock => -1 (Permission denied) [2011-02-24 09:58:12.738834] W [fuse-bridge.c:1510:fuse_create_cbk] glusterfs-fuse: 23582: / c9_refresh.lock => -1 (Permission denied) [2011-02-24 09:59:10.210166] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) [2011-02-24 09:59:11.851656] I [dht-common.c:369:dht_revalidate_cbk] loader-dht: subvolume loader-client-3 returned -1 (Invalid argument) I am running the rebalance again to see if it will fix the layout issue. Any ideas why I'm seeing these errors after adding new nodes? Regards, John Lao _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
