Hi, Trying to solve my problem of corrupted files on CephFS, I create a new thread to talk about the warning "1 MDSs report slow requests" which often occur when a process locks a file for a long time while others processes asks for the lock too. Is it a wrong situation ? Does it really need to set cluster state to HEALTH_WARN ? For my example, here are my ops_in_flight & MDS cache dump related to a file in this situation (see attachments). Thank you Florent
{ "ino": 1099536687316, "rdev": 0, "ctime": "2017-12-13 14:44:00.875020", "btime": "2017-12-13 14:44:00.804427", "mode": 33152, "uid": 5000, "gid": 5000, "nlink": 1, "dir_layout": { "dir_hash": 0 }, "layout": { "stripe_unit": 1048576, "stripe_count": 3, "object_size": 4194304, "pool_id": 30, "pool_ns": "" }, "old_pools": [ 0 ], "size": 24516, "truncate_seq": 1, "truncate_size": 18446744073709551615, "truncate_from": 0, "truncate_pending": 0, "mtime": "2017-12-13 14:44:12.015739", "atime": "2017-12-13 14:44:00.804427", "time_warp_seq": 0, "change_attr": 5, "export_pin": -1, "client_ranges": [ { "client": 462286797, "byte range": { "first": 0, "last": 12582912 }, "follows": 1 } ], "dirstat": { "version": 0, "mtime": "0.000000", "num_files": 0, "num_subdirs": 0 }, "rstat": { "version": 0, "rbytes": 24516, "rfiles": 1, "rsubdirs": 0, "rsnaprealms": 0, "rctime": "0.000000" }, "accounted_rstat": { "version": 0, "rbytes": 24516, "rfiles": 1, "rsubdirs": 0, "rsnaprealms": 0, "rctime": "0.000000" }, "version": 74667240, "file_data_version": 0, "xattr_version": 1, "backtrace_version": 74667146, "stray_prior_path": "", "symlink": "", "old_inodes": [], "dirfragtree": { "splits": [] }, "is_auth": true, "auth_state": { "replicas": {} }, "replica_state": { "authority": [ 0, -2 ], "replica_nonce": 0 }, "auth_pins": 0, "nested_auth_pins": 0, "is_frozen": false, "is_freezing": false, "pins": { "ptrwaiter": 0, "request": 5, "lock": 0, "caps": 1, "dirtyparent": 1, "dirty": 1, "waiter": 1, "authpin": 0 }, "nref": 9, "versionlock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "authlock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "linklock": {}, "dirfragtreelock": {}, "filelock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "xattrlock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "snaplock": {}, "nestlock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "flocklock": {}, "policylock": {}, "states": [ "auth", "dirty", "dirtyparent", "dirtypool" ], "client_caps": [ { "client_id": 462286797, "pending": "pAsxLsXsxFsxcrwb", "issued": "pAsxLsXsxFsxcrwb", "wanted": "pAsxXsxFsxcrwb", "last_sent": "Ax" } ], "loner": 462286797, "want_loner": 462286797, "mds_caps_wanted": [], "dirfrags": [] }, -- { "path": "maildata1/mydomain.com/myuser/mdbox/storage/dovecot.map.index.log", "path_ino": 1, "snap_first": 2, "snap_last": 18446744073709551614, "is_primary": true, "is_remote": false, "is_null": false, "is_new": false, "inode": 1099536687316, "remote_type": "", "version": 74667240, "projected_version": 74667240, "auth_pins": 0, "nested_auth_pins": 0, "is_auth": true, "auth_state": { "replicas": {} }, "replica_state": { "authority": [ 0, -2 ], "replica_nonce": 0 }, "auth_pins": 0, "nested_auth_pins": 0, "is_frozen": false, "is_freezing": false, "pins": { "request": 0, "lock": 0, "inodepin": 1, "dirty": 1, "authpin": 0, "clientlease": 0 }, "nref": 2, "lock": {}, "versionlock": { "gather_set": [], "num_client_lease": 0, "num_rdlocks": 0, "num_wrlocks": 0, "num_xlocks": 0, "xlock_by": {} }, "states": [ "auth", "dirty" ] }
{ "ops": [ { "description": "client_request(client.462286797:2639 setfilelockrule 1, type 2, owner 14522995601528809479, pid 27832, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:46:06.928750 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:46:06.935081", "age": 162.957982, "duration": 162.957992, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:2639", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 2639 }, "events": [ { "time": "2017-12-13 14:46:06.935081", "event": "initiated" }, { "time": "2017-12-13 14:46:06.935212", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.242343", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.259144", "event": "acquired locks" } ] } }, { "description": "client_request(client.462286797:2794 setfilelockrule 1, type 2, owner 18143998180001628474, pid 27834, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:46:21.581788 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:46:21.588153", "age": 148.304909, "duration": 148.304935, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:2794", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 2794 }, "events": [ { "time": "2017-12-13 14:46:21.588153", "event": "initiated" }, { "time": "2017-12-13 14:46:21.588284", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.242355", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.259159", "event": "acquired locks" } ] } }, { "description": "client_request(client.462286797:3435 setfilelockrule 1, type 2, owner 13551808070419737801, pid 27833, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:47:35.026035 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:47:35.031979", "age": 74.861083, "duration": 74.861120, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:3435", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 3435 }, "events": [ { "time": "2017-12-13 14:47:35.031979", "event": "initiated" }, { "time": "2017-12-13 14:47:35.032115", "event": "acquired locks" } ] } }, { "description": "client_request(client.462286797:3555 setfilelockrule 1, type 2, owner 15564041790451060973, pid 28105, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:47:51.502330 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:47:51.507899", "age": 58.385164, "duration": 58.385209, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:3555", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 3555 }, "events": [ { "time": "2017-12-13 14:47:51.507899", "event": "initiated" }, { "time": "2017-12-13 14:47:51.507982", "event": "acquired locks" } ] } }, { "description": "client_request(client.462286797:2776 setfilelockrule 1, type 2, owner 15225477367501707241, pid 27827, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:46:21.507653 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:46:21.513974", "age": 148.379089, "duration": 148.379144, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:2776", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 2776 }, "events": [ { "time": "2017-12-13 14:46:21.513974", "event": "initiated" }, { "time": "2017-12-13 14:46:21.514092", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.242349", "event": "acquired locks" }, { "time": "2017-12-13 14:47:21.259153", "event": "acquired locks" } ] } }, { "description": "client_request(client.462286797:3326 setfilelockrule 1, type 2, owner 18095535510671540056, pid 27835, start 0, length 0, wait 1 #0x100017e60d4 2017-12-13 14:47:21.900625 caller_uid=5000, caller_gid=5000{5000,})", "initiated_at": "2017-12-13 14:47:21.906494", "age": 87.986568, "duration": 87.986634, "type_data": { "flag_point": "acquired locks", "reqid": "client.462286797:3326", "op_type": "client_request", "client_info": { "client": "client.462286797", "tid": 3326 }, "events": [ { "time": "2017-12-13 14:47:21.906494", "event": "initiated" }, { "time": "2017-12-13 14:47:21.906647", "event": "acquired locks" } ] } } ], "num_ops": 6 }
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com