Gantt
Feature #2374: ceph-client: start laying the groundwork for Linux tracepoints Bug #2590: possible irq lock inversion dependency with con->mutex and osdc->request_mutex Feature #4888: krbd: support boot from root file system on an rbd image Bug #7139: dead tcp connections during connection negotiation may lead to hangs Bug #9192: krbd: poor read (about 10%) vs write performance Feature #10933: refactor krbd map/unmap paths Cleanup #11230: get rid of struct rbd_mapping Cleanup #11232: split up struct rbd_device into struct rbd_device and struct rbd_image Cleanup #11233: decouple header read-in from running checks (supported features, etc) Fix #11234: rbd does many requests to the header on start-up Fix #11418: rbd: feature bits should be re-read during header refresh Feature #14198: rbd: renaming a pool does not update the pool names in /dev/rbd or /sys/bus/rbd Bug #15432: kcephfs: umount -f can fail after mds reconnect failure Bug #20996: WARN_ON in request_reinit() Bug #21420: ceph_osdc_writepages(): pre-allocated osdc->msgpool_op messages vs large number of snapshots Bug #24976: can not umount and kernel crush Bug #36299: Kernel panic: kernel BUG at fs/ceph/mds_client.c:1279! on CentOS 7.5.1804 Bug #37577: kclient mount does not detect newly active rank 0 Bug #38224: Race handling ceph_snap_context in kernel client Bug #40362: amending caps with "ceph auth caps" vs using an existing client Feature #41796: fs/ceph: add lazyio propagate/synchronize support Bug #43290: unrecoverable OOM during rbd_concurrent.sh Bug #44177: kclient: BUG: KASAN: use-after-free in __ceph_open_session+0x2a9/0x370 [libceph] Bug #44695: client: enable fscache will hit "CacheFiles: Assertion failed" with large size read Feature #44700: Add support for sparse-read and "sparse_copyup" writes against RBD clones Feature #46690: Add fscrypt support to the kernel CephFS client Feature #47808: add "full-force" unmap option Feature #48043: add a ->setlease implementation to kcephfs Bug #48104: fs/ceph: ceph.dir.entries does not acquire necessary caps Bug #48749: Use after free in osdmap handling Feature #49581: IP dual stack support for cephfs linux kernel client Bug #50223: qa: "client.4737 isn't responding to mclientcaps(revoke)" Bug #51112: RHEL 8.4: libceph considers osdmap corrupt if numbering is discontinuous Bug #51845: pre-single-major kernel for ubuntu 20.04 is missing Bug #52059: xfstests generic/001 failure Bug #52921: kclient: the read path is buggy when reading the inline data Bug #52973: add test for mounting volume after blocklisting Bug #53418: [krbd] rbd: udev enumerate failed, retrying Bug #53427: krbd_map failed with error code 91 Feature #54410: implement sparse read support for the kclient Bug #55052: when mounting with new dev syntax and -o ms_mode=legacy, the option is not shown Bug #55090: mounting subvolume shows size/used bytes for entire fs, not subvolume Bug #55408: libceph: corrupt inc osdmap (-12) epoch 409760 off 60 (ffffacad17925058 of ffffacad1792501c-ffffacad179edf02) Bug #55823: NETDEV WATCHDOG: enp3s0f1 (ixgbe): transmit queue 3 timed out Bug #55850: libceph socket closed Bug #56531: CephFS Mounts via Linux kernel not releasing locks Bug #56601: ceph kernel client mount.ceph hangs Bug #56693: MDS changed truncate_seq with client caps still outstanding Bug #57656: [testing] dbench: write failed on handle 10009 (Resource temporarily unavailable) Bug #57898: ceph client extremely slow kernel version between 5.15 and 6.0 Feature #58055: feature to block kclient from establishing session Bug #58126: kclient: WARNING: fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0 Support #58635: MDS blacklists clients causing hang at mountpoint Bug #58732: quincy - kernel BUG at fs/ceph/inode.c:1376 Feature #58831: krbd: track blocklisted clients and skip them in rbd_client_find() Bug #58834: kclient: xfstests-dev generic/075 failed Bug #59162: kernel completes umount without waiting for mds close Bug #61331: libcephfs: incorrectly showing the size for snapshots when stating them Bug #61524: kclient: do not send metrics until the MDS rank is ready Bug #61590: add more context for log messages Bug #61843: kclient: was evicted without responding for 300 seconds Bug #62145: kclient: make num_fwd and num_retry to __u32 Bug #62489: testing: did not reconnect to MDS during up:reconnect Documentation #62837: Add support for read_from_replica=localize for cephfs similar to krbd Bug #63324: kclient: watchdog: BUG: soft lockup - CPU#11 stuck for 25738s! [kworker/11:1:1724873] Bug #63346: kclient: fscrypt xfstest generic/317 failed with "execvp: Permission denied" Bug #63586: libceph: osd_sparse_read: failed to allocate 2208169984 sparse read extents Bug #63814: File deletion is 20x slower on kernel mount compared to libcephfs Bug #64035: fscrypt test trigger "kernel BUG at fs/ceph/addr.c:1183!" with the kernel 6.7 Bug #64068: Fails to parse dual stack monlist: another match of type 2 in addrvec Bug #64607: ceph: fstest generic/580 test failure with infinitely loop Feature #64847: krbd/kcephfs: Support read_from_replica everywhere Feature #24: mdsc: preallocate reply msgs Feature #25: mdsc: mempool for cap writeback? Feature #119: avoid looping connect/retry errors on console Feature #206: make a 'soft' mode Feature #387: expose directory subtree partition/replication/fragmentation via ceph.* xattrs Bug #1247: kicking capsnaps can send dups Feature #1296: Support fanotify/inotify Feature #1355: use SKB destructor in messenger? Bug #1701: krbd: limits and constants are not consistent in kernel and userspace Bug #1766: mon_client: sends request before authentication Bug #1769: osd_client: susceptibility to low memory deadlocks Feature #1837: krbd: freeze filesystem on snapshot Cleanup #2085: kclient: improve mtime update in page_mkwrite Bug #2129: ceph: xattr: call __build_xattrs() *before* cap check Cleanup #2131: ceph: xattr: use the generic kernel xattr code Bug #3886: Futher testing result for the issue "ceph: avoid 32-bit page index overflow" Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit Bug #4652: libceph: messages from pool not initialized Bug #4689: libceph: don't have alloc_msg methods limit length Feature #4690: krbd: support arbitrary length responses to class operations Bug #4869: libceph: osd_client: get_reply() generalize for more ops Bug #6809: 3.11 kernel panic: Workqueue: ceph-msgr con_work Feature #8196: Document which features are supported by the kernel client Bug #8275: krbd: 'rbd unmap' gets stuck Bug #8341: improve falover to next available MON Bug #9573: krbd: investigate a dd-in-a-loop slowdown Bug #10313: IO drop outs/timeouts on one of the rbd client Bug #10793: kernel BUG at net/ceph/messenger.c:2954 (while copying on cephfs) Bug #10905: kdb on ceph_tcp_sendmsg Bug #11424: messenger.c: short reads corrupt following ops Bug #11615: Memory Spike and page fault in slab allocator Fix #11767: qa: clean up krbd workunits and add any missing cases to qa suite Bug #11841: umount stuck on NFS over RBD switch over by using Pacemaker Cleanup #11863: osd_client: consolidate exported functions Bug #11976: cephfs kernel driver overuses GFP_NOFS Bug #12544: CEPH_QA_SUITE/AARCH64: Command failed (workunit test rbd/kernel.sh) Support #12648: [old topic] OSD will stuck if running kernel rbd or rbd-fuse on the same node with OSD daemons Feature #12874: krbd: get rid of RBD_MAX_SNAP_COUNT Cleanup #13489: osd_client: consolidate similar osd ops Bug #13587: IO hang when writing to a cached erasure pool Bug #13643: task kworker/u128:1:11460 blocked for more than 120 seconds. with rbd device and dd on it Documentation #15323: Clarify krbd CRUSH map tunables and rbd feature support Feature #17013: wire up SG_IO pages 0x83 and possibly 0x80 for /dev/rbd devices? Bug #19272: kcephfs: got forward for unsafe request Bug #19419: XFS filesystem on RBD image was corrupt after remount Bug #22110: Failures in run_xfstests in krbd-luminous-testing-basic-smithi Bug #24402: wrong used space with ceph df for large objects Bug #36232: node crash && bad crc in data ->kernel: libceph: socket closed (con state OPEN) Bug #37435: mds operates hung at ceph_mdsc_do_request Bug #41551: kclient: mds session hang in opening state Bug #42492: ms_inject_socket_failures vs watch/notify (and exclusive lock) code Bug #59735: fs/ceph: cross check passed in fsid during mount with cluster fsid Bug #61332: dbench test results in call trace in dmesg Bug #64172: Test failure: test_multiple_path_r (tasks.cephfs.test_admin.TestFsAuthorize) Bug #20927: libceph does not give up reconnecting on broken network Bug #22005: result -108 xferred 2000, blk_update_request: I/O error Bug #37769: __ceph_remove_cap caused kernel crash Bug #39945: RBD I/O error leads to ghost-mapped RBD Bug #45456: The read and write operations of libceph are blocked waiting for IO to complete, causing a deadlock Bug #45563: __list_add_valid kernel NULL pointer in _ceph_remove_cap Bug #23272: switch port down ,cephfs kernel client lost session, blocked not recover ok util port up Documentation #40996: Calling messenger v1 protocol legacy is misleading Bug #44166: Client fails to release capabilities, lazy collective shared file I/O (simplified PoC provided). Feature #39542: ceph: cgroup controller for limiting client ops Bug #61333: kernel/fuse client using ceph ID with uid restricted MDS caps cannot update caps
|
« Previous | Next » |