Nfs-ganesha V2.7.4 with the following MDCACHE patches applied:

https://review.gerrithub.io/c/ffilz/nfs-ganesha/+/457970

https://github.com/nfs-ganesha/nfs-ganesha/commit/c98ad1e238f5db9db5ab8db8cea1c5cf1f123d76

https://github.com/nfs-ganesha/nfs-ganesha/commit/136df4f262c3f9bc29df456eac50921321826da3

 

Crash when freeing a dirent.

 

(gdb) bt

#0  0x00007fe0a2084277 in raise () from /lib64/libc.so.6

#1  0x00007fe0a2085968 in abort () from /lib64/libc.so.6

#2  0x00007fe0a20c6d97 in __libc_message () from /lib64/libc.so.6

#3  0x00007fe0a20cf4f9 in _int_free () from /lib64/libc.so.6

#4  0x0000000000543e9c in gsh_free (p=0x1b72140) at /src/src/include/abstract_mem.h:246

#5  0x0000000000544b0c in mdcache_avl_remove (parent=0x1b17000, dirent=0x1b72140)

    at /src/src/FSAL/Stackable_FSALs/FSAL_MDCACHE/mdcache_avl.c:240

#6  0x0000000000545e4d in mdcache_avl_clean_trees (parent=0x1b17000)

    at /src/src/FSAL/Stackable_FSALs/FSAL_MDCACHE/mdcache_avl.c:614

#7  0x000000000053a11b in mdcache_dirent_invalidate_all (entry=0x1b17000)

    at /src/src/FSAL/Stackable_FSALs/FSAL_MDCACHE/mdcache_helpers.c:606

#8  0x0000000000541b15 in mdcache_readdir_chunked (directory=0x1b17000, whence=5012127, dir_state=0x7fe097debaf0, 

    cb=0x4323ed <populate_dirent>, attrmask=0, eod_met=0x7fe097debfeb)

    at /src/src/FSAL/Stackable_FSALs/FSAL_MDCACHE/mdcache_helpers.c:2864

#9  0x000000000053054c in mdcache_readdir (dir_hdl=0x1b17038, whence=0x7fe097debad0, dir_state=0x7fe097debaf0, 

    cb=0x4323ed <populate_dirent>, attrmask=0, eod_met=0x7fe097debfeb)

    at /src/src/FSAL/Stackable_FSALs/FSAL_MDCACHE/mdcache_handle.c:559

#10 0x0000000000432d14 in fsal_readdir (directory=0x1b17038, cookie=5012127, nbfound=0x7fe097debfec, 

    eod_met=0x7fe097debfeb, attrmask=0, cb=0x491d35 <nfs3_readdir_callback>, opaque=0x7fe097debfa0)

    at /src/src/FSAL/fsal_helper.c:1164

#11 0x0000000000491b1d in nfs3_readdir (arg=0x1e12508, req=0x1e11e00, res=0x1be41e0)

    at /src/src/Protocols/NFS/nfs3_readdir.c:289

#12 0x0000000000457c16 in nfs_rpc_process_request (reqdata=0x1e11e00) at /src/src/MainNFSD/nfs_worker_thread.c:1328

#13 0x00000000004583d5 in nfs_rpc_valid_NFS (req=0x1e11e00) at /src/src/MainNFSD/nfs_worker_thread.c:1548

#14 0x00007fe0a3821034 in svc_vc_decode (req=0x1e11e00) at /src/src/libntirpc/src/svc_vc.c:829

#15 0x000000000044adc5 in nfs_rpc_decode_request (xprt=0x1b040e0, xdrs=0x1be4000)

    at /src/src/MainNFSD/nfs_rpc_dispatcher_thread.c:1345

#16 0x00007fe0a3820f45 in svc_vc_recv (xprt=0x1b040e0) at /src/src/libntirpc/src/svc_vc.c:802

#17 0x00007fe0a381d689 in svc_rqst_xprt_task (wpe=0x1b042f8) at /src/src/libntirpc/src/svc_rqst.c:769

#18 0x00007fe0a381dae6 in svc_rqst_epoll_events (sr_rec=0x1ae45f0, n_events=1)

    at /src/src/libntirpc/src/svc_rqst.c:941

#19 0x00007fe0a381dd7b in svc_rqst_epoll_loop (sr_rec=0x1ae45f0) at /src/src/libntirpc/src/svc_rqst.c:1014

---Type <return> to continue, or q <return> to quit---q

Quit

(gdb) select-frame 5

(gdb) info args

parent = 0x1b17000

dirent = 0x1b72140

(gdb) info locals

chunk = 0x1b4b510

__func__ = "mdcache_avl_remove"

(gdb) print *chunk

$1 = {chunks = {next = 0x1b172a0, prev = 0x1b172a0}, dirents = {next = 0x1b29930, prev = 0x1bc2840}, 

  parent = 0x1b17000, chunk_lru = {q = {next = 0x0, prev = 0x0}, qid = LRU_ENTRY_L1, refcnt = 0, flags = 0, 

    lane = 16, cf = 0}, reload_ck = 5012127, next_ck = 0, num_entries = 297}

(gdb) print *dirent

$2 = {chunk_list = {next = 0x0, prev = 0x0}, chunk = 0x0, node_name = {left = 0x0, right = 0x0, parent = 28852730}, 

  node_ck = {left = 0x1b78ff0, right = 0x1b68970, parent = 28718322}, node_sorted = {left = 0x0, right = 0x0, 

    parent = 0}, ck = 5019809, eod = false, namehash = 6207075547366218433, ckey = {hk = 15362064496009940491, 

    fsal = 0x7fe09f949080 <FOO>, kv = {addr = 0x0, len = 0}}, flags = 0, entry = 0x0, name = 0x1b721f0 "random.37", 

  name_buffer = 0x1b721f0 "random.37"}

(gdb) 

 

I am happy to provide any additional debug info you want from the core.

Thanks,

Vandana