Date: Sun, 3 Mar 2024 13:17:30 -0800 From: Rick Macklem <rick.macklem@gmail.com> To: Garrett Wollman <wollman@bimajority.org> Cc: stable@freebsd.org Subject: Re: 13-stable NFS server hang Message-ID: <CAM5tNy4BM3fwccjF53ROP-7NojsWMM2fUY2_RA-4GMWfc6Sn4g@mail.gmail.com> In-Reply-To: <26083.64612.717082.366639@hergotha.csail.mit.edu> References: <26078.50375.679881.64018@hergotha.csail.mit.edu> <CAM5tNy7ZZ2bVLmYnOCWzrS9wq6yudoV5JKG5ObRU0=wLt1ofZw@mail.gmail.com> <26083.64612.717082.366639@hergotha.csail.mit.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Mar 2, 2024 at 8:28=E2=80=AFPM Garrett Wollman <wollman@bimajority.= org> wrote: > > > I wrote previously: > > PID TID COMM TDNAME KSTACK > > 997 108481 nfsd nfsd: master mi_switch sleepq_tim= edwait _sleep nfsv4_lock nfsrvd_dorpc nfssvc_program svc_run_internal svc_r= un nfsrvd_nfsd nfssvc_nfsd sys_nfssvc amd64_syscall fast_syscall_common > > 997 960918 nfsd nfsd: service mi_switch sleepq_tim= edwait _sleep nfsv4_lock nfsrv_setclient nfsrvd_exchangeid nfsrvd_dorpc nfs= svc_program svc_run_internal svc_thread_start fork_exit fork_trampoline > > 997 962232 nfsd nfsd: service mi_switch _cv_wait t= xg_wait_synced_impl txg_wait_synced dmu_offset_next zfs_holey zfs_freebsd_i= octl vn_generic_copy_file_range vop_stdcopy_file_range VOP_COPY_FILE_RANGE = vn_copy_file_range nfsrvd_copy_file_range nfsrvd_dorpc nfssvc_program svc_r= un_internal svc_thread_start fork_exit fork_trampoline > > I spent some time this evening looking at this last stack trace, and > stumbled across the following comment in > sys/contrib/openzfs/module/zfs/dmu.c: > > | /* > | * Enable/disable forcing txg sync when dirty checking for holes with l= seek(). > | * By default this is enabled to ensure accurate hole reporting, it can= result > | * in a significant performance penalty for lseek(SEEK_HOLE) heavy work= loads. > | * Disabling this option will result in holes never being reported in d= irty > | * files which is always safe. > | */ > | int zfs_dmu_offset_next_sync =3D 1; > > I believe this explains why vn_copy_file_range sometimes takes much > longer than a second: our servers often have lots of data waiting to > be written to disk, and if the file being copied was recently modified > (and so is dirty), this might take several seconds. I've set > vfs.zfs.dmu_offset_next_sync=3D0 on the server that was hurting the most > and am watching to see if we have more freezes. > > If this does the trick, then I can delay deploying a new kernel until > April, after my upcoming vacation. Interesting. Please let us know how it goes. And enjoy your vacation, rick > > -GAWollman >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAM5tNy4BM3fwccjF53ROP-7NojsWMM2fUY2_RA-4GMWfc6Sn4g>