| Message ID | 52BD53CA.5050205@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi- On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: > On 12/24/2013 01:39 AM, J. Bruce Fields wrote: >> On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: >>> Hi, >>> >>> I'm trying to run NFS with protocol version 4 only (that is, with v2 >>> & v3 disabled) on a CentOS 6.5 install running as a KVM guest. >>> >>> The RedHat documentation (amongst others) states that rpcbind isn't >>> needed with v4, but if I start nfs without rpcbind I get errors. >> >> I suspect the kernel code needs to be fixed to not attempt to register >> with rpcbind n the v4-only case. (Or to attempt to register but ignore >> any error, I'm not sure which is best.) >> >> And this may not be the only issue in the v4-only case. This isn't >> really a priority for me right now, but I'd happily look at patches. > > Hi all, > > I make a patch for this problem, please have a check, thanks. > > From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 > From: Kinglong Mee <kinglongmee@gmail.com> > Date: Fri, 27 Dec 2013 18:06:25 +0800 > Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind > > 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not a hidden service, like the client's callback server which can only be discovered by a forward advertisement (SETCLIENTID). I think I prefer ignoring the rpcb_set error for NFSv4. > 2. don't start lockd when only supports nfsv4. > > Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> > Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> > --- > fs/nfsd/netns.h | 3 +++ > fs/nfsd/nfs4proc.c | 1 + > fs/nfsd/nfsctl.c | 3 +++ > fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- > 4 files changed, 23 insertions(+), 5 deletions(-) > > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h > index 849a7c3..ae2c179 100644 > --- a/fs/nfsd/netns.h > +++ b/fs/nfsd/netns.h > @@ -96,6 +96,9 @@ struct nfsd_net { > > bool nfsd_net_up; > > + bool lockd_up; > + u32 nfsd_needs_lockd; > + > /* > * Time of server startup > */ > diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c > index 419572f..1496376 100644 > --- a/fs/nfsd/nfs4proc.c > +++ b/fs/nfsd/nfs4proc.c > @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { > .vs_proc = nfsd_procedures4, > .vs_dispatch = nfsd_dispatch, > .vs_xdrsize = NFS4_SVC_XDRSIZE, > + .vs_hidden = 1, > }; > > /* > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c > index 7f55517..8c7b0f0 100644 > --- a/fs/nfsd/nfsctl.c > +++ b/fs/nfsd/nfsctl.c > @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) > switch(num) { > case 2: > case 3: > + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); > + break; > case 4: > nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > break; > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c > index 760c85a..2b841d8 100644 > --- a/fs/nfsd/nfssvc.c > +++ b/fs/nfsd/nfssvc.c > @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net *net) > ret = nfsd_init_socks(net); > if (ret) > goto out_socks; > - ret = lockd_up(net); > - if (ret) > - goto out_socks; > + > + if (nn->nfsd_needs_lockd && !nn->lockd_up) { > + ret = lockd_up(net); > + if (ret) > + goto out_socks; > + nn->lockd_up = 1; > + } > + > ret = nfs4_state_start_net(net); > if (ret) > goto out_lockd; > @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net *net) > return 0; > > out_lockd: > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > out_socks: > nfsd_shutdown_generic(); > return ret; > @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) > struct nfsd_net *nn = net_generic(net, nfsd_net_id); > > nfs4_state_shutdown_net(net); > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > nn->nfsd_net_up = false; > nfsd_shutdown_generic(); > } > -- > 1.8.4.2 > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Dec 27, 2013 at 11:05:05AM -0500, Chuck Lever wrote: > Hi- > > On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: > > > On 12/24/2013 01:39 AM, J. Bruce Fields wrote: > >> On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: > >>> Hi, > >>> > >>> I'm trying to run NFS with protocol version 4 only (that is, with v2 > >>> & v3 disabled) on a CentOS 6.5 install running as a KVM guest. > >>> > >>> The RedHat documentation (amongst others) states that rpcbind isn't > >>> needed with v4, but if I start nfs without rpcbind I get errors. > >> > >> I suspect the kernel code needs to be fixed to not attempt to register > >> with rpcbind n the v4-only case. (Or to attempt to register but ignore > >> any error, I'm not sure which is best.) > >> > >> And this may not be the only issue in the v4-only case. This isn't > >> really a priority for me right now, but I'd happily look at patches. > > > > Hi all, > > > > I make a patch for this problem, please have a check, thanks. > > > > From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 > > From: Kinglong Mee <kinglongmee@gmail.com> > > Date: Fri, 27 Dec 2013 18:06:25 +0800 > > Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind > > > > 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind > > IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not a hidden service, like the client's callback server which can only be discovered by a forward advertisement (SETCLIENTID). > > I think I prefer ignoring the rpcb_set error for NFSv4. Agreed. My only concern would be that there be no unnecessary delays or errors logged in the v4-only case if rpcbind isn't running. --b. > > > > 2. don't start lockd when only supports nfsv4. > > > > Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> > > Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> > > --- > > fs/nfsd/netns.h | 3 +++ > > fs/nfsd/nfs4proc.c | 1 + > > fs/nfsd/nfsctl.c | 3 +++ > > fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- > > 4 files changed, 23 insertions(+), 5 deletions(-) > > > > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h > > index 849a7c3..ae2c179 100644 > > --- a/fs/nfsd/netns.h > > +++ b/fs/nfsd/netns.h > > @@ -96,6 +96,9 @@ struct nfsd_net { > > > > bool nfsd_net_up; > > > > + bool lockd_up; > > + u32 nfsd_needs_lockd; > > + > > /* > > * Time of server startup > > */ > > diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c > > index 419572f..1496376 100644 > > --- a/fs/nfsd/nfs4proc.c > > +++ b/fs/nfsd/nfs4proc.c > > @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { > > .vs_proc = nfsd_procedures4, > > .vs_dispatch = nfsd_dispatch, > > .vs_xdrsize = NFS4_SVC_XDRSIZE, > > + .vs_hidden = 1, > > }; > > > > /* > > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c > > index 7f55517..8c7b0f0 100644 > > --- a/fs/nfsd/nfsctl.c > > +++ b/fs/nfsd/nfsctl.c > > @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) > > switch(num) { > > case 2: > > case 3: > > + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > > + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); > > + break; > > case 4: > > nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > > break; > > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c > > index 760c85a..2b841d8 100644 > > --- a/fs/nfsd/nfssvc.c > > +++ b/fs/nfsd/nfssvc.c > > @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net *net) > > ret = nfsd_init_socks(net); > > if (ret) > > goto out_socks; > > - ret = lockd_up(net); > > - if (ret) > > - goto out_socks; > > + > > + if (nn->nfsd_needs_lockd && !nn->lockd_up) { > > + ret = lockd_up(net); > > + if (ret) > > + goto out_socks; > > + nn->lockd_up = 1; > > + } > > + > > ret = nfs4_state_start_net(net); > > if (ret) > > goto out_lockd; > > @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net *net) > > return 0; > > > > out_lockd: > > - lockd_down(net); > > + if (nn->lockd_up) { > > + lockd_down(net); > > + nn->lockd_up = 0; > > + } > > out_socks: > > nfsd_shutdown_generic(); > > return ret; > > @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) > > struct nfsd_net *nn = net_generic(net, nfsd_net_id); > > > > nfs4_state_shutdown_net(net); > > - lockd_down(net); > > + if (nn->lockd_up) { > > + lockd_down(net); > > + nn->lockd_up = 0; > > + } > > nn->nfsd_net_up = false; > > nfsd_shutdown_generic(); > > } > > -- > > 1.8.4.2 > > > > > > -- > > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > > the body of a message to majordomo@vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html > > -- > Chuck Lever > chuck[dot]lever[at]oracle[dot]com > > > > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Dec 27, 2013, at 1:43 PM, J.;Bruce Fields <bfields@fieldses.org> wrote: > On Fri, Dec 27, 2013 at 11:05:05AM -0500, Chuck Lever wrote: >> Hi- >> >> On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: >> >>> On 12/24/2013 01:39 AM, J. Bruce Fields wrote: >>>> On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: >>>>> Hi, >>>>> >>>>> I'm trying to run NFS with protocol version 4 only (that is, with v2 >>>>> & v3 disabled) on a CentOS 6.5 install running as a KVM guest. >>>>> >>>>> The RedHat documentation (amongst others) states that rpcbind isn't >>>>> needed with v4, but if I start nfs without rpcbind I get errors. >>>> >>>> I suspect the kernel code needs to be fixed to not attempt to register >>>> with rpcbind n the v4-only case. (Or to attempt to register but ignore >>>> any error, I'm not sure which is best.) >>>> >>>> And this may not be the only issue in the v4-only case. This isn't >>>> really a priority for me right now, but I'd happily look at patches. >>> >>> Hi all, >>> >>> I make a patch for this problem, please have a check, thanks. >>> >>> From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 >>> From: Kinglong Mee <kinglongmee@gmail.com> >>> Date: Fri, 27 Dec 2013 18:06:25 +0800 >>> Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind >>> >>> 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind >> >> IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not a hidden service, like the client's callback server which can only be discovered by a forward advertisement (SETCLIENTID). >> >> I think I prefer ignoring the rpcb_set error for NFSv4. > > Agreed. My only concern would be that there be no unnecessary delays or > errors logged in the v4-only case if rpcbind isn't running. I believe the rpcb_set upcall now uses the AF_LOCAL transport, which should be able to detect immediately that rpcbind is not listening. The OP did not report a delay or hang, thankfully. > > --b. > >> >> >>> 2. don't start lockd when only supports nfsv4. >>> >>> Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> >>> Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> >>> --- >>> fs/nfsd/netns.h | 3 +++ >>> fs/nfsd/nfs4proc.c | 1 + >>> fs/nfsd/nfsctl.c | 3 +++ >>> fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- >>> 4 files changed, 23 insertions(+), 5 deletions(-) >>> >>> diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h >>> index 849a7c3..ae2c179 100644 >>> --- a/fs/nfsd/netns.h >>> +++ b/fs/nfsd/netns.h >>> @@ -96,6 +96,9 @@ struct nfsd_net { >>> >>> bool nfsd_net_up; >>> >>> + bool lockd_up; >>> + u32 nfsd_needs_lockd; >>> + >>> /* >>> * Time of server startup >>> */ >>> diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c >>> index 419572f..1496376 100644 >>> --- a/fs/nfsd/nfs4proc.c >>> +++ b/fs/nfsd/nfs4proc.c >>> @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { >>> .vs_proc = nfsd_procedures4, >>> .vs_dispatch = nfsd_dispatch, >>> .vs_xdrsize = NFS4_SVC_XDRSIZE, >>> + .vs_hidden = 1, >>> }; >>> >>> /* >>> diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c >>> index 7f55517..8c7b0f0 100644 >>> --- a/fs/nfsd/nfsctl.c >>> +++ b/fs/nfsd/nfsctl.c >>> @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) >>> switch(num) { >>> case 2: >>> case 3: >>> + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); >>> + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); >>> + break; >>> case 4: >>> nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); >>> break; >>> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c >>> index 760c85a..2b841d8 100644 >>> --- a/fs/nfsd/nfssvc.c >>> +++ b/fs/nfsd/nfssvc.c >>> @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net *net) >>> ret = nfsd_init_socks(net); >>> if (ret) >>> goto out_socks; >>> - ret = lockd_up(net); >>> - if (ret) >>> - goto out_socks; >>> + >>> + if (nn->nfsd_needs_lockd && !nn->lockd_up) { >>> + ret = lockd_up(net); >>> + if (ret) >>> + goto out_socks; >>> + nn->lockd_up = 1; >>> + } >>> + >>> ret = nfs4_state_start_net(net); >>> if (ret) >>> goto out_lockd; >>> @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net *net) >>> return 0; >>> >>> out_lockd: >>> - lockd_down(net); >>> + if (nn->lockd_up) { >>> + lockd_down(net); >>> + nn->lockd_up = 0; >>> + } >>> out_socks: >>> nfsd_shutdown_generic(); >>> return ret; >>> @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) >>> struct nfsd_net *nn = net_generic(net, nfsd_net_id); >>> >>> nfs4_state_shutdown_net(net); >>> - lockd_down(net); >>> + if (nn->lockd_up) { >>> + lockd_down(net); >>> + nn->lockd_up = 0; >>> + } >>> nn->nfsd_net_up = false; >>> nfsd_shutdown_generic(); >>> } >>> -- >>> 1.8.4.2 >>> >>> >>> -- >>> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in >>> the body of a message to majordomo@vger.kernel.org >>> More majordomo info at http://vger.kernel.org/majordomo-info.html >> >> -- >> Chuck Lever >> chuck[dot]lever[at]oracle[dot]com >> >> >> >> > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html
I get the trace when rpc.nfsd hang. 1608 Dec 29 14:25:12 localhost kernel: [ 1224.449293] rpc.nfsd D c0d94300 0 1199 991 0x00000080 1609 Dec 29 14:25:12 localhost kernel: [ 1224.451347] d9a9bc98 00000086 c046aa48 c0d94300 ddb66540 c0d79300 58625871 0000011c 1610 Dec 29 14:25:12 localhost kernel: [ 1224.453426] c0d79300 dfff4300 dcd93a80 c0461738 00000000 c0d94300 00000000 00000020 1611 Dec 29 14:25:12 localhost kernel: [ 1224.455701] da4d53a0 00000020 ddb66540 da4d53b0 d9a9bc84 c046add9 dcd93a80 00000292 1612 Dec 29 14:25:12 localhost kernel: [ 1224.457853] Call Trace: 1613 Dec 29 14:25:12 localhost kernel: [ 1224.459919] [<c046aa48>] ? insert_work+0x38/0x80 1614 Dec 29 14:25:12 localhost kernel: [ 1224.462055] [<c0461738>] ? mod_timer+0xe8/0x1c0 1615 Dec 29 14:25:12 localhost kernel: [ 1224.464230] [<c046add9>] ? __queue_delayed_work+0x89/0x140 1616 Dec 29 14:25:12 localhost kernel: [ 1224.466304] [<e092d970>] ? __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] 1617 Dec 29 14:25:12 localhost kernel: [ 1224.468561] [<c09bd543>] schedule+0x23/0x60 1618 Dec 29 14:25:12 localhost kernel: [ 1224.470671] [<e092d99d>] rpc_wait_bit_killable+0x2d/0x80 [sunrpc] 1619 Dec 29 14:25:12 localhost kernel: [ 1224.472785] [<c09bdae1>] __wait_on_bit+0x51/0x70 1620 Dec 29 14:25:12 localhost kernel: [ 1224.474974] [<e092d970>] ? __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] 1621 Dec 29 14:25:12 localhost kernel: [ 1224.477170] [<e092d970>] ? __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] 1622 Dec 29 14:25:12 localhost kernel: [ 1224.479389] [<c09bdb5b>] out_of_line_wait_on_bit+0x5b/0x70 1623 Dec 29 14:25:12 localhost kernel: [ 1224.481739] [<c048e440>] ? autoremove_wake_function+0x40/0x40 1624 Dec 29 14:25:12 localhost kernel: [ 1224.483881] [<e092e703>] __rpc_execute+0x1f3/0x3a0 [sunrpc] 1625 Dec 29 14:25:12 localhost kernel: [ 1224.486030] [<c0516283>] ? mempool_alloc_slab+0x13/0x20 1626 Dec 29 14:25:12 localhost kernel: [ 1224.488194] [<c051638e>] ? mempool_alloc+0x3e/0x100 1627 Dec 29 14:25:12 localhost kernel: [ 1224.490307] [<e0925d80>] ? call_bind_status+0x260/0x260 [sunrpc] 1628 Dec 29 14:25:12 localhost kernel: [ 1224.492559] [<c048e09c>] ? wake_up_bit+0x1c/0x20 1629 Dec 29 14:25:12 localhost kernel: [ 1224.494844] [<e092f866>] rpc_execute+0x56/0x90 [sunrpc] 1630 Dec 29 14:25:12 localhost kernel: [ 1224.496935] [<e0926cf9>] rpc_run_task+0x59/0x70 [sunrpc] 1631 Dec 29 14:25:12 localhost kernel: [ 1224.499122] [<e0926d4c>] rpc_call_sync+0x3c/0x90 [sunrpc] 1632 Dec 29 14:25:12 localhost kernel: [ 1224.501260] [<e0926de8>] rpc_ping+0x48/0x60 [sunrpc] 1633 Dec 29 14:25:12 localhost kernel: [ 1224.503367] [<e092703b>] rpc_bind_new_program+0x4b/0x70 [sunrpc] 1634 Dec 29 14:25:12 localhost kernel: [ 1224.505608] [<e0938333>] rpcb_create_local+0x163/0x1f0 [sunrpc] 1635 Dec 29 14:25:12 localhost kernel: [ 1224.507720] [<e0932199>] ? __svc_create+0x119/0x1f0 [sunrpc] 1636 Dec 29 14:25:12 localhost kernel: [ 1224.509830] [<e0932016>] svc_rpcb_setup+0x16/0x30 [sunrpc] 1637 Dec 29 14:25:12 localhost kernel: [ 1224.511963] [<e0932052>] svc_bind+0x22/0x30 [sunrpc] 1638 Dec 29 14:25:12 localhost kernel: [ 1224.514056] [<e09b73a4>] nfsd_create_serv+0xc4/0x1d0 [nfsd] 1639 Dec 29 14:25:12 localhost kernel: [ 1224.516844] [<e09b7600>] ? nfsd_destroy+0x70/0x70 [nfsd] 1640 Dec 29 14:25:12 localhost kernel: [ 1224.518870] [<e09b8d1f>] write_ports+0x21f/0x2b0 [nfsd] 1641 Dec 29 14:25:12 localhost kernel: [ 1224.521359] [<c06a182c>] ? _copy_from_user+0x2c/0x40 1642 Dec 29 14:25:12 localhost kernel: [ 1224.523358] [<c05854fe>] ? simple_transaction_get+0x8e/0xa0 1643 Dec 29 14:25:12 localhost kernel: [ 1224.525383] [<e09b8b00>] ? write_recoverydir+0xf0/0xf0 [nfsd] 1644 Dec 29 14:25:12 localhost kernel: [ 1224.527386] [<e09b7f3b>] nfsctl_transaction_write+0x3b/0x60 [nfsd] 1645 Dec 29 14:25:12 localhost kernel: [ 1224.529302] [<e09b7f00>] ? export_features_show+0x30/0x30 [nfsd] 1646 Dec 29 14:25:12 localhost kernel: [ 1224.531366] [<c0564695>] vfs_write+0x95/0x1c0 1647 Dec 29 14:25:12 localhost kernel: [ 1224.533401] [<c0564d49>] SyS_write+0x49/0x90 1648 Dec 29 14:25:12 localhost kernel: [ 1224.535380] [<c09c730d>] sysenter_do_call+0x12/0x28 thanks, Kinglong Mee 2013/12/28 Kinglong Mee <kinglongmee@gmail.com>: > > ? 2013?12?28????3:40?Chuck Lever <chuck.lever@oracle.com> ??? > > > On Dec 27, 2013, at 1:43 PM, J.;Bruce Fields <bfields@fieldses.org> wrote: > > On Fri, Dec 27, 2013 at 11:05:05AM -0500, Chuck Lever wrote: > > Hi- > > On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: > > On 12/24/2013 01:39 AM, J. Bruce Fields wrote: > > On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: > > Hi, > > I'm trying to run NFS with protocol version 4 only (that is, with v2 > & v3 disabled) on a CentOS 6.5 install running as a KVM guest. > > The RedHat documentation (amongst others) states that rpcbind isn't > needed with v4, but if I start nfs without rpcbind I get errors. > > > I suspect the kernel code needs to be fixed to not attempt to register > with rpcbind n the v4-only case. (Or to attempt to register but ignore > any error, I'm not sure which is best.) > > And this may not be the only issue in the v4-only case. This isn't > really a priority for me right now, but I'd happily look at patches. > > > Hi all, > > I make a patch for this problem, please have a check, thanks. > > From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 > From: Kinglong Mee <kinglongmee@gmail.com> > Date: Fri, 27 Dec 2013 18:06:25 +0800 > Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind > > 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind > > > IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not > a hidden service, like the client's callback server which can only be > discovered by a forward advertisement (SETCLIENTID). > > I think I prefer ignoring the rpcb_set error for NFSv4. > > > Agreed. My only concern would be that there be no unnecessary delays or > errors logged in the v4-only case if rpcbind isn't running. > > > I believe the rpcb_set upcall now uses the AF_LOCAL transport, which should > be able to detect immediately that rpcbind is not listening. > > The OP did not report a delay or hang, thankfully. > > > I meet a problem when testing on Fedora 20 with latest kernel, > svc_register for nfsv4 not report immediately, instead of a delay and > return EIO. > > After that, rpc.nfsd also hang there, not return utils rpcbind start. > I will have a check for that. > > thanks. > Kinglong Mee > > > > --b. > > > > 2. don't start lockd when only supports nfsv4. > > Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> > Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> > --- > fs/nfsd/netns.h | 3 +++ > fs/nfsd/nfs4proc.c | 1 + > fs/nfsd/nfsctl.c | 3 +++ > fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- > 4 files changed, 23 insertions(+), 5 deletions(-) > > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h > index 849a7c3..ae2c179 100644 > --- a/fs/nfsd/netns.h > +++ b/fs/nfsd/netns.h > @@ -96,6 +96,9 @@ struct nfsd_net { > > bool nfsd_net_up; > > + bool lockd_up; > + u32 nfsd_needs_lockd; > + > /* > * Time of server startup > */ > diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c > index 419572f..1496376 100644 > --- a/fs/nfsd/nfs4proc.c > +++ b/fs/nfsd/nfs4proc.c > @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { > .vs_proc = nfsd_procedures4, > .vs_dispatch = nfsd_dispatch, > .vs_xdrsize = NFS4_SVC_XDRSIZE, > + .vs_hidden = 1, > }; > > /* > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c > index 7f55517..8c7b0f0 100644 > --- a/fs/nfsd/nfsctl.c > +++ b/fs/nfsd/nfsctl.c > @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char > *buf, size_t size) > switch(num) { > case 2: > case 3: > + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); > + break; > case 4: > nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > break; > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c > index 760c85a..2b841d8 100644 > --- a/fs/nfsd/nfssvc.c > +++ b/fs/nfsd/nfssvc.c > @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net > *net) > ret = nfsd_init_socks(net); > if (ret) > goto out_socks; > - ret = lockd_up(net); > - if (ret) > - goto out_socks; > + > + if (nn->nfsd_needs_lockd && !nn->lockd_up) { > + ret = lockd_up(net); > + if (ret) > + goto out_socks; > + nn->lockd_up = 1; > + } > + > ret = nfs4_state_start_net(net); > if (ret) > goto out_lockd; > @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net > *net) > return 0; > > out_lockd: > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > out_socks: > nfsd_shutdown_generic(); > return ret; > @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) > struct nfsd_net *nn = net_generic(net, nfsd_net_id); > > nfs4_state_shutdown_net(net); > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > nn->nfsd_net_up = false; > nfsd_shutdown_generic(); > } > -- > 1.8.4.2 > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > > > -- > Chuck Lever > chuck[dot]lever[at]oracle[dot]com > > > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > > > -- > Chuck Lever > chuck[dot]lever[at]oracle[dot]com > > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Hi all, I found the commit 561ec1603171cd9b38dcf6cac53e8710f437a48d "SUNRPC: call_connect_status should recheck bind and connect status on error" causes the loop. Without this patch, I can get error immediately as Williams reports. I will make a patch for this problem without the commit. Before that, we need fix the loop. Ps: cc Trond thanks, Kinglong Mee On Sun, Dec 29, 2013 at 4:17 PM, Kinglong Mee <kinglongmee@gmail.com> wrote: > After open the debug log, found rpc.nfsd hang in a loop in __rpc_execute. > > [ 6179.978202] RPC: 1 sync task resuming > [ 6179.981254] RPC: 1 xprt_connect_status: retrying > [ 6179.984289] RPC: 1 call_connect_status (status -11) > [ 6179.987292] RPC: 1 call_bind (status 0) > [ 6179.990273] RPC: 1 call_connect xprt da4d5000 is not connected > [ 6179.993271] RPC: 1 xprt_connect xprt da4d5000 is not connected > [ 6179.996196] RPC: 1 sleep_on(queue "xprt_pending" time 5876962) > [ 6179.999043] RPC: 1 added to queue da4d518c "xprt_pending" > [ 6180.001885] RPC: 1 setting alarm for 60000 ms > [ 6180.004725] RPC: xs_connect scheduled xprt da4d5000 > [ 6180.007549] RPC: 1 sync task going to sleep > [ 6180.049927] RPC: disconnecting xprt da4d5000 to reuse port > [ 6180.054460] RPC: AF_UNSPEC connect return code 0 > [ 6180.059560] RPC: worker connecting xprt da4d5000 via tcp to > 127.0.0.1 (port 111) > [ 6180.062384] RPC: xs_tcp_state_change client da4d5000... > [ 6180.065013] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 > [ 6180.067891] RPC: disconnected transport da4d5000 > [ 6180.070465] RPC: 1 __rpc_wake_up_task (now 5877036) > [ 6180.073014] RPC: 1 disabling timer > [ 6180.075553] RPC: 1 removed from queue da4d518c "xprt_pending" > [ 6180.078036] RPC: __rpc_wake_up_task done > [ 6180.080545] RPC: da4d5000 connect status 115 connected 0 sock state > 7 > [ 6180.085953] RPC: 1 sync task resuming > [ 6180.088376] RPC: 1 xprt_connect_status: retrying > [ 6180.090699] RPC: 1 call_connect_status (status -11) > > thanks, > Kinglong Mee > > ? 2013?12?29????2:39?Kinglong Mee <kinglongmee@gmail.com> ??? > > I get the trace when rpc.nfsd hang. > > 1608 Dec 29 14:25:12 localhost kernel: [ 1224.449293] rpc.nfsd > D c0d94300 0 1199 991 0x00000080 > > 1609 Dec 29 14:25:12 localhost kernel: [ 1224.451347] d9a9bc98 > 00000086 c046aa48 c0d94300 ddb66540 c0d79300 58625871 0000011c > > 1610 Dec 29 14:25:12 localhost kernel: [ 1224.453426] c0d79300 > dfff4300 dcd93a80 c0461738 00000000 c0d94300 00000000 00000020 > > 1611 Dec 29 14:25:12 localhost kernel: [ 1224.455701] da4d53a0 > 00000020 ddb66540 da4d53b0 d9a9bc84 c046add9 dcd93a80 00000292 > > 1612 Dec 29 14:25:12 localhost kernel: [ 1224.457853] Call Trace: > > 1613 Dec 29 14:25:12 localhost kernel: [ 1224.459919] [<c046aa48>] ? > insert_work+0x38/0x80 > > 1614 Dec 29 14:25:12 localhost kernel: [ 1224.462055] [<c0461738>] ? > mod_timer+0xe8/0x1c0 > > 1615 Dec 29 14:25:12 localhost kernel: [ 1224.464230] [<c046add9>] ? > __queue_delayed_work+0x89/0x140 > > 1616 Dec 29 14:25:12 localhost kernel: [ 1224.466304] [<e092d970>] ? > __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] > > 1617 Dec 29 14:25:12 localhost kernel: [ 1224.468561] [<c09bd543>] > schedule+0x23/0x60 > > 1618 Dec 29 14:25:12 localhost kernel: [ 1224.470671] [<e092d99d>] > rpc_wait_bit_killable+0x2d/0x80 [sunrpc] > > 1619 Dec 29 14:25:12 localhost kernel: [ 1224.472785] [<c09bdae1>] > __wait_on_bit+0x51/0x70 > > 1620 Dec 29 14:25:12 localhost kernel: [ 1224.474974] [<e092d970>] ? > __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] > > 1621 Dec 29 14:25:12 localhost kernel: [ 1224.477170] [<e092d970>] ? > __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] > > 1622 Dec 29 14:25:12 localhost kernel: [ 1224.479389] [<c09bdb5b>] > out_of_line_wait_on_bit+0x5b/0x70 > > 1623 Dec 29 14:25:12 localhost kernel: [ 1224.481739] [<c048e440>] ? > autoremove_wake_function+0x40/0x40 > > 1624 Dec 29 14:25:12 localhost kernel: [ 1224.483881] [<e092e703>] > __rpc_execute+0x1f3/0x3a0 [sunrpc] > > 1625 Dec 29 14:25:12 localhost kernel: [ 1224.486030] [<c0516283>] ? > mempool_alloc_slab+0x13/0x20 > > 1626 Dec 29 14:25:12 localhost kernel: [ 1224.488194] [<c051638e>] ? > mempool_alloc+0x3e/0x100 > > 1627 Dec 29 14:25:12 localhost kernel: [ 1224.490307] [<e0925d80>] ? > call_bind_status+0x260/0x260 [sunrpc] > > 1628 Dec 29 14:25:12 localhost kernel: [ 1224.492559] [<c048e09c>] ? > wake_up_bit+0x1c/0x20 > > 1629 Dec 29 14:25:12 localhost kernel: [ 1224.494844] [<e092f866>] > rpc_execute+0x56/0x90 [sunrpc] > > 1630 Dec 29 14:25:12 localhost kernel: [ 1224.496935] [<e0926cf9>] > rpc_run_task+0x59/0x70 [sunrpc] > > 1631 Dec 29 14:25:12 localhost kernel: [ 1224.499122] [<e0926d4c>] > rpc_call_sync+0x3c/0x90 [sunrpc] > > 1632 Dec 29 14:25:12 localhost kernel: [ 1224.501260] [<e0926de8>] > rpc_ping+0x48/0x60 [sunrpc] > > 1633 Dec 29 14:25:12 localhost kernel: [ 1224.503367] [<e092703b>] > rpc_bind_new_program+0x4b/0x70 [sunrpc] > > 1634 Dec 29 14:25:12 localhost kernel: [ 1224.505608] [<e0938333>] > rpcb_create_local+0x163/0x1f0 [sunrpc] > > 1635 Dec 29 14:25:12 localhost kernel: [ 1224.507720] [<e0932199>] ? > __svc_create+0x119/0x1f0 [sunrpc] > > 1636 Dec 29 14:25:12 localhost kernel: [ 1224.509830] [<e0932016>] > svc_rpcb_setup+0x16/0x30 [sunrpc] > > 1637 Dec 29 14:25:12 localhost kernel: [ 1224.511963] [<e0932052>] > svc_bind+0x22/0x30 [sunrpc] > > 1638 Dec 29 14:25:12 localhost kernel: [ 1224.514056] [<e09b73a4>] > nfsd_create_serv+0xc4/0x1d0 [nfsd] > > 1639 Dec 29 14:25:12 localhost kernel: [ 1224.516844] [<e09b7600>] ? > nfsd_destroy+0x70/0x70 [nfsd] > > 1640 Dec 29 14:25:12 localhost kernel: [ 1224.518870] [<e09b8d1f>] > write_ports+0x21f/0x2b0 [nfsd] > > 1641 Dec 29 14:25:12 localhost kernel: [ 1224.521359] [<c06a182c>] ? > _copy_from_user+0x2c/0x40 > > 1642 Dec 29 14:25:12 localhost kernel: [ 1224.523358] [<c05854fe>] ? > simple_transaction_get+0x8e/0xa0 > > 1643 Dec 29 14:25:12 localhost kernel: [ 1224.525383] [<e09b8b00>] ? > write_recoverydir+0xf0/0xf0 [nfsd] > > 1644 Dec 29 14:25:12 localhost kernel: [ 1224.527386] [<e09b7f3b>] > nfsctl_transaction_write+0x3b/0x60 [nfsd] > > 1645 Dec 29 14:25:12 localhost kernel: [ 1224.529302] [<e09b7f00>] ? > export_features_show+0x30/0x30 [nfsd] > > 1646 Dec 29 14:25:12 localhost kernel: [ 1224.531366] [<c0564695>] > vfs_write+0x95/0x1c0 > > 1647 Dec 29 14:25:12 localhost kernel: [ 1224.533401] [<c0564d49>] > SyS_write+0x49/0x90 > > 1648 Dec 29 14:25:12 localhost kernel: [ 1224.535380] [<c09c730d>] > sysenter_do_call+0x12/0x28 > > thanks, > Kinglong Mee > > 2013/12/28 Kinglong Mee <kinglongmee@gmail.com>: > > > ? 2013?12?28????3:40?Chuck Lever <chuck.lever@oracle.com> ??? > > > On Dec 27, 2013, at 1:43 PM, J.;Bruce Fields <bfields@fieldses.org> wrote: > > On Fri, Dec 27, 2013 at 11:05:05AM -0500, Chuck Lever wrote: > > Hi- > > On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: > > On 12/24/2013 01:39 AM, J. Bruce Fields wrote: > > On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: > > Hi, > > I'm trying to run NFS with protocol version 4 only (that is, with v2 > & v3 disabled) on a CentOS 6.5 install running as a KVM guest. > > The RedHat documentation (amongst others) states that rpcbind isn't > needed with v4, but if I start nfs without rpcbind I get errors. > > > I suspect the kernel code needs to be fixed to not attempt to register > with rpcbind n the v4-only case. (Or to attempt to register but ignore > any error, I'm not sure which is best.) > > And this may not be the only issue in the v4-only case. This isn't > really a priority for me right now, but I'd happily look at patches. > > > Hi all, > > I make a patch for this problem, please have a check, thanks. > > From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 > From: Kinglong Mee <kinglongmee@gmail.com> > Date: Fri, 27 Dec 2013 18:06:25 +0800 > Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind > > 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind > > > IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not > a hidden service, like the client's callback server which can only be > discovered by a forward advertisement (SETCLIENTID). > > I think I prefer ignoring the rpcb_set error for NFSv4. > > > Agreed. My only concern would be that there be no unnecessary delays or > errors logged in the v4-only case if rpcbind isn't running. > > > I believe the rpcb_set upcall now uses the AF_LOCAL transport, which should > be able to detect immediately that rpcbind is not listening. > > The OP did not report a delay or hang, thankfully. > > > I meet a problem when testing on Fedora 20 with latest kernel, > svc_register for nfsv4 not report immediately, instead of a delay and > return EIO. > > After that, rpc.nfsd also hang there, not return utils rpcbind start. > I will have a check for that. > > thanks. > Kinglong Mee > > > > --b. > > > > 2. don't start lockd when only supports nfsv4. > > Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> > Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> > --- > fs/nfsd/netns.h | 3 +++ > fs/nfsd/nfs4proc.c | 1 + > fs/nfsd/nfsctl.c | 3 +++ > fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- > 4 files changed, 23 insertions(+), 5 deletions(-) > > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h > index 849a7c3..ae2c179 100644 > --- a/fs/nfsd/netns.h > +++ b/fs/nfsd/netns.h > @@ -96,6 +96,9 @@ struct nfsd_net { > > bool nfsd_net_up; > > + bool lockd_up; > + u32 nfsd_needs_lockd; > + > /* > * Time of server startup > */ > diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c > index 419572f..1496376 100644 > --- a/fs/nfsd/nfs4proc.c > +++ b/fs/nfsd/nfs4proc.c > @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { > .vs_proc = nfsd_procedures4, > .vs_dispatch = nfsd_dispatch, > .vs_xdrsize = NFS4_SVC_XDRSIZE, > + .vs_hidden = 1, > }; > > /* > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c > index 7f55517..8c7b0f0 100644 > --- a/fs/nfsd/nfsctl.c > +++ b/fs/nfsd/nfsctl.c > @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char > *buf, size_t size) > switch(num) { > case 2: > case 3: > + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); > + break; > case 4: > nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); > break; > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c > index 760c85a..2b841d8 100644 > --- a/fs/nfsd/nfssvc.c > +++ b/fs/nfsd/nfssvc.c > @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net > *net) > ret = nfsd_init_socks(net); > if (ret) > goto out_socks; > - ret = lockd_up(net); > - if (ret) > - goto out_socks; > + > + if (nn->nfsd_needs_lockd && !nn->lockd_up) { > + ret = lockd_up(net); > + if (ret) > + goto out_socks; > + nn->lockd_up = 1; > + } > + > ret = nfs4_state_start_net(net); > if (ret) > goto out_lockd; > @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net > *net) > return 0; > > out_lockd: > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > out_socks: > nfsd_shutdown_generic(); > return ret; > @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) > struct nfsd_net *nn = net_generic(net, nfsd_net_id); > > nfs4_state_shutdown_net(net); > - lockd_down(net); > + if (nn->lockd_up) { > + lockd_down(net); > + nn->lockd_up = 0; > + } > nn->nfsd_net_up = false; > nfsd_shutdown_generic(); > } > -- > 1.8.4.2 > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > > > -- > Chuck Lever > chuck[dot]lever[at]oracle[dot]com > > > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > > > -- > Chuck Lever > chuck[dot]lever[at]oracle[dot]com > > > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 12/29/2013 05:11 PM, Kinglong Mee wrote: > Hi all, > > I found the commit 561ec1603171cd9b38dcf6cac53e8710f437a48d > "SUNRPC: call_connect_status should recheck bind and connect status on error" > causes the loop. Without this patch, I can get error immediately as > Williams reports. > > I will make a patch for this problem without the commit. > Before that, we need fix the loop. After reverting that commit, two new patches for this problem will be sent out. thanks, Kinglong Mee > On Sun, Dec 29, 2013 at 4:17 PM, Kinglong Mee <kinglongmee@gmail.com> wrote: >> After open the debug log, found rpc.nfsd hang in a loop in __rpc_execute. >> >> [ 6179.978202] RPC: 1 sync task resuming >> [ 6179.981254] RPC: 1 xprt_connect_status: retrying >> [ 6179.984289] RPC: 1 call_connect_status (status -11) >> [ 6179.987292] RPC: 1 call_bind (status 0) >> [ 6179.990273] RPC: 1 call_connect xprt da4d5000 is not connected >> [ 6179.993271] RPC: 1 xprt_connect xprt da4d5000 is not connected >> [ 6179.996196] RPC: 1 sleep_on(queue "xprt_pending" time 5876962) >> [ 6179.999043] RPC: 1 added to queue da4d518c "xprt_pending" >> [ 6180.001885] RPC: 1 setting alarm for 60000 ms >> [ 6180.004725] RPC: xs_connect scheduled xprt da4d5000 >> [ 6180.007549] RPC: 1 sync task going to sleep >> [ 6180.049927] RPC: disconnecting xprt da4d5000 to reuse port >> [ 6180.054460] RPC: AF_UNSPEC connect return code 0 >> [ 6180.059560] RPC: worker connecting xprt da4d5000 via tcp to >> 127.0.0.1 (port 111) >> [ 6180.062384] RPC: xs_tcp_state_change client da4d5000... >> [ 6180.065013] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 >> [ 6180.067891] RPC: disconnected transport da4d5000 >> [ 6180.070465] RPC: 1 __rpc_wake_up_task (now 5877036) >> [ 6180.073014] RPC: 1 disabling timer >> [ 6180.075553] RPC: 1 removed from queue da4d518c "xprt_pending" >> [ 6180.078036] RPC: __rpc_wake_up_task done >> [ 6180.080545] RPC: da4d5000 connect status 115 connected 0 sock state >> 7 >> [ 6180.085953] RPC: 1 sync task resuming >> [ 6180.088376] RPC: 1 xprt_connect_status: retrying >> [ 6180.090699] RPC: 1 call_connect_status (status -11) >> >> thanks, >> Kinglong Mee >> >> ? 2013?12?29????2:39?Kinglong Mee <kinglongmee@gmail.com> ??? >> >> I get the trace when rpc.nfsd hang. >> >> 1608 Dec 29 14:25:12 localhost kernel: [ 1224.449293] rpc.nfsd >> D c0d94300 0 1199 991 0x00000080 >> >> 1609 Dec 29 14:25:12 localhost kernel: [ 1224.451347] d9a9bc98 >> 00000086 c046aa48 c0d94300 ddb66540 c0d79300 58625871 0000011c >> >> 1610 Dec 29 14:25:12 localhost kernel: [ 1224.453426] c0d79300 >> dfff4300 dcd93a80 c0461738 00000000 c0d94300 00000000 00000020 >> >> 1611 Dec 29 14:25:12 localhost kernel: [ 1224.455701] da4d53a0 >> 00000020 ddb66540 da4d53b0 d9a9bc84 c046add9 dcd93a80 00000292 >> >> 1612 Dec 29 14:25:12 localhost kernel: [ 1224.457853] Call Trace: >> >> 1613 Dec 29 14:25:12 localhost kernel: [ 1224.459919] [<c046aa48>] ? >> insert_work+0x38/0x80 >> >> 1614 Dec 29 14:25:12 localhost kernel: [ 1224.462055] [<c0461738>] ? >> mod_timer+0xe8/0x1c0 >> >> 1615 Dec 29 14:25:12 localhost kernel: [ 1224.464230] [<c046add9>] ? >> __queue_delayed_work+0x89/0x140 >> >> 1616 Dec 29 14:25:12 localhost kernel: [ 1224.466304] [<e092d970>] ? >> __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] >> >> 1617 Dec 29 14:25:12 localhost kernel: [ 1224.468561] [<c09bd543>] >> schedule+0x23/0x60 >> >> 1618 Dec 29 14:25:12 localhost kernel: [ 1224.470671] [<e092d99d>] >> rpc_wait_bit_killable+0x2d/0x80 [sunrpc] >> >> 1619 Dec 29 14:25:12 localhost kernel: [ 1224.472785] [<c09bdae1>] >> __wait_on_bit+0x51/0x70 >> >> 1620 Dec 29 14:25:12 localhost kernel: [ 1224.474974] [<e092d970>] ? >> __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] >> >> 1621 Dec 29 14:25:12 localhost kernel: [ 1224.477170] [<e092d970>] ? >> __rpc_wait_for_completion_task+0x30/0x30 [sunrpc] >> >> 1622 Dec 29 14:25:12 localhost kernel: [ 1224.479389] [<c09bdb5b>] >> out_of_line_wait_on_bit+0x5b/0x70 >> >> 1623 Dec 29 14:25:12 localhost kernel: [ 1224.481739] [<c048e440>] ? >> autoremove_wake_function+0x40/0x40 >> >> 1624 Dec 29 14:25:12 localhost kernel: [ 1224.483881] [<e092e703>] >> __rpc_execute+0x1f3/0x3a0 [sunrpc] >> >> 1625 Dec 29 14:25:12 localhost kernel: [ 1224.486030] [<c0516283>] ? >> mempool_alloc_slab+0x13/0x20 >> >> 1626 Dec 29 14:25:12 localhost kernel: [ 1224.488194] [<c051638e>] ? >> mempool_alloc+0x3e/0x100 >> >> 1627 Dec 29 14:25:12 localhost kernel: [ 1224.490307] [<e0925d80>] ? >> call_bind_status+0x260/0x260 [sunrpc] >> >> 1628 Dec 29 14:25:12 localhost kernel: [ 1224.492559] [<c048e09c>] ? >> wake_up_bit+0x1c/0x20 >> >> 1629 Dec 29 14:25:12 localhost kernel: [ 1224.494844] [<e092f866>] >> rpc_execute+0x56/0x90 [sunrpc] >> >> 1630 Dec 29 14:25:12 localhost kernel: [ 1224.496935] [<e0926cf9>] >> rpc_run_task+0x59/0x70 [sunrpc] >> >> 1631 Dec 29 14:25:12 localhost kernel: [ 1224.499122] [<e0926d4c>] >> rpc_call_sync+0x3c/0x90 [sunrpc] >> >> 1632 Dec 29 14:25:12 localhost kernel: [ 1224.501260] [<e0926de8>] >> rpc_ping+0x48/0x60 [sunrpc] >> >> 1633 Dec 29 14:25:12 localhost kernel: [ 1224.503367] [<e092703b>] >> rpc_bind_new_program+0x4b/0x70 [sunrpc] >> >> 1634 Dec 29 14:25:12 localhost kernel: [ 1224.505608] [<e0938333>] >> rpcb_create_local+0x163/0x1f0 [sunrpc] >> >> 1635 Dec 29 14:25:12 localhost kernel: [ 1224.507720] [<e0932199>] ? >> __svc_create+0x119/0x1f0 [sunrpc] >> >> 1636 Dec 29 14:25:12 localhost kernel: [ 1224.509830] [<e0932016>] >> svc_rpcb_setup+0x16/0x30 [sunrpc] >> >> 1637 Dec 29 14:25:12 localhost kernel: [ 1224.511963] [<e0932052>] >> svc_bind+0x22/0x30 [sunrpc] >> >> 1638 Dec 29 14:25:12 localhost kernel: [ 1224.514056] [<e09b73a4>] >> nfsd_create_serv+0xc4/0x1d0 [nfsd] >> >> 1639 Dec 29 14:25:12 localhost kernel: [ 1224.516844] [<e09b7600>] ? >> nfsd_destroy+0x70/0x70 [nfsd] >> >> 1640 Dec 29 14:25:12 localhost kernel: [ 1224.518870] [<e09b8d1f>] >> write_ports+0x21f/0x2b0 [nfsd] >> >> 1641 Dec 29 14:25:12 localhost kernel: [ 1224.521359] [<c06a182c>] ? >> _copy_from_user+0x2c/0x40 >> >> 1642 Dec 29 14:25:12 localhost kernel: [ 1224.523358] [<c05854fe>] ? >> simple_transaction_get+0x8e/0xa0 >> >> 1643 Dec 29 14:25:12 localhost kernel: [ 1224.525383] [<e09b8b00>] ? >> write_recoverydir+0xf0/0xf0 [nfsd] >> >> 1644 Dec 29 14:25:12 localhost kernel: [ 1224.527386] [<e09b7f3b>] >> nfsctl_transaction_write+0x3b/0x60 [nfsd] >> >> 1645 Dec 29 14:25:12 localhost kernel: [ 1224.529302] [<e09b7f00>] ? >> export_features_show+0x30/0x30 [nfsd] >> >> 1646 Dec 29 14:25:12 localhost kernel: [ 1224.531366] [<c0564695>] >> vfs_write+0x95/0x1c0 >> >> 1647 Dec 29 14:25:12 localhost kernel: [ 1224.533401] [<c0564d49>] >> SyS_write+0x49/0x90 >> >> 1648 Dec 29 14:25:12 localhost kernel: [ 1224.535380] [<c09c730d>] >> sysenter_do_call+0x12/0x28 >> >> thanks, >> Kinglong Mee >> >> 2013/12/28 Kinglong Mee <kinglongmee@gmail.com>: >> >> >> ? 2013?12?28????3:40?Chuck Lever <chuck.lever@oracle.com> ??? >> >> >> On Dec 27, 2013, at 1:43 PM, J.;Bruce Fields <bfields@fieldses.org> wrote: >> >> On Fri, Dec 27, 2013 at 11:05:05AM -0500, Chuck Lever wrote: >> >> Hi- >> >> On Dec 27, 2013, at 5:17 AM, Kinglong Mee <kinglongmee@gmail.com> wrote: >> >> On 12/24/2013 01:39 AM, J. Bruce Fields wrote: >> >> On Fri, Dec 20, 2013 at 05:10:42PM +0000, Gareth Williams wrote: >> >> Hi, >> >> I'm trying to run NFS with protocol version 4 only (that is, with v2 >> & v3 disabled) on a CentOS 6.5 install running as a KVM guest. >> >> The RedHat documentation (amongst others) states that rpcbind isn't >> needed with v4, but if I start nfs without rpcbind I get errors. >> >> >> I suspect the kernel code needs to be fixed to not attempt to register >> with rpcbind n the v4-only case. (Or to attempt to register but ignore >> any error, I'm not sure which is best.) >> >> And this may not be the only issue in the v4-only case. This isn't >> really a priority for me right now, but I'd happily look at patches. >> >> >> Hi all, >> >> I make a patch for this problem, please have a check, thanks. >> >> From 64c1f96348213f39b9411ab25699a292edbef4ef Mon Sep 17 00:00:00 2001 >> From: Kinglong Mee <kinglongmee@gmail.com> >> Date: Fri, 27 Dec 2013 18:06:25 +0800 >> Subject: [PATCH] NFSD: supports nfsv4 service without rpcbind >> >> 1. set vs_hidden in nfsd_version4 to avoid register nfsv4 to rpcbind >> >> >> IMO we do want the NFS port registered if rpcbind is running. NFSv4 is not >> a hidden service, like the client's callback server which can only be >> discovered by a forward advertisement (SETCLIENTID). >> >> I think I prefer ignoring the rpcb_set error for NFSv4. >> >> >> Agreed. My only concern would be that there be no unnecessary delays or >> errors logged in the v4-only case if rpcbind isn't running. >> >> >> I believe the rpcb_set upcall now uses the AF_LOCAL transport, which should >> be able to detect immediately that rpcbind is not listening. >> >> The OP did not report a delay or hang, thankfully. >> >> >> I meet a problem when testing on Fedora 20 with latest kernel, >> svc_register for nfsv4 not report immediately, instead of a delay and >> return EIO. >> >> After that, rpc.nfsd also hang there, not return utils rpcbind start. >> I will have a check for that. >> >> thanks. >> Kinglong Mee >> >> >> >> --b. >> >> >> >> 2. don't start lockd when only supports nfsv4. >> >> Reported-by: Gareth Williams <gareth@garethwilliams.me.uk> >> Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> >> --- >> fs/nfsd/netns.h | 3 +++ >> fs/nfsd/nfs4proc.c | 1 + >> fs/nfsd/nfsctl.c | 3 +++ >> fs/nfsd/nfssvc.c | 21 ++++++++++++++++----- >> 4 files changed, 23 insertions(+), 5 deletions(-) >> >> diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h >> index 849a7c3..ae2c179 100644 >> --- a/fs/nfsd/netns.h >> +++ b/fs/nfsd/netns.h >> @@ -96,6 +96,9 @@ struct nfsd_net { >> >> bool nfsd_net_up; >> >> + bool lockd_up; >> + u32 nfsd_needs_lockd; >> + >> /* >> * Time of server startup >> */ >> diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c >> index 419572f..1496376 100644 >> --- a/fs/nfsd/nfs4proc.c >> +++ b/fs/nfsd/nfs4proc.c >> @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { >> .vs_proc = nfsd_procedures4, >> .vs_dispatch = nfsd_dispatch, >> .vs_xdrsize = NFS4_SVC_XDRSIZE, >> + .vs_hidden = 1, >> }; >> >> /* >> diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c >> index 7f55517..8c7b0f0 100644 >> --- a/fs/nfsd/nfsctl.c >> +++ b/fs/nfsd/nfsctl.c >> @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char >> *buf, size_t size) >> switch(num) { >> case 2: >> case 3: >> + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); >> + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); >> + break; >> case 4: >> nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); >> break; >> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c >> index 760c85a..2b841d8 100644 >> --- a/fs/nfsd/nfssvc.c >> +++ b/fs/nfsd/nfssvc.c >> @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net >> *net) >> ret = nfsd_init_socks(net); >> if (ret) >> goto out_socks; >> - ret = lockd_up(net); >> - if (ret) >> - goto out_socks; >> + >> + if (nn->nfsd_needs_lockd && !nn->lockd_up) { >> + ret = lockd_up(net); >> + if (ret) >> + goto out_socks; >> + nn->lockd_up = 1; >> + } >> + >> ret = nfs4_state_start_net(net); >> if (ret) >> goto out_lockd; >> @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net >> *net) >> return 0; >> >> out_lockd: >> - lockd_down(net); >> + if (nn->lockd_up) { >> + lockd_down(net); >> + nn->lockd_up = 0; >> + } >> out_socks: >> nfsd_shutdown_generic(); >> return ret; >> @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) >> struct nfsd_net *nn = net_generic(net, nfsd_net_id); >> >> nfs4_state_shutdown_net(net); >> - lockd_down(net); >> + if (nn->lockd_up) { >> + lockd_down(net); >> + nn->lockd_up = 0; >> + } >> nn->nfsd_net_up = false; >> nfsd_shutdown_generic(); >> } >> -- >> 1.8.4.2 >> >> >> -- >> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in >> the body of a message to majordomo@vger.kernel.org >> More majordomo info at http://vger.kernel.org/majordomo-info.html >> >> >> -- >> Chuck Lever >> chuck[dot]lever[at]oracle[dot]com >> >> >> >> >> -- >> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in >> the body of a message to majordomo@vger.kernel.org >> More majordomo info at http://vger.kernel.org/majordomo-info.html >> >> >> -- >> Chuck Lever >> chuck[dot]lever[at]oracle[dot]com >> >> >> > -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 849a7c3..ae2c179 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -96,6 +96,9 @@ struct nfsd_net { bool nfsd_net_up; + bool lockd_up; + u32 nfsd_needs_lockd; + /* * Time of server startup */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 419572f..1496376 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1881,6 +1881,7 @@ struct svc_version nfsd_version4 = { .vs_proc = nfsd_procedures4, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, + .vs_hidden = 1, }; /* diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7f55517..8c7b0f0 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -575,6 +575,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) switch(num) { case 2: case 3: + nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); + nn->nfsd_needs_lockd = nfsd_vers(num, NFSD_TEST); + break; case 4: nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET); break; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 760c85a..2b841d8 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -255,9 +255,14 @@ static int nfsd_startup_net(int nrservs, struct net *net) ret = nfsd_init_socks(net); if (ret) goto out_socks; - ret = lockd_up(net); - if (ret) - goto out_socks; + + if (nn->nfsd_needs_lockd && !nn->lockd_up) { + ret = lockd_up(net); + if (ret) + goto out_socks; + nn->lockd_up = 1; + } + ret = nfs4_state_start_net(net); if (ret) goto out_lockd; @@ -266,7 +271,10 @@ static int nfsd_startup_net(int nrservs, struct net *net) return 0; out_lockd: - lockd_down(net); + if (nn->lockd_up) { + lockd_down(net); + nn->lockd_up = 0; + } out_socks: nfsd_shutdown_generic(); return ret; @@ -277,7 +285,10 @@ static void nfsd_shutdown_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); nfs4_state_shutdown_net(net); - lockd_down(net); + if (nn->lockd_up) { + lockd_down(net); + nn->lockd_up = 0; + } nn->nfsd_net_up = false; nfsd_shutdown_generic(); }