sm-notify's early ending of the grace period when it has no hosts to
notify can cause problems in some high availability configurations,
which may be running one sm-notify per floating IP address in the
cluster. This commit makes that behavior configurable via the
nfs.conf (I don't think having a corresponding command line option
would be particularly useful, hence none was added).
Signed-off-by: Scott Mayhew <[email protected]>
---
nfs.conf | 1 +
utils/statd/sm-notify.c | 6 +++++-
utils/statd/sm-notify.man | 18 ++++++++++++++++++
3 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/nfs.conf b/nfs.conf
index 81ece06..690645c 100644
--- a/nfs.conf
+++ b/nfs.conf
@@ -65,6 +65,7 @@
# retry-time=900
# outgoing-port=
# outgoing-addr=
+# lift-grace=y
#
#[svcgssd]
# principal=
diff --git a/utils/statd/sm-notify.c b/utils/statd/sm-notify.c
index 623213e..0c6766f 100644
--- a/utils/statd/sm-notify.c
+++ b/utils/statd/sm-notify.c
@@ -45,6 +45,8 @@
#define NLM_END_GRACE_FILE "/proc/fs/lockd/nlm_end_grace"
+int lift_grace = 1;
+
struct nsm_host {
struct nsm_host * next;
char * name;
@@ -494,6 +496,7 @@ main(int argc, char **argv)
opt_max_retry = conf_get_num("sm-notify", "retry-time", opt_max_retry / 60) * 60;
opt_srcport = conf_get_str("sm-notify", "outgoing-port");
opt_srcaddr = conf_get_str("sm-notify", "outgoing-addr");
+ lift_grace = conf_get_bool("sm-notify", "lift-grace", lift_grace);
s = conf_get_str("statd", "state-directory-path");
if (s && !nsm_setup_pathnames(argv[0], s))
exit(1);
@@ -570,7 +573,8 @@ usage: fprintf(stderr,
(void)nsm_retire_monitored_hosts();
if (nsm_load_notify_list(smn_get_host) == 0) {
xlog(D_GENERAL, "No hosts to notify; exiting");
- nsm_lift_grace_period();
+ if (lift_grace)
+ nsm_lift_grace_period();
return 0;
}
diff --git a/utils/statd/sm-notify.man b/utils/statd/sm-notify.man
index bb7f6e0..cfe1e4b 100644
--- a/utils/statd/sm-notify.man
+++ b/utils/statd/sm-notify.man
@@ -241,6 +241,24 @@ These have the same effect as the command line options
.B v
respectively.
+An additional value recognized in the
+.B [sm-notify]
+section is
+.BR lift-grace .
+By default,
+.B sm-notify
+will lift lockd's grace period early if it has no hosts to notify.
+Some high availability configurations will run one
+.B sm-notify
+per floating IP address. In these configurations, lifting the
+grace period early may prevent clients from reclaiming locks.
+.RB "Setting " lift-grace " to " n
+will prevent
+.B sm-notify
+from ending the grace period early.
+.B lift-grace
+has no corresponding command line option.
+
The value recognized in the
.B [statd]
section is
--
2.7.4
On Fri, Mar 10, 2017 at 04:39:19PM -0500, Scott Mayhew wrote:
> sm-notify's early ending of the grace period when it has no hosts to
> notify can cause problems in some high availability configurations,
> which may be running one sm-notify per floating IP address in the
> cluster.
So, there may be no hosts associated with this floating IP, but there
may be with another?
> This commit makes that behavior configurable via the
> nfs.conf (I don't think having a corresponding command line option
> would be particularly useful, hence none was added).
And, I see that you're defaulting it to on to match existing behavior.
Makes sense to me, ACK.--b.
>
> Signed-off-by: Scott Mayhew <[email protected]>
> ---
> nfs.conf | 1 +
> utils/statd/sm-notify.c | 6 +++++-
> utils/statd/sm-notify.man | 18 ++++++++++++++++++
> 3 files changed, 24 insertions(+), 1 deletion(-)
>
> diff --git a/nfs.conf b/nfs.conf
> index 81ece06..690645c 100644
> --- a/nfs.conf
> +++ b/nfs.conf
> @@ -65,6 +65,7 @@
> # retry-time=900
> # outgoing-port=
> # outgoing-addr=
> +# lift-grace=y
> #
> #[svcgssd]
> # principal=
> diff --git a/utils/statd/sm-notify.c b/utils/statd/sm-notify.c
> index 623213e..0c6766f 100644
> --- a/utils/statd/sm-notify.c
> +++ b/utils/statd/sm-notify.c
> @@ -45,6 +45,8 @@
>
> #define NLM_END_GRACE_FILE "/proc/fs/lockd/nlm_end_grace"
>
> +int lift_grace = 1;
> +
> struct nsm_host {
> struct nsm_host * next;
> char * name;
> @@ -494,6 +496,7 @@ main(int argc, char **argv)
> opt_max_retry = conf_get_num("sm-notify", "retry-time", opt_max_retry / 60) * 60;
> opt_srcport = conf_get_str("sm-notify", "outgoing-port");
> opt_srcaddr = conf_get_str("sm-notify", "outgoing-addr");
> + lift_grace = conf_get_bool("sm-notify", "lift-grace", lift_grace);
> s = conf_get_str("statd", "state-directory-path");
> if (s && !nsm_setup_pathnames(argv[0], s))
> exit(1);
> @@ -570,7 +573,8 @@ usage: fprintf(stderr,
> (void)nsm_retire_monitored_hosts();
> if (nsm_load_notify_list(smn_get_host) == 0) {
> xlog(D_GENERAL, "No hosts to notify; exiting");
> - nsm_lift_grace_period();
> + if (lift_grace)
> + nsm_lift_grace_period();
> return 0;
> }
>
> diff --git a/utils/statd/sm-notify.man b/utils/statd/sm-notify.man
> index bb7f6e0..cfe1e4b 100644
> --- a/utils/statd/sm-notify.man
> +++ b/utils/statd/sm-notify.man
> @@ -241,6 +241,24 @@ These have the same effect as the command line options
> .B v
> respectively.
>
> +An additional value recognized in the
> +.B [sm-notify]
> +section is
> +.BR lift-grace .
> +By default,
> +.B sm-notify
> +will lift lockd's grace period early if it has no hosts to notify.
> +Some high availability configurations will run one
> +.B sm-notify
> +per floating IP address. In these configurations, lifting the
> +grace period early may prevent clients from reclaiming locks.
> +.RB "Setting " lift-grace " to " n
> +will prevent
> +.B sm-notify
> +from ending the grace period early.
> +.B lift-grace
> +has no corresponding command line option.
> +
> The value recognized in the
> .B [statd]
> section is
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, 13 Mar 2017, J. Bruce Fields wrote:
> On Fri, Mar 10, 2017 at 04:39:19PM -0500, Scott Mayhew wrote:
> > sm-notify's early ending of the grace period when it has no hosts to
> > notify can cause problems in some high availability configurations,
> > which may be running one sm-notify per floating IP address in the
> > cluster.
>
> So, there may be no hosts associated with this floating IP, but there
> may be with another?
Exactly. What was happening in my testing was that clients would
receive and respond to a NOTIFY, and would immediately send a LOCK with
reclaim=yes but would get NFSERR_NO_GRACE in return.
BTW I had a cluster with this change running at Connectathon.
-Scott
>
> > This commit makes that behavior configurable via the
> > nfs.conf (I don't think having a corresponding command line option
> > would be particularly useful, hence none was added).
>
> And, I see that you're defaulting it to on to match existing behavior.
>
> Makes sense to me, ACK.--b.
>
> >
> > Signed-off-by: Scott Mayhew <[email protected]>
> > ---
> > nfs.conf | 1 +
> > utils/statd/sm-notify.c | 6 +++++-
> > utils/statd/sm-notify.man | 18 ++++++++++++++++++
> > 3 files changed, 24 insertions(+), 1 deletion(-)
> >
> > diff --git a/nfs.conf b/nfs.conf
> > index 81ece06..690645c 100644
> > --- a/nfs.conf
> > +++ b/nfs.conf
> > @@ -65,6 +65,7 @@
> > # retry-time=900
> > # outgoing-port=
> > # outgoing-addr=
> > +# lift-grace=y
> > #
> > #[svcgssd]
> > # principal=
> > diff --git a/utils/statd/sm-notify.c b/utils/statd/sm-notify.c
> > index 623213e..0c6766f 100644
> > --- a/utils/statd/sm-notify.c
> > +++ b/utils/statd/sm-notify.c
> > @@ -45,6 +45,8 @@
> >
> > #define NLM_END_GRACE_FILE "/proc/fs/lockd/nlm_end_grace"
> >
> > +int lift_grace = 1;
> > +
> > struct nsm_host {
> > struct nsm_host * next;
> > char * name;
> > @@ -494,6 +496,7 @@ main(int argc, char **argv)
> > opt_max_retry = conf_get_num("sm-notify", "retry-time", opt_max_retry / 60) * 60;
> > opt_srcport = conf_get_str("sm-notify", "outgoing-port");
> > opt_srcaddr = conf_get_str("sm-notify", "outgoing-addr");
> > + lift_grace = conf_get_bool("sm-notify", "lift-grace", lift_grace);
> > s = conf_get_str("statd", "state-directory-path");
> > if (s && !nsm_setup_pathnames(argv[0], s))
> > exit(1);
> > @@ -570,7 +573,8 @@ usage: fprintf(stderr,
> > (void)nsm_retire_monitored_hosts();
> > if (nsm_load_notify_list(smn_get_host) == 0) {
> > xlog(D_GENERAL, "No hosts to notify; exiting");
> > - nsm_lift_grace_period();
> > + if (lift_grace)
> > + nsm_lift_grace_period();
> > return 0;
> > }
> >
> > diff --git a/utils/statd/sm-notify.man b/utils/statd/sm-notify.man
> > index bb7f6e0..cfe1e4b 100644
> > --- a/utils/statd/sm-notify.man
> > +++ b/utils/statd/sm-notify.man
> > @@ -241,6 +241,24 @@ These have the same effect as the command line options
> > .B v
> > respectively.
> >
> > +An additional value recognized in the
> > +.B [sm-notify]
> > +section is
> > +.BR lift-grace .
> > +By default,
> > +.B sm-notify
> > +will lift lockd's grace period early if it has no hosts to notify.
> > +Some high availability configurations will run one
> > +.B sm-notify
> > +per floating IP address. In these configurations, lifting the
> > +grace period early may prevent clients from reclaiming locks.
> > +.RB "Setting " lift-grace " to " n
> > +will prevent
> > +.B sm-notify
> > +from ending the grace period early.
> > +.B lift-grace
> > +has no corresponding command line option.
> > +
> > The value recognized in the
> > .B [statd]
> > section is
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> > the body of a message to [email protected]
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Mar 13, 2017 at 05:10:26PM -0400, Scott Mayhew wrote:
> On Mon, 13 Mar 2017, J. Bruce Fields wrote:
>
> > On Fri, Mar 10, 2017 at 04:39:19PM -0500, Scott Mayhew wrote:
> > > sm-notify's early ending of the grace period when it has no hosts to
> > > notify can cause problems in some high availability configurations,
> > > which may be running one sm-notify per floating IP address in the
> > > cluster.
> >
> > So, there may be no hosts associated with this floating IP, but there
> > may be with another?
>
> Exactly. What was happening in my testing was that clients would
> receive and respond to a NOTIFY, and would immediately send a LOCK with
> reclaim=yes but would get NFSERR_NO_GRACE in return.
>
> BTW I had a cluster with this change running at Connectathon.
Great, thanks.--b.
>
> -Scott
> >
> > > This commit makes that behavior configurable via the
> > > nfs.conf (I don't think having a corresponding command line option
> > > would be particularly useful, hence none was added).
> >
> > And, I see that you're defaulting it to on to match existing behavior.
> >
> > Makes sense to me, ACK.--b.
> >
> > >
> > > Signed-off-by: Scott Mayhew <[email protected]>
> > > ---
> > > nfs.conf | 1 +
> > > utils/statd/sm-notify.c | 6 +++++-
> > > utils/statd/sm-notify.man | 18 ++++++++++++++++++
> > > 3 files changed, 24 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/nfs.conf b/nfs.conf
> > > index 81ece06..690645c 100644
> > > --- a/nfs.conf
> > > +++ b/nfs.conf
> > > @@ -65,6 +65,7 @@
> > > # retry-time=900
> > > # outgoing-port=
> > > # outgoing-addr=
> > > +# lift-grace=y
> > > #
> > > #[svcgssd]
> > > # principal=
> > > diff --git a/utils/statd/sm-notify.c b/utils/statd/sm-notify.c
> > > index 623213e..0c6766f 100644
> > > --- a/utils/statd/sm-notify.c
> > > +++ b/utils/statd/sm-notify.c
> > > @@ -45,6 +45,8 @@
> > >
> > > #define NLM_END_GRACE_FILE "/proc/fs/lockd/nlm_end_grace"
> > >
> > > +int lift_grace = 1;
> > > +
> > > struct nsm_host {
> > > struct nsm_host * next;
> > > char * name;
> > > @@ -494,6 +496,7 @@ main(int argc, char **argv)
> > > opt_max_retry = conf_get_num("sm-notify", "retry-time", opt_max_retry / 60) * 60;
> > > opt_srcport = conf_get_str("sm-notify", "outgoing-port");
> > > opt_srcaddr = conf_get_str("sm-notify", "outgoing-addr");
> > > + lift_grace = conf_get_bool("sm-notify", "lift-grace", lift_grace);
> > > s = conf_get_str("statd", "state-directory-path");
> > > if (s && !nsm_setup_pathnames(argv[0], s))
> > > exit(1);
> > > @@ -570,7 +573,8 @@ usage: fprintf(stderr,
> > > (void)nsm_retire_monitored_hosts();
> > > if (nsm_load_notify_list(smn_get_host) == 0) {
> > > xlog(D_GENERAL, "No hosts to notify; exiting");
> > > - nsm_lift_grace_period();
> > > + if (lift_grace)
> > > + nsm_lift_grace_period();
> > > return 0;
> > > }
> > >
> > > diff --git a/utils/statd/sm-notify.man b/utils/statd/sm-notify.man
> > > index bb7f6e0..cfe1e4b 100644
> > > --- a/utils/statd/sm-notify.man
> > > +++ b/utils/statd/sm-notify.man
> > > @@ -241,6 +241,24 @@ These have the same effect as the command line options
> > > .B v
> > > respectively.
> > >
> > > +An additional value recognized in the
> > > +.B [sm-notify]
> > > +section is
> > > +.BR lift-grace .
> > > +By default,
> > > +.B sm-notify
> > > +will lift lockd's grace period early if it has no hosts to notify.
> > > +Some high availability configurations will run one
> > > +.B sm-notify
> > > +per floating IP address. In these configurations, lifting the
> > > +grace period early may prevent clients from reclaiming locks.
> > > +.RB "Setting " lift-grace " to " n
> > > +will prevent
> > > +.B sm-notify
> > > +from ending the grace period early.
> > > +.B lift-grace
> > > +has no corresponding command line option.
> > > +
> > > The value recognized in the
> > > .B [statd]
> > > section is
> > > --
> > > 2.7.4
> > >
> > > --
> > > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> > > the body of a message to [email protected]
> > > More majordomo info at http://vger.kernel.org/majordomo-info.html
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
On 03/10/2017 04:39 PM, Scott Mayhew wrote:
> sm-notify's early ending of the grace period when it has no hosts to
> notify can cause problems in some high availability configurations,
> which may be running one sm-notify per floating IP address in the
> cluster. This commit makes that behavior configurable via the
> nfs.conf (I don't think having a corresponding command line option
> would be particularly useful, hence none was added).
>
> Signed-off-by: Scott Mayhew <[email protected]>
Committed...
steved.
> ---
> nfs.conf | 1 +
> utils/statd/sm-notify.c | 6 +++++-
> utils/statd/sm-notify.man | 18 ++++++++++++++++++
> 3 files changed, 24 insertions(+), 1 deletion(-)
>
> diff --git a/nfs.conf b/nfs.conf
> index 81ece06..690645c 100644
> --- a/nfs.conf
> +++ b/nfs.conf
> @@ -65,6 +65,7 @@
> # retry-time=900
> # outgoing-port=
> # outgoing-addr=
> +# lift-grace=y
> #
> #[svcgssd]
> # principal=
> diff --git a/utils/statd/sm-notify.c b/utils/statd/sm-notify.c
> index 623213e..0c6766f 100644
> --- a/utils/statd/sm-notify.c
> +++ b/utils/statd/sm-notify.c
> @@ -45,6 +45,8 @@
>
> #define NLM_END_GRACE_FILE "/proc/fs/lockd/nlm_end_grace"
>
> +int lift_grace = 1;
> +
> struct nsm_host {
> struct nsm_host * next;
> char * name;
> @@ -494,6 +496,7 @@ main(int argc, char **argv)
> opt_max_retry = conf_get_num("sm-notify", "retry-time", opt_max_retry / 60) * 60;
> opt_srcport = conf_get_str("sm-notify", "outgoing-port");
> opt_srcaddr = conf_get_str("sm-notify", "outgoing-addr");
> + lift_grace = conf_get_bool("sm-notify", "lift-grace", lift_grace);
> s = conf_get_str("statd", "state-directory-path");
> if (s && !nsm_setup_pathnames(argv[0], s))
> exit(1);
> @@ -570,7 +573,8 @@ usage: fprintf(stderr,
> (void)nsm_retire_monitored_hosts();
> if (nsm_load_notify_list(smn_get_host) == 0) {
> xlog(D_GENERAL, "No hosts to notify; exiting");
> - nsm_lift_grace_period();
> + if (lift_grace)
> + nsm_lift_grace_period();
> return 0;
> }
>
> diff --git a/utils/statd/sm-notify.man b/utils/statd/sm-notify.man
> index bb7f6e0..cfe1e4b 100644
> --- a/utils/statd/sm-notify.man
> +++ b/utils/statd/sm-notify.man
> @@ -241,6 +241,24 @@ These have the same effect as the command line options
> .B v
> respectively.
>
> +An additional value recognized in the
> +.B [sm-notify]
> +section is
> +.BR lift-grace .
> +By default,
> +.B sm-notify
> +will lift lockd's grace period early if it has no hosts to notify.
> +Some high availability configurations will run one
> +.B sm-notify
> +per floating IP address. In these configurations, lifting the
> +grace period early may prevent clients from reclaiming locks.
> +.RB "Setting " lift-grace " to " n
> +will prevent
> +.B sm-notify
> +from ending the grace period early.
> +.B lift-grace
> +has no corresponding command line option.
> +
> The value recognized in the
> .B [statd]
> section is
>