Current behaviour: every time a v3 operation is re-sent to the server
we update (double) the timeout. There is no distinction between whether
or not the previous timer had expired before the re-sent happened.
Here's the scenario:
1. Client sends a v3 operation
2. Server RST-s the connection (prior to the timeout) (eg., connection
is immediately reset)
3. Client re-sends a v3 operation but the timeout is now 120sec.
As a result, an application sees 2mins pause before a retry in case
server again does not reply.
Instead, this patch proposes to keep track off when the minor timeout
should happen and if it didn't, then don't update the new timeout.
Signed-off-by: Olga Kornievskaia <[email protected]>
---
include/linux/sunrpc/xprt.h | 1 +
net/sunrpc/xprt.c | 11 +++++++++++
2 files changed, 12 insertions(+)
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index e64bd82..a603d48 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -101,6 +101,7 @@ struct rpc_rqst {
* used in the softirq.
*/
unsigned long rq_majortimeo; /* major timeout alarm */
+ unsigned long rq_minortimeo; /* minor timeout alarm */
unsigned long rq_timeout; /* Current timeout value */
ktime_t rq_rtt; /* round-trip time */
unsigned int rq_retries; /* # of retries */
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d5cc5db..c0ce232 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req)
req->rq_majortimeo += xprt_calc_majortimeo(req);
}
+static void xprt_reset_minortimeo(struct rpc_rqst *req)
+{
+ req->rq_minortimeo = jiffies + req->rq_timeout;
+}
+
static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
{
unsigned long time_init;
@@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
req->rq_timeout = task->tk_client->cl_timeout->to_initval;
req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+ req->rq_minortimeo = time_init + req->rq_timeout;
}
/**
@@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
int status = 0;
+ if (time_before(jiffies, req->rq_minortimeo)) {
+ xprt_reset_minortimeo(req);
+ return status;
+ }
if (time_before(jiffies, req->rq_majortimeo)) {
if (to->to_exponential)
req->rq_timeout <<= 1;
@@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
req->rq_timeout += to->to_increment;
if (to->to_maxval && req->rq_timeout >= to->to_maxval)
req->rq_timeout = to->to_maxval;
+ xprt_reset_minortimeo(req);
req->rq_retries++;
} else {
req->rq_timeout = to->to_initval;
--
1.8.3.1
Hi Olga
On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> Current behaviour: every time a v3 operation is re-sent to the server
> we update (double) the timeout. There is no distinction between
> whether
> or not the previous timer had expired before the re-sent happened.
>
> Here's the scenario:
> 1. Client sends a v3 operation
> 2. Server RST-s the connection (prior to the timeout) (eg.,
> connection
> is immediately reset)
> 3. Client re-sends a v3 operation but the timeout is now 120sec.
>
> As a result, an application sees 2mins pause before a retry in case
> server again does not reply.
>
> Instead, this patch proposes to keep track off when the minor timeout
> should happen and if it didn't, then don't update the new timeout.
>
> Signed-off-by: Olga Kornievskaia <[email protected]>
> ---
> include/linux/sunrpc/xprt.h | 1 +
> net/sunrpc/xprt.c | 11 +++++++++++
> 2 files changed, 12 insertions(+)
>
> diff --git a/include/linux/sunrpc/xprt.h
> b/include/linux/sunrpc/xprt.h
> index e64bd82..a603d48 100644
> --- a/include/linux/sunrpc/xprt.h
> +++ b/include/linux/sunrpc/xprt.h
> @@ -101,6 +101,7 @@ struct rpc_rqst {
> * used in the
> softirq.
> */
> unsigned long rq_majortimeo; /* major timeout
> alarm */
> + unsigned long rq_minortimeo; /* minor timeout
> alarm */
> unsigned long rq_timeout; /* Current timeout
> value */
> ktime_t rq_rtt; /* round-trip time */
> unsigned int rq_retries; /* # of retries */
> diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> index d5cc5db..c0ce232 100644
> --- a/net/sunrpc/xprt.c
> +++ b/net/sunrpc/xprt.c
> @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> rpc_rqst *req)
> req->rq_majortimeo += xprt_calc_majortimeo(req);
> }
>
> +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> +{
> + req->rq_minortimeo = jiffies + req->rq_timeout;
> +}
> +
> static void xprt_init_majortimeo(struct rpc_task *task, struct
> rpc_rqst *req)
> {
> unsigned long time_init;
> @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task
> *task, struct rpc_rqst *req)
> time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
> req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> + req->rq_minortimeo = time_init + req->rq_timeout;
> }
>
> /**
> @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> const struct rpc_timeout *to = req->rq_task->tk_client-
> >cl_timeout;
> int status = 0;
>
> + if (time_before(jiffies, req->rq_minortimeo)) {
> + xprt_reset_minortimeo(req);
> + return status;
Shouldn't this case be just returning without updating the timeout?
After all, this is the case where nothing has expired yet.
> + }
> if (time_before(jiffies, req->rq_majortimeo)) {
> if (to->to_exponential)
> req->rq_timeout <<= 1;
> @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> req->rq_timeout += to->to_increment;
> if (to->to_maxval && req->rq_timeout >= to->to_maxval)
> req->rq_timeout = to->to_maxval;
> + xprt_reset_minortimeo(req);
...and then perhaps this can just be moved out of the time_before()
condition, since it looks to me as if we also want to reset req-
>rq_minortimeo when a major timeout occurs.
> req->rq_retries++;
> } else {
> req->rq_timeout = to->to_initval;
--
Trond Myklebust
Linux NFS client maintainer, Hammerspace
[email protected]
On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <[email protected]> wrote:
>
> Hi Olga
>
> On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > Current behaviour: every time a v3 operation is re-sent to the server
> > we update (double) the timeout. There is no distinction between
> > whether
> > or not the previous timer had expired before the re-sent happened.
> >
> > Here's the scenario:
> > 1. Client sends a v3 operation
> > 2. Server RST-s the connection (prior to the timeout) (eg.,
> > connection
> > is immediately reset)
> > 3. Client re-sends a v3 operation but the timeout is now 120sec.
> >
> > As a result, an application sees 2mins pause before a retry in case
> > server again does not reply.
> >
> > Instead, this patch proposes to keep track off when the minor timeout
> > should happen and if it didn't, then don't update the new timeout.
> >
> > Signed-off-by: Olga Kornievskaia <[email protected]>
> > ---
> > include/linux/sunrpc/xprt.h | 1 +
> > net/sunrpc/xprt.c | 11 +++++++++++
> > 2 files changed, 12 insertions(+)
> >
> > diff --git a/include/linux/sunrpc/xprt.h
> > b/include/linux/sunrpc/xprt.h
> > index e64bd82..a603d48 100644
> > --- a/include/linux/sunrpc/xprt.h
> > +++ b/include/linux/sunrpc/xprt.h
> > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > * used in the
> > softirq.
> > */
> > unsigned long rq_majortimeo; /* major timeout
> > alarm */
> > + unsigned long rq_minortimeo; /* minor timeout
> > alarm */
> > unsigned long rq_timeout; /* Current timeout
> > value */
> > ktime_t rq_rtt; /* round-trip time */
> > unsigned int rq_retries; /* # of retries */
> > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > index d5cc5db..c0ce232 100644
> > --- a/net/sunrpc/xprt.c
> > +++ b/net/sunrpc/xprt.c
> > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > rpc_rqst *req)
> > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > }
> >
> > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > +{
> > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > +}
> > +
> > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > rpc_rqst *req)
> > {
> > unsigned long time_init;
> > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task
> > *task, struct rpc_rqst *req)
> > time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
> > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > + req->rq_minortimeo = time_init + req->rq_timeout;
> > }
> >
> > /**
> > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > const struct rpc_timeout *to = req->rq_task->tk_client-
> > >cl_timeout;
> > int status = 0;
> >
> > + if (time_before(jiffies, req->rq_minortimeo)) {
> > + xprt_reset_minortimeo(req);
> > + return status;
>
> Shouldn't this case be just returning without updating the timeout?
> After all, this is the case where nothing has expired yet.
I think we perhaps should readjust the minor timeout every here but I
can't figure out what the desired behaviour should be. When should we
consider it's appropriate to double the timer. Consider the following:
time1: v3 op sent
time1+50s: server RSTs
We check that it's not yet the minor timeout (time1+60s)
time1+50s: v3 op re-sent (say we don't reset the minor timeout to be
current time+60s)
time1+60s: server RSTs
Client will resend the op but now it's past the initial minor timeout
so the timeout will be doubled. Is that what we really want? Maybe it
is.
Say now the server RSTs the connection again (shortly after or in less
than 60s), since we are not updating the minor timeout value, then the
client will again modify the timeout before resending. Is that Ok?
That's why my reasoning was that at every re-evaluation of the timeout
value, we have the minor timeout set for current time+60s and we get
an RST within it then we don't modify the timeout value.
>
> > + }
> > if (time_before(jiffies, req->rq_majortimeo)) {
> > if (to->to_exponential)
> > req->rq_timeout <<= 1;
> > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > req->rq_timeout += to->to_increment;
> > if (to->to_maxval && req->rq_timeout >= to->to_maxval)
> > req->rq_timeout = to->to_maxval;
> > + xprt_reset_minortimeo(req);
>
> ...and then perhaps this can just be moved out of the time_before()
> condition, since it looks to me as if we also want to reset req-
> >rq_minortimeo when a major timeout occurs.
>
> > req->rq_retries++;
> > } else {
> > req->rq_timeout = to->to_initval;
>
>
> --
> Trond Myklebust
> Linux NFS client maintainer, Hammerspace
> [email protected]
>
>
On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> [email protected]> wrote:
> > Hi Olga
> >
> > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > Current behaviour: every time a v3 operation is re-sent to the
> > > server
> > > we update (double) the timeout. There is no distinction between
> > > whether
> > > or not the previous timer had expired before the re-sent
> > > happened.
> > >
> > > Here's the scenario:
> > > 1. Client sends a v3 operation
> > > 2. Server RST-s the connection (prior to the timeout) (eg.,
> > > connection
> > > is immediately reset)
> > > 3. Client re-sends a v3 operation but the timeout is now 120sec.
> > >
> > > As a result, an application sees 2mins pause before a retry in
> > > case
> > > server again does not reply.
> > >
> > > Instead, this patch proposes to keep track off when the minor
> > > timeout
> > > should happen and if it didn't, then don't update the new
> > > timeout.
> > >
> > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > ---
> > > include/linux/sunrpc/xprt.h | 1 +
> > > net/sunrpc/xprt.c | 11 +++++++++++
> > > 2 files changed, 12 insertions(+)
> > >
> > > diff --git a/include/linux/sunrpc/xprt.h
> > > b/include/linux/sunrpc/xprt.h
> > > index e64bd82..a603d48 100644
> > > --- a/include/linux/sunrpc/xprt.h
> > > +++ b/include/linux/sunrpc/xprt.h
> > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > * used in
> > > the
> > > softirq.
> > > */
> > > unsigned long rq_majortimeo; /* major timeout
> > > alarm */
> > > + unsigned long rq_minortimeo; /* minor timeout
> > > alarm */
> > > unsigned long rq_timeout; /* Current timeout
> > > value */
> > > ktime_t rq_rtt; /* round-trip time
> > > */
> > > unsigned int rq_retries; /* # of retries */
> > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > index d5cc5db..c0ce232 100644
> > > --- a/net/sunrpc/xprt.c
> > > +++ b/net/sunrpc/xprt.c
> > > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > > rpc_rqst *req)
> > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > }
> > >
> > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > +{
> > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > +}
> > > +
> > > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > > rpc_rqst *req)
> > > {
> > > unsigned long time_init;
> > > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > > rpc_task
> > > *task, struct rpc_rqst *req)
> > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > >tk_start);
> > > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > }
> > >
> > > /**
> > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst
> > > *req)
> > > const struct rpc_timeout *to = req->rq_task->tk_client-
> > > > cl_timeout;
> > > int status = 0;
> > >
> > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > + xprt_reset_minortimeo(req);
> > > + return status;
> >
> > Shouldn't this case be just returning without updating the timeout?
> > After all, this is the case where nothing has expired yet.
>
> I think we perhaps should readjust the minor timeout every here but I
> can't figure out what the desired behaviour should be. When should we
> consider it's appropriate to double the timer. Consider the
> following:
>
> time1: v3 op sent
> time1+50s: server RSTs
> We check that it's not yet the minor timeout (time1+60s)
> time1+50s: v3 op re-sent (say we don't reset the minor timeout to be
> current time+60s)
> time1+60s: server RSTs
> Client will resend the op but now it's past the initial minor timeout
> so the timeout will be doubled. Is that what we really want? Maybe it
> is.
> Say now the server RSTs the connection again (shortly after or in
> less
> than 60s), since we are not updating the minor timeout value, then
> the
> client will again modify the timeout before resending. Is that Ok?
>
> That's why my reasoning was that at every re-evaluation of the
> timeout
> value, we have the minor timeout set for current time+60s and we get
> an RST within it then we don't modify the timeout value.
So a couple of issues with that:
The first is that a series of RST calls could cause the timeout to get
pushed to the max value fairly quickly (btw, xprt_reset_minortimeo()
does not enforce a limit right now).
The second is that we end up pushing out the major timeout value, since
the major timeout cannot occur unless the value of jiffies is after the
minor timeout (which keeps changing on each pass).
>
>
> > > + }
> > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > if (to->to_exponential)
> > > req->rq_timeout <<= 1;
> > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > req->rq_timeout += to->to_increment;
> > > if (to->to_maxval && req->rq_timeout >= to-
> > > >to_maxval)
> > > req->rq_timeout = to->to_maxval;
> > > + xprt_reset_minortimeo(req);
> >
> > ...and then perhaps this can just be moved out of the time_before()
> > condition, since it looks to me as if we also want to reset req-
> > > rq_minortimeo when a major timeout occurs.
> > > req->rq_retries++;
> > > } else {
> > > req->rq_timeout = to->to_initval;
--
Trond Myklebust
Linux NFS client maintainer, Hammerspace
[email protected]
On Thu, Jul 9, 2020 at 1:19 PM Trond Myklebust <[email protected]> wrote:
>
> On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> > On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> > [email protected]> wrote:
> > > Hi Olga
> > >
> > > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > > Current behaviour: every time a v3 operation is re-sent to the
> > > > server
> > > > we update (double) the timeout. There is no distinction between
> > > > whether
> > > > or not the previous timer had expired before the re-sent
> > > > happened.
> > > >
> > > > Here's the scenario:
> > > > 1. Client sends a v3 operation
> > > > 2. Server RST-s the connection (prior to the timeout) (eg.,
> > > > connection
> > > > is immediately reset)
> > > > 3. Client re-sends a v3 operation but the timeout is now 120sec.
> > > >
> > > > As a result, an application sees 2mins pause before a retry in
> > > > case
> > > > server again does not reply.
> > > >
> > > > Instead, this patch proposes to keep track off when the minor
> > > > timeout
> > > > should happen and if it didn't, then don't update the new
> > > > timeout.
> > > >
> > > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > > ---
> > > > include/linux/sunrpc/xprt.h | 1 +
> > > > net/sunrpc/xprt.c | 11 +++++++++++
> > > > 2 files changed, 12 insertions(+)
> > > >
> > > > diff --git a/include/linux/sunrpc/xprt.h
> > > > b/include/linux/sunrpc/xprt.h
> > > > index e64bd82..a603d48 100644
> > > > --- a/include/linux/sunrpc/xprt.h
> > > > +++ b/include/linux/sunrpc/xprt.h
> > > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > > * used in
> > > > the
> > > > softirq.
> > > > */
> > > > unsigned long rq_majortimeo; /* major timeout
> > > > alarm */
> > > > + unsigned long rq_minortimeo; /* minor timeout
> > > > alarm */
> > > > unsigned long rq_timeout; /* Current timeout
> > > > value */
> > > > ktime_t rq_rtt; /* round-trip time
> > > > */
> > > > unsigned int rq_retries; /* # of retries */
> > > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > > index d5cc5db..c0ce232 100644
> > > > --- a/net/sunrpc/xprt.c
> > > > +++ b/net/sunrpc/xprt.c
> > > > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > > > rpc_rqst *req)
> > > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > > }
> > > >
> > > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > > +{
> > > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > > +}
> > > > +
> > > > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > > > rpc_rqst *req)
> > > > {
> > > > unsigned long time_init;
> > > > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > > > rpc_task
> > > > *task, struct rpc_rqst *req)
> > > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > > >tk_start);
> > > > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > > > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > > }
> > > >
> > > > /**
> > > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst
> > > > *req)
> > > > const struct rpc_timeout *to = req->rq_task->tk_client-
> > > > > cl_timeout;
> > > > int status = 0;
> > > >
> > > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > > + xprt_reset_minortimeo(req);
> > > > + return status;
> > >
> > > Shouldn't this case be just returning without updating the timeout?
> > > After all, this is the case where nothing has expired yet.
> >
> > I think we perhaps should readjust the minor timeout every here but I
> > can't figure out what the desired behaviour should be. When should we
> > consider it's appropriate to double the timer. Consider the
> > following:
> >
> > time1: v3 op sent
> > time1+50s: server RSTs
> > We check that it's not yet the minor timeout (time1+60s)
> > time1+50s: v3 op re-sent (say we don't reset the minor timeout to be
> > current time+60s)
> > time1+60s: server RSTs
> > Client will resend the op but now it's past the initial minor timeout
> > so the timeout will be doubled. Is that what we really want? Maybe it
> > is.
> > Say now the server RSTs the connection again (shortly after or in
> > less
> > than 60s), since we are not updating the minor timeout value, then
> > the
> > client will again modify the timeout before resending. Is that Ok?
> >
> > That's why my reasoning was that at every re-evaluation of the
> > timeout
> > value, we have the minor timeout set for current time+60s and we get
> > an RST within it then we don't modify the timeout value.
>
> So a couple of issues with that:
>
> The first is that a series of RST calls could cause the timeout to get
> pushed to the max value fairly quickly (btw, xprt_reset_minortimeo()
> does not enforce a limit right now).
>
> The second is that we end up pushing out the major timeout value, since
> the major timeout cannot occur unless the value of jiffies is after the
> minor timeout (which keeps changing on each pass).
But dont we want to push out the major timeout?
Actually i think, back in my example of getting the RST, at
(time1+50s). shouldn't minor_timeo and majortimeo be reset to
currenttime+appropriate value of minor/major? If we are evaluating
the timer and the time difference between when the operation was sent
and now is less than 60s, we shouldn't say a timeout has occurried
(it's a pre-mature timeout) and thus its value shouldn't be modified.
Thoughts?
>
> >
> >
> > > > + }
> > > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > > if (to->to_exponential)
> > > > req->rq_timeout <<= 1;
> > > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > > req->rq_timeout += to->to_increment;
> > > > if (to->to_maxval && req->rq_timeout >= to-
> > > > >to_maxval)
> > > > req->rq_timeout = to->to_maxval;
> > > > + xprt_reset_minortimeo(req);
> > >
> > > ...and then perhaps this can just be moved out of the time_before()
> > > condition, since it looks to me as if we also want to reset req-
> > > > rq_minortimeo when a major timeout occurs.
> > > > req->rq_retries++;
> > > > } else {
> > > > req->rq_timeout = to->to_initval;
>
> --
> Trond Myklebust
> Linux NFS client maintainer, Hammerspace
> [email protected]
>
>
On Thu, Jul 9, 2020 at 5:07 PM Olga Kornievskaia
<[email protected]> wrote:
>
> On Thu, Jul 9, 2020 at 1:19 PM Trond Myklebust <[email protected]> wrote:
> >
> > On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> > > On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> > > [email protected]> wrote:
> > > > Hi Olga
> > > >
> > > > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > > > Current behaviour: every time a v3 operation is re-sent to the
> > > > > server
> > > > > we update (double) the timeout. There is no distinction between
> > > > > whether
> > > > > or not the previous timer had expired before the re-sent
> > > > > happened.
> > > > >
> > > > > Here's the scenario:
> > > > > 1. Client sends a v3 operation
> > > > > 2. Server RST-s the connection (prior to the timeout) (eg.,
> > > > > connection
> > > > > is immediately reset)
> > > > > 3. Client re-sends a v3 operation but the timeout is now 120sec.
> > > > >
> > > > > As a result, an application sees 2mins pause before a retry in
> > > > > case
> > > > > server again does not reply.
> > > > >
> > > > > Instead, this patch proposes to keep track off when the minor
> > > > > timeout
> > > > > should happen and if it didn't, then don't update the new
> > > > > timeout.
> > > > >
> > > > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > > > ---
> > > > > include/linux/sunrpc/xprt.h | 1 +
> > > > > net/sunrpc/xprt.c | 11 +++++++++++
> > > > > 2 files changed, 12 insertions(+)
> > > > >
> > > > > diff --git a/include/linux/sunrpc/xprt.h
> > > > > b/include/linux/sunrpc/xprt.h
> > > > > index e64bd82..a603d48 100644
> > > > > --- a/include/linux/sunrpc/xprt.h
> > > > > +++ b/include/linux/sunrpc/xprt.h
> > > > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > > > * used in
> > > > > the
> > > > > softirq.
> > > > > */
> > > > > unsigned long rq_majortimeo; /* major timeout
> > > > > alarm */
> > > > > + unsigned long rq_minortimeo; /* minor timeout
> > > > > alarm */
> > > > > unsigned long rq_timeout; /* Current timeout
> > > > > value */
> > > > > ktime_t rq_rtt; /* round-trip time
> > > > > */
> > > > > unsigned int rq_retries; /* # of retries */
> > > > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > > > index d5cc5db..c0ce232 100644
> > > > > --- a/net/sunrpc/xprt.c
> > > > > +++ b/net/sunrpc/xprt.c
> > > > > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > > > > rpc_rqst *req)
> > > > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > > > }
> > > > >
> > > > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > > > +{
> > > > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > > > +}
> > > > > +
> > > > > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > > > > rpc_rqst *req)
> > > > > {
> > > > > unsigned long time_init;
> > > > > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > > > > rpc_task
> > > > > *task, struct rpc_rqst *req)
> > > > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > > > >tk_start);
> > > > > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > > > > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > > > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > > > }
> > > > >
> > > > > /**
> > > > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst
> > > > > *req)
> > > > > const struct rpc_timeout *to = req->rq_task->tk_client-
> > > > > > cl_timeout;
> > > > > int status = 0;
> > > > >
> > > > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > > > + xprt_reset_minortimeo(req);
> > > > > + return status;
> > > >
> > > > Shouldn't this case be just returning without updating the timeout?
> > > > After all, this is the case where nothing has expired yet.
> > >
> > > I think we perhaps should readjust the minor timeout every here but I
> > > can't figure out what the desired behaviour should be. When should we
> > > consider it's appropriate to double the timer. Consider the
> > > following:
> > >
> > > time1: v3 op sent
> > > time1+50s: server RSTs
> > > We check that it's not yet the minor timeout (time1+60s)
> > > time1+50s: v3 op re-sent (say we don't reset the minor timeout to be
> > > current time+60s)
> > > time1+60s: server RSTs
> > > Client will resend the op but now it's past the initial minor timeout
> > > so the timeout will be doubled. Is that what we really want? Maybe it
> > > is.
> > > Say now the server RSTs the connection again (shortly after or in
> > > less
> > > than 60s), since we are not updating the minor timeout value, then
> > > the
> > > client will again modify the timeout before resending. Is that Ok?
> > >
> > > That's why my reasoning was that at every re-evaluation of the
> > > timeout
> > > value, we have the minor timeout set for current time+60s and we get
> > > an RST within it then we don't modify the timeout value.
> >
> > So a couple of issues with that:
> >
> > The first is that a series of RST calls could cause the timeout to get
> > pushed to the max value fairly quickly (btw, xprt_reset_minortimeo()
> > does not enforce a limit right now).
> >
> > The second is that we end up pushing out the major timeout value, since
> > the major timeout cannot occur unless the value of jiffies is after the
> > minor timeout (which keeps changing on each pass).
>
> But dont we want to push out the major timeout?
>
> Actually i think, back in my example of getting the RST, at
> (time1+50s). shouldn't minor_timeo and majortimeo be reset to
> currenttime+appropriate value of minor/major? If we are evaluating
> the timer and the time difference between when the operation was sent
> and now is less than 60s, we shouldn't say a timeout has occurried
> (it's a pre-mature timeout) and thus its value shouldn't be modified.
>
> Thoughts?
Do you feel that the following approach is incorrect? Sry it's just
cut-and-paste but the logic is there. Thank you.
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index e64bd82..a603d48 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -101,6 +101,7 @@ struct rpc_rqst {
* used in the softirq.
*/
unsigned long rq_majortimeo; /* major timeout alarm */
+ unsigned long rq_minortimeo; /* minor timeout alarm */
unsigned long rq_timeout; /* Current timeout value */
ktime_t rq_rtt; /* round-trip time */
unsigned int rq_retries; /* # of retries */
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d5cc5db..66d412b 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req)
req->rq_majortimeo += xprt_calc_majortimeo(req);
}
+static void xprt_reset_minortimeo(struct rpc_rqst *req)
+{
+ req->rq_minortimeo = jiffies + req->rq_timeout;
+}
+
static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
{
unsigned long time_init;
@@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task
*task, struct rpc_rqst *req)
time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
req->rq_timeout = task->tk_client->cl_timeout->to_initval;
req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+ req->rq_minortimeo = time_init + req->rq_timeout;
}
/**
@@ -631,6 +637,11 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
int status = 0;
+ if (time_before(jiffies, req->rq_minortimeo)) {
+ req->rq_majortimeo = jiffies + xprt_calc_majortimeo(req);
+ req->rq_minortimeo = jiffies + req->rq_timeout;
+ return status;
+ }
if (time_before(jiffies, req->rq_majortimeo)) {
if (to->to_exponential)
req->rq_timeout <<= 1;
@@ -649,6 +660,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
spin_unlock(&xprt->transport_lock);
status = -ETIMEDOUT;
}
+ xprt_reset_minortimeo(req);
if (req->rq_timeout == 0) {
printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
--
> > > > > + }
> > > > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > > > if (to->to_exponential)
> > > > > req->rq_timeout <<= 1;
> > > > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > > > req->rq_timeout += to->to_increment;
> > > > > if (to->to_maxval && req->rq_timeout >= to-
> > > > > >to_maxval)
> > > > > req->rq_timeout = to->to_maxval;
> > > > > + xprt_reset_minortimeo(req);
> > > >
> > > > ...and then perhaps this can just be moved out of the time_before()
> > > > condition, since it looks to me as if we also want to reset req-
> > > > > rq_minortimeo when a major timeout occurs.
> > > > > req->rq_retries++;
> > > > > } else {
> > > > > req->rq_timeout = to->to_initval;
> >
> > --
> > Trond Myklebust
> > Linux NFS client maintainer, Hammerspace
> > [email protected]
> >
> >
On Fri, Jul 10, 2020 at 1:35 PM Olga Kornievskaia
<[email protected]> wrote:
>
> On Thu, Jul 9, 2020 at 5:07 PM Olga Kornievskaia
> <[email protected]> wrote:
> >
> > On Thu, Jul 9, 2020 at 1:19 PM Trond Myklebust <[email protected]> wrote:
> > >
> > > On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> > > > On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> > > > [email protected]> wrote:
> > > > > Hi Olga
> > > > >
> > > > > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > > > > Current behaviour: every time a v3 operation is re-sent to the
> > > > > > server
> > > > > > we update (double) the timeout. There is no distinction between
> > > > > > whether
> > > > > > or not the previous timer had expired before the re-sent
> > > > > > happened.
> > > > > >
> > > > > > Here's the scenario:
> > > > > > 1. Client sends a v3 operation
> > > > > > 2. Server RST-s the connection (prior to the timeout) (eg.,
> > > > > > connection
> > > > > > is immediately reset)
> > > > > > 3. Client re-sends a v3 operation but the timeout is now 120sec.
> > > > > >
> > > > > > As a result, an application sees 2mins pause before a retry in
> > > > > > case
> > > > > > server again does not reply.
> > > > > >
> > > > > > Instead, this patch proposes to keep track off when the minor
> > > > > > timeout
> > > > > > should happen and if it didn't, then don't update the new
> > > > > > timeout.
> > > > > >
> > > > > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > > > > ---
> > > > > > include/linux/sunrpc/xprt.h | 1 +
> > > > > > net/sunrpc/xprt.c | 11 +++++++++++
> > > > > > 2 files changed, 12 insertions(+)
> > > > > >
> > > > > > diff --git a/include/linux/sunrpc/xprt.h
> > > > > > b/include/linux/sunrpc/xprt.h
> > > > > > index e64bd82..a603d48 100644
> > > > > > --- a/include/linux/sunrpc/xprt.h
> > > > > > +++ b/include/linux/sunrpc/xprt.h
> > > > > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > > > > * used in
> > > > > > the
> > > > > > softirq.
> > > > > > */
> > > > > > unsigned long rq_majortimeo; /* major timeout
> > > > > > alarm */
> > > > > > + unsigned long rq_minortimeo; /* minor timeout
> > > > > > alarm */
> > > > > > unsigned long rq_timeout; /* Current timeout
> > > > > > value */
> > > > > > ktime_t rq_rtt; /* round-trip time
> > > > > > */
> > > > > > unsigned int rq_retries; /* # of retries */
> > > > > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > > > > index d5cc5db..c0ce232 100644
> > > > > > --- a/net/sunrpc/xprt.c
> > > > > > +++ b/net/sunrpc/xprt.c
> > > > > > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > > > > > rpc_rqst *req)
> > > > > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > > > > }
> > > > > >
> > > > > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > > > > +{
> > > > > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > > > > +}
> > > > > > +
> > > > > > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > > > > > rpc_rqst *req)
> > > > > > {
> > > > > > unsigned long time_init;
> > > > > > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > > > > > rpc_task
> > > > > > *task, struct rpc_rqst *req)
> > > > > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > > > > >tk_start);
> > > > > > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > > > > > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > > > > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > > > > }
> > > > > >
> > > > > > /**
> > > > > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct rpc_rqst
> > > > > > *req)
> > > > > > const struct rpc_timeout *to = req->rq_task->tk_client-
> > > > > > > cl_timeout;
> > > > > > int status = 0;
> > > > > >
> > > > > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > > > > + xprt_reset_minortimeo(req);
> > > > > > + return status;
> > > > >
> > > > > Shouldn't this case be just returning without updating the timeout?
> > > > > After all, this is the case where nothing has expired yet.
> > > >
> > > > I think we perhaps should readjust the minor timeout every here but I
> > > > can't figure out what the desired behaviour should be. When should we
> > > > consider it's appropriate to double the timer. Consider the
> > > > following:
> > > >
> > > > time1: v3 op sent
> > > > time1+50s: server RSTs
> > > > We check that it's not yet the minor timeout (time1+60s)
> > > > time1+50s: v3 op re-sent (say we don't reset the minor timeout to be
> > > > current time+60s)
> > > > time1+60s: server RSTs
> > > > Client will resend the op but now it's past the initial minor timeout
> > > > so the timeout will be doubled. Is that what we really want? Maybe it
> > > > is.
> > > > Say now the server RSTs the connection again (shortly after or in
> > > > less
> > > > than 60s), since we are not updating the minor timeout value, then
> > > > the
> > > > client will again modify the timeout before resending. Is that Ok?
> > > >
> > > > That's why my reasoning was that at every re-evaluation of the
> > > > timeout
> > > > value, we have the minor timeout set for current time+60s and we get
> > > > an RST within it then we don't modify the timeout value.
> > >
> > > So a couple of issues with that:
> > >
> > > The first is that a series of RST calls could cause the timeout to get
> > > pushed to the max value fairly quickly (btw, xprt_reset_minortimeo()
> > > does not enforce a limit right now).
> > >
> > > The second is that we end up pushing out the major timeout value, since
> > > the major timeout cannot occur unless the value of jiffies is after the
> > > minor timeout (which keeps changing on each pass).
> >
> > But dont we want to push out the major timeout?
> >
> > Actually i think, back in my example of getting the RST, at
> > (time1+50s). shouldn't minor_timeo and majortimeo be reset to
> > currenttime+appropriate value of minor/major? If we are evaluating
> > the timer and the time difference between when the operation was sent
> > and now is less than 60s, we shouldn't say a timeout has occurried
> > (it's a pre-mature timeout) and thus its value shouldn't be modified.
> >
> > Thoughts?
>
> Do you feel that the following approach is incorrect? Sry it's just
> cut-and-paste but the logic is there. Thank you.
Scratch this... So with this we'd never timeout an operation at all.
> diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
> index e64bd82..a603d48 100644
> --- a/include/linux/sunrpc/xprt.h
> +++ b/include/linux/sunrpc/xprt.h
> @@ -101,6 +101,7 @@ struct rpc_rqst {
> * used in the softirq.
> */
> unsigned long rq_majortimeo; /* major timeout alarm */
> + unsigned long rq_minortimeo; /* minor timeout alarm */
> unsigned long rq_timeout; /* Current timeout value */
> ktime_t rq_rtt; /* round-trip time */
> unsigned int rq_retries; /* # of retries */
> diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> index d5cc5db..66d412b 100644
> --- a/net/sunrpc/xprt.c
> +++ b/net/sunrpc/xprt.c
> @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req)
> req->rq_majortimeo += xprt_calc_majortimeo(req);
> }
>
> +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> +{
> + req->rq_minortimeo = jiffies + req->rq_timeout;
> +}
> +
> static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
> {
> unsigned long time_init;
> @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task
> *task, struct rpc_rqst *req)
> time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
> req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> + req->rq_minortimeo = time_init + req->rq_timeout;
> }
>
> /**
> @@ -631,6 +637,11 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
> int status = 0;
>
> + if (time_before(jiffies, req->rq_minortimeo)) {
> + req->rq_majortimeo = jiffies + xprt_calc_majortimeo(req);
> + req->rq_minortimeo = jiffies + req->rq_timeout;
> + return status;
> + }
> if (time_before(jiffies, req->rq_majortimeo)) {
> if (to->to_exponential)
> req->rq_timeout <<= 1;
> @@ -649,6 +660,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> spin_unlock(&xprt->transport_lock);
> status = -ETIMEDOUT;
> }
> + xprt_reset_minortimeo(req);
>
> if (req->rq_timeout == 0) {
> printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
> --
>
> > > > > > + }
> > > > > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > > > > if (to->to_exponential)
> > > > > > req->rq_timeout <<= 1;
> > > > > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > > > > req->rq_timeout += to->to_increment;
> > > > > > if (to->to_maxval && req->rq_timeout >= to-
> > > > > > >to_maxval)
> > > > > > req->rq_timeout = to->to_maxval;
> > > > > > + xprt_reset_minortimeo(req);
> > > > >
> > > > > ...and then perhaps this can just be moved out of the time_before()
> > > > > condition, since it looks to me as if we also want to reset req-
> > > > > > rq_minortimeo when a major timeout occurs.
> > > > > > req->rq_retries++;
> > > > > > } else {
> > > > > > req->rq_timeout = to->to_initval;
> > >
> > > --
> > > Trond Myklebust
> > > Linux NFS client maintainer, Hammerspace
> > > [email protected]
> > >
> > >
Hi Olga
On Fri, 2020-07-10 at 14:40 -0400, Olga Kornievskaia wrote:
> On Fri, Jul 10, 2020 at 1:35 PM Olga Kornievskaia
> <[email protected]> wrote:
> > On Thu, Jul 9, 2020 at 5:07 PM Olga Kornievskaia
> > <[email protected]> wrote:
> > > On Thu, Jul 9, 2020 at 1:19 PM Trond Myklebust <
> > > [email protected]> wrote:
> > > > On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> > > > > On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> > > > > [email protected]> wrote:
> > > > > > Hi Olga
> > > > > >
> > > > > > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > > > > > Current behaviour: every time a v3 operation is re-sent
> > > > > > > to the
> > > > > > > server
> > > > > > > we update (double) the timeout. There is no distinction
> > > > > > > between
> > > > > > > whether
> > > > > > > or not the previous timer had expired before the re-sent
> > > > > > > happened.
> > > > > > >
> > > > > > > Here's the scenario:
> > > > > > > 1. Client sends a v3 operation
> > > > > > > 2. Server RST-s the connection (prior to the timeout)
> > > > > > > (eg.,
> > > > > > > connection
> > > > > > > is immediately reset)
> > > > > > > 3. Client re-sends a v3 operation but the timeout is now
> > > > > > > 120sec.
> > > > > > >
> > > > > > > As a result, an application sees 2mins pause before a
> > > > > > > retry in
> > > > > > > case
> > > > > > > server again does not reply.
> > > > > > >
> > > > > > > Instead, this patch proposes to keep track off when the
> > > > > > > minor
> > > > > > > timeout
> > > > > > > should happen and if it didn't, then don't update the new
> > > > > > > timeout.
> > > > > > >
> > > > > > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > > > > > ---
> > > > > > > include/linux/sunrpc/xprt.h | 1 +
> > > > > > > net/sunrpc/xprt.c | 11 +++++++++++
> > > > > > > 2 files changed, 12 insertions(+)
> > > > > > >
> > > > > > > diff --git a/include/linux/sunrpc/xprt.h
> > > > > > > b/include/linux/sunrpc/xprt.h
> > > > > > > index e64bd82..a603d48 100644
> > > > > > > --- a/include/linux/sunrpc/xprt.h
> > > > > > > +++ b/include/linux/sunrpc/xprt.h
> > > > > > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > > > > > *
> > > > > > > used in
> > > > > > > the
> > > > > > > softirq.
> > > > > > > */
> > > > > > > unsigned long rq_majortimeo; /* major
> > > > > > > timeout
> > > > > > > alarm */
> > > > > > > + unsigned long rq_minortimeo; /* minor
> > > > > > > timeout
> > > > > > > alarm */
> > > > > > > unsigned long rq_timeout; /* Current
> > > > > > > timeout
> > > > > > > value */
> > > > > > > ktime_t rq_rtt; /* round-
> > > > > > > trip time
> > > > > > > */
> > > > > > > unsigned int rq_retries; /* # of
> > > > > > > retries */
> > > > > > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > > > > > index d5cc5db..c0ce232 100644
> > > > > > > --- a/net/sunrpc/xprt.c
> > > > > > > +++ b/net/sunrpc/xprt.c
> > > > > > > @@ -607,6 +607,11 @@ static void
> > > > > > > xprt_reset_majortimeo(struct
> > > > > > > rpc_rqst *req)
> > > > > > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > > > > > }
> > > > > > >
> > > > > > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > > > > > +{
> > > > > > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > > > > > +}
> > > > > > > +
> > > > > > > static void xprt_init_majortimeo(struct rpc_task *task,
> > > > > > > struct
> > > > > > > rpc_rqst *req)
> > > > > > > {
> > > > > > > unsigned long time_init;
> > > > > > > @@ -618,6 +623,7 @@ static void
> > > > > > > xprt_init_majortimeo(struct
> > > > > > > rpc_task
> > > > > > > *task, struct rpc_rqst *req)
> > > > > > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > > > > > > tk_start);
> > > > > > > req->rq_timeout = task->tk_client->cl_timeout-
> > > > > > > >to_initval;
> > > > > > > req->rq_majortimeo = time_init +
> > > > > > > xprt_calc_majortimeo(req);
> > > > > > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > > > > > }
> > > > > > >
> > > > > > > /**
> > > > > > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct
> > > > > > > rpc_rqst
> > > > > > > *req)
> > > > > > > const struct rpc_timeout *to = req->rq_task-
> > > > > > > >tk_client-
> > > > > > > > cl_timeout;
> > > > > > > int status = 0;
> > > > > > >
> > > > > > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > > > > > + xprt_reset_minortimeo(req);
> > > > > > > + return status;
> > > > > >
> > > > > > Shouldn't this case be just returning without updating the
> > > > > > timeout?
> > > > > > After all, this is the case where nothing has expired yet.
> > > > >
> > > > > I think we perhaps should readjust the minor timeout every
> > > > > here but I
> > > > > can't figure out what the desired behaviour should be. When
> > > > > should we
> > > > > consider it's appropriate to double the timer. Consider the
> > > > > following:
> > > > >
> > > > > time1: v3 op sent
> > > > > time1+50s: server RSTs
> > > > > We check that it's not yet the minor timeout (time1+60s)
> > > > > time1+50s: v3 op re-sent (say we don't reset the minor
> > > > > timeout to be
> > > > > current time+60s)
> > > > > time1+60s: server RSTs
> > > > > Client will resend the op but now it's past the initial minor
> > > > > timeout
> > > > > so the timeout will be doubled. Is that what we really want?
> > > > > Maybe it
> > > > > is.
> > > > > Say now the server RSTs the connection again (shortly after
> > > > > or in
> > > > > less
> > > > > than 60s), since we are not updating the minor timeout value,
> > > > > then
> > > > > the
> > > > > client will again modify the timeout before resending. Is
> > > > > that Ok?
> > > > >
> > > > > That's why my reasoning was that at every re-evaluation of
> > > > > the
> > > > > timeout
> > > > > value, we have the minor timeout set for current time+60s and
> > > > > we get
> > > > > an RST within it then we don't modify the timeout value.
> > > >
> > > > So a couple of issues with that:
> > > >
> > > > The first is that a series of RST calls could cause the timeout
> > > > to get
> > > > pushed to the max value fairly quickly (btw,
> > > > xprt_reset_minortimeo()
> > > > does not enforce a limit right now).
> > > >
> > > > The second is that we end up pushing out the major timeout
> > > > value, since
> > > > the major timeout cannot occur unless the value of jiffies is
> > > > after the
> > > > minor timeout (which keeps changing on each pass).
> > >
> > > But dont we want to push out the major timeout?
> > >
> > > Actually i think, back in my example of getting the RST, at
> > > (time1+50s). shouldn't minor_timeo and majortimeo be reset to
> > > currenttime+appropriate value of minor/major? If we are
> > > evaluating
> > > the timer and the time difference between when the operation was
> > > sent
> > > and now is less than 60s, we shouldn't say a timeout has
> > > occurried
> > > (it's a pre-mature timeout) and thus its value shouldn't be
> > > modified.
> > >
> > > Thoughts?
> >
> > Do you feel that the following approach is incorrect? Sry it's just
> > cut-and-paste but the logic is there. Thank you.
>
> Scratch this... So with this we'd never timeout an operation at all.
I think the ideal solution would respect the fact that most sysadmins
who read the nfs manpage assume that timeouts are a predictable
feature, and that if I set timeo=600, retrans=2, for a TCP mount, then
the minor timeouts will occur 60s, and 180s (60+120) after the RPC call
was initially attempted sent, and then the first major timeout will
occur 360s (60+120+180) after the RPC call was initially attempted
sent.
i.e. the timeouts are calculated relative to the time at which the RPC
call was initially attempted transmitted.
If we start extending any one of those timeouts, then things like soft
mounts become unpredictable, and we no longer control when the EIO is
going to be reported to the application. This has been a source of
complaints from users in the past.
>
> > diff --git a/include/linux/sunrpc/xprt.h
> > b/include/linux/sunrpc/xprt.h
> > index e64bd82..a603d48 100644
> > --- a/include/linux/sunrpc/xprt.h
> > +++ b/include/linux/sunrpc/xprt.h
> > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > * used in the softirq.
> > */
> > unsigned long rq_majortimeo; /* major timeout alarm */
> > + unsigned long rq_minortimeo; /* minor timeout alarm */
> > unsigned long rq_timeout; /* Current timeout value */
> > ktime_t rq_rtt; /* round-trip time */
> > unsigned int rq_retries; /* # of retries */
> > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > index d5cc5db..66d412b 100644
> > --- a/net/sunrpc/xprt.c
> > +++ b/net/sunrpc/xprt.c
> > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > rpc_rqst *req)
> > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > }
> >
> > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > +{
> > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > +}
> > +
> > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > rpc_rqst *req)
> > {
> > unsigned long time_init;
> > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > rpc_task
> > *task, struct rpc_rqst *req)
> > time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
> > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > + req->rq_minortimeo = time_init + req->rq_timeout;
> > }
> >
> > /**
> > @@ -631,6 +637,11 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > const struct rpc_timeout *to = req->rq_task->tk_client-
> > >cl_timeout;
> > int status = 0;
> >
> > + if (time_before(jiffies, req->rq_minortimeo)) {
> > + req->rq_majortimeo = jiffies + xprt_calc_majortimeo(req);
> > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > + return status;
> > + }
> > if (time_before(jiffies, req->rq_majortimeo)) {
> > if (to->to_exponential)
> > req->rq_timeout <<= 1;
> > @@ -649,6 +660,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > spin_unlock(&xprt->transport_lock);
> > status = -ETIMEDOUT;
> > }
> > + xprt_reset_minortimeo(req);
> >
> > if (req->rq_timeout == 0) {
> > printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
> > --
> >
> > > > > > > + }
> > > > > > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > > > > > if (to->to_exponential)
> > > > > > > req->rq_timeout <<= 1;
> > > > > > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct
> > > > > > > rpc_rqst *req)
> > > > > > > req->rq_timeout += to-
> > > > > > > >to_increment;
> > > > > > > if (to->to_maxval && req->rq_timeout >= to-
> > > > > > > > to_maxval)
> > > > > > > req->rq_timeout = to->to_maxval;
> > > > > > > + xprt_reset_minortimeo(req);
> > > > > >
> > > > > > ...and then perhaps this can just be moved out of the
> > > > > > time_before()
> > > > > > condition, since it looks to me as if we also want to reset
> > > > > > req-
> > > > > > > rq_minortimeo when a major timeout occurs.
> > > > > > > req->rq_retries++;
> > > > > > > } else {
> > > > > > > req->rq_timeout = to->to_initval;
> > > >
--
Trond Myklebust
Linux NFS client maintainer, Hammerspace
[email protected]
On Mon, Jul 13, 2020 at 9:47 AM Trond Myklebust <[email protected]> wrote:
>
> Hi Olga
>
> On Fri, 2020-07-10 at 14:40 -0400, Olga Kornievskaia wrote:
> > On Fri, Jul 10, 2020 at 1:35 PM Olga Kornievskaia
> > <[email protected]> wrote:
> > > On Thu, Jul 9, 2020 at 5:07 PM Olga Kornievskaia
> > > <[email protected]> wrote:
> > > > On Thu, Jul 9, 2020 at 1:19 PM Trond Myklebust <
> > > > [email protected]> wrote:
> > > > > On Thu, 2020-07-09 at 11:43 -0400, Olga Kornievskaia wrote:
> > > > > > On Thu, Jul 9, 2020 at 8:08 AM Trond Myklebust <
> > > > > > [email protected]> wrote:
> > > > > > > Hi Olga
> > > > > > >
> > > > > > > On Wed, 2020-07-08 at 17:05 -0400, Olga Kornievskaia wrote:
> > > > > > > > Current behaviour: every time a v3 operation is re-sent
> > > > > > > > to the
> > > > > > > > server
> > > > > > > > we update (double) the timeout. There is no distinction
> > > > > > > > between
> > > > > > > > whether
> > > > > > > > or not the previous timer had expired before the re-sent
> > > > > > > > happened.
> > > > > > > >
> > > > > > > > Here's the scenario:
> > > > > > > > 1. Client sends a v3 operation
> > > > > > > > 2. Server RST-s the connection (prior to the timeout)
> > > > > > > > (eg.,
> > > > > > > > connection
> > > > > > > > is immediately reset)
> > > > > > > > 3. Client re-sends a v3 operation but the timeout is now
> > > > > > > > 120sec.
> > > > > > > >
> > > > > > > > As a result, an application sees 2mins pause before a
> > > > > > > > retry in
> > > > > > > > case
> > > > > > > > server again does not reply.
> > > > > > > >
> > > > > > > > Instead, this patch proposes to keep track off when the
> > > > > > > > minor
> > > > > > > > timeout
> > > > > > > > should happen and if it didn't, then don't update the new
> > > > > > > > timeout.
> > > > > > > >
> > > > > > > > Signed-off-by: Olga Kornievskaia <[email protected]>
> > > > > > > > ---
> > > > > > > > include/linux/sunrpc/xprt.h | 1 +
> > > > > > > > net/sunrpc/xprt.c | 11 +++++++++++
> > > > > > > > 2 files changed, 12 insertions(+)
> > > > > > > >
> > > > > > > > diff --git a/include/linux/sunrpc/xprt.h
> > > > > > > > b/include/linux/sunrpc/xprt.h
> > > > > > > > index e64bd82..a603d48 100644
> > > > > > > > --- a/include/linux/sunrpc/xprt.h
> > > > > > > > +++ b/include/linux/sunrpc/xprt.h
> > > > > > > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > > > > > > *
> > > > > > > > used in
> > > > > > > > the
> > > > > > > > softirq.
> > > > > > > > */
> > > > > > > > unsigned long rq_majortimeo; /* major
> > > > > > > > timeout
> > > > > > > > alarm */
> > > > > > > > + unsigned long rq_minortimeo; /* minor
> > > > > > > > timeout
> > > > > > > > alarm */
> > > > > > > > unsigned long rq_timeout; /* Current
> > > > > > > > timeout
> > > > > > > > value */
> > > > > > > > ktime_t rq_rtt; /* round-
> > > > > > > > trip time
> > > > > > > > */
> > > > > > > > unsigned int rq_retries; /* # of
> > > > > > > > retries */
> > > > > > > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > > > > > > index d5cc5db..c0ce232 100644
> > > > > > > > --- a/net/sunrpc/xprt.c
> > > > > > > > +++ b/net/sunrpc/xprt.c
> > > > > > > > @@ -607,6 +607,11 @@ static void
> > > > > > > > xprt_reset_majortimeo(struct
> > > > > > > > rpc_rqst *req)
> > > > > > > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > > > > > > }
> > > > > > > >
> > > > > > > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > > > > > > +{
> > > > > > > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > > > > > > +}
> > > > > > > > +
> > > > > > > > static void xprt_init_majortimeo(struct rpc_task *task,
> > > > > > > > struct
> > > > > > > > rpc_rqst *req)
> > > > > > > > {
> > > > > > > > unsigned long time_init;
> > > > > > > > @@ -618,6 +623,7 @@ static void
> > > > > > > > xprt_init_majortimeo(struct
> > > > > > > > rpc_task
> > > > > > > > *task, struct rpc_rqst *req)
> > > > > > > > time_init = xprt_abs_ktime_to_jiffies(task-
> > > > > > > > > tk_start);
> > > > > > > > req->rq_timeout = task->tk_client->cl_timeout-
> > > > > > > > >to_initval;
> > > > > > > > req->rq_majortimeo = time_init +
> > > > > > > > xprt_calc_majortimeo(req);
> > > > > > > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > > > > > > }
> > > > > > > >
> > > > > > > > /**
> > > > > > > > @@ -631,6 +637,10 @@ int xprt_adjust_timeout(struct
> > > > > > > > rpc_rqst
> > > > > > > > *req)
> > > > > > > > const struct rpc_timeout *to = req->rq_task-
> > > > > > > > >tk_client-
> > > > > > > > > cl_timeout;
> > > > > > > > int status = 0;
> > > > > > > >
> > > > > > > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > > > > > > + xprt_reset_minortimeo(req);
> > > > > > > > + return status;
> > > > > > >
> > > > > > > Shouldn't this case be just returning without updating the
> > > > > > > timeout?
> > > > > > > After all, this is the case where nothing has expired yet.
> > > > > >
> > > > > > I think we perhaps should readjust the minor timeout every
> > > > > > here but I
> > > > > > can't figure out what the desired behaviour should be. When
> > > > > > should we
> > > > > > consider it's appropriate to double the timer. Consider the
> > > > > > following:
> > > > > >
> > > > > > time1: v3 op sent
> > > > > > time1+50s: server RSTs
> > > > > > We check that it's not yet the minor timeout (time1+60s)
> > > > > > time1+50s: v3 op re-sent (say we don't reset the minor
> > > > > > timeout to be
> > > > > > current time+60s)
> > > > > > time1+60s: server RSTs
> > > > > > Client will resend the op but now it's past the initial minor
> > > > > > timeout
> > > > > > so the timeout will be doubled. Is that what we really want?
> > > > > > Maybe it
> > > > > > is.
> > > > > > Say now the server RSTs the connection again (shortly after
> > > > > > or in
> > > > > > less
> > > > > > than 60s), since we are not updating the minor timeout value,
> > > > > > then
> > > > > > the
> > > > > > client will again modify the timeout before resending. Is
> > > > > > that Ok?
> > > > > >
> > > > > > That's why my reasoning was that at every re-evaluation of
> > > > > > the
> > > > > > timeout
> > > > > > value, we have the minor timeout set for current time+60s and
> > > > > > we get
> > > > > > an RST within it then we don't modify the timeout value.
> > > > >
> > > > > So a couple of issues with that:
> > > > >
> > > > > The first is that a series of RST calls could cause the timeout
> > > > > to get
> > > > > pushed to the max value fairly quickly (btw,
> > > > > xprt_reset_minortimeo()
> > > > > does not enforce a limit right now).
> > > > >
> > > > > The second is that we end up pushing out the major timeout
> > > > > value, since
> > > > > the major timeout cannot occur unless the value of jiffies is
> > > > > after the
> > > > > minor timeout (which keeps changing on each pass).
> > > >
> > > > But dont we want to push out the major timeout?
> > > >
> > > > Actually i think, back in my example of getting the RST, at
> > > > (time1+50s). shouldn't minor_timeo and majortimeo be reset to
> > > > currenttime+appropriate value of minor/major? If we are
> > > > evaluating
> > > > the timer and the time difference between when the operation was
> > > > sent
> > > > and now is less than 60s, we shouldn't say a timeout has
> > > > occurried
> > > > (it's a pre-mature timeout) and thus its value shouldn't be
> > > > modified.
> > > >
> > > > Thoughts?
> > >
> > > Do you feel that the following approach is incorrect? Sry it's just
> > > cut-and-paste but the logic is there. Thank you.
> >
> > Scratch this... So with this we'd never timeout an operation at all.
>
> I think the ideal solution would respect the fact that most sysadmins
> who read the nfs manpage assume that timeouts are a predictable
> feature, and that if I set timeo=600, retrans=2, for a TCP mount, then
> the minor timeouts will occur 60s, and 180s (60+120) after the RPC call
> was initially attempted sent, and then the first major timeout will
> occur 360s (60+120+180) after the RPC call was initially attempted
> sent.
> i.e. the timeouts are calculated relative to the time at which the RPC
> call was initially attempted transmitted.
>
> If we start extending any one of those timeouts, then things like soft
> mounts become unpredictable, and we no longer control when the EIO is
> going to be reported to the application. This has been a source of
> complaints from users in the past.
Thanks Trond. I re-submitted the patch with your initial suggestion.
> > > diff --git a/include/linux/sunrpc/xprt.h
> > > b/include/linux/sunrpc/xprt.h
> > > index e64bd82..a603d48 100644
> > > --- a/include/linux/sunrpc/xprt.h
> > > +++ b/include/linux/sunrpc/xprt.h
> > > @@ -101,6 +101,7 @@ struct rpc_rqst {
> > > * used in the softirq.
> > > */
> > > unsigned long rq_majortimeo; /* major timeout alarm */
> > > + unsigned long rq_minortimeo; /* minor timeout alarm */
> > > unsigned long rq_timeout; /* Current timeout value */
> > > ktime_t rq_rtt; /* round-trip time */
> > > unsigned int rq_retries; /* # of retries */
> > > diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
> > > index d5cc5db..66d412b 100644
> > > --- a/net/sunrpc/xprt.c
> > > +++ b/net/sunrpc/xprt.c
> > > @@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct
> > > rpc_rqst *req)
> > > req->rq_majortimeo += xprt_calc_majortimeo(req);
> > > }
> > >
> > > +static void xprt_reset_minortimeo(struct rpc_rqst *req)
> > > +{
> > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > +}
> > > +
> > > static void xprt_init_majortimeo(struct rpc_task *task, struct
> > > rpc_rqst *req)
> > > {
> > > unsigned long time_init;
> > > @@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct
> > > rpc_task
> > > *task, struct rpc_rqst *req)
> > > time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
> > > req->rq_timeout = task->tk_client->cl_timeout->to_initval;
> > > req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
> > > + req->rq_minortimeo = time_init + req->rq_timeout;
> > > }
> > >
> > > /**
> > > @@ -631,6 +637,11 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > const struct rpc_timeout *to = req->rq_task->tk_client-
> > > >cl_timeout;
> > > int status = 0;
> > >
> > > + if (time_before(jiffies, req->rq_minortimeo)) {
> > > + req->rq_majortimeo = jiffies + xprt_calc_majortimeo(req);
> > > + req->rq_minortimeo = jiffies + req->rq_timeout;
> > > + return status;
> > > + }
> > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > if (to->to_exponential)
> > > req->rq_timeout <<= 1;
> > > @@ -649,6 +660,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
> > > spin_unlock(&xprt->transport_lock);
> > > status = -ETIMEDOUT;
> > > }
> > > + xprt_reset_minortimeo(req);
> > >
> > > if (req->rq_timeout == 0) {
> > > printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");
> > > --
> > >
> > > > > > > > + }
> > > > > > > > if (time_before(jiffies, req->rq_majortimeo)) {
> > > > > > > > if (to->to_exponential)
> > > > > > > > req->rq_timeout <<= 1;
> > > > > > > > @@ -638,6 +648,7 @@ int xprt_adjust_timeout(struct
> > > > > > > > rpc_rqst *req)
> > > > > > > > req->rq_timeout += to-
> > > > > > > > >to_increment;
> > > > > > > > if (to->to_maxval && req->rq_timeout >= to-
> > > > > > > > > to_maxval)
> > > > > > > > req->rq_timeout = to->to_maxval;
> > > > > > > > + xprt_reset_minortimeo(req);
> > > > > > >
> > > > > > > ...and then perhaps this can just be moved out of the
> > > > > > > time_before()
> > > > > > > condition, since it looks to me as if we also want to reset
> > > > > > > req-
> > > > > > > > rq_minortimeo when a major timeout occurs.
> > > > > > > > req->rq_retries++;
> > > > > > > > } else {
> > > > > > > > req->rq_timeout = to->to_initval;
> > > > >
> --
> Trond Myklebust
> Linux NFS client maintainer, Hammerspace
> [email protected]
>
>