Hi -
Walking a linked list to find an idle thread is not CPU cache-
friendly, and in fact I've noted palpable per-request latency
impacts as the number of nfsd threads on the server increases.
After discussing some possible improvements with Jeff at LSF/MM,
I've been experimenting with the following series. I've measured an
order of magnitude latency improvement in the thread lookup time,
and have managed to keep the whole thing lockless.
The only thing I don't like is that allocating the idle bitmaps in
advance means we've got an /a priori/ cap on the number of NFSD
threads that can be created. I'd love to find a way to enable
the pool idle bitmaps to expand dynamically. Suggestions welcome.
Cc: Lorenzo - I'm not sure whether this work would be applied first
or whether your rpc_status patch would be. If yours goes first, I
can handle converting nfsd_rpc_status() to use the pool's thread
xarray.
---
Chuck Lever (8):
SUNRPC: Deduplicate thread wake-up code
SUNRPC: Report when no service thread is available.
SUNRPC: Split the svc_xprt_dequeue tracepoint
SUNRPC: Clean up svc_set_num_threads
SUNRPC: Replace dprintk() call site in __svc_create()
SUNRPC: Replace sp_threads_all with an xarray
SUNRPC: Convert RQ_BUSY into a per-pool bitmap
SUNRPC: Don't disable BH's when taking sp_lock
fs/nfsd/nfssvc.c | 3 +-
include/linux/sunrpc/svc.h | 17 ++--
include/trace/events/sunrpc.h | 160 ++++++++++++++++++++++++++++----
net/sunrpc/svc.c | 169 ++++++++++++++++++++++------------
net/sunrpc/svc_xprt.c | 103 +++++++++++----------
5 files changed, 316 insertions(+), 136 deletions(-)
--
Chuck Lever
From: Chuck Lever <[email protected]>
Refactor: Extract the loop that finds an idle service thread from
svc_xprt_enqueue() and svc_wake_up().
Signed-off-by: Chuck Lever <[email protected]>
---
include/linux/sunrpc/svc.h | 1 +
net/sunrpc/svc.c | 28 +++++++++++++++++++++++++++
net/sunrpc/svc_xprt.c | 46 +++++++++++++-------------------------------
3 files changed, 43 insertions(+), 32 deletions(-)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index f8751118c122..dc2d90a655e2 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -427,6 +427,7 @@ int svc_register(const struct svc_serv *, struct net *, const int,
void svc_wake_up(struct svc_serv *);
void svc_reserve(struct svc_rqst *rqstp, int space);
+struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool);
struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv);
char * svc_print_addr(struct svc_rqst *, char *, size_t);
const char * svc_proc_name(const struct svc_rqst *rqstp);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 587811a002c9..e81ce5f76abd 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -689,6 +689,34 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
return rqstp;
}
+/**
+ * svc_pool_wake_idle_thread - wake an idle thread in @pool
+ * @pool: service thread pool
+ *
+ * Returns an idle service thread (now marked BUSY), or NULL
+ * if no service threads are available. Finding an idle service
+ * thread and marking it BUSY is atomic with respect to other
+ * calls to svc_pool_wake_idle_thread().
+ */
+struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool)
+{
+ struct svc_rqst *rqstp;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+ if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
+ continue;
+
+ rcu_read_unlock();
+ WRITE_ONCE(rqstp->rq_qtime, ktime_get());
+ wake_up_process(rqstp->rq_task);
+ percpu_counter_inc(&pool->sp_threads_woken);
+ return rqstp;
+ }
+ rcu_read_unlock();
+ return NULL;
+}
+
/*
* Choose a pool in which to create a new thread, for svc_set_num_threads
*/
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 62c7919ea610..f14476d11b67 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -455,8 +455,8 @@ static bool svc_xprt_ready(struct svc_xprt *xprt)
*/
void svc_xprt_enqueue(struct svc_xprt *xprt)
{
+ struct svc_rqst *rqstp;
struct svc_pool *pool;
- struct svc_rqst *rqstp = NULL;
if (!svc_xprt_ready(xprt))
return;
@@ -476,20 +476,10 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
spin_unlock_bh(&pool->sp_lock);
- /* find a thread for this xprt */
- rcu_read_lock();
- list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
- if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
- continue;
- percpu_counter_inc(&pool->sp_threads_woken);
- rqstp->rq_qtime = ktime_get();
- wake_up_process(rqstp->rq_task);
- goto out_unlock;
- }
- set_bit(SP_CONGESTED, &pool->sp_flags);
- rqstp = NULL;
-out_unlock:
- rcu_read_unlock();
+ rqstp = svc_pool_wake_idle_thread(pool);
+ if (!rqstp)
+ set_bit(SP_CONGESTED, &pool->sp_flags);
+
trace_svc_xprt_enqueue(xprt, rqstp);
}
EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
@@ -581,7 +571,10 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
svc_xprt_put(xprt);
}
-/*
+/**
+ * svc_wake_up - Wake up a service thread for non-transport work
+ * @serv: RPC service
+ *
* Some svc_serv's will have occasional work to do, even when a xprt is not
* waiting to be serviced. This function is there to "kick" a task in one of
* those services so that it can wake up and do that work. Note that we only
@@ -590,27 +583,16 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
*/
void svc_wake_up(struct svc_serv *serv)
{
+ struct svc_pool *pool = &serv->sv_pools[0];
struct svc_rqst *rqstp;
- struct svc_pool *pool;
- pool = &serv->sv_pools[0];
-
- rcu_read_lock();
- list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
- /* skip any that aren't queued */
- if (test_bit(RQ_BUSY, &rqstp->rq_flags))
- continue;
- rcu_read_unlock();
- wake_up_process(rqstp->rq_task);
- trace_svc_wake_up(rqstp->rq_task->pid);
+ rqstp = svc_pool_wake_idle_thread(pool);
+ if (!rqstp) {
+ set_bit(SP_TASK_PENDING, &pool->sp_flags);
return;
}
- rcu_read_unlock();
- /* No free entries available */
- set_bit(SP_TASK_PENDING, &pool->sp_flags);
- smp_wmb();
- trace_svc_wake_up(0);
+ trace_svc_wake_up(rqstp->rq_task->pid);
}
EXPORT_SYMBOL_GPL(svc_wake_up);
From: Chuck Lever <[email protected]>
Count and record thread starvation. Administrators can take action
by increasing thread count or decreasing workload.
Signed-off-by: Chuck Lever <[email protected]>
---
include/linux/sunrpc/svc.h | 5 +++-
include/trace/events/sunrpc.h | 49 ++++++++++++++++++++++++++++++++++-------
net/sunrpc/svc.c | 9 +++++++-
net/sunrpc/svc_xprt.c | 21 ++++++++++--------
4 files changed, 64 insertions(+), 20 deletions(-)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index dc2d90a655e2..fbfe6ea737c8 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -22,7 +22,6 @@
#include <linux/pagevec.h>
/*
- *
* RPC service thread pool.
*
* Pool of threads and temporary sockets. Generally there is only
@@ -42,6 +41,7 @@ struct svc_pool {
struct percpu_counter sp_sockets_queued;
struct percpu_counter sp_threads_woken;
struct percpu_counter sp_threads_timedout;
+ struct percpu_counter sp_threads_starved;
#define SP_TASK_PENDING (0) /* still work to do even if no
* xprt is queued. */
@@ -427,7 +427,8 @@ int svc_register(const struct svc_serv *, struct net *, const int,
void svc_wake_up(struct svc_serv *);
void svc_reserve(struct svc_rqst *rqstp, int space);
-struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool);
+struct svc_rqst *svc_pool_wake_idle_thread(struct svc_serv *serv,
+ struct svc_pool *pool);
struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv);
char * svc_print_addr(struct svc_rqst *, char *, size_t);
const char * svc_proc_name(const struct svc_rqst *rqstp);
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 69e42ef30979..9813f4560eef 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1918,21 +1918,21 @@ TRACE_EVENT(svc_xprt_create_err,
TRACE_EVENT(svc_xprt_enqueue,
TP_PROTO(
const struct svc_xprt *xprt,
- const struct svc_rqst *rqst
+ const struct svc_rqst *wakee
),
- TP_ARGS(xprt, rqst),
+ TP_ARGS(xprt, wakee),
TP_STRUCT__entry(
SVC_XPRT_ENDPOINT_FIELDS(xprt)
- __field(int, pid)
+ __field(pid_t, pid)
),
TP_fast_assign(
SVC_XPRT_ENDPOINT_ASSIGNMENTS(xprt);
- __entry->pid = rqst? rqst->rq_task->pid : 0;
+ __entry->pid = wakee->rq_task->pid;
),
TP_printk(SVC_XPRT_ENDPOINT_FORMAT " pid=%d",
@@ -1963,6 +1963,39 @@ TRACE_EVENT(svc_xprt_dequeue,
SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup)
);
+#define show_svc_pool_flags(x) \
+ __print_flags(x, "|", \
+ { BIT(SP_TASK_PENDING), "TASK_PENDING" }, \
+ { BIT(SP_CONGESTED), "CONGESTED" })
+
+TRACE_EVENT(svc_pool_starved,
+ TP_PROTO(
+ const struct svc_serv *serv,
+ const struct svc_pool *pool
+ ),
+
+ TP_ARGS(serv, pool),
+
+ TP_STRUCT__entry(
+ __string(name, serv->sv_name)
+ __field(int, pool_id)
+ __field(unsigned int, nrthreads)
+ __field(unsigned long, flags)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, serv->sv_name);
+ __entry->pool_id = pool->sp_id;
+ __entry->nrthreads = pool->sp_nrthreads;
+ __entry->flags = pool->sp_flags;
+ ),
+
+ TP_printk("service=%s pool=%d flags=%s nrthreads=%u",
+ __get_str(name), __entry->pool_id,
+ show_svc_pool_flags(__entry->flags), __entry->nrthreads
+ )
+);
+
DECLARE_EVENT_CLASS(svc_xprt_event,
TP_PROTO(
const struct svc_xprt *xprt
@@ -2033,16 +2066,16 @@ TRACE_EVENT(svc_xprt_accept,
);
TRACE_EVENT(svc_wake_up,
- TP_PROTO(int pid),
+ TP_PROTO(const struct svc_rqst *wakee),
- TP_ARGS(pid),
+ TP_ARGS(wakee),
TP_STRUCT__entry(
- __field(int, pid)
+ __field(pid_t, pid)
),
TP_fast_assign(
- __entry->pid = pid;
+ __entry->pid = wakee->rq_task->pid;
),
TP_printk("pid=%d", __entry->pid)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e81ce5f76abd..04151e22ec44 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -516,6 +516,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_timedout, 0, GFP_KERNEL);
+ percpu_counter_init(&pool->sp_threads_starved, 0, GFP_KERNEL);
}
return serv;
@@ -591,6 +592,7 @@ svc_destroy(struct kref *ref)
percpu_counter_destroy(&pool->sp_sockets_queued);
percpu_counter_destroy(&pool->sp_threads_woken);
percpu_counter_destroy(&pool->sp_threads_timedout);
+ percpu_counter_destroy(&pool->sp_threads_starved);
}
kfree(serv->sv_pools);
kfree(serv);
@@ -691,6 +693,7 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
/**
* svc_pool_wake_idle_thread - wake an idle thread in @pool
+ * @serv: RPC service
* @pool: service thread pool
*
* Returns an idle service thread (now marked BUSY), or NULL
@@ -698,7 +701,8 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
* thread and marking it BUSY is atomic with respect to other
* calls to svc_pool_wake_idle_thread().
*/
-struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool)
+struct svc_rqst *svc_pool_wake_idle_thread(struct svc_serv *serv,
+ struct svc_pool *pool)
{
struct svc_rqst *rqstp;
@@ -714,6 +718,9 @@ struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool)
return rqstp;
}
rcu_read_unlock();
+
+ trace_svc_pool_starved(serv, pool);
+ percpu_counter_inc(&pool->sp_threads_starved);
return NULL;
}
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index f14476d11b67..859eecb7d52c 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -455,7 +455,7 @@ static bool svc_xprt_ready(struct svc_xprt *xprt)
*/
void svc_xprt_enqueue(struct svc_xprt *xprt)
{
- struct svc_rqst *rqstp;
+ struct svc_rqst *rqstp;
struct svc_pool *pool;
if (!svc_xprt_ready(xprt))
@@ -476,9 +476,11 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
spin_unlock_bh(&pool->sp_lock);
- rqstp = svc_pool_wake_idle_thread(pool);
- if (!rqstp)
+ rqstp = svc_pool_wake_idle_thread(xprt->xpt_server, pool);
+ if (!rqstp) {
set_bit(SP_CONGESTED, &pool->sp_flags);
+ return;
+ }
trace_svc_xprt_enqueue(xprt, rqstp);
}
@@ -584,15 +586,15 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
void svc_wake_up(struct svc_serv *serv)
{
struct svc_pool *pool = &serv->sv_pools[0];
- struct svc_rqst *rqstp;
+ struct svc_rqst *rqstp;
- rqstp = svc_pool_wake_idle_thread(pool);
+ rqstp = svc_pool_wake_idle_thread(serv, pool);
if (!rqstp) {
set_bit(SP_TASK_PENDING, &pool->sp_flags);
return;
}
- trace_svc_wake_up(rqstp->rq_task->pid);
+ trace_svc_wake_up(rqstp);
}
EXPORT_SYMBOL_GPL(svc_wake_up);
@@ -1434,16 +1436,17 @@ static int svc_pool_stats_show(struct seq_file *m, void *p)
struct svc_pool *pool = p;
if (p == SEQ_START_TOKEN) {
- seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n");
+ seq_puts(m, "# pool packets-arrived xprts-enqueued threads-woken threads-timedout starved\n");
return 0;
}
- seq_printf(m, "%u %llu %llu %llu %llu\n",
+ seq_printf(m, "%u %llu %llu %llu %llu %llu\n",
pool->sp_id,
percpu_counter_sum_positive(&pool->sp_sockets_queued),
percpu_counter_sum_positive(&pool->sp_sockets_queued),
percpu_counter_sum_positive(&pool->sp_threads_woken),
- percpu_counter_sum_positive(&pool->sp_threads_timedout));
+ percpu_counter_sum_positive(&pool->sp_threads_timedout),
+ percpu_counter_sum_positive(&pool->sp_threads_starved));
return 0;
}
From: Chuck Lever <[email protected]>
Document the API contract and remove stale or obvious comments.
Signed-off-by: Chuck Lever <[email protected]>
---
net/sunrpc/svc.c | 60 +++++++++++++++++++++++-------------------------------
1 file changed, 25 insertions(+), 35 deletions(-)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 04151e22ec44..cf2e58ead35d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -724,23 +724,14 @@ struct svc_rqst *svc_pool_wake_idle_thread(struct svc_serv *serv,
return NULL;
}
-/*
- * Choose a pool in which to create a new thread, for svc_set_num_threads
- */
-static inline struct svc_pool *
-choose_pool(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
+static struct svc_pool *
+svc_pool_next(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
- if (pool != NULL)
- return pool;
-
- return &serv->sv_pools[(*state)++ % serv->sv_nrpools];
+ return pool ? pool : &serv->sv_pools[(*state)++ % serv->sv_nrpools];
}
-/*
- * Choose a thread to kill, for svc_set_num_threads
- */
-static inline struct task_struct *
-choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
+static struct task_struct *
+svc_pool_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
unsigned int i;
struct task_struct *task = NULL;
@@ -748,7 +739,6 @@ choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
if (pool != NULL) {
spin_lock_bh(&pool->sp_lock);
} else {
- /* choose a pool in round-robin fashion */
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
spin_lock_bh(&pool->sp_lock);
@@ -763,21 +753,15 @@ choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
if (!list_empty(&pool->sp_all_threads)) {
struct svc_rqst *rqstp;
- /*
- * Remove from the pool->sp_all_threads list
- * so we don't try to kill it again.
- */
rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
set_bit(RQ_VICTIM, &rqstp->rq_flags);
list_del_rcu(&rqstp->rq_all);
task = rqstp->rq_task;
}
spin_unlock_bh(&pool->sp_lock);
-
return task;
}
-/* create new threads */
static int
svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
@@ -789,13 +773,12 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
do {
nrservs--;
- chosen_pool = choose_pool(serv, pool, &state);
-
+ chosen_pool = svc_pool_next(serv, pool, &state);
node = svc_pool_map_get_node(chosen_pool->sp_id);
+
rqstp = svc_prepare_thread(serv, chosen_pool, node);
if (IS_ERR(rqstp))
return PTR_ERR(rqstp);
-
task = kthread_create_on_node(serv->sv_threadfn, rqstp,
node, "%s", serv->sv_name);
if (IS_ERR(task)) {
@@ -814,15 +797,6 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
return 0;
}
-/*
- * Create or destroy enough new threads to make the number
- * of threads the given number. If `pool' is non-NULL, applies
- * only to threads in that pool, otherwise round-robins between
- * all pools. Caller must ensure that mutual exclusion between this and
- * server startup or shutdown.
- */
-
-/* destroy old threads */
static int
svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
@@ -830,9 +804,8 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
struct task_struct *task;
unsigned int state = serv->sv_nrthreads-1;
- /* destroy old threads */
do {
- task = choose_victim(serv, pool, &state);
+ task = svc_pool_victim(serv, pool, &state);
if (task == NULL)
break;
rqstp = kthread_data(task);
@@ -844,6 +817,23 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
return 0;
}
+/**
+ * svc_set_num_threads - adjust number of threads per RPC service
+ * @serv: RPC service to adjust
+ * @pool: Specific pool from which to choose threads, or NULL
+ * @nrservs: New number of threads for @serv (0 or less means kill all threads)
+ *
+ * Create or destroy threads to make the number of threads for @serv the
+ * given number. If @pool is non-NULL, change only threads in that pool;
+ * otherwise, round-robin between all pools for @serv. @serv's
+ * sv_nrthreads is adjusted for each thread created or destroyed.
+ *
+ * Caller must ensure mutual exclusion between this and server startup or
+ * shutdown.
+ *
+ * Returns zero on success or a negative errno if an error occurred while
+ * starting a thread.
+ */
int
svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
From: Chuck Lever <[email protected]>
Distinguish between the case where new work was picked up just by
looking at the transport queue versus when the thread was awoken.
This gives us better visibility about how well-utilized the thread
pool is.
Signed-off-by: Chuck Lever <[email protected]>
---
include/trace/events/sunrpc.h | 48 +++++++++++++++++++++++++++++++----------
net/sunrpc/svc_xprt.c | 9 +++++---
2 files changed, 42 insertions(+), 15 deletions(-)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 9813f4560eef..cf3d404ca6d8 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1939,34 +1939,58 @@ TRACE_EVENT(svc_xprt_enqueue,
SVC_XPRT_ENDPOINT_VARARGS, __entry->pid)
);
-TRACE_EVENT(svc_xprt_dequeue,
+#define show_svc_pool_flags(x) \
+ __print_flags(x, "|", \
+ { BIT(SP_TASK_PENDING), "TASK_PENDING" }, \
+ { BIT(SP_CONGESTED), "CONGESTED" })
+
+DECLARE_EVENT_CLASS(svc_pool_scheduler_class,
TP_PROTO(
- const struct svc_rqst *rqst
+ const struct svc_pool *pool,
+ const struct svc_rqst *rqstp
),
- TP_ARGS(rqst),
+ TP_ARGS(pool, rqstp),
TP_STRUCT__entry(
- SVC_XPRT_ENDPOINT_FIELDS(rqst->rq_xprt)
+ SVC_XPRT_ENDPOINT_FIELDS(rqstp->rq_xprt)
+ __string(name, rqstp->rq_server->sv_name)
+ __field(int, pool_id)
+ __field(unsigned int, nrthreads)
+ __field(unsigned long, pool_flags)
__field(unsigned long, wakeup)
),
TP_fast_assign(
- SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+ SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqstp->rq_xprt);
+ __assign_str(name, rqstp->rq_server->sv_name);
+ __entry->pool_id = pool->sp_id;
+ __entry->nrthreads = pool->sp_nrthreads;
+ __entry->pool_flags = pool->sp_flags;
__entry->wakeup = ktime_to_us(ktime_sub(ktime_get(),
- rqst->rq_qtime));
+ rqstp->rq_qtime));
),
- TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu",
- SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup)
+ TP_printk(SVC_XPRT_ENDPOINT_FORMAT
+ " service=%s pool=%d pool_flags=%s nrthreads=%u wakeup-us=%lu",
+ SVC_XPRT_ENDPOINT_VARARGS, __get_str(name), __entry->pool_id,
+ show_svc_pool_flags(__entry->pool_flags), __entry->nrthreads,
+ __entry->wakeup
+ )
);
-#define show_svc_pool_flags(x) \
- __print_flags(x, "|", \
- { BIT(SP_TASK_PENDING), "TASK_PENDING" }, \
- { BIT(SP_CONGESTED), "CONGESTED" })
+#define DEFINE_SVC_POOL_SCHEDULER_EVENT(name) \
+ DEFINE_EVENT(svc_pool_scheduler_class, svc_pool_##name, \
+ TP_PROTO( \
+ const struct svc_pool *pool, \
+ const struct svc_rqst *rqstp \
+ ), \
+ TP_ARGS(pool, rqstp))
+
+DEFINE_SVC_POOL_SCHEDULER_EVENT(polled);
+DEFINE_SVC_POOL_SCHEDULER_EVENT(awoken);
TRACE_EVENT(svc_pool_starved,
TP_PROTO(
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 859eecb7d52c..7d5aed4d1766 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -743,8 +743,10 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
WARN_ON_ONCE(rqstp->rq_xprt);
rqstp->rq_xprt = svc_xprt_dequeue(pool);
- if (rqstp->rq_xprt)
+ if (rqstp->rq_xprt) {
+ trace_svc_pool_polled(pool, rqstp);
goto out_found;
+ }
/*
* We have to be able to interrupt this wait
@@ -766,8 +768,10 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
set_bit(RQ_BUSY, &rqstp->rq_flags);
smp_mb__after_atomic();
rqstp->rq_xprt = svc_xprt_dequeue(pool);
- if (rqstp->rq_xprt)
+ if (rqstp->rq_xprt) {
+ trace_svc_pool_awoken(pool, rqstp);
goto out_found;
+ }
if (!time_left)
percpu_counter_inc(&pool->sp_threads_timedout);
@@ -783,7 +787,6 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
rqstp->rq_chandle.thread_wait = 5*HZ;
else
rqstp->rq_chandle.thread_wait = 1*HZ;
- trace_svc_xprt_dequeue(rqstp);
return rqstp->rq_xprt;
}
From: Chuck Lever <[email protected]>
Done as part of converting SunRPC observability from printk to
tracepoints.
Signed-off-by: Chuck Lever <[email protected]>
---
include/trace/events/sunrpc.h | 23 +++++++++++++++++++++++
net/sunrpc/svc.c | 5 ++---
2 files changed, 25 insertions(+), 3 deletions(-)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index cf3d404ca6d8..70f3bc22c429 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1842,6 +1842,29 @@ TRACE_EVENT(svc_stats_latency,
__get_str(procedure), __entry->execute)
);
+TRACE_EVENT(svc_pool_init,
+ TP_PROTO(
+ const struct svc_serv *serv,
+ const struct svc_pool *pool
+ ),
+
+ TP_ARGS(serv, pool),
+
+ TP_STRUCT__entry(
+ __string(name, serv->sv_name)
+ __field(int, pool_id)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, serv->sv_name);
+ __entry->pool_id = pool->sp_id;
+ ),
+
+ TP_printk("service=%s pool=%d",
+ __get_str(name), __entry->pool_id
+ )
+);
+
#define show_svc_xprt_flags(flags) \
__print_flags(flags, "|", \
{ BIT(XPT_BUSY), "BUSY" }, \
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index cf2e58ead35d..828d28883ea8 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -505,9 +505,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_pool *pool = &serv->sv_pools[i];
- dprintk("svc: initialising pool %u for %s\n",
- i, serv->sv_name);
-
pool->sp_id = i;
INIT_LIST_HEAD(&pool->sp_sockets);
INIT_LIST_HEAD(&pool->sp_all_threads);
@@ -517,6 +514,8 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_timedout, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_starved, 0, GFP_KERNEL);
+
+ trace_svc_pool_init(serv, pool);
}
return serv;
From: Chuck Lever <[email protected]>
We want a thread lookup operation that can be done with RCU only,
but to avoid the linked-list walk, which does not scale well in the
number of svc threads.
BH-disabled locking is no longer necessary because we're no longer
sharing the pool's sp_lock to protect either the xarray or the
pool's thread count. sp_lock also protects transport activity. As
far as I can tell, there are no callers of svc_set_num_threads()
that run outside of process context.
Signed-off-by: Chuck Lever <[email protected]>
---
fs/nfsd/nfssvc.c | 3 +-
include/linux/sunrpc/svc.h | 11 +++----
include/trace/events/sunrpc.h | 47 +++++++++++++++++++++++++++++-
net/sunrpc/svc.c | 65 +++++++++++++++++++++++++----------------
net/sunrpc/svc_xprt.c | 2 +
5 files changed, 92 insertions(+), 36 deletions(-)
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 2154fa63c5f2..d42b2a40c93c 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -62,8 +62,7 @@ static __be32 nfsd_init_request(struct svc_rqst *,
* If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
* properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
* nn->keep_active is set). That number of nfsd threads must
- * exist and each must be listed in ->sp_all_threads in some entry of
- * ->sv_pools[].
+ * exist and each must be listed in some entry of ->sv_pools[].
*
* Each active thread holds a counted reference on nn->nfsd_serv, as does
* the nn->keep_active flag and various transient calls to svc_get().
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index fbfe6ea737c8..45aa7648dca6 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -32,10 +32,10 @@
*/
struct svc_pool {
unsigned int sp_id; /* pool id; also node id on NUMA */
- spinlock_t sp_lock; /* protects all fields */
+ spinlock_t sp_lock; /* protects sp_sockets */
struct list_head sp_sockets; /* pending sockets */
unsigned int sp_nrthreads; /* # of threads in pool */
- struct list_head sp_all_threads; /* all server threads */
+ struct xarray sp_thread_xa;
/* statistics on pool operation */
struct percpu_counter sp_sockets_queued;
@@ -194,7 +194,6 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);
* processed.
*/
struct svc_rqst {
- struct list_head rq_all; /* all threads list */
struct rcu_head rq_rcu_head; /* for RCU deferred kfree */
struct svc_xprt * rq_xprt; /* transport ptr */
@@ -239,10 +238,10 @@ struct svc_rqst {
#define RQ_SPLICE_OK (4) /* turned off in gss privacy
* to prevent encrypting page
* cache pages */
-#define RQ_VICTIM (5) /* about to be shut down */
-#define RQ_BUSY (6) /* request is busy */
-#define RQ_DATA (7) /* request has data */
+#define RQ_BUSY (5) /* request is busy */
+#define RQ_DATA (6) /* request has data */
unsigned long rq_flags; /* flags field */
+ u32 rq_thread_id; /* xarray index */
ktime_t rq_qtime; /* enqueue time */
void * rq_argp; /* decoded arguments */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 70f3bc22c429..4ec746048f15 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1600,7 +1600,6 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
svc_rqst_flag(USEDEFERRAL) \
svc_rqst_flag(DROPME) \
svc_rqst_flag(SPLICE_OK) \
- svc_rqst_flag(VICTIM) \
svc_rqst_flag(BUSY) \
svc_rqst_flag_end(DATA)
@@ -2043,6 +2042,52 @@ TRACE_EVENT(svc_pool_starved,
)
);
+DECLARE_EVENT_CLASS(svc_thread_lifetime_class,
+ TP_PROTO(
+ const struct svc_serv *serv,
+ const struct svc_pool *pool,
+ const struct svc_rqst *rqstp
+ ),
+
+ TP_ARGS(serv, pool, rqstp),
+
+ TP_STRUCT__entry(
+ __string(name, serv->sv_name)
+ __field(int, pool_id)
+ __field(unsigned int, nrthreads)
+ __field(unsigned long, pool_flags)
+ __field(u32, thread_id)
+ __field(const void *, rqstp)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, serv->sv_name);
+ __entry->pool_id = pool->sp_id;
+ __entry->nrthreads = pool->sp_nrthreads;
+ __entry->pool_flags = pool->sp_flags;
+ __entry->thread_id = rqstp->rq_thread_id;
+ __entry->rqstp = rqstp;
+ ),
+
+ TP_printk("service=%s pool=%d pool_flags=%s nrthreads=%u thread_id=%u",
+ __get_str(name), __entry->pool_id,
+ show_svc_pool_flags(__entry->pool_flags),
+ __entry->nrthreads, __entry->thread_id
+ )
+);
+
+#define DEFINE_SVC_THREAD_LIFETIME_EVENT(name) \
+ DEFINE_EVENT(svc_thread_lifetime_class, svc_pool_##name, \
+ TP_PROTO( \
+ const struct svc_serv *serv, \
+ const struct svc_pool *pool, \
+ const struct svc_rqst *rqstp \
+ ), \
+ TP_ARGS(serv, pool, rqstp))
+
+DEFINE_SVC_THREAD_LIFETIME_EVENT(thread_init);
+DEFINE_SVC_THREAD_LIFETIME_EVENT(thread_exit);
+
DECLARE_EVENT_CLASS(svc_xprt_event,
TP_PROTO(
const struct svc_xprt *xprt
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 828d28883ea8..18fbb98895ea 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -507,8 +507,8 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
pool->sp_id = i;
INIT_LIST_HEAD(&pool->sp_sockets);
- INIT_LIST_HEAD(&pool->sp_all_threads);
spin_lock_init(&pool->sp_lock);
+ xa_init_flags(&pool->sp_thread_xa, XA_FLAGS_ALLOC);
percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
@@ -592,6 +592,8 @@ svc_destroy(struct kref *ref)
percpu_counter_destroy(&pool->sp_threads_woken);
percpu_counter_destroy(&pool->sp_threads_timedout);
percpu_counter_destroy(&pool->sp_threads_starved);
+
+ xa_destroy(&pool->sp_thread_xa);
}
kfree(serv->sv_pools);
kfree(serv);
@@ -672,7 +674,11 @@ EXPORT_SYMBOL_GPL(svc_rqst_alloc);
static struct svc_rqst *
svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
{
+ static const struct xa_limit limit = {
+ .max = UINT_MAX,
+ };
struct svc_rqst *rqstp;
+ int ret;
rqstp = svc_rqst_alloc(serv, pool, node);
if (!rqstp)
@@ -683,11 +689,21 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
serv->sv_nrthreads += 1;
spin_unlock_bh(&serv->sv_lock);
- spin_lock_bh(&pool->sp_lock);
+ xa_lock(&pool->sp_thread_xa);
+ ret = __xa_alloc(&pool->sp_thread_xa, &rqstp->rq_thread_id, rqstp,
+ limit, GFP_KERNEL);
+ if (ret) {
+ xa_unlock(&pool->sp_thread_xa);
+ goto out_free;
+ }
pool->sp_nrthreads++;
- list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
- spin_unlock_bh(&pool->sp_lock);
+ xa_unlock(&pool->sp_thread_xa);
+ trace_svc_pool_thread_init(serv, pool, rqstp);
return rqstp;
+
+out_free:
+ svc_rqst_free(rqstp);
+ return ERR_PTR(ret);
}
/**
@@ -704,19 +720,17 @@ struct svc_rqst *svc_pool_wake_idle_thread(struct svc_serv *serv,
struct svc_pool *pool)
{
struct svc_rqst *rqstp;
+ unsigned long index;
- rcu_read_lock();
- list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+ xa_for_each(&pool->sp_thread_xa, index, rqstp) {
if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
continue;
- rcu_read_unlock();
WRITE_ONCE(rqstp->rq_qtime, ktime_get());
wake_up_process(rqstp->rq_task);
percpu_counter_inc(&pool->sp_threads_woken);
return rqstp;
}
- rcu_read_unlock();
trace_svc_pool_starved(serv, pool);
percpu_counter_inc(&pool->sp_threads_starved);
@@ -732,32 +746,31 @@ svc_pool_next(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
static struct task_struct *
svc_pool_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
- unsigned int i;
struct task_struct *task = NULL;
+ struct svc_rqst *rqstp;
+ unsigned long zero = 0;
+ unsigned int i;
if (pool != NULL) {
- spin_lock_bh(&pool->sp_lock);
+ xa_lock(&pool->sp_thread_xa);
} else {
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
- spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&pool->sp_all_threads))
+ xa_lock(&pool->sp_thread_xa);
+ if (!xa_empty(&pool->sp_thread_xa))
goto found_pool;
- spin_unlock_bh(&pool->sp_lock);
+ xa_unlock(&pool->sp_thread_xa);
}
return NULL;
}
found_pool:
- if (!list_empty(&pool->sp_all_threads)) {
- struct svc_rqst *rqstp;
-
- rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
- set_bit(RQ_VICTIM, &rqstp->rq_flags);
- list_del_rcu(&rqstp->rq_all);
+ rqstp = xa_find(&pool->sp_thread_xa, &zero, U32_MAX, XA_PRESENT);
+ if (rqstp) {
+ __xa_erase(&pool->sp_thread_xa, rqstp->rq_thread_id);
task = rqstp->rq_task;
}
- spin_unlock_bh(&pool->sp_lock);
+ xa_unlock(&pool->sp_thread_xa);
return task;
}
@@ -839,9 +852,9 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
if (pool == NULL) {
nrservs -= serv->sv_nrthreads;
} else {
- spin_lock_bh(&pool->sp_lock);
+ xa_lock(&pool->sp_thread_xa);
nrservs -= pool->sp_nrthreads;
- spin_unlock_bh(&pool->sp_lock);
+ xa_unlock(&pool->sp_thread_xa);
}
if (nrservs > 0)
@@ -928,11 +941,11 @@ svc_exit_thread(struct svc_rqst *rqstp)
struct svc_serv *serv = rqstp->rq_server;
struct svc_pool *pool = rqstp->rq_pool;
- spin_lock_bh(&pool->sp_lock);
+ xa_lock(&pool->sp_thread_xa);
pool->sp_nrthreads--;
- if (!test_and_set_bit(RQ_VICTIM, &rqstp->rq_flags))
- list_del_rcu(&rqstp->rq_all);
- spin_unlock_bh(&pool->sp_lock);
+ __xa_erase(&pool->sp_thread_xa, rqstp->rq_thread_id);
+ xa_unlock(&pool->sp_thread_xa);
+ trace_svc_pool_thread_exit(serv, pool, rqstp);
spin_lock_bh(&serv->sv_lock);
serv->sv_nrthreads -= 1;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 7d5aed4d1766..77fc20b2181d 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -46,7 +46,7 @@ static LIST_HEAD(svc_xprt_class_list);
/* SMP locking strategy:
*
- * svc_pool->sp_lock protects most of the fields of that pool.
+ * svc_pool->sp_lock protects sp_sockets.
* svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
* when both need to be taken (rare), svc_serv->sv_lock is first.
* The "service mutex" protects svc_serv->sv_nrthread.
From: Chuck Lever <[email protected]>
I've noticed that server request latency goes up simply when the
nfsd thread count is increased.
List walking is known to be memory-inefficient. On a busy server
with many threads, enqueuing a transport will walk the "all threads"
list quite frequently. This also pulls in the cache lines for some
hot fields in each svc_rqst.
The svc_xprt_enqueue() call that concerns me most is the one in
svc_rdma_wc_receive(), which is single-threaded per CQ. Slowing
down completion handling will limit the total throughput per
RDMA connection.
So, avoid walking the "all threads" list to find an idle thread to
wake. Instead, set up an idle bitmap and use find_next_bit, which
should work the same way as RQ_BUSY but it will touch only the
cacheline that the bitmap is in. I think we can stick with atomic
bit operations here to avoid taking the pool lock.
The server can keep track of up to 64 threads in just one unsigned
long, and the bitmap can be multiple words long to handle even more
threads.
Signed-off-by: Chuck Lever <[email protected]>
---
include/linux/sunrpc/svc.h | 6 ++++--
include/trace/events/sunrpc.h | 1 -
net/sunrpc/svc.c | 38 ++++++++++++++++++++++++++------------
net/sunrpc/svc_xprt.c | 23 +++++++++++++++++++----
4 files changed, 49 insertions(+), 19 deletions(-)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 45aa7648dca6..ffa58a7a689d 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -35,6 +35,7 @@ struct svc_pool {
spinlock_t sp_lock; /* protects sp_sockets */
struct list_head sp_sockets; /* pending sockets */
unsigned int sp_nrthreads; /* # of threads in pool */
+ unsigned long *sp_idle_map; /* idle threads */
struct xarray sp_thread_xa;
/* statistics on pool operation */
@@ -189,6 +190,8 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);
#define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \
+ 2 + 1)
+#define RPCSVC_MAXPOOLTHREADS (256)
+
/*
* The context of a single thread, including the request currently being
* processed.
@@ -238,8 +241,7 @@ struct svc_rqst {
#define RQ_SPLICE_OK (4) /* turned off in gss privacy
* to prevent encrypting page
* cache pages */
-#define RQ_BUSY (5) /* request is busy */
-#define RQ_DATA (6) /* request has data */
+#define RQ_DATA (5) /* request has data */
unsigned long rq_flags; /* flags field */
u32 rq_thread_id; /* xarray index */
ktime_t rq_qtime; /* enqueue time */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 4ec746048f15..f64c255975ab 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1600,7 +1600,6 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
svc_rqst_flag(USEDEFERRAL) \
svc_rqst_flag(DROPME) \
svc_rqst_flag(SPLICE_OK) \
- svc_rqst_flag(BUSY) \
svc_rqst_flag_end(DATA)
#undef svc_rqst_flag
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 18fbb98895ea..c2cba61a890c 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -509,6 +509,12 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
INIT_LIST_HEAD(&pool->sp_sockets);
spin_lock_init(&pool->sp_lock);
xa_init_flags(&pool->sp_thread_xa, XA_FLAGS_ALLOC);
+ /* All threads initially marked "busy" */
+ pool->sp_idle_map =
+ bitmap_zalloc_node(RPCSVC_MAXPOOLTHREADS, GFP_KERNEL,
+ svc_pool_map_get_node(i));
+ if (!pool->sp_idle_map)
+ return NULL;
percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
@@ -594,6 +600,8 @@ svc_destroy(struct kref *ref)
percpu_counter_destroy(&pool->sp_threads_starved);
xa_destroy(&pool->sp_thread_xa);
+ bitmap_free(pool->sp_idle_map);
+ pool->sp_idle_map = NULL;
}
kfree(serv->sv_pools);
kfree(serv);
@@ -645,7 +653,6 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
folio_batch_init(&rqstp->rq_fbatch);
- __set_bit(RQ_BUSY, &rqstp->rq_flags);
rqstp->rq_server = serv;
rqstp->rq_pool = pool;
@@ -675,7 +682,7 @@ static struct svc_rqst *
svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
{
static const struct xa_limit limit = {
- .max = UINT_MAX,
+ .max = RPCSVC_MAXPOOLTHREADS,
};
struct svc_rqst *rqstp;
int ret;
@@ -720,18 +727,24 @@ struct svc_rqst *svc_pool_wake_idle_thread(struct svc_serv *serv,
struct svc_pool *pool)
{
struct svc_rqst *rqstp;
- unsigned long index;
+ unsigned long bit;
- xa_for_each(&pool->sp_thread_xa, index, rqstp) {
- if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
- continue;
+ bit = 0;
+ do {
+ bit = find_next_bit(pool->sp_idle_map, pool->sp_nrthreads, bit);
+ if (bit == pool->sp_nrthreads)
+ goto out_starved;
+ } while (!test_and_clear_bit(bit, pool->sp_idle_map));
- WRITE_ONCE(rqstp->rq_qtime, ktime_get());
- wake_up_process(rqstp->rq_task);
- percpu_counter_inc(&pool->sp_threads_woken);
- return rqstp;
- }
+ rqstp = xa_find(&pool->sp_thread_xa, &bit, bit, XA_PRESENT);
+ if (!rqstp)
+ goto out_starved;
+ WRITE_ONCE(rqstp->rq_qtime, ktime_get());
+ wake_up_process(rqstp->rq_task);
+ percpu_counter_inc(&pool->sp_threads_woken);
+ return rqstp;
+out_starved:
trace_svc_pool_starved(serv, pool);
percpu_counter_inc(&pool->sp_threads_starved);
return NULL;
@@ -765,7 +778,8 @@ svc_pool_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *stat
}
found_pool:
- rqstp = xa_find(&pool->sp_thread_xa, &zero, U32_MAX, XA_PRESENT);
+ rqstp = xa_find(&pool->sp_thread_xa, &zero, RPCSVC_MAXPOOLTHREADS,
+ XA_PRESENT);
if (rqstp) {
__xa_erase(&pool->sp_thread_xa, rqstp->rq_thread_id);
task = rqstp->rq_task;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 77fc20b2181d..e22f1432aabb 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -734,6 +734,18 @@ rqst_should_sleep(struct svc_rqst *rqstp)
return true;
}
+static void svc_rqst_mark_idle(struct svc_rqst *rqstp)
+{
+ set_bit(rqstp->rq_thread_id, rqstp->rq_pool->sp_idle_map);
+ smp_mb__after_atomic();
+}
+
+static void svc_rqst_mark_busy(struct svc_rqst *rqstp)
+{
+ clear_bit(rqstp->rq_thread_id, rqstp->rq_pool->sp_idle_map);
+ smp_mb__after_atomic();
+}
+
static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
{
struct svc_pool *pool = rqstp->rq_pool;
@@ -755,8 +767,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
set_current_state(TASK_INTERRUPTIBLE);
smp_mb__before_atomic();
clear_bit(SP_CONGESTED, &pool->sp_flags);
- clear_bit(RQ_BUSY, &rqstp->rq_flags);
- smp_mb__after_atomic();
+ svc_rqst_mark_idle(rqstp);
if (likely(rqst_should_sleep(rqstp)))
time_left = schedule_timeout(timeout);
@@ -765,8 +776,12 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
try_to_freeze();
- set_bit(RQ_BUSY, &rqstp->rq_flags);
- smp_mb__after_atomic();
+ /* Post-sleep: look for more work.
+ *
+ * Note: If we were awoken, then this rqstp has already
+ * been marked busy.
+ */
+ svc_rqst_mark_busy(rqstp);
rqstp->rq_xprt = svc_xprt_dequeue(pool);
if (rqstp->rq_xprt) {
trace_svc_pool_awoken(pool, rqstp);
From: Chuck Lever <[email protected]>
Consumers of sp_lock now all run in process context.
Signed-off-by: Chuck Lever <[email protected]>
---
net/sunrpc/svc_xprt.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index e22f1432aabb..6a56cd202148 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -472,9 +472,9 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
pool = svc_pool_for_cpu(xprt->xpt_server);
percpu_counter_inc(&pool->sp_sockets_queued);
- spin_lock_bh(&pool->sp_lock);
+ spin_lock(&pool->sp_lock);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
- spin_unlock_bh(&pool->sp_lock);
+ spin_unlock(&pool->sp_lock);
rqstp = svc_pool_wake_idle_thread(xprt->xpt_server, pool);
if (!rqstp) {
@@ -496,14 +496,14 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
if (list_empty(&pool->sp_sockets))
goto out;
- spin_lock_bh(&pool->sp_lock);
+ spin_lock(&pool->sp_lock);
if (likely(!list_empty(&pool->sp_sockets))) {
xprt = list_first_entry(&pool->sp_sockets,
struct svc_xprt, xpt_ready);
list_del_init(&xprt->xpt_ready);
svc_xprt_get(xprt);
}
- spin_unlock_bh(&pool->sp_lock);
+ spin_unlock(&pool->sp_lock);
out:
return xprt;
}
@@ -1129,15 +1129,15 @@ static struct svc_xprt *svc_dequeue_net(struct svc_serv *serv, struct net *net)
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[i];
- spin_lock_bh(&pool->sp_lock);
+ spin_lock(&pool->sp_lock);
list_for_each_entry_safe(xprt, tmp, &pool->sp_sockets, xpt_ready) {
if (xprt->xpt_net != net)
continue;
list_del_init(&xprt->xpt_ready);
- spin_unlock_bh(&pool->sp_lock);
+ spin_unlock(&pool->sp_lock);
return xprt;
}
- spin_unlock_bh(&pool->sp_lock);
+ spin_unlock(&pool->sp_lock);
}
return NULL;
}
On Fri, 30 Jun 2023, Chuck Lever wrote:
> Hi -
>
> Walking a linked list to find an idle thread is not CPU cache-
> friendly, and in fact I've noted palpable per-request latency
> impacts as the number of nfsd threads on the server increases.
>
> After discussing some possible improvements with Jeff at LSF/MM,
> I've been experimenting with the following series. I've measured an
> order of magnitude latency improvement in the thread lookup time,
> and have managed to keep the whole thing lockless.
>
> The only thing I don't like is that allocating the idle bitmaps in
> advance means we've got an /a priori/ cap on the number of NFSD
> threads that can be created. I'd love to find a way to enable
> the pool idle bitmaps to expand dynamically. Suggestions welcome.
Hi Chuck,
The series looks good. I did notice that patch 6/8 used UINT_MAX and
U32_MAX in different places for the same number, though the next patch
replaced them both for a new number - the same in both places now.
I agree that an a priori cap on number of threads is not ideal.
Have you considered using the xarray to only store busy threads?
I think its lookup mechanism mostly relies on a bitmap of present
entries, but I'm not completely sure.
That would require some extra work for svc_stop_threads() which is the
only place we are interested in threads that aren't busy. We would
need to record a target number of threads, and whenever a thread
becomes idle it checks if the number is exceeded. If so it exits
decrementing the number of threads, other wise it re-inserts into the
xa (if it cannot find a transport to handle).
Alternately we could store bitmaps as values in an xarray, much like
the ida code does.
Thanks,
NeilBrown
On Fri, 30 Jun 2023, NeilBrown wrote:
>
> I agree that an a priori cap on number of threads is not ideal.
> Have you considered using the xarray to only store busy threads?
> I think its lookup mechanism mostly relies on a bitmap of present
> entries, but I'm not completely sure.
It might be event better to use xa_set_mark() and xa_clear_mark() to
manage the busy state.
These are not atomic so you would need an atomic operation in the rqst.
#define XA_MARK_IDLE XA_MARK_1
do {
rqstp = xa_find(xa, ..., XA_MARK_IDLE);
if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) {
xa_clear_mark(xa, rqstp->xa_index, XA_MARK_IDLE);
break;
}
} while {rqstp);
xa_find() should be nearly as fast at find_next_bit()
NeilBrown
> On Jun 29, 2023, at 11:04 PM, NeilBrown <[email protected]> wrote:
>
> On Fri, 30 Jun 2023, NeilBrown wrote:
>>
>> I agree that an a priori cap on number of threads is not ideal.
>> Have you considered using the xarray to only store busy threads?
>> I think its lookup mechanism mostly relies on a bitmap of present
>> entries, but I'm not completely sure.
>
> It might be event better to use xa_set_mark() and xa_clear_mark() to
> manage the busy state.
> These are not atomic so you would need an atomic operation in the rqst.
>
> #define XA_MARK_IDLE XA_MARK_1
>
> do {
> rqstp = xa_find(xa, ..., XA_MARK_IDLE);
> if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) {
> xa_clear_mark(xa, rqstp->xa_index, XA_MARK_IDLE);
> break;
> }
> } while {rqstp);
>
> xa_find() should be nearly as fast at find_next_bit()
Yes, xa_find() is fast, and takes only the RCU read lock. Unfortunately,
xa_clear_mark and xa_set_mark (and adding and removing items) require
taking the xa_lock().
The current list-based mechanism is lockless, and so is the replacement
I've proposed. Jeff and I regarded the addition of a spin lock in the
select-an-idle-thread-and-wake-it-up function as something we want to
avoid.
Thus the pool's idle bitmap enables the use of atomic bit testing,
setting, and clearing to make it unnecessary to hold a spin lock while
selecting and marking the chosen thread. After selection, only the RCU
read lock is needed to safely map that bit position to an svc_rqst
pointer.
We might be able to use another sp_flags bit to cause thread selection
to sleep, if we also protect the thread selection process with the RCU
read lock. Flip the bit on, wait one RCU grace period, and it should be
safe to copy and replace the idle bitmap. Once bitmap replacement is
complete, clear the bit and wake up any threads waiting to find an idle
worker.
The balancing act is whether we want to add that kind of cleverness to
handle a situation that will be relatively rare. Is it sensible to
allow more than a few thousand RPC service threads in a pool?
--
Chuck Lever
On Thu, 2023-06-29 at 14:42 -0400, Chuck Lever wrote:
> From: Chuck Lever <[email protected]>
>
> Refactor: Extract the loop that finds an idle service thread from
> svc_xprt_enqueue() and svc_wake_up().
>
> Signed-off-by: Chuck Lever <[email protected]>
> ---
> include/linux/sunrpc/svc.h | 1 +
> net/sunrpc/svc.c | 28 +++++++++++++++++++++++++++
> net/sunrpc/svc_xprt.c | 46 +++++++++++++-------------------------------
> 3 files changed, 43 insertions(+), 32 deletions(-)
>
> diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
> index f8751118c122..dc2d90a655e2 100644
> --- a/include/linux/sunrpc/svc.h
> +++ b/include/linux/sunrpc/svc.h
> @@ -427,6 +427,7 @@ int svc_register(const struct svc_serv *, struct net *, const int,
>
> void svc_wake_up(struct svc_serv *);
> void svc_reserve(struct svc_rqst *rqstp, int space);
> +struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool);
> struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv);
> char * svc_print_addr(struct svc_rqst *, char *, size_t);
> const char * svc_proc_name(const struct svc_rqst *rqstp);
> diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
> index 587811a002c9..e81ce5f76abd 100644
> --- a/net/sunrpc/svc.c
> +++ b/net/sunrpc/svc.c
> @@ -689,6 +689,34 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
> return rqstp;
> }
>
> +/**
> + * svc_pool_wake_idle_thread - wake an idle thread in @pool
> + * @pool: service thread pool
> + *
> + * Returns an idle service thread (now marked BUSY), or NULL
> + * if no service threads are available. Finding an idle service
> + * thread and marking it BUSY is atomic with respect to other
> + * calls to svc_pool_wake_idle_thread().
> + */
> +struct svc_rqst *svc_pool_wake_idle_thread(struct svc_pool *pool)
> +{
> + struct svc_rqst *rqstp;
> +
> + rcu_read_lock();
> + list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
> + if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
> + continue;
> +
> + rcu_read_unlock();
> + WRITE_ONCE(rqstp->rq_qtime, ktime_get());
> + wake_up_process(rqstp->rq_task);
> + percpu_counter_inc(&pool->sp_threads_woken);
> + return rqstp;
> + }
> + rcu_read_unlock();
> + return NULL;
> +}
> +
> /*
> * Choose a pool in which to create a new thread, for svc_set_num_threads
> */
> diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
> index 62c7919ea610..f14476d11b67 100644
> --- a/net/sunrpc/svc_xprt.c
> +++ b/net/sunrpc/svc_xprt.c
> @@ -455,8 +455,8 @@ static bool svc_xprt_ready(struct svc_xprt *xprt)
> */
> void svc_xprt_enqueue(struct svc_xprt *xprt)
> {
> + struct svc_rqst *rqstp;
> struct svc_pool *pool;
> - struct svc_rqst *rqstp = NULL;
>
> if (!svc_xprt_ready(xprt))
> return;
> @@ -476,20 +476,10 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
> list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
> spin_unlock_bh(&pool->sp_lock);
>
> - /* find a thread for this xprt */
> - rcu_read_lock();
> - list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
> - if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags))
> - continue;
> - percpu_counter_inc(&pool->sp_threads_woken);
> - rqstp->rq_qtime = ktime_get();
> - wake_up_process(rqstp->rq_task);
> - goto out_unlock;
> - }
> - set_bit(SP_CONGESTED, &pool->sp_flags);
> - rqstp = NULL;
> -out_unlock:
> - rcu_read_unlock();
> + rqstp = svc_pool_wake_idle_thread(pool);
> + if (!rqstp)
> + set_bit(SP_CONGESTED, &pool->sp_flags);
> +
> trace_svc_xprt_enqueue(xprt, rqstp);
> }
> EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
> @@ -581,7 +571,10 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
> svc_xprt_put(xprt);
> }
>
> -/*
> +/**
> + * svc_wake_up - Wake up a service thread for non-transport work
> + * @serv: RPC service
> + *
> * Some svc_serv's will have occasional work to do, even when a xprt is not
> * waiting to be serviced. This function is there to "kick" a task in one of
> * those services so that it can wake up and do that work. Note that we only
> @@ -590,27 +583,16 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
> */
> void svc_wake_up(struct svc_serv *serv)
> {
> + struct svc_pool *pool = &serv->sv_pools[0];
> struct svc_rqst *rqstp;
> - struct svc_pool *pool;
>
> - pool = &serv->sv_pools[0];
> -
> - rcu_read_lock();
> - list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
> - /* skip any that aren't queued */
> - if (test_bit(RQ_BUSY, &rqstp->rq_flags))
> - continue;
> - rcu_read_unlock();
> - wake_up_process(rqstp->rq_task);
> - trace_svc_wake_up(rqstp->rq_task->pid);
> + rqstp = svc_pool_wake_idle_thread(pool);
> + if (!rqstp) {
> + set_bit(SP_TASK_PENDING, &pool->sp_flags);
nit: it might be good to add this here, for better conformance with the
old tracepoint behavior:
trace_svc_wake_up(0);
> return;
> }
> - rcu_read_unlock();
>
> - /* No free entries available */
> - set_bit(SP_TASK_PENDING, &pool->sp_flags);
> - smp_wmb();
I assume this wmb was for the set_bit above? Do we need that in the
!rqstp case?
> - trace_svc_wake_up(0);
> + trace_svc_wake_up(rqstp->rq_task->pid);
> }
> EXPORT_SYMBOL_GPL(svc_wake_up);
>