diff --git a/src/fastlock.cpp b/src/fastlock.cpp
index f265f3908..1a8d51165 100644
--- a/src/fastlock.cpp
+++ b/src/fastlock.cpp
@@ -43,6 +43,13 @@
  ****************************************************/
 
 static_assert(sizeof(pid_t) <= sizeof(fastlock::m_pidOwner), "fastlock::m_pidOwner not large enough");
+uint64_t g_longwaits = 0;
+
+uint64_t fastlock_getlongwaitcount()
+{
+    return g_longwaits;
+}
+
 
 extern "C" pid_t gettid()
 {
@@ -75,7 +82,10 @@ extern "C" void fastlock_lock(struct fastlock *lock)
     while (__atomic_load_2(&lock->m_ticket.m_active, __ATOMIC_ACQUIRE) != myticket)
     {
         if ((++cloops % 1024*1024) == 0)
+        {
             sched_yield();
+            ++g_longwaits;
+        }
 #if defined(__i386__) || defined(__amd64__)
         __asm__ ("pause");
 #endif
diff --git a/src/fastlock.h b/src/fastlock.h
index b5a70c530..b8027de54 100644
--- a/src/fastlock.h
+++ b/src/fastlock.h
@@ -13,6 +13,8 @@ int fastlock_trylock(struct fastlock *lock);
 void fastlock_unlock(struct fastlock *lock);
 void fastlock_free(struct fastlock *lock);
 
+uint64_t fastlock_getlongwaitcount();   // this is a global value
+
 /* End C API */
 #ifdef __cplusplus
 }
diff --git a/src/fastlock_x64.asm b/src/fastlock_x64.asm
index 1b876350f..7645d3baa 100644
--- a/src/fastlock_x64.asm
+++ b/src/fastlock_x64.asm
@@ -2,6 +2,7 @@ section .text
 
 extern gettid
 extern sched_yield
+extern g_longwaits
 
 ;	This is the first use of assembly in this codebase, a valid question is WHY?
 ;	The spinlock we implement here is performance critical, and simply put GCC
@@ -49,6 +50,8 @@ ALIGN 16
 	syscall                 ; give up our timeslice we'll be here a while
 	pop rax
 	pop rsi
+	mov rcx, g_longwaits
+	inc qword [rcx]         ; increment our long wait counter
 	mov rdi, [rsp]          ; our struct pointer is on the stack already
 	xor ecx, ecx            ; Reset our loop counter
 	jmp .LLoop              ; Get back in the game
diff --git a/src/networking.cpp b/src/networking.cpp
index 4a6794d98..b4f14f238 100644
--- a/src/networking.cpp
+++ b/src/networking.cpp
@@ -138,6 +138,7 @@ void linkClient(client *c) {
      * this way removing the client in unlinkClient() will not require
      * a linear scan, but just a constant time operation. */
     c->client_list_node = listLast(server.clients);
+    if (c->fd != -1) atomicIncr(server.rgthreadvar[c->iel].cclients, 1);
     uint64_t id = htonu64(c->id);
     raxInsert(server.clients_index,(unsigned char*)&id,sizeof(id),c,NULL);
 }
@@ -1208,6 +1209,8 @@ void unlinkClient(client *c) {
         aeDeleteFileEvent(server.rgthreadvar[c->iel].el,c->fd,AE_WRITABLE);
         close(c->fd);
         c->fd = -1;
+
+        atomicDecr(server.rgthreadvar[c->iel].cclients, 1);
     }
 
     /* Remove from the list of pending writes if needed. */
diff --git a/src/server.cpp b/src/server.cpp
index 8707b07f5..72a589c73 100644
--- a/src/server.cpp
+++ b/src/server.cpp
@@ -2815,6 +2815,7 @@ static void initServerThread(struct redisServerThreadVars *pvar, int fMain)
     pvar->unblocked_clients = listCreate();
     pvar->clients_pending_asyncwrite = listCreate();
     pvar->ipfd_count = 0;
+    pvar->cclients = 0;
     pvar->el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);
     if (pvar->el == NULL) {
         serverLog(LL_WARNING,
@@ -3997,6 +3998,12 @@ extern "C" sds genRedisInfoString(const char *section) {
             listLength(server.clients)-listLength(server.slaves),
             maxin, maxout,
             server.blocked_clients);
+        for (int ithread = 0; ithread < server.cthreads; ++ithread)
+        {
+            info = sdscatprintf(info,
+                "thread_%d_clients:%d\r\n",
+                ithread, server.rgthreadvar[ithread].cclients);
+        }
     }
 
     /* Memory */
@@ -4401,11 +4408,15 @@ extern "C" sds genRedisInfoString(const char *section) {
         "used_cpu_sys:%ld.%06ld\r\n"
         "used_cpu_user:%ld.%06ld\r\n"
         "used_cpu_sys_children:%ld.%06ld\r\n"
-        "used_cpu_user_children:%ld.%06ld\r\n",
+        "used_cpu_user_children:%ld.%06ld\r\n"
+        "server_threads:%d\r\n"
+        "long_lock_waits:%" PRIu64 "\r\n",
         (long)self_ru.ru_stime.tv_sec, (long)self_ru.ru_stime.tv_usec,
         (long)self_ru.ru_utime.tv_sec, (long)self_ru.ru_utime.tv_usec,
         (long)c_ru.ru_stime.tv_sec, (long)c_ru.ru_stime.tv_usec,
-        (long)c_ru.ru_utime.tv_sec, (long)c_ru.ru_utime.tv_usec);
+        (long)c_ru.ru_utime.tv_sec, (long)c_ru.ru_utime.tv_usec,
+        server.cthreads,
+        fastlock_getlongwaitcount());
     }
 
     /* Command statistics */
diff --git a/src/server.h b/src/server.h
index 3fa5f90a3..3417d9696 100644
--- a/src/server.h
+++ b/src/server.h
@@ -1053,6 +1053,7 @@ struct redisServerThreadVars {
     list *clients_pending_write; /* There is to write or install handler. */
     list *unblocked_clients;     /* list of clients to unblock before next loop NOT THREADSAFE */
     list *clients_pending_asyncwrite;
+    int cclients;
     struct fastlock lockPendingWrite;
 };