[PATCH -mm 1/3] sysv ipc: increase msgmnb default value wrt. the number of cpus

[<Solofo.Ramangalahy@bull.net>]

[-- Attachment #1: ipc-scale-msgmnb-with-the-number-of-cpus.patch --]
[-- Type: text/plain, Size: 5447 bytes --]

From: Solofo Ramangalahy <Solofo.Ramangalahy@bull.net>

Initialize msgmnb value to
min(MSGMNB * num_online_cpus(), MSGMNB * MSG_CPU_SCALE)
to increase the default value for larger machines.

MSG_CPU_SCALE scaling factor is defined to be 4, as 16384 x 4 = 65536
is an already used and recommended value.

The msgmni value is made dependant of msgmnb to keep the memory
dedicated to message queues within the 1/MSG_MEM_SCALE of lowmem
bound.

Unlike msgmni, the value is not scaled (down) with respect to the
number of ipc namespaces for simplicity.

To disable recomputation when user explicitely set a value,
we reuse the callback defined for msgmni.

As msgmni and msgmnb are correlated, user settings of any of the two
disable recomputation of both, for now. This is refined in a later
patch.

When a negative value is put in /proc/sys/kernel/msgmnb
automatic recomputing is re-enabled.


Signed-off-by: Solofo Ramangalahy <Solofo.Ramangalahy@bull.net>

---
 Documentation/sysctl/kernel.txt |   28 ++++++++++++++++++++++++++++
 include/linux/msg.h             |    6 ++++++
 ipc/ipc_sysctl.c                |    5 +++--
 ipc/msg.c                       |   17 +++++++++++++----
 4 files changed, 50 insertions(+), 6 deletions(-)

Index: b/ipc/msg.c
===================================================================
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -38,6 +38,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/cpumask.h>
 
 #include <asm/current.h>
 #include <asm/uaccess.h>
@@ -92,7 +93,7 @@ void recompute_msgmni(struct ipc_namespa
 
 	si_meminfo(&i);
 	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
-		/ MSGMNB;
+		/ ns->msg_ctlmnb;
 	nb_ns = atomic_read(&nr_ipc_ns);
 	allowed /= nb_ns;
 
@@ -108,11 +109,19 @@ void recompute_msgmni(struct ipc_namespa
 
 	ns->msg_ctlmni = allowed;
 }
+/*
+ * Scale msgmnb with the number of online cpus, up to 4x MSGMNB.
+ */
+void recompute_msgmnb(struct ipc_namespace *ns)
+{
+	ns->msg_ctlmnb =
+		min(MSGMNB * num_online_cpus(), MSGMNB * MSG_CPU_SCALE);
+}
 
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
-	ns->msg_ctlmnb = MSGMNB;
+	recompute_msgmnb(ns);
 
 	recompute_msgmni(ns);
 
@@ -132,8 +141,8 @@ void __init msg_init(void)
 {
 	msg_init_ns(&init_ipc_ns);
 
-	printk(KERN_INFO "msgmni has been set to %d\n",
-		init_ipc_ns.msg_ctlmni);
+	printk(KERN_INFO "msgmni has been set to %d, msgmnb to %d\n",
+	       init_ipc_ns.msg_ctlmni, init_ipc_ns.msg_ctlmnb);
 
 	ipc_init_proc_interface("sysvipc/msg",
 				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
Index: b/include/linux/msg.h
===================================================================
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -58,6 +58,12 @@ struct msginfo {
  * more than 16 GB : msgmni = 32K (IPCMNI)
  */
 #define MSG_MEM_SCALE 32
+/*
+ * Scaling factor to compute msgmnb: ns->msg_ctlmnb is between MSGMNB
+ * and MSGMNB * MSG_CPU_SCALE. This leads to a max msgmnb value of
+ * 65536 which is an already used and recommended value.
+ */
+#define MSG_CPU_SCALE 4
 
 #define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
Index: b/ipc/ipc_sysctl.c
===================================================================
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -42,6 +42,7 @@ static void tunable_set_callback(int val
 		 * Re-enable automatic recomputing only if not already
 		 * enabled.
 		 */
+		recompute_msgmnb(current->nsproxy->ipc_ns);
 		recompute_msgmni(current->nsproxy->ipc_ns);
 		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
 	}
@@ -210,8 +211,8 @@ static struct ctl_table ipc_kern_table[]
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof (init_ipc_ns.msg_ctlmnb),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
+		.proc_handler	= proc_ipc_callback_dointvec,
+		.strategy	= sysctl_ipc_registered_data,
 	},
 	{
 		.ctl_name	= KERN_SEM,
Index: b/Documentation/sysctl/kernel.txt
===================================================================
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -179,6 +179,34 @@ kernel stack.
 
 ==============================================================
 
+msgmnb
+
+Maximum size in bytes (not in message count) of a single SystemV IPC
+message queue (b stands for bytes).
+
+This value is dynamic and depends on the online cpu count of the
+machine (taking cpu hotplug into account).
+
+Computed values are between MSGMNB and MSGMNB*MSG_CPU_SCALE #define
+constants (currently [16384,65536]).
+
+The exact value is automatically (re)computed, but:
+. If the value is positioned from user space (via procfs or sysctl()),
+  to a positive value then the automatic recomputation is
+  disabled. This leaves control to user space. E.g.
+
+  # echo 16384 > /proc/sys/kernel/msgmnb
+
+. If the value is positioned from user space to a negative value, then
+  the computation is reenabled. E.g.
+
+  # echo -1 > /proc/sys/kernel/msgmnb
+
+See recompute_msgmnb() function in ipc/ directory for details.
+The value of msgmnb is coupled with the value of msgmni.
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease

--