[PATCH -mm v2 1/3] sysv ipc: increase msgmnb default value wrt. thenumber of cpus

[Solofo.Ramangalahy]

From: Solofo Ramangalahy <Solofo.Ramangalahy@xxxxxxxx>

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@xxxxxxxx>

---
 include/linux/msg.h |    7 +++++++
 ipc/ipc_sysctl.c    |    5 +++--
 ipc/msg.c           |   22 ++++++++++++++++++----
 ipc/util.h          |    1 +
 4 files changed, 29 insertions(+), 6 deletions(-)

Index: linux-2.6.26-rc8-mm1-MSGMNB3/ipc/msg.c
===================================================================
--- linux-2.6.26-rc8-mm1-MSGMNB3.orig/ipc/msg.c
+++ linux-2.6.26-rc8-mm1-MSGMNB3/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 +109,24 @@ void recompute_msgmni(struct ipc_namespa
 
 	ns->msg_ctlmni = allowed;
 }
+/*
+ * Scale msgmnb with the number of online cpus, up to 4x MSGMNB.  For
+ * simplicity, it is not adjusted wrt. ipc namespaces.  This is done
+ * indirectly by msgmni for the whole message pool.  Zero-sized
+ * messages can be enqueued up to msgmnb consuming memory.  If this
+ * becomes a problem, this function can be updated with a constraint
+ * on low memory like in recompute_msgmni().
+ */
+void ipc_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;
+	ipc_recompute_msgmnb(ns);
 
 	recompute_msgmni(ns);
 
@@ -132,8 +146,8 @@ 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: linux-2.6.26-rc8-mm1-MSGMNB3/include/linux/msg.h
===================================================================
--- linux-2.6.26-rc8-mm1-MSGMNB3.orig/include/linux/msg.h
+++ linux-2.6.26-rc8-mm1-MSGMNB3/include/linux/msg.h
@@ -58,6 +58,13 @@ 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.
+ * Note that zero-sized messages can be enqueued up to this max 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: linux-2.6.26-rc8-mm1-MSGMNB3/ipc/ipc_sysctl.c
===================================================================
--- linux-2.6.26-rc8-mm1-MSGMNB3.orig/ipc/ipc_sysctl.c
+++ linux-2.6.26-rc8-mm1-MSGMNB3/ipc/ipc_sysctl.c
@@ -44,6 +44,7 @@ static void ipc_auto_callback(int val)
 		 * Re-enable automatic recomputing only if not already
 		 * enabled.
 		 */
+		ipc_recompute_msgmnb(current->nsproxy->ipc_ns);
 		recompute_msgmni(current->nsproxy->ipc_ns);
 		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
 	}
@@ -246,8 +247,8 @@ 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: linux-2.6.26-rc8-mm1-MSGMNB3/ipc/util.h
===================================================================
--- linux-2.6.26-rc8-mm1-MSGMNB3.orig/ipc/util.h
+++ linux-2.6.26-rc8-mm1-MSGMNB3/ipc/util.h
@@ -122,6 +122,7 @@ extern struct msg_msg *load_msg(const vo
 extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
 
 extern void recompute_msgmni(struct ipc_namespace *);
+extern void ipc_recompute_msgmnb(struct ipc_namespace *);
 
 static inline int ipc_buildid(int id, int seq)
 {

-- 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/