diff options
authorNadia Derbey <>2008-04-29 01:00:39 -0700
committerLinus Torvalds <>2008-04-29 08:06:12 -0700
commitf7bf3df8be72d98afa84f5ff183e14c1ba1e560d (patch)
parent48dea404ed01869313f1908cca8a15774dcd8ee5 (diff)
ipc: scale msgmni to the amount of lowmem
On large systems we'd like to allow a larger number of message queues. In some cases up to 32K. However simply setting MSGMNI to a larger value may cause problems for smaller systems. The first patch of this series introduces a default maximum number of message queue ids that scales with the amount of lowmem. Since msgmni is per namespace and there is no amount of memory dedicated to each namespace so far, the second patch of this series scales msgmni to the number of ipc namespaces too. Since msgmni depends on the amount of memory, it becomes necessary to recompute it upon memory add/remove. In the 4th patch, memory hotplug management is added: a notifier block is registered into the memory hotplug notifier chain for the ipc subsystem. Since the ipc namespaces are not linked together, they have their own notification chain: one notifier_block is defined per ipc namespace. Each time an ipc namespace is created (removed) it registers (unregisters) its notifier block in (from) the ipcns chain. The callback routine registered in the memory chain invokes the ipcns notifier chain with the IPCNS_MEMCHANGE event. Each callback routine registered in the ipcns namespace, in turn, recomputes msgmni for the owning namespace. The 5th patch makes it possible to keep the memory hotplug notifier chain's lock for a lesser amount of time: instead of directly notifying the ipcns notifier chain upon memory add/remove, a work item is added to the global workqueue. When activated, this work item is the one who notifies the ipcns notifier chain. Since msgmni depends on the number of ipc namespaces, it becomes necessary to recompute it upon ipc namespace creation / removal. The 6th patch uses the ipc namespace notifier chain for that purpose: that chain is notified each time an ipc namespace is created or removed. This makes it possible to recompute msgmni for all the namespaces each time one of them is created or removed. When msgmni is explicitely set from userspace, we should avoid recomputing it upon memory add/remove or ipcns creation/removal. This is what the 7th patch does: it simply unregisters the ipcns callback routine as soon as msgmni has been changed from procfs or sysctl(). Even if msgmni is set by hand, it should be possible to make it back automatically recomputed upon memory add/remove or ipcns creation/removal. This what is achieved in patch 8: if set to a negative value, msgmni is added back to the ipcns notifier chain, making it automatically recomputed again. This patch: Compute msg_ctlmni to make it scale with the amount of lowmem. msg_ctlmni is now set to make the message queues occupy 1/32 of the available lowmem. Some cleaning has also been done for the MSGPOOL constant: the msgctl man page says it's not used, but it also defines it as a size in bytes (the code expresses it in Kbytes). Signed-off-by: Nadia Derbey <> Cc: Yasunori Goto <> Cc: Matt Helsley <> Cc: Mingming Cao <> Cc: Pierre Peiffer <> Signed-off-by: Andrew Morton <> Signed-off-by: Linus Torvalds <>
2 files changed, 48 insertions, 3 deletions
diff --git a/include/linux/msg.h b/include/linux/msg.h
index 10a3d5a1abff..6f3b8e79a991 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -49,16 +49,26 @@ struct msginfo {
unsigned short msgseg;
+ * Scaling factor to compute msgmni:
+ * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
+ * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
+ * up to 8MB : msgmni = 16 (MSGMNI)
+ * 4 GB : msgmni = 8K
+ * more than 16 GB : msgmni = 32K (IPCMNI)
+ */
+#define MSG_MEM_SCALE 32
#define MSGMNI 16 /* <= IPCMNI */ /* max # of msg queue identifiers */
#define MSGMAX 8192 /* <= INT_MAX */ /* max size of message (bytes) */
#define MSGMNB 16384 /* <= INT_MAX */ /* default max size of a message queue */
/* unused */
-#define MSGPOOL (MSGMNI*MSGMNB/1024) /* size in kilobytes of message pool */
+#define MSGPOOL (MSGMNI * MSGMNB) /* size in bytes of message pool */
#define MSGTQL MSGMNB /* number of system message headers */
#define MSGMAP MSGMNB /* number of entries in message map */
#define MSGSSZ 16 /* message segment size */
-#define __MSGSEG ((MSGPOOL*1024)/ MSGSSZ) /* max no. of segments */
+#define __MSGSEG (MSGPOOL / MSGSSZ) /* max no. of segments */
#define MSGSEG (__MSGSEG <= 0xffff ? __MSGSEG : 0xffff)
#ifdef __KERNEL__
diff --git a/ipc/msg.c b/ipc/msg.c
index 805ee08ec8bb..9e7211122e27 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -27,6 +27,7 @@
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
+#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/list.h>
#include <linux/security.h>
@@ -77,11 +78,45 @@ static int newque(struct ipc_namespace *, struct ipc_params *);
static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
+ * Scale msgmni with the available lowmem size: the memory dedicated to msg
+ * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
+ * This should be done staying within the (MSGMNI , IPCMNI) range.
+ */
+static void recompute_msgmni(struct ipc_namespace *ns)
+ struct sysinfo i;
+ unsigned long allowed;
+ si_meminfo(&i);
+ allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
+ if (allowed < MSGMNI) {
+ ns->msg_ctlmni = MSGMNI;
+ goto out_callback;
+ }
+ if (allowed > IPCMNI) {
+ ns->msg_ctlmni = IPCMNI;
+ goto out_callback;
+ }
+ ns->msg_ctlmni = allowed;
+ printk(KERN_INFO "msgmni has been set to %d for ipc namespace %p\n",
+ ns->msg_ctlmni, ns);
void msg_init_ns(struct ipc_namespace *ns)
ns->msg_ctlmax = MSGMAX;
ns->msg_ctlmnb = MSGMNB;
- ns->msg_ctlmni = MSGMNI;
+ recompute_msgmni(ns);
atomic_set(&ns->msg_bytes, 0);
atomic_set(&ns->msg_hdrs, 0);