Allow to define per-UID virtual memory overcommit handling. Configuration is
stored in a hash list in kernel space reachable through /proc/overcommit_uid
(surely there're better ways to do it, i.e. via configfs).
Hash elements are defined using a triple:
uid:overcommit_memory:overcommit_ratio
The overcommit_* values have the same semantic of their respective sysctl
variables.
If a user is not present in the hash, the default system policy will be used
(defined by /proc/sys/vm/overcommit_memory and /proc/sys/vm/overcommit_ratio).
Example:
- Enable "always overcommit" policy for admin:
root@host # echo 0:1:0 > /proc/overcommit_uid
- processes belonging to sshd (uid=100) and ntp (uid=102) users can be quite
critical, so use a classic heuristic overcommit:
root@host # echo 100:0:50 > /proc/overcommit_uid
root@host # echo 102:0:50 > /proc/overcommit_uid
- allow uid=1001 and uid=1002 (common users) to allocate memory only if the
total committed space is below the 50% of the physical RAM + the size of
swap:
root@host # echo 1001:2:50 > /proc/overcommit_uid
root@host # echo 1002:2:50 > /proc/overcommit_uid
- Deny VM allocation to others:
root@host # echo 2 > /proc/sys/vm/overcommit_memory && echo 0 > /proc/sys/vm/overcommit_ratio
TODO:
- GID overcommit policy,
- per-user/group VM accounting,
- VM quotas,
- a lot of improvements,
- more testing...
Signed-off-by: Andrea Righi <[email protected]>
---
diff -urpN linux-2.6.21/include/linux/mman.h linux-2.6.21-vm-acct-user/include/linux/mman.h
--- linux-2.6.21/include/linux/mman.h 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/include/linux/mman.h 2007-05-07 20:20:42.000000000 +0200
@@ -18,6 +18,14 @@
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern atomic_t vm_committed_space;
+#ifdef CONFIG_VM_ACCT_USER
+struct vm_acct_values
+{
+ int overcommit_memory;
+ int overcommit_ratio;
+};
+extern int vm_acct_get_config(struct vm_acct_values *v, uid_t uid);
+#endif
#ifdef CONFIG_SMP
extern void vm_acct_memory(long pages);
diff -urpN linux-2.6.21/ipc/shm.c linux-2.6.21-vm-acct-user/ipc/shm.c
--- linux-2.6.21/ipc/shm.c 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/ipc/shm.c 2007-05-07 20:20:42.000000000 +0200
@@ -370,12 +370,24 @@ static int newseg (struct ipc_namespace
shp->mlock_user = current->user;
} else {
int acctflag = VM_ACCOUNT;
+#ifdef CONFIG_VM_ACCT_USER
+ int overcommit_memory;
+ struct vm_acct_values v;
+
+ if (!vm_acct_get_config(&v, current->uid)) {
+ overcommit_memory = v.overcommit_memory;
+ } else {
+ overcommit_memory = sysctl_overcommit_memory;
+ }
+#else
+#define overcommit_memory sysctl_overcommit_memory
+#endif
/*
* Do not allow no accounting for OVERCOMMIT_NEVER, even
* if it's asked for.
*/
if ((shmflg & SHM_NORESERVE) &&
- sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+ overcommit_memory != OVERCOMMIT_NEVER)
acctflag = 0;
sprintf (name, "SYSV%08x", key);
file = shmem_file_setup(name, size, acctflag);
diff -urpN linux-2.6.21/mm/Kconfig linux-2.6.21-vm-acct-user/mm/Kconfig
--- linux-2.6.21/mm/Kconfig 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/Kconfig 2007-05-07 20:21:21.000000000 +0200
@@ -163,3 +163,11 @@ config ZONE_DMA_FLAG
default "0" if !ZONE_DMA
default "1"
+config VM_ACCT_USER
+ bool "Per-user VM overcommit policy (EXPERIMENTAL)"
+ depends on PROC_FS && EXPERIMENTAL
+ def_bool n
+ help
+ Say Y here to enable per-user virtual memory overcommit handling.
+ Overcommit configuration will be available via /proc/overcommit_uid.
+
diff -urpN linux-2.6.21/mm/mmap.c linux-2.6.21-vm-acct-user/mm/mmap.c
--- linux-2.6.21/mm/mmap.c 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/mmap.c 2007-05-07 20:20:42.000000000 +0200
@@ -95,16 +95,30 @@ atomic_t vm_committed_space = ATOMIC_INI
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
-
+#ifdef CONFIG_VM_ACCT_USER
+ int overcommit_memory, overcommit_ratio;
+ struct vm_acct_values v;
+
+ if (!vm_acct_get_config(&v, current->uid)) {
+ overcommit_memory = v.overcommit_memory;
+ overcommit_ratio = v.overcommit_ratio;
+ } else {
+ overcommit_memory = sysctl_overcommit_memory;
+ overcommit_ratio = sysctl_overcommit_ratio;
+ }
+#else
+#define overcommit_memory sysctl_overcommit_memory
+#define overcommit_ratio sysctl_overcommit_ratio
+#endif
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ if (overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -155,7 +169,7 @@ int __vm_enough_memory(long pages, int c
}
allowed = (totalram_pages - hugetlb_total_pages())
- * sysctl_overcommit_ratio / 100;
+ * overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
@@ -901,6 +915,10 @@ unsigned long do_mmap_pgoff(struct file
struct rb_node ** rb_link, * rb_parent;
int accountable = 1;
unsigned long charged = 0, reqprot = prot;
+#ifdef CONFIG_VM_ACCT_USER
+ int overcommit_memory;
+ struct vm_acct_values v;
+#endif
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
@@ -1040,8 +1058,15 @@ munmap_back:
if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
+#ifdef CONFIG_VM_ACCT_USER
+ if (!vm_acct_get_config(&v, current->uid)) {
+ overcommit_memory = v.overcommit_memory;
+ } else {
+ overcommit_memory = sysctl_overcommit_memory;
+ }
+#endif
if (accountable && (!(flags & MAP_NORESERVE) ||
- sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
+ overcommit_memory == OVERCOMMIT_NEVER)) {
if (vm_flags & VM_SHARED) {
/* Check memory availability in shmem_file_setup? */
vm_flags |= VM_ACCOUNT;
diff -urpN linux-2.6.21/mm/nommu.c linux-2.6.21-vm-acct-user/mm/nommu.c
--- linux-2.6.21/mm/nommu.c 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/nommu.c 2007-05-07 20:20:42.000000000 +0200
@@ -1240,16 +1240,31 @@ EXPORT_SYMBOL(get_unmapped_area);
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
+#ifdef CONFIG_VM_ACCT_USER
+ int overcommit_memory, overcommit_ratio;
+ struct vm_acct_values v;
+
+ if (!vm_acct_get_config(&v, current->uid)) {
+ overcommit_memory = v.overcommit_memory;
+ overcommit_ratio = v.overcommit_ratio;
+ } else {
+ overcommit_memory = sysctl_overcommit_memory;
+ overcommit_ratio = sysctl_overcommit_ratio;
+ }
+#else
+#define overcommit_memory sysctl_overcommit_memory
+#define overcommit_ratio sysctl_overcommit_ratio
+#endif
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ if (overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -1299,7 +1314,7 @@ int __vm_enough_memory(long pages, int c
goto error;
}
- allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+ allowed = totalram_pages * overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
diff -urpN linux-2.6.21/mm/swap.c linux-2.6.21-vm-acct-user/mm/swap.c
--- linux-2.6.21/mm/swap.c 2007-05-07 20:20:24.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/swap.c 2007-05-07 20:20:42.000000000 +0200
@@ -30,6 +30,10 @@
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/seq_file.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
@@ -455,6 +459,196 @@ unsigned pagevec_lookup_tag(struct pagev
EXPORT_SYMBOL(pagevec_lookup_tag);
+#ifdef CONFIG_VM_ACCT_USER
+
+#define VM_ACCT_HASH_SHIFT 10
+#define VM_ACCT_HASH_SIZE (1UL << VM_ACCT_HASH_SHIFT)
+#define vm_acct_hashfn(uid) hash_long((unsigned long)uid, VM_ACCT_HASH_SHIFT)
+
+/* User VM overcommit configuration */
+typedef struct vm_acct_hash_struct
+{
+ uid_t uid;
+ struct vm_acct_values val;
+ struct hlist_node vm_acct_chain;
+} vm_acct_hash_t;
+
+/* Hash list used to store per-user VM overcommit configurations */
+static struct hlist_head *vm_acct_hash;
+
+/* VM overcommit hash table spinlock */
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(vm_acct_lock);
+
+/*
+ * Get user VM configuration from the hash list.
+ */
+int vm_acct_get_config(struct vm_acct_values *v, uid_t uid)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
+ vm_acct_chain) {
+ if (p->uid == uid) {
+ v->overcommit_memory = p->val.overcommit_memory;
+ v->overcommit_ratio = p->val.overcommit_ratio;
+ spin_unlock_irq(&vm_acct_lock);
+ return 0;
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ return -ENOENT;
+}
+
+/*
+ * Create a new element in the VM configuration hash list.
+ */
+static int __vm_acct_set_element(uid_t uid,
+ int overcommit_memory, int overcommit_ratio)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+ int ret = 0;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
+ vm_acct_chain) {
+ if (p->uid == uid) {
+ p->val.overcommit_memory = overcommit_memory;
+ p->val.overcommit_ratio = overcommit_ratio;
+ goto out;
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ /* Allocate new element */
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (unlikely(!p)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ p->uid = uid;
+ p->val.overcommit_memory = overcommit_memory;
+ p->val.overcommit_ratio = overcommit_ratio;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_add_head(&p->vm_acct_chain, &vm_acct_hash[vm_acct_hashfn(uid)]);
+out:
+ spin_unlock_irq(&vm_acct_lock);
+ return ret;
+}
+
+/*
+ * Set VM user parameters via /proc/overcommit_uid.
+ */
+static int vm_acct_set(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *data)
+{
+ char buf[128];
+ char *om, *or;
+ int __ret;
+
+ /*
+ * Parse ':'-separated arguments
+ * uid:overcommit_memory:overcommit_ratio
+ */
+ if (count > sizeof(buf) - 1)
+ return -EFAULT;
+
+ if (copy_from_user(buf, buffer, count))
+ return -EFAULT;
+
+ buf[sizeof(buf) - 1] = '\0';
+
+ om = strstr(buf, ":");
+ if ((om == NULL) || (*++om == '\0')) {
+ return -EINVAL;
+ }
+
+ or = strstr(om, ":");
+ if ((or == NULL) || (*++or == '\0')) {
+ return -EINVAL;
+ }
+
+ /* Set VM configuration */
+ __ret = __vm_acct_set_element((uid_t)simple_strtoul(buf, NULL, 10),
+ (int)simple_strtol(om, NULL, 10),
+ (int)simple_strtol(or, NULL, 10));
+ if (__ret)
+ return __ret;
+
+ return count;
+}
+
+/*
+ * Print VM overcommit configurations.
+ */
+static int vm_acct_show(struct seq_file *m, void *v)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+ int i;
+
+ spin_lock_irq(&vm_acct_lock);
+ for (i = 0; i < VM_ACCT_HASH_SIZE; i++) {
+ if (!&vm_acct_hash[i])
+ continue;
+ hlist_for_each_entry(p, elem, &vm_acct_hash[i],
+ vm_acct_chain) {
+ seq_printf(m, "%i:%i:%i\n",
+ p->uid, p->val.overcommit_memory,
+ p->val.overcommit_ratio);
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ return 0;
+}
+
+static int vm_acct_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, vm_acct_show, NULL);
+}
+
+static struct file_operations vm_acct_ops = {
+ .open = vm_acct_open,
+ .read = seq_read,
+ .write = vm_acct_set,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init init_vm_acct(void)
+{
+ struct proc_dir_entry *pe;
+ int i;
+
+ vm_acct_hash = kmalloc(VM_ACCT_HASH_SIZE * sizeof(*(vm_acct_hash)),
+ GFP_KERNEL);
+ if (!vm_acct_hash)
+ return -ENOMEM;
+
+ printk(KERN_INFO "vm_acct_uid hash table entries: %lu\n",
+ VM_ACCT_HASH_SIZE / sizeof(*(vm_acct_hash)));
+
+ spin_lock_irq(&vm_acct_lock);
+ for (i = 0; i < VM_ACCT_HASH_SIZE; i++)
+ INIT_HLIST_HEAD(&vm_acct_hash[i]);
+ spin_unlock_irq(&vm_acct_lock);
+
+ pe = create_proc_entry("overcommit_uid", 0600, NULL);
+ if (!pe)
+ return -ENOMEM;
+ pe->proc_fops = &vm_acct_ops;
+
+ return 0;
+}
+__initcall(init_vm_acct);
+
+#endif /* CONFIG_VM_ACCT_USER */
+
#ifdef CONFIG_SMP
/*
* We tolerate a little inaccuracy to avoid ping-ponging the counter between
On Mon, May 07, 2007 at 08:56:39PM +0200, Andrea Righi wrote:
> Allow to define per-UID virtual memory overcommit handling. Configuration is
> stored in a hash list in kernel space reachable through /proc/overcommit_uid
> (surely there're better ways to do it, i.e. via configfs).
> Hash elements are defined using a triple:
> uid:overcommit_memory:overcommit_ratio
> The overcommit_* values have the same semantic of their respective sysctl
> variables.
> If a user is not present in the hash, the default system policy will be used
> (defined by /proc/sys/vm/overcommit_memory and /proc/sys/vm/overcommit_ratio).
While I think it's a step in the right direction, I'm not convinced of
the soundness of the approach. I expect one might be better served by
per-user limits on committed memory, perhaps even proportional limits.
The basic idea is that committed memory is a relatively global resource.
You can apportion it and limit the global pool, but it's difficult to
arrange for overall overcommitment policy on a per-anything basis
without some sort of OOM-isolated domains for users and processes to run
within. Those are particularly interesting as they relate to kernel
memory allocations.
The /proc/ interface is probably going to raise a few eyebrows. I'm
unaware of what sorts of interfaces would be recommended for all this.
The following stanza occurs often:
+ if (!vm_acct_get_config(&v, current->uid)) {
+ overcommit_memory = v.overcommit_memory;
+ overcommit_ratio = v.overcommit_ratio;
+ } else {
+ overcommit_memory = sysctl_overcommit_memory;
+ overcommit_ratio = sysctl_overcommit_ratio;
+ }
suggesting that vm_acct_get_config() isn't the proper abstraction.
Instead of
int vm_acct_get_config(struct vm_acct_values *, uid_t);
you could just have
int vm_acct_get_config(struct vm_acct_values *);
which conditionally uses current->uid, and then unconditionally use
v.overcommit_memory and v.overcommit_ratio vs. sysctl_overcommit_memory
and sysctl_overcommit_ratio in the sequel.
-- wli
Hi,
a few comments on the patch:
Andrea Righi <[email protected]> ha scritto:
> diff -urpN linux-2.6.21/include/linux/mman.h linux-2.6.21-vm-acct-user/include/linux/mman.h
> --- linux-2.6.21/include/linux/mman.h 2007-05-07 20:20:24.000000000 +0200
> +++ linux-2.6.21-vm-acct-user/include/linux/mman.h 2007-05-07 20:20:42.000000000 +0200
> @@ -18,6 +18,14 @@
> extern int sysctl_overcommit_memory;
> extern int sysctl_overcommit_ratio;
> extern atomic_t vm_committed_space;
> +#ifdef CONFIG_VM_ACCT_USER
> +struct vm_acct_values
> +{
> + int overcommit_memory;
> + int overcommit_ratio;
> +};
> +extern int vm_acct_get_config(struct vm_acct_values *v, uid_t uid);
> +#endif
>
> #ifdef CONFIG_SMP
> extern void vm_acct_memory(long pages);
> diff -urpN linux-2.6.21/ipc/shm.c linux-2.6.21-vm-acct-user/ipc/shm.c
> --- linux-2.6.21/ipc/shm.c 2007-05-07 20:20:24.000000000 +0200
> +++ linux-2.6.21-vm-acct-user/ipc/shm.c 2007-05-07 20:20:42.000000000 +0200
> @@ -370,12 +370,24 @@ static int newseg (struct ipc_namespace
> shp->mlock_user = current->user;
> } else {
> int acctflag = VM_ACCOUNT;
> +#ifdef CONFIG_VM_ACCT_USER
> + int overcommit_memory;
> + struct vm_acct_values v;
> +
> + if (!vm_acct_get_config(&v, current->uid)) {
> + overcommit_memory = v.overcommit_memory;
> + } else {
> + overcommit_memory = sysctl_overcommit_memory;
> + }
> +#else
> +#define overcommit_memory sysctl_overcommit_memory
> +#endif
> /*
> * Do not allow no accounting for OVERCOMMIT_NEVER, even
> * if it's asked for.
> */
> if ((shmflg & SHM_NORESERVE) &&
> - sysctl_overcommit_memory != OVERCOMMIT_NEVER)
> + overcommit_memory != OVERCOMMIT_NEVER)
Ugly... very ugly ;)
Don't hide 'overcommit_memory' inside the ifdef block. The compiler
should be smart enough to optimize away the extra var.
There's also a problem with the #ifdef scattered all over the code. You
need a static inline 'vm_acct_get_config' for the !CONFIG_VM_ACCT_USER
case:
static inline int vm_acct_get_config(struct vm_acct_values *v,
uid_t uid)
{
return 0;
}
in this way you can remove the #ifdef. Futhermore, I'd also move the
branch with the fallback to sysctl values inside the vm_acct_get_config.
So, for !CONFIG_VM_ACCT_USER:
static inline int vm_acct_get_config(struct vm_acct_values *v,
uid_t uid)
{
v->overcommit_memory = sysctl_overcommit_memory;
v->overcommit_ratio = sysctl_overcommit_ratio;
}
(Yes, gcc will optimize it)
and for CONFIG_VM_ACCT_USER:
int vm_acct_get_config(struct vm_acct_values *v, uid_t uid)
{
if (found uid) {
v->overcommit_memory = foo;
v->overcommit_ratio = bar;
} else {
v->overcommit_memory = sysctl_overcommit_memory;
v->overcommit_ratio = sysctl_overcommit_ratio;
}
}
> diff -urpN linux-2.6.21/mm/swap.c linux-2.6.21-vm-acct-user/mm/swap.c
> --- linux-2.6.21/mm/swap.c 2007-05-07 20:20:24.000000000 +0200
> +++ linux-2.6.21-vm-acct-user/mm/swap.c 2007-05-07 20:20:42.000000000 +0200
> @@ -30,6 +30,10 @@
> #include <linux/cpu.h>
> #include <linux/notifier.h>
> #include <linux/init.h>
> +#include <linux/hash.h>
> +#include <linux/seq_file.h>
> +#include <linux/kernel.h>
> +#include <linux/proc_fs.h>
>
> /* How many pages do we try to swap or page in/out together? */
> int page_cluster;
> @@ -455,6 +459,196 @@ unsigned pagevec_lookup_tag(struct pagev
>
> EXPORT_SYMBOL(pagevec_lookup_tag);
>
> +#ifdef CONFIG_VM_ACCT_USER
> +
> +#define VM_ACCT_HASH_SHIFT 10
> +#define VM_ACCT_HASH_SIZE (1UL << VM_ACCT_HASH_SHIFT)
> +#define vm_acct_hashfn(uid) hash_long((unsigned long)uid, VM_ACCT_HASH_SHIFT)
> +
> +/* User VM overcommit configuration */
> +typedef struct vm_acct_hash_struct
> +{
> + uid_t uid;
> + struct vm_acct_values val;
> + struct hlist_node vm_acct_chain;
> +} vm_acct_hash_t;
> +
> +/* Hash list used to store per-user VM overcommit configurations */
> +static struct hlist_head *vm_acct_hash;
> +
> +/* VM overcommit hash table spinlock */
> +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(vm_acct_lock);
> +
> +/*
> + * Get user VM configuration from the hash list.
> + */
> +int vm_acct_get_config(struct vm_acct_values *v, uid_t uid)
> +{
> + struct hlist_node *elem;
> + vm_acct_hash_t *p;
> +
> + spin_lock_irq(&vm_acct_lock);
> + hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
> + vm_acct_chain) {
> + if (p->uid == uid) {
> + v->overcommit_memory = p->val.overcommit_memory;
> + v->overcommit_ratio = p->val.overcommit_ratio;
> + spin_unlock_irq(&vm_acct_lock);
> + return 0;
> + }
> + }
> + spin_unlock_irq(&vm_acct_lock);
> +
> + return -ENOENT;
> +}
> +
> +/*
> + * Create a new element in the VM configuration hash list.
> + */
> +static int __vm_acct_set_element(uid_t uid,
> + int overcommit_memory, int overcommit_ratio)
> +{
> + struct hlist_node *elem;
> + vm_acct_hash_t *p;
> + int ret = 0;
> +
> + spin_lock_irq(&vm_acct_lock);
> + hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
> + vm_acct_chain) {
> + if (p->uid == uid) {
> + p->val.overcommit_memory = overcommit_memory;
> + p->val.overcommit_ratio = overcommit_ratio;
> + goto out;
> + }
> + }
> + spin_unlock_irq(&vm_acct_lock);
> +
> + /* Allocate new element */
> + p = kzalloc(sizeof(*p), GFP_KERNEL);
> + if (unlikely(!p)) {
> + ret = -ENOMEM;
> + goto out;
> + }
> + p->uid = uid;
> + p->val.overcommit_memory = overcommit_memory;
> + p->val.overcommit_ratio = overcommit_ratio;
> +
> + spin_lock_irq(&vm_acct_lock);
> + hlist_add_head(&p->vm_acct_chain, &vm_acct_hash[vm_acct_hashfn(uid)]);
> +out:
In the error path (kzalloc failure) you release vm_acct_lock which is not
held.
> + spin_unlock_irq(&vm_acct_lock);
> + return ret;
> +}
> +
> +/*
> + * Set VM user parameters via /proc/overcommit_uid.
> + */
> +static int vm_acct_set(struct file *filp, const char __user *buffer,
> + size_t count, loff_t *data)
> +{
> + char buf[128];
> + char *om, *or;
> + int __ret;
^^ uh?
> +
> + /*
> + * Parse ':'-separated arguments
> + * uid:overcommit_memory:overcommit_ratio
> + */
> + if (count > sizeof(buf) - 1)
> + return -EFAULT;
> +
> + if (copy_from_user(buf, buffer, count))
> + return -EFAULT;
> +
> + buf[sizeof(buf) - 1] = '\0';
> +
> + om = strstr(buf, ":");
> + if ((om == NULL) || (*++om == '\0')) {
> + return -EINVAL;
> + }
> +
> + or = strstr(om, ":");
> + if ((or == NULL) || (*++or == '\0')) {
> + return -EINVAL;
> + }
> +
> + /* Set VM configuration */
> + __ret = __vm_acct_set_element((uid_t)simple_strtoul(buf, NULL, 10),
> + (int)simple_strtol(om, NULL, 10),
> + (int)simple_strtol(or, NULL, 10));
> + if (__ret)
> + return __ret;
> +
> + return count;
> +}
> +
> +/*
> + * Print VM overcommit configurations.
> + */
> +static int vm_acct_show(struct seq_file *m, void *v)
> +{
> + struct hlist_node *elem;
> + vm_acct_hash_t *p;
> + int i;
> +
> + spin_lock_irq(&vm_acct_lock);
> + for (i = 0; i < VM_ACCT_HASH_SIZE; i++) {
> + if (!&vm_acct_hash[i])
> + continue;
> + hlist_for_each_entry(p, elem, &vm_acct_hash[i],
> + vm_acct_chain) {
> + seq_printf(m, "%i:%i:%i\n",
> + p->uid, p->val.overcommit_memory,
> + p->val.overcommit_ratio);
> + }
> + }
> + spin_unlock_irq(&vm_acct_lock);
> +
> + return 0;
> +}
> +
> +static int vm_acct_open(struct inode *inode, struct file *filp)
> +{
> + return single_open(filp, vm_acct_show, NULL);
> +}
> +
> +static struct file_operations vm_acct_ops = {
> + .open = vm_acct_open,
> + .read = seq_read,
> + .write = vm_acct_set,
> + .llseek = seq_lseek,
> + .release = seq_release,
> +};
> +
> +static int __init init_vm_acct(void)
> +{
> + struct proc_dir_entry *pe;
> + int i;
> +
> + vm_acct_hash = kmalloc(VM_ACCT_HASH_SIZE * sizeof(*(vm_acct_hash)),
> + GFP_KERNEL);
> + if (!vm_acct_hash)
> + return -ENOMEM;
> +
> + printk(KERN_INFO "vm_acct_uid hash table entries: %lu\n",
> + VM_ACCT_HASH_SIZE / sizeof(*(vm_acct_hash)));
> +
> + spin_lock_irq(&vm_acct_lock);
> + for (i = 0; i < VM_ACCT_HASH_SIZE; i++)
> + INIT_HLIST_HEAD(&vm_acct_hash[i]);
> + spin_unlock_irq(&vm_acct_lock);
> +
> + pe = create_proc_entry("overcommit_uid", 0600, NULL);
> + if (!pe)
> + return -ENOMEM;
> + pe->proc_fops = &vm_acct_ops;
> +
> + return 0;
> +}
> +__initcall(init_vm_acct);
> +
> +#endif /* CONFIG_VM_ACCT_USER */
> +
> #ifdef CONFIG_SMP
> /*
> * We tolerate a little inaccuracy to avoid ping-ponging the counter between
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
Luca
--
Porc i' mond che cio' sott i piedi!
V. Catozzo
On Mon, May 07, 2007 at 12:16:58PM -0700, William Lee Irwin III wrote:
> The following stanza occurs often:
> + if (!vm_acct_get_config(&v, current->uid)) {
> + overcommit_memory = v.overcommit_memory;
> + overcommit_ratio = v.overcommit_ratio;
> + } else {
> + overcommit_memory = sysctl_overcommit_memory;
> + overcommit_ratio = sysctl_overcommit_ratio;
> + }
>
> suggesting that vm_acct_get_config() isn't the proper abstraction.
> Instead of
> int vm_acct_get_config(struct vm_acct_values *, uid_t);
> you could just have
> int vm_acct_get_config(struct vm_acct_values *);
> which conditionally uses current->uid, and then unconditionally use
> v.overcommit_memory and v.overcommit_ratio vs. sysctl_overcommit_memory
> and sysctl_overcommit_ratio in the sequel.
Something like this (untested/uncompiled) may do.
Index: righi/include/linux/mman.h
===================================================================
--- righi.orig/include/linux/mman.h 2007-05-07 12:36:05.897386369 -0700
+++ righi/include/linux/mman.h 2007-05-07 12:42:29.803263919 -0700
@@ -18,14 +18,13 @@
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern atomic_t vm_committed_space;
-#ifdef CONFIG_VM_ACCT_USER
+
struct vm_acct_values
{
int overcommit_memory;
int overcommit_ratio;
};
-extern int vm_acct_get_config(struct vm_acct_values *v, uid_t uid);
-#endif
+void vm_acct_get_config(struct vm_acct_values *v);
#ifdef CONFIG_SMP
extern void vm_acct_memory(long pages);
Index: righi/mm/swap.c
===================================================================
--- righi.orig/mm/swap.c 2007-05-07 12:37:13.965265337 -0700
+++ righi/mm/swap.c 2007-05-07 12:42:14.914415451 -0700
@@ -482,10 +482,11 @@
/*
* Get user VM configuration from the hash list.
*/
-int vm_acct_get_config(struct vm_acct_values *v, uid_t uid)
+void vm_acct_get_config(struct vm_acct_values *v)
{
struct hlist_node *elem;
vm_acct_hash_t *p;
+ uid_t uid = current->uid;
spin_lock_irq(&vm_acct_lock);
hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
@@ -494,12 +495,12 @@
v->overcommit_memory = p->val.overcommit_memory;
v->overcommit_ratio = p->val.overcommit_ratio;
spin_unlock_irq(&vm_acct_lock);
- return 0;
+ return;
}
}
spin_unlock_irq(&vm_acct_lock);
-
- return -ENOENT;
+ v->overcommit_memory = sysctl_overcommit_memory;
+ v->overcommit_ratio = sysctl_overcommit_ratio;
}
/*
@@ -646,8 +647,13 @@
return 0;
}
__initcall(init_vm_acct);
-
-#endif /* CONFIG_VM_ACCT_USER */
+#else /* !CONFIG_VM_ACCT_USER */
+void vm_acct_get_config(struct vm_acct_values *v)
+{
+ v->overcommit_memory = sysctl_overcommit_memory;
+ v->overcommit_ratio = sysctl_overcommit_ratio;
+}
+#endif /* !CONFIG_VM_ACCT_USER */
#ifdef CONFIG_SMP
/*
Index: righi/ipc/shm.c
===================================================================
--- righi.orig/ipc/shm.c 2007-05-07 12:40:35.576754521 -0700
+++ righi/ipc/shm.c 2007-05-07 12:43:32.714849046 -0700
@@ -370,24 +370,15 @@
shp->mlock_user = current->user;
} else {
int acctflag = VM_ACCOUNT;
-#ifdef CONFIG_VM_ACCT_USER
- int overcommit_memory;
struct vm_acct_values v;
- if (!vm_acct_get_config(&v, current->uid)) {
- overcommit_memory = v.overcommit_memory;
- } else {
- overcommit_memory = sysctl_overcommit_memory;
- }
-#else
-#define overcommit_memory sysctl_overcommit_memory
-#endif
+ vm_acct_get_config(&v);
/*
* Do not allow no accounting for OVERCOMMIT_NEVER, even
* if it's asked for.
*/
if ((shmflg & SHM_NORESERVE) &&
- overcommit_memory != OVERCOMMIT_NEVER)
+ v.overcommit_memory != OVERCOMMIT_NEVER)
acctflag = 0;
sprintf (name, "SYSV%08x", key);
file = shmem_file_setup(name, size, acctflag);
Index: righi/mm/mmap.c
===================================================================
--- righi.orig/mm/mmap.c 2007-05-07 12:43:48.143728287 -0700
+++ righi/mm/mmap.c 2007-05-07 12:46:02.775400509 -0700
@@ -96,30 +96,18 @@
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
-#ifdef CONFIG_VM_ACCT_USER
- int overcommit_memory, overcommit_ratio;
struct vm_acct_values v;
- if (!vm_acct_get_config(&v, current->uid)) {
- overcommit_memory = v.overcommit_memory;
- overcommit_ratio = v.overcommit_ratio;
- } else {
- overcommit_memory = sysctl_overcommit_memory;
- overcommit_ratio = sysctl_overcommit_ratio;
- }
-#else
-#define overcommit_memory sysctl_overcommit_memory
-#define overcommit_ratio sysctl_overcommit_ratio
-#endif
+ vm_acct_get_config(&v);
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (v.overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (overcommit_memory == OVERCOMMIT_GUESS) {
+ if (v.overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -170,7 +158,7 @@
}
allowed = (totalram_pages - hugetlb_total_pages())
- * overcommit_ratio / 100;
+ * v.overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
@@ -916,10 +904,7 @@
struct rb_node ** rb_link, * rb_parent;
int accountable = 1;
unsigned long charged = 0, reqprot = prot;
-#ifdef CONFIG_VM_ACCT_USER
- int overcommit_memory;
struct vm_acct_values v;
-#endif
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
@@ -1059,15 +1044,9 @@
if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
-#ifdef CONFIG_VM_ACCT_USER
- if (!vm_acct_get_config(&v, current->uid)) {
- overcommit_memory = v.overcommit_memory;
- } else {
- overcommit_memory = sysctl_overcommit_memory;
- }
-#endif
+ vm_acct_get_config(&v);
if (accountable && (!(flags & MAP_NORESERVE) ||
- overcommit_memory == OVERCOMMIT_NEVER)) {
+ v.overcommit_memory == OVERCOMMIT_NEVER)) {
if (vm_flags & VM_SHARED) {
/* Check memory availability in shmem_file_setup? */
vm_flags |= VM_ACCOUNT;
Index: righi/mm/nommu.c
===================================================================
--- righi.orig/mm/nommu.c 2007-05-07 12:46:09.667793284 -0700
+++ righi/mm/nommu.c 2007-05-07 12:46:52.490233596 -0700
@@ -1240,31 +1240,18 @@
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
-#ifdef CONFIG_VM_ACCT_USER
- int overcommit_memory, overcommit_ratio;
struct vm_acct_values v;
- if (!vm_acct_get_config(&v, current->uid)) {
- overcommit_memory = v.overcommit_memory;
- overcommit_ratio = v.overcommit_ratio;
- } else {
- overcommit_memory = sysctl_overcommit_memory;
- overcommit_ratio = sysctl_overcommit_ratio;
- }
-#else
-#define overcommit_memory sysctl_overcommit_memory
-#define overcommit_ratio sysctl_overcommit_ratio
-#endif
-
+ vm_acct_get_config(&v);
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (v.overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (overcommit_memory == OVERCOMMIT_GUESS) {
+ if (v.overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -1314,7 +1301,7 @@
goto error;
}
- allowed = totalram_pages * overcommit_ratio / 100;
+ allowed = totalram_pages * v.overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
> - allow uid=1001 and uid=1002 (common users) to allocate memory only if the
> total committed space is below the 50% of the physical RAM + the size of
> swap:
> root@host # echo 1001:2:50 > /proc/overcommit_uid
> root@host # echo 1002:2:50 > /proc/overcommit_uid
There are some fundamental problems with this model - the moment you mix
strict overcommit with anything else it ceases to be a strict overcommit
and you might as well use existing overcommit rules for most stuff
The other thing you are sort of faking is per user resource management -
which is a subset of per group of users resource management which is
useful - eg "students can't hog the machine"
I don't see that this is the right approach compared with the container
work and openvz work that is currently active and far more flexible.
Alan
William Lee Irwin III wrote:
> On Mon, May 07, 2007 at 12:16:58PM -0700, William Lee Irwin III wrote:
>> The following stanza occurs often:
>> + if (!vm_acct_get_config(&v, current->uid)) {
>> + overcommit_memory = v.overcommit_memory;
>> + overcommit_ratio = v.overcommit_ratio;
>> + } else {
>> + overcommit_memory = sysctl_overcommit_memory;
>> + overcommit_ratio = sysctl_overcommit_ratio;
>> + }
>>
>> suggesting that vm_acct_get_config() isn't the proper abstraction.
>> Instead of
>> int vm_acct_get_config(struct vm_acct_values *, uid_t);
>> you could just have
>> int vm_acct_get_config(struct vm_acct_values *);
>> which conditionally uses current->uid, and then unconditionally use
>> v.overcommit_memory and v.overcommit_ratio vs. sysctl_overcommit_memory
>> and sysctl_overcommit_ratio in the sequel.
>
> Something like this (untested/uncompiled) may do.
[snip]
I agree with everything, applied all the changes and fixed the bug reported by
Luca (see below). It seems to compile and work without problem. Thanks!
Signed-off-by: Andrea Righi <[email protected]>
---
diff -urpN linux-2.6.21/include/linux/mman.h linux-2.6.21-vm-acct-user/include/linux/mman.h
--- linux-2.6.21/include/linux/mman.h 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/include/linux/mman.h 2007-05-07 23:33:16.000000000 +0200
@@ -18,6 +18,20 @@
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern atomic_t vm_committed_space;
+struct vm_acct_values
+{
+ int overcommit_memory;
+ int overcommit_ratio;
+};
+#ifdef CONFIG_VM_ACCT_USER
+extern void vm_acct_get_config(struct vm_acct_values *v);
+#else
+static inline void vm_acct_get_config(struct vm_acct_values *v)
+{
+ v->overcommit_memory = sysctl_overcommit_memory;
+ v->overcommit_ratio = sysctl_overcommit_ratio;
+}
+#endif
#ifdef CONFIG_SMP
extern void vm_acct_memory(long pages);
diff -urpN linux-2.6.21/ipc/shm.c linux-2.6.21-vm-acct-user/ipc/shm.c
--- linux-2.6.21/ipc/shm.c 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/ipc/shm.c 2007-05-07 23:24:04.000000000 +0200
@@ -370,12 +370,15 @@ static int newseg (struct ipc_namespace
shp->mlock_user = current->user;
} else {
int acctflag = VM_ACCOUNT;
+ struct vm_acct_values v;
+
+ vm_acct_get_config(&v);
/*
* Do not allow no accounting for OVERCOMMIT_NEVER, even
* if it's asked for.
*/
if ((shmflg & SHM_NORESERVE) &&
- sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+ v.overcommit_memory != OVERCOMMIT_NEVER)
acctflag = 0;
sprintf (name, "SYSV%08x", key);
file = shmem_file_setup(name, size, acctflag);
diff -urpN linux-2.6.21/mm/Kconfig linux-2.6.21-vm-acct-user/mm/Kconfig
--- linux-2.6.21/mm/Kconfig 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/Kconfig 2007-05-07 23:15:51.000000000 +0200
@@ -163,3 +163,11 @@ config ZONE_DMA_FLAG
default "0" if !ZONE_DMA
default "1"
+config VM_ACCT_USER
+ bool "Per-user VM overcommit policy (EXPERIMENTAL)"
+ depends on PROC_FS && EXPERIMENTAL
+ def_bool n
+ help
+ Say Y here to enable per-user virtual memory overcommit handling.
+ Overcommit configuration will be available via /proc/overcommit_uid.
+
diff -urpN linux-2.6.21/mm/mmap.c linux-2.6.21-vm-acct-user/mm/mmap.c
--- linux-2.6.21/mm/mmap.c 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/mmap.c 2007-05-07 23:25:56.000000000 +0200
@@ -95,16 +95,18 @@ atomic_t vm_committed_space = ATOMIC_INI
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
-
+ struct vm_acct_values v;
+
+ vm_acct_get_config(&v);
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (v.overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ if (v.overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -155,7 +157,7 @@ int __vm_enough_memory(long pages, int c
}
allowed = (totalram_pages - hugetlb_total_pages())
- * sysctl_overcommit_ratio / 100;
+ * v.overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
@@ -901,6 +903,7 @@ unsigned long do_mmap_pgoff(struct file
struct rb_node ** rb_link, * rb_parent;
int accountable = 1;
unsigned long charged = 0, reqprot = prot;
+ struct vm_acct_values v;
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
@@ -1040,8 +1043,9 @@ munmap_back:
if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
+ vm_acct_get_config(&v);
if (accountable && (!(flags & MAP_NORESERVE) ||
- sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
+ v.overcommit_memory == OVERCOMMIT_NEVER)) {
if (vm_flags & VM_SHARED) {
/* Check memory availability in shmem_file_setup? */
vm_flags |= VM_ACCOUNT;
diff -urpN linux-2.6.21/mm/nommu.c linux-2.6.21-vm-acct-user/mm/nommu.c
--- linux-2.6.21/mm/nommu.c 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/nommu.c 2007-05-07 23:27:03.000000000 +0200
@@ -1240,16 +1240,18 @@ EXPORT_SYMBOL(get_unmapped_area);
int __vm_enough_memory(long pages, int cap_sys_admin)
{
unsigned long free, allowed;
+ struct vm_acct_values v;
+ vm_acct_get_config(&v);
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
- if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ if (v.overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
- if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ if (v.overcommit_memory == OVERCOMMIT_GUESS) {
unsigned long n;
free = global_page_state(NR_FILE_PAGES);
@@ -1299,7 +1301,7 @@ int __vm_enough_memory(long pages, int c
goto error;
}
- allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+ allowed = totalram_pages * v.overcommit_ratio / 100;
/*
* Leave the last 3% for root
*/
diff -urpN linux-2.6.21/mm/swap.c linux-2.6.21-vm-acct-user/mm/swap.c
--- linux-2.6.21/mm/swap.c 2007-05-07 20:44:50.000000000 +0200
+++ linux-2.6.21-vm-acct-user/mm/swap.c 2007-05-07 23:33:40.000000000 +0200
@@ -30,6 +30,10 @@
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/seq_file.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
@@ -455,6 +459,196 @@ unsigned pagevec_lookup_tag(struct pagev
EXPORT_SYMBOL(pagevec_lookup_tag);
+#ifdef CONFIG_VM_ACCT_USER
+
+#define VM_ACCT_HASH_SHIFT 10
+#define VM_ACCT_HASH_SIZE (1UL << VM_ACCT_HASH_SHIFT)
+#define vm_acct_hashfn(uid) hash_long((unsigned long)uid, VM_ACCT_HASH_SHIFT)
+
+/* User VM overcommit configuration */
+typedef struct vm_acct_hash_struct
+{
+ uid_t uid;
+ struct vm_acct_values val;
+ struct hlist_node vm_acct_chain;
+} vm_acct_hash_t;
+
+/* Hash list used to store per-user VM overcommit configurations */
+static struct hlist_head *vm_acct_hash;
+
+/* VM overcommit hash table spinlock */
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(vm_acct_lock);
+
+/*
+ * Get user VM configuration from the hash list.
+ */
+void vm_acct_get_config(struct vm_acct_values *v)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+ uid_t uid = current->uid;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
+ vm_acct_chain) {
+ if (p->uid == uid) {
+ v->overcommit_memory = p->val.overcommit_memory;
+ v->overcommit_ratio = p->val.overcommit_ratio;
+ spin_unlock_irq(&vm_acct_lock);
+ return;
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ v->overcommit_memory = sysctl_overcommit_memory;
+ v->overcommit_ratio = sysctl_overcommit_ratio;
+}
+
+/*
+ * Create a new element in the VM configuration hash list.
+ */
+static int __vm_acct_set_element(uid_t uid,
+ int overcommit_memory, int overcommit_ratio)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+ int ret = 0;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_for_each_entry(p, elem, &vm_acct_hash[vm_acct_hashfn(uid)],
+ vm_acct_chain) {
+ if (p->uid == uid) {
+ p->val.overcommit_memory = overcommit_memory;
+ p->val.overcommit_ratio = overcommit_ratio;
+ goto out;
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ /* Allocate new element */
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (unlikely(!p)) {
+ return -ENOMEM;
+ }
+ p->uid = uid;
+ p->val.overcommit_memory = overcommit_memory;
+ p->val.overcommit_ratio = overcommit_ratio;
+
+ spin_lock_irq(&vm_acct_lock);
+ hlist_add_head(&p->vm_acct_chain, &vm_acct_hash[vm_acct_hashfn(uid)]);
+out:
+ spin_unlock_irq(&vm_acct_lock);
+ return ret;
+}
+
+/*
+ * Set VM user parameters via /proc/overcommit_uid.
+ */
+static int vm_acct_set(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *data)
+{
+ char buf[128];
+ char *om, *or;
+ int ret;
+
+ /*
+ * Parse ':'-separated arguments
+ * uid:overcommit_memory:overcommit_ratio
+ */
+ if (count > sizeof(buf) - 1)
+ return -EFAULT;
+
+ if (copy_from_user(buf, buffer, count))
+ return -EFAULT;
+
+ buf[sizeof(buf) - 1] = '\0';
+
+ om = strstr(buf, ":");
+ if ((om == NULL) || (*++om == '\0')) {
+ return -EINVAL;
+ }
+
+ or = strstr(om, ":");
+ if ((or == NULL) || (*++or == '\0')) {
+ return -EINVAL;
+ }
+
+ /* Set VM configuration */
+ ret = __vm_acct_set_element((uid_t)simple_strtoul(buf, NULL, 10),
+ (int)simple_strtol(om, NULL, 10),
+ (int)simple_strtol(or, NULL, 10));
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+/*
+ * Print VM overcommit configurations.
+ */
+static int vm_acct_show(struct seq_file *m, void *v)
+{
+ struct hlist_node *elem;
+ vm_acct_hash_t *p;
+ int i;
+
+ spin_lock_irq(&vm_acct_lock);
+ for (i = 0; i < VM_ACCT_HASH_SIZE; i++) {
+ if (!&vm_acct_hash[i])
+ continue;
+ hlist_for_each_entry(p, elem, &vm_acct_hash[i],
+ vm_acct_chain) {
+ seq_printf(m, "%i:%i:%i\n",
+ p->uid, p->val.overcommit_memory,
+ p->val.overcommit_ratio);
+ }
+ }
+ spin_unlock_irq(&vm_acct_lock);
+
+ return 0;
+}
+
+static int vm_acct_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, vm_acct_show, NULL);
+}
+
+static struct file_operations vm_acct_ops = {
+ .open = vm_acct_open,
+ .read = seq_read,
+ .write = vm_acct_set,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init init_vm_acct(void)
+{
+ struct proc_dir_entry *pe;
+ int i;
+
+ vm_acct_hash = kmalloc(VM_ACCT_HASH_SIZE * sizeof(*(vm_acct_hash)),
+ GFP_KERNEL);
+ if (!vm_acct_hash)
+ return -ENOMEM;
+
+ printk(KERN_INFO "vm_acct_uid hash table entries: %lu\n",
+ VM_ACCT_HASH_SIZE / sizeof(*(vm_acct_hash)));
+
+ spin_lock_irq(&vm_acct_lock);
+ for (i = 0; i < VM_ACCT_HASH_SIZE; i++)
+ INIT_HLIST_HEAD(&vm_acct_hash[i]);
+ spin_unlock_irq(&vm_acct_lock);
+
+ pe = create_proc_entry("overcommit_uid", 0600, NULL);
+ if (!pe)
+ return -ENOMEM;
+ pe->proc_fops = &vm_acct_ops;
+
+ return 0;
+}
+__initcall(init_vm_acct);
+#endif /* CONFIG_VM_ACCT_USER */
+
#ifdef CONFIG_SMP
/*
* We tolerate a little inaccuracy to avoid ping-ponging the counter between
Alan Cox wrote:
>> - allow uid=1001 and uid=1002 (common users) to allocate memory only if the
>> total committed space is below the 50% of the physical RAM + the size of
>> swap:
>> root@host # echo 1001:2:50 > /proc/overcommit_uid
>> root@host # echo 1002:2:50 > /proc/overcommit_uid
>
> There are some fundamental problems with this model - the moment you mix
> strict overcommit with anything else it ceases to be a strict overcommit
> and you might as well use existing overcommit rules for most stuff
>
> The other thing you are sort of faking is per user resource management -
> which is a subset of per group of users resource management which is
> useful - eg "students can't hog the machine"
>
> I don't see that this is the right approach compared with the container
> work and openvz work that is currently active and far more flexible.
>
Obviously I was not proposing a nice theoretical model, my work is more similar
to a quick and dirty hack that could resolve some problems (at least in my case)
like the crash of critical services due to OOM-killing (or due to the failure of
a malloc() when OOM-killer is disabled).
When $VERY_CRITICAL_DAEMON dies *all* the users blame the sysadmin [me]. If a
user application dies because a malloc() returns NULL, the sysadmin [I] can
blame the user saying: "hey! _you_ tried to hog the machine and _your_
application is not able to handle the NULL result of the malloc()s!"... :-)
A solution could be to define the critical processes unkillable via
/proc/<pid>/oom_adj, but the per-process approach doesn't resolve all the
possible cases and it's quite difficult to manage in big environments, like HPC
clusters.
Anyway, it seems that I need to deepen my knowledge about the recent development
of process containers and openvz...
Thanks,
-Andrea
> When $VERY_CRITICAL_DAEMON dies *all* the users blame the sysadmin [me]. If a
> user application dies because a malloc() returns NULL, the sysadmin [I] can
> blame the user saying: "hey! _you_ tried to hog the machine and _your_
> application is not able to handle the NULL result of the malloc()s!"... :-)
If you allow overcommit by the daemons and not user space then some of
the time you will still get out of memory kills which may well hit your
daemon process.
> A solution could be to define the critical processes unkillable via
> /proc/<pid>/oom_adj, but the per-process approach doesn't resolve all the
> possible cases and it's quite difficult to manage in big environments, like HPC
> clusters.
If you are running no overcommit you should never get an out of memory
kill.
> Anyway, it seems that I need to deepen my knowledge about the recent development
> of process containers and openvz...
I think that does what you need - you'd create containers for critical
services and for the users and split resources to protect one from the
other.