Home » Mailing lists » Devel » [PATCH v5 00/10] per-cgroup tcp memory pressure
| [PATCH v5 02/10] foundations of per-cgroup memory pressure controlling. [message #43998 is a reply to message #43996] |
Mon, 07 November 2011 15:26   |
Glauber Costa
Messages: 916
Registered: October 2011
|
Senior Member |
|
|
This patch replaces all uses of struct sock fields' memory_pressure,
memory_allocated, sockets_allocated, and sysctl_mem to acessor
macros. Those macros can either receive a socket argument, or a mem_cgroup
argument, depending on the context they live in.
Since we're only doing a macro wrapping here, no performance impact at all is
expected in the case where we don't have cgroups disabled.
Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: David S. Miller <davem@davemloft.net>
CC: Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: Eric Dumazet <eric.dumazet@gmail.com>
---
include/linux/memcontrol.h | 4 ++
include/net/sock.h | 86 ++++++++++++++++++++++++++++++++++++++-----
include/net/tcp.h | 3 +-
net/core/sock.c | 55 +++++++++++++++++-----------
net/ipv4/proc.c | 7 ++--
net/ipv4/tcp_input.c | 12 +++---
net/ipv4/tcp_ipv4.c | 4 +-
net/ipv4/tcp_output.c | 2 +-
net/ipv4/tcp_timer.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
10 files changed, 130 insertions(+), 47 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ac797fa..e9ff93a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -362,6 +362,10 @@ static inline
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
{
}
+static inline struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+{
+ return NULL;
+}
#endif /* CONFIG_CGROUP_MEM_CONT */
#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
diff --git a/include/net/sock.h b/include/net/sock.h
index c6658be..8959dcc 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,6 +54,7 @@
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/cgroup.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
@@ -168,6 +169,8 @@ struct sock_common {
/* public: */
};
+struct mem_cgroup;
+
/**
* struct sock - network layer representation of sockets
* @__sk_common: shared layout with inet_timewait_sock
@@ -793,22 +796,21 @@ struct proto {
unsigned int inuse_idx;
#endif
- /* Memory pressure */
- void (*enter_memory_pressure)(struct sock *sk);
- atomic_long_t *memory_allocated; /* Current allocated memory. */
- struct percpu_counter *sockets_allocated; /* Current number of sockets. */
+ void (*enter_memory_pressure)(struct sock *sk);
+ atomic_long_t *memory_allocated; /* Current allocated memory. */
+ struct percpu_counter *sockets_allocated; /* Current number of sockets. */
/*
* Pressure flag: try to collapse.
* Technical note: it is used by multiple contexts non atomically.
* All the __sk_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
- int *memory_pressure;
- long *sysctl_mem;
- int *sysctl_wmem;
- int *sysctl_rmem;
- int max_header;
- bool no_autobind;
+ int *memory_pressure;
+ long *sysctl_mem;
+ int *sysctl_wmem;
+ int *sysctl_rmem;
+ int max_header;
+ bool no_autobind;
struct kmem_cache *slab;
unsigned int obj_size;
@@ -863,6 +865,70 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */
+#include <linux/memcontrol.h>
+static inline int *sk_memory_pressure(const struct sock *sk)
+{
+ return sk->sk_prot->memory_pressure;
+}
+
+static inline long sk_prot_mem(const struct sock *sk, int index)
+{
+ long *prot = sk->sk_prot->sysctl_mem;
+ return prot[index];
+}
+
+static inline long
+sk_memory_allocated(const struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ return atomic_long_read(prot->memory_allocated);
+}
+
+static inline long
+sk_memory_allocated_add(struct sock *sk, int amt)
+{
+ struct proto *prot = sk->sk_prot;
+ return atomic_long_add_return(amt, prot->memory_allocated);
+}
+
+static inline void
+sk_memory_allocated_sub(struct sock *sk, int amt)
+{
+ struct proto *prot = sk->sk_prot;
+ atomic_long_sub(amt, prot->memory_allocated);
+}
+
+static inline void sk_sockets_allocated_dec(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ percpu_counter_dec(prot->sockets_allocated);
+}
+
+static inline void sk_sockets_allocated_inc(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ percpu_counter_inc(prot->sockets_allocated);
+}
+
+static inline int
+sk_sockets_allocated_read_positive(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+
+ return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline int
+kcg_sockets_allocated_sum_positive(struct proto *prot, struct mem_cgroup *cg)
+{
+ return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline long
+kcg_memory_allocated(struct proto *prot, struct mem_cgroup *cg)
+{
+ return atomic_long_read(prot->memory_allocated);
+}
#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e147f42..ccaa3b6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -44,6 +44,7 @@
#include <net/dst.h>
#include <linux/seq_file.h>
+#include <linux/memcontrol.h>
extern struct inet_hashinfo tcp_hashinfo;
@@ -285,7 +286,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
}
if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
- atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
+ sk_memory_allocated(sk) > sk_prot_mem(sk, 2))
return true;
return false;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 4ed7b1d..26bdb1c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1288,7 +1288,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
newsk->sk_wq = NULL;
if (newsk->sk_prot->sockets_allocated)
- percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+ sk_sockets_allocated_inc(newsk);
if (sock_flag(newsk, SOCK_TIMESTAMP) ||
sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1677,30 +1677,32 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
struct proto *prot = sk->sk_prot;
int amt = sk_mem_pages(size);
long allocated;
+ int *memory_pressure;
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
- allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+ memory_pressure = sk_memory_pressure(sk);
+ allocated = sk_memory_allocated_add(sk, amt);
/* Under limit. */
- if (allocated <= prot->sysctl_mem[0]) {
- if (prot->memory_pressure && *prot->memory_pressure)
- *prot->memory_pressure = 0;
- return 1;
- }
+ if (allocated <= sk_prot_mem(sk, 0))
+ if (memory_pressure && *memory_pressure)
+ *memory_pressure = 0;
/* Under pressure. */
- if (allocated > prot->sysctl_mem[1])
+ if (allocated > sk_prot_mem(sk, 1))
if (prot->enter_memory_pressure)
prot->enter_memory_pressure(sk);
/* Over hard limit. */
- if (allocated > prot->sysctl_mem[2])
+ if (allocated > sk_prot_mem(sk, 2))
goto suppress_allocation;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
return 1;
+
} else { /* SK_MEM_SEND */
if (sk->sk_type == SOCK_STREAM) {
if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
@@ -1710,13 +1712,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
return 1;
}
- if (prot->memory_pressure) {
+ if (memory_pressure) {
int alloc;
- if (!*prot->memory_pressure)
+ if (!*memory_pressure)
return 1;
- alloc = percpu_counter_read_positive(prot->sockets_allocated);
- if (prot->sysctl_mem[2] > alloc *
+ alloc = sk_sockets_allocated_read_positive(sk);
+ if (sk_prot_mem(sk, 2) > alloc *
sk_mem_pages(sk->sk_wmem_queued +
atomic_read(&sk->sk_rmem_alloc) +
sk->sk_forward_alloc))
@@ -1739,7 +1741,9 @@ suppress_allocation:
/* Alas. Undo changes. */
sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
- atomic_long_sub(amt, prot->memory_allocated);
+
+ sk_memory_allocated_sub(sk, amt);
+
return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1750,15 +1754,15 @@ EXPORT_SYMBOL(__sk_mem_schedule);
*/
void __sk_mem_reclaim(struct sock *sk)
{
- struct proto *prot = sk->sk_prot;
+ int *memory_pressure = sk_memory_pressure(sk);
- atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
- prot->memory_allocated);
+ sk_memory_allocated_sub(sk,
+ sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT);
sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
- if (prot->memory_pressure && *prot->memory_pressure &&
- (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
- *prot->memory_pressure = 0;
+ if (memory_pressure && *memory_pressure &&
+ (sk_memory_allocated(sk) < sk_prot_mem(sk, 0)))
+ *memory_pressure = 0;
}
EXPORT_SYMBOL(__sk_mem_reclaim);
@@ -2477,13 +2481,20 @@ static char proto_method_implemented(const void *method)
static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
+ struct mem_cgroup *cg = mem_cgroup_from_task(current);
+ int *memory_pressure = NULL;
+
+ if (proto->memory_pressure)
+ memory_pressure = proto->memory_pressure;
+
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->o
...
|
|
|
|
Current Time: Fri Sep 05 11:32:49 GMT 2025
Total time taken to generate the page: 0.08376 seconds
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
