Home » Mailing lists » Devel » [PATCH v6 0/8] per-cgroup tcp memory pressure handling
| [PATCH v6 3/8] foundations of per-cgroup memory pressure controlling. [message #43725 is a reply to message #43724] |
Mon, 10 October 2011 10:24   |
Glauber Costa
Messages: 916
Registered: October 2011
|
Senior Member |
|
|
This patch converts struct sock fields memory_pressure,
memory_allocated, sockets_allocated, and sysctl_mem (now prot_mem)
to function pointers, receiving a struct mem_cgroup parameter.
enter_memory_pressure is kept the same, since all its callers
have socket a context, and the kmem_cgroup can be derived from
the socket itself.
To keep things working, the patch convert all users of those fields
to use acessor functions.
In my benchmarks I didn't see a significant performance difference
with this patch applied compared to a baseline (around 1 % diff, thus
inside error margin).
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>
---
crypto/af_alg.c | 8 +++-
include/linux/memcontrol.h | 22 ++++++++-
include/net/sock.h | 114 ++++++++++++++++++++++++++++++++++++++++--
include/net/tcp.h | 12 +++--
include/net/udp.h | 4 +-
include/trace/events/sock.h | 10 ++--
mm/memcontrol.c | 19 ++++++-
net/core/sock.c | 62 ++++++++++++++---------
net/decnet/af_decnet.c | 22 +++++++-
net/ipv4/proc.c | 7 ++-
net/ipv4/tcp.c | 28 +++++++++-
net/ipv4/tcp_input.c | 12 ++--
net/ipv4/tcp_ipv4.c | 12 ++--
net/ipv4/tcp_output.c | 2 +-
net/ipv4/tcp_timer.c | 2 +-
net/ipv4/udp.c | 21 ++++++--
net/ipv6/tcp_ipv6.c | 10 ++--
net/ipv6/udp.c | 4 +-
net/sctp/socket.c | 37 +++++++++++---
19 files changed, 320 insertions(+), 88 deletions(-)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ac33d5f..09cdf11 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -29,10 +29,16 @@ struct alg_type_list {
static atomic_long_t alg_memory_allocated;
+static long memory_allocated_alg(struct mem_cgroup *memcg, long val,
+ int *parent_status)
+{
+ return atomic_long_add_return(val, &alg_memory_allocated);
+}
+
static struct proto alg_proto = {
.name = "ALG",
.owner = THIS_MODULE,
- .memory_allocated = &alg_memory_allocated,
+ .mem_allocated_add = memory_allocated_alg,
.obj_size = sizeof(struct alg_sock),
};
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 88aea1b..99a8ba2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -361,6 +361,10 @@ 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)
@@ -377,12 +381,28 @@ mem_cgroup_print_bad_page(struct page *page)
#endif
#ifdef CONFIG_INET
+enum {
+ UNDER_LIMIT,
+ OVER_LIMIT,
+};
+
struct sock;
+struct proto;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
void sock_update_memcg(struct sock *sk);
void sock_release_memcg(struct sock *sk);
-
+void memcg_sockets_allocated_dec(struct mem_cgroup *memcg, struct proto *prot);
+void memcg_sockets_allocated_inc(struct mem_cgroup *memcg, struct proto *prot);
#else
+/* memcontrol includes sockets.h, that includes memcontrol.h ... */
+static inline void memcg_sockets_allocated_dec(struct mem_cgroup *memcg,
+ struct proto *prot)
+{
+}
+static inline void memcg_sockets_allocated_inc(struct mem_cgroup *memcg,
+ struct proto *prot)
+{
+}
static inline void sock_update_memcg(struct sock *sk)
{
}
diff --git a/include/net/sock.h b/include/net/sock.h
index afe1467..163f87b 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
@@ -786,18 +789,36 @@ struct proto {
unsigned int inuse_idx;
#endif
+ /*
+ * per-cgroup memory tracking:
+ *
+ * The following functions track memory consumption of network buffers
+ * by cgroup (kmem_cgroup) for the current protocol. As of the rest
+ * of the fields in this structure, not all protocols are required
+ * to implement them. Protocols that don't want to do per-cgroup
+ * memory pressure management, can just assume the root cgroup is used.
+ *
+ */
/* 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. */
/*
- * Pressure flag: try to collapse.
+ * Add a value in pages to the current memory allocation,
+ * and return the current value.
+ */
+ long (*mem_allocated_add)(struct mem_cgroup *memcg,
+ long val, int *parent_status);
+ /* Pointer to the current number of sockets in this cgroup. */
+ struct percpu_counter *(*sockets_allocated)(const struct mem_cgroup *memcg);
+ /*
+ * Per cgroup pointer to the 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 *(*memory_pressure)(const struct mem_cgroup *memcg);
+ /* Pointer to the per-cgroup version of the the sysctl_mem field */
+ long *(*prot_mem)(const struct mem_cgroup *memcg);
+
int *sysctl_wmem;
int *sysctl_rmem;
int max_header;
@@ -856,6 +877,87 @@ 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(struct sock *sk)
+{
+ int *ret = NULL;
+ if (sk->sk_prot->memory_pressure)
+ ret = sk->sk_prot->memory_pressure(sk->sk_cgrp);
+ return ret;
+}
+
+static inline long sk_prot_mem(struct sock *sk, int index)
+{
+ long *prot = sk->sk_prot->prot_mem(sk->sk_cgrp);
+ return prot[index];
+}
+
+static inline long
+sk_memory_allocated(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ return prot->mem_allocated_add(cg, 0, NULL);
+}
+
+static inline long
+sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ return prot->mem_allocated_add(cg, amt, parent_status);
+}
+
+static inline void
+sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ prot->mem_allocated_add(cg, -amt, &parent_status);
+}
+
+static inline void sk_sockets_allocated_dec(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ percpu_counter_dec(prot->sockets_allocated(cg));
+ memcg_sockets_allocated_dec(cg, prot);
+}
+
+static inline void sk_sockets_allocated_inc(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ percpu_counter_inc(prot->sockets_allocated(cg));
+ memcg_sockets_allocated_inc(cg, prot);
+}
+
+static inline int
+sk_sockets_allocated_read_positive(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ struct mem_cgroup *cg = sk->sk_cgrp;
+
+ return percpu_counter_sum_positive(prot->sockets_allocated(cg));
+}
+
+static inline int
+kcg_sockets_allocated_sum_positive(struct proto *prot, struct mem_cgroup *cg)
+{
+ return percpu_counter_sum_positive(prot->sockets_allocated(cg));
+}
+
+static inline long
+kcg_memory_allocated(struct proto *prot, struct mem_cgroup *cg)
+{
+ return prot->mem_allocated_add(cg, 0, NULL);
+}
+
#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
@@ -952,7 +1054,7 @@ static inline int sk_mem_pages(int amt)
static inline int sk_has_account(struct sock *sk)
{
/* return true if protocol supports memory accounting */
- return !!sk->sk_prot->memory_allocated;
+ return !!sk->sk_prot->mem_allocated_add;
}
static inline int sk_wmem_schedule(struct sock *sk, int size)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index acc620a..eac7bf6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -45,6 +45,7 @@
#include <net/dst.h>
#include <linux/seq_file.h>
+#include <linux/memcontrol.h>
extern struct inet_hashinfo tcp_hashinfo;
@@ -253,9 +254,12 @@ extern int sysctl_tcp_cookie_size;
extern int sysctl_tcp_thin_linear_timeouts;
extern int sysctl_tcp_thin_dupack;
-extern atomic_long_t tcp_memory_allocated;
-extern struct percpu_counter tcp_sockets_allocated;
-extern int tcp_memory_pressure;
+struct mem_cgroup;
+extern long *tcp_sysctl_mem(const struct mem_cgroup *memcg);
+struct percpu_counter *sockets_allocated_tcp(const struct mem_cgroup *memcg);
+int *memory_pressure_tcp(const struct mem_cgroup *memcg);
+long memory_allocated_tcp_add(struct mem_cgroup *memcg, long val,
+ int *parent_status);
/*
* The next routines deal with comparing 32 bit unsigned ints
@@ -286,7 +290,7 @@ 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/include/net/udp.h b/include/net/udp.h
index 67ea6fc..eecd727 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -105,7 +105,9 @@
...
|
|
|
|
Current Time: Wed Oct 02 20:33:27 GMT 2024
Total time taken to generate the page: 0.06140 seconds
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
