[2/2] core: add tracepoints for queueing skb to rcvbuf

This patch adds 2 tracepoints to get a status of a socket receive queue
and related parameter. 

One tracepoint is added to sock_queue_rcv_skb. It records rcvbuf size
and its usage. The other tracepoint is added to __sk_mem_schedule and
it records limitations of memory for sockets and current usage.

By using these tracepoints we're able to know detailed reason why kernel
drop the packet.

Signed-off-by: Satoru Moriya <satoru.moriya@hds.com>
---
 include/trace/events/sock.h |   68 +++++++++++++++++++++++++++++++++++++++++++
 net/core/net-traces.c       |    1 +
 net/core/sock.c             |    5 +++
 3 files changed, 74 insertions(+), 0 deletions(-)
 create mode 100644 include/trace/events/sock.h

On Fri, Jun 17, 2011 at 06:00:03PM -0400, Satoru Moriya wrote:
> This patch adds 2 tracepoints to get a status of a socket receive queue
> and related parameter. 
> 
> One tracepoint is added to sock_queue_rcv_skb. It records rcvbuf size
> and its usage. The other tracepoint is added to __sk_mem_schedule and
> it records limitations of memory for sockets and current usage.
> 
> By using these tracepoints we're able to know detailed reason why kernel
> drop the packet.
> 
> Signed-off-by: Satoru Moriya <satoru.moriya@hds.com>
> ---
>  include/trace/events/sock.h |   68 +++++++++++++++++++++++++++++++++++++++++++
>  net/core/net-traces.c       |    1 +
>  net/core/sock.c             |    5 +++
>  3 files changed, 74 insertions(+), 0 deletions(-)
>  create mode 100644 include/trace/events/sock.h
> 
> diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
> new file mode 100644
> index 0000000..779abb9
> --- /dev/null
> +++ b/include/trace/events/sock.h
> @@ -0,0 +1,68 @@
> +#undef TRACE_SYSTEM
> +#define TRACE_SYSTEM sock
> +
> +#if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ)
> +#define _TRACE_SOCK_H
> +
> +#include <net/sock.h>
> +#include <linux/tracepoint.h>
> +
> +TRACE_EVENT(sock_rcvqueue_full,
> +
> +	TP_PROTO(struct sock *sk, struct sk_buff *skb),
> +
> +	TP_ARGS(sk, skb),
> +
> +	TP_STRUCT__entry(
> +		__field(int, rmem_alloc)
> +		__field(unsigned int, truesize)
> +		__field(int, sk_rcvbuf)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
> +		__entry->truesize   = skb->truesize;
> +		__entry->sk_rcvbuf  = sk->sk_rcvbuf;
> +	),
> +
> +	TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d",
> +		__entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf)
> +);
> +
> +TRACE_EVENT(sock_exceed_buf_limit,
> +
> +	TP_PROTO(struct sock *sk, struct proto *prot, long allocated),
> +
> +	TP_ARGS(sk, prot, allocated),
> +
> +	TP_STRUCT__entry(
> +		__array(char, name, 32)
> +		__field(long *, sysctl_mem)
> +		__field(long, allocated)
> +		__field(int, sysctl_rmem)
> +		__field(int, rmem_alloc)
> +	),
> +
> +	TP_fast_assign(
> +		strncpy(__entry->name, prot->name, 32);
> +		__entry->sysctl_mem = prot->sysctl_mem;
> +		__entry->allocated = allocated;
> +		__entry->sysctl_rmem = prot->sysctl_rmem[0];
> +		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
> +	),
> +
> +	TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld "
> +		"sysctl_rmem=%d rmem_alloc=%d",
> +		__entry->name,
> +		__entry->sysctl_mem[0],
> +		__entry->sysctl_mem[1],
> +		__entry->sysctl_mem[2],
> +		__entry->allocated,
> +		__entry->sysctl_rmem,
> +		__entry->rmem_alloc)
> +);
> +
> +#endif /* _TRACE_SOCK_H */
> +
> +/* This part must be outside protection */
> +#include <trace/define_trace.h>
> diff --git a/net/core/net-traces.c b/net/core/net-traces.c
> index 13aab64..52380b1 100644
> --- a/net/core/net-traces.c
> +++ b/net/core/net-traces.c
> @@ -28,6 +28,7 @@
>  #include <trace/events/skb.h>
>  #include <trace/events/net.h>
>  #include <trace/events/napi.h>
> +#include <trace/events/sock.h>
>  #include <trace/events/udp.h>
>  
>  EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 6e81978..76c4031 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -128,6 +128,8 @@
>  
>  #include <linux/filter.h>
>  
> +#include <trace/events/sock.h>
> +
>  #ifdef CONFIG_INET
>  #include <net/tcp.h>
>  #endif
> @@ -292,6 +294,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
>  	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
>  	    (unsigned)sk->sk_rcvbuf) {
>  		atomic_inc(&sk->sk_drops);
> +		trace_sock_rcvqueue_full(sk, skb);
>  		return -ENOMEM;
>  	}
>  
> @@ -1736,6 +1739,8 @@ suppress_allocation:
>  			return 1;
>  	}
>  
> +	trace_sock_exceed_buf_limit(sk, prot, allocated);
> +
>  	/* Alas. Undo changes. */
>  	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
>  	atomic_long_sub(amt, prot->memory_allocated);
> -- 
> 1.7.1
> 
> 
> 
Acked-by: Neil Horman <nhorman@tuxdriver.com>

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html