* [RFC/PATCH 3/3] UDP memory usage accounting (take 2): measurement
@ 2007-09-28 13:41 Satoshi OSHIMA
2007-09-28 14:37 ` Evgeniy Polyakov
0 siblings, 1 reply; 3+ messages in thread
From: Satoshi OSHIMA @ 2007-09-28 13:41 UTC (permalink / raw)
To: Andi Kleen, Evgeniy Polyakov, netdev
Cc: 吉藤 英明, Yumiko SUGITA,
"青木@RedHat"
This patch introduces memory usage measurement for UDP.
These 3 points were updated.
- UDP specific codes in IP layer were removed.
- atomic_sub() in a loop was removed
- accounting during socket destruction
signed-off-by: Satoshi Oshima <satoshi.oshima.fk@hitachi•com>
signed-off-by: Hideo Aoki <haoki@redhat•com>
Index: 2.6.23-rc8-udp_limit/net/ipv4/ip_output.c
===================================================================
--- 2.6.23-rc8-udp_limit.orig/net/ipv4/ip_output.c
+++ 2.6.23-rc8-udp_limit/net/ipv4/ip_output.c
@@ -743,6 +743,8 @@ static inline int ip_ufo_append_data(str
/* specify the length of each IP datagram fragment*/
skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+ atomic_add(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
__skb_queue_tail(&sk->sk_write_queue, skb);
return 0;
@@ -924,6 +926,9 @@ alloc_new_skb:
}
if (skb == NULL)
goto error;
+ if (sk->sk_prot->memory_allocated)
+ atomic_add(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
/*
* Fill in the control structures
@@ -1023,6 +1028,8 @@ alloc_new_skb:
frag = &skb_shinfo(skb)->frags[i];
skb->truesize += PAGE_SIZE;
atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
+ if (sk->sk_prot->memory_allocated)
+ atomic_inc(sk->sk_prot->memory_allocated);
} else {
err = -EMSGSIZE;
goto error;
@@ -1123,7 +1130,9 @@ ssize_t ip_append_page(struct sock *sk,
if (unlikely(!skb)) {
err = -ENOBUFS;
goto error;
- }
+ } else if (sk->sk_prot->memory_allocated)
+ atomic_add(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
/*
* Fill in the control structures
@@ -1152,6 +1161,8 @@ ssize_t ip_append_page(struct sock *sk,
/*
* Put the packet on the pending queue.
*/
+ atomic_add(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
@@ -1202,13 +1213,14 @@ int ip_push_pending_frames(struct sock *
struct iphdr *iph;
__be16 df = 0;
__u8 ttl;
- int err = 0;
+ int err = 0, send_page_size;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
+ send_page_size = sk_datagram_pages(skb->truesize);
if (skb->data < skb_network_header(skb))
__skb_pull(skb, skb_network_offset(skb));
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
@@ -1218,6 +1230,7 @@ int ip_push_pending_frames(struct sock *
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
+ send_page_size += sk_datagram_pages(tmp_skb->truesize);
__sock_put(tmp_skb->sk);
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
@@ -1269,6 +1282,8 @@ int ip_push_pending_frames(struct sock *
/* Netfilter gets whole the not fragmented skb. */
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL,
skb->dst->dev, dst_output);
+ if (sk->sk_prot->memory_allocated)
+ atomic_sub(send_page_size, sk->sk_prot->memory_allocated);
if (err) {
if (err > 0)
err = inet->recverr ? net_xmit_errno(err) : 0;
@@ -1298,9 +1313,15 @@ void ip_flush_pending_frames(struct sock
{
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
+ int num_flush_mem = 0;
- while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
+ while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
+ num_flush_mem += sk_datagram_pages(skb->truesize);
kfree_skb(skb);
+ }
+
+ if (sk->sk_prot->memory_allocated)
+ atomic_sub(num_flush_mem, sk->sk_prot->memory_allocated);
inet->cork.flags &= ~IPCORK_OPT;
kfree(inet->cork.opt);
Index: 2.6.23-rc8-udp_limit/net/ipv4/udp.c
===================================================================
--- 2.6.23-rc8-udp_limit.orig/net/ipv4/udp.c
+++ 2.6.23-rc8-udp_limit/net/ipv4/udp.c
@@ -887,6 +887,9 @@ try_again:
err = ulen;
out_free:
+ atomic_sub(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
+
skb_free_datagram(sk, skb);
out:
return err;
@@ -894,6 +897,9 @@ out:
csum_copy_err:
UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+ atomic_sub(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
+
skb_kill_datagram(sk, skb, flags);
if (noblock)
@@ -1019,6 +1025,9 @@ int udp_queue_rcv_skb(struct sock * sk,
goto drop;
}
+ atomic_add(sk_datagram_pages(skb->truesize),
+ sk->sk_prot->memory_allocated);
+
UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
return 0;
@@ -1443,6 +1452,7 @@ struct proto udp_prot = {
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
+ .memory_allocated = &udp_memory_allocated,
.obj_size = sizeof(struct udp_sock),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
Index: 2.6.23-rc8-udp_limit/net/ipv4/af_inet.c
===================================================================
--- 2.6.23-rc8-udp_limit.orig/net/ipv4/af_inet.c
+++ 2.6.23-rc8-udp_limit/net/ipv4/af_inet.c
@@ -126,13 +126,41 @@ extern void ip_mc_drop_socket(struct soc
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);
+/**
+ * __skb_queue_purge_and_sub_memory_allocated
+ * - empty a list and subtruct memory allocation counter
+ * @sk: sk
+ * @list: list to empty
+ * Delete all buffers on an &sk_buff list and subtruct the
+ * turesize of the sk_buff for memory accounting. Each buffer
+ * is removed from the list and one reference dropped. This
+ * function does not take the list lock and the caller must
+ * hold the relevant locks to use it.
+ */
+void __skb_queue_purge_and_sub_memory_allocated(struct sock *sk,
+ struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+ int purged_skb_size = 0;
+ while ((skb = __skb_dequeue(list)) != NULL) {
+ purged_skb_size += sk_datagram_pages(skb->truesize);
+ kfree_skb(skb);
+ }
+ atomic_sub(purged_skb_size, sk->sk_prot->memory_allocated);
+}
+
/* New destruction routine */
void inet_sock_destruct(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
- __skb_queue_purge(&sk->sk_receive_queue);
+ if (sk->sk_prot->memory_allocated && sk->sk_type != SOCK_STREAM)
+ __skb_queue_purge_and_sub_memory_allocated(sk,
+ &sk->sk_receive_queue);
+ else
+ __skb_queue_purge(&sk->sk_receive_queue);
+
__skb_queue_purge(&sk->sk_error_queue);
if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [RFC/PATCH 3/3] UDP memory usage accounting (take 2): measurement
2007-09-28 13:41 [RFC/PATCH 3/3] UDP memory usage accounting (take 2): measurement Satoshi OSHIMA
@ 2007-09-28 14:37 ` Evgeniy Polyakov
2007-10-01 13:52 ` Satoshi OSHIMA
0 siblings, 1 reply; 3+ messages in thread
From: Evgeniy Polyakov @ 2007-09-28 14:37 UTC (permalink / raw)
To: Satoshi OSHIMA
Cc: Andi Kleen, netdev, 吉藤 英明,
Yumiko SUGITA, 青木@RedHat
On Fri, Sep 28, 2007 at 10:41:31PM +0900, Satoshi OSHIMA (satoshi.oshima.fk@hitachi•com) wrote:
> This patch introduces memory usage measurement for UDP.
>
> These 3 points were updated.
>
> - UDP specific codes in IP layer were removed.
>
> - atomic_sub() in a loop was removed
>
> - accounting during socket destruction
Another approach is to account only at the highest UDP layer and having
datagram skb destructor just like it is done in TCP, but this approach
is also resonable.
I already told that patches 1 and 3 have broken indent, please fix that.
A hint: when you are about to submit something network related for inclusion,
and strongly believes it is ready, it can be a not that bad idea to add
David Miller <davem@davemloft•net> to copy list, he can complain about
backlog and so on, but will read you mail twice :) but do not tell anyone.
--
Evgeniy Polyakov
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [RFC/PATCH 3/3] UDP memory usage accounting (take 2): measurement
2007-09-28 14:37 ` Evgeniy Polyakov
@ 2007-10-01 13:52 ` Satoshi OSHIMA
0 siblings, 0 replies; 3+ messages in thread
From: Satoshi OSHIMA @ 2007-10-01 13:52 UTC (permalink / raw)
To: Evgeniy Polyakov
Cc: Andi Kleen, netdev, ?? ??, Yumiko SUGITA, "??@RedHat",
David Miller, Herbert Xu
Evgeniy Polyakov wrote:
> On Fri, Sep 28, 2007 at 10:41:31PM +0900, Satoshi OSHIMA
(satoshi.oshima.fk@hitachi•com) wrote:
>> This patch introduces memory usage measurement for UDP.
>>
>> These 3 points were updated.
>>
>> - UDP specific codes in IP layer were removed.
>>
>> - atomic_sub() in a loop was removed
>>
>> - accounting during socket destruction
>
> Another approach is to account only at the highest UDP layer and having
> datagram skb destructor just like it is done in TCP, but this approach
> is also resonable.
This patch set try to introduce a memory accounting by the page
because TCP does. And ip_append_data() merges payloads to a sk_buff
if previous sk_buff has enough space. The problem is that
udp_append_data() doesn't recognize whether this merge happens or not.
If the accounting must be in UDP layer, we need to change
the interface of ip_append_data() to know this merge happens.
Once the interface is changed, we have to maintain other
protocol stacks to keep up with the change.
But I didn't want to do it to keep this patch set small
in the first step.
> I already told that patches 1 and 3 have broken indent, please fix that.
Oops! I will fix that.
> A hint: when you are about to submit something network related for
inclusion,
> and strongly believes it is ready, it can be a not that bad idea to add
> David Miller <davem@davemloft•net> to copy list, he can complain about
> backlog and so on, but will read you mail twice :) but do not tell anyone.
Thank you for your advice. I will do that!
Satoshi Oshima
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2007-10-01 13:52 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-09-28 13:41 [RFC/PATCH 3/3] UDP memory usage accounting (take 2): measurement Satoshi OSHIMA
2007-09-28 14:37 ` Evgeniy Polyakov
2007-10-01 13:52 ` Satoshi OSHIMA
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox