The amount of memory allocated to sockets buffer can become significant.
However, we do not display the amount of memory consumed by sockets
buffer. In this case, knowing where the memory is consumed by the kernel
is very difficult. On our server with 500GB RAM, sometimes we can see
25GB disappear through /proc/meminfo. After our analysis, we found the
following memory allocation path which consumes the memory with page_owner
enabled.
849698 times:
Page allocated via order 3, mask 0x4052c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP)
__alloc_pages_nodemask+0x11d/0x290
skb_page_frag_refill+0x68/0xf0
sk_page_frag_refill+0x19/0x70
tcp_sendmsg_locked+0x2f4/0xd10
tcp_sendmsg+0x29/0xa0
sock_sendmsg+0x30/0x40
sock_write_iter+0x8f/0x100
__vfs_write+0x10b/0x190
vfs_write+0xb0/0x190
ksys_write+0x5a/0xd0
do_syscall_64+0x5d/0x110
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: Muchun Song <[email protected]>
---
drivers/base/node.c | 2 ++
drivers/net/virtio_net.c | 3 +--
fs/proc/meminfo.c | 1 +
include/linux/mmzone.h | 1 +
include/linux/skbuff.h | 43 ++++++++++++++++++++++++++++++++++++++--
kernel/exit.c | 3 +--
mm/page_alloc.c | 7 +++++--
mm/vmstat.c | 1 +
net/core/sock.c | 8 ++++----
net/ipv4/tcp.c | 3 +--
net/xfrm/xfrm_state.c | 3 +--
11 files changed, 59 insertions(+), 16 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..6f92775da85c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -418,6 +418,7 @@ static ssize_t node_read_meminfo(struct device *dev,
#ifdef CONFIG_SHADOW_CALL_STACK
"Node %d ShadowCallStack:%8lu kB\n"
#endif
+ "Node %d Sock: %8lu kB\n"
"Node %d PageTables: %8lu kB\n"
"Node %d NFS_Unstable: %8lu kB\n"
"Node %d Bounce: %8lu kB\n"
@@ -441,6 +442,7 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
nid, K(i.sharedram),
nid, node_page_state(pgdat, NR_KERNEL_STACK_KB),
+ nid, K(node_page_state(pgdat, NR_SOCK)),
#ifdef CONFIG_SHADOW_CALL_STACK
nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
#endif
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 263b005981bd..e7183f67ae4a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2646,8 +2646,7 @@ static void free_receive_page_frags(struct virtnet_info *vi)
{
int i;
for (i = 0; i < vi->max_queue_pairs; i++)
- if (vi->rq[i].alloc_frag.page)
- put_page(vi->rq[i].alloc_frag.page);
+ put_page_frag(&vi->rq[i].alloc_frag);
}
static void free_unused_bufs(struct virtnet_info *vi)
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 887a5532e449..1dcf3120d831 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -106,6 +106,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
seq_printf(m, "ShadowCallStack:%8lu kB\n",
global_node_page_state(NR_KERNEL_SCS_KB));
#endif
+ show_val_kb(m, "Sock: ", global_node_page_state(NR_SOCK));
show_val_kb(m, "PageTables: ",
global_zone_page_state(NR_PAGETABLE));
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 31712bb61f7f..1996713d2c6b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -207,6 +207,7 @@ enum node_stat_item {
#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
NR_KERNEL_SCS_KB, /* measured in KiB */
#endif
+ NR_SOCK, /* Count of socket buffer pages */
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fcd53f97c186..7e5108da4d84 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -19,7 +19,8 @@
#include <linux/rbtree.h>
#include <linux/socket.h>
#include <linux/refcount.h>
-
+#include <linux/memcontrol.h>
+#include <linux/mm.h>
#include <linux/atomic.h>
#include <asm/types.h>
#include <linux/spinlock.h>
@@ -3003,6 +3004,25 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
}
+static inline void inc_sock_node_page_state(struct page *page)
+{
+ mod_node_page_state(page_pgdat(page), NR_SOCK, compound_nr(page));
+ /*
+ * Indicate that we need to decrease the Sock page state when
+ * the page freed.
+ */
+ SetPagePrivate(page);
+}
+
+static inline void dec_sock_node_page_state(struct page *page)
+{
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ mod_node_page_state(page_pgdat(page), NR_SOCK,
+ -compound_nr(page));
+ }
+}
+
/**
* __skb_frag_unref - release a reference on a paged fragment.
* @frag: the paged fragment
@@ -3011,7 +3031,12 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
*/
static inline void __skb_frag_unref(skb_frag_t *frag)
{
- put_page(skb_frag_page(frag));
+ struct page *page = skb_frag_page(frag);
+
+ if (put_page_testzero(page)) {
+ dec_sock_node_page_state(page);
+ __put_page(page);
+ }
}
/**
@@ -3091,6 +3116,20 @@ static inline void skb_frag_set_page(struct sk_buff *skb, int f,
__skb_frag_set_page(&skb_shinfo(skb)->frags[f], page);
}
+static inline bool put_page_frag(struct page_frag *pfrag)
+{
+ struct page *page = pfrag->page;
+
+ if (page) {
+ if (put_page_testzero(page)) {
+ dec_sock_node_page_state(page);
+ __put_page(page);
+ }
+ return true;
+ }
+ return false;
+}
+
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);
/**
diff --git a/kernel/exit.c b/kernel/exit.c
index 62912406d74a..58d373767d16 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -841,8 +841,7 @@ void __noreturn do_exit(long code)
if (tsk->splice_pipe)
free_pipe_info(tsk->splice_pipe);
- if (tsk->task_frag.page)
- put_page(tsk->task_frag.page);
+ put_page_frag(&tsk->task_frag);
validate_creds_for_do_exit(tsk);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cefbef32bf4a..6c543158aa06 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5379,7 +5379,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
" unevictable:%lu dirty:%lu writeback:%lu\n"
" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
- " free:%lu free_pcp:%lu free_cma:%lu\n",
+ " free:%lu free_pcp:%lu free_cma:%lu sock:%lu\n",
global_node_page_state(NR_ACTIVE_ANON),
global_node_page_state(NR_INACTIVE_ANON),
global_node_page_state(NR_ISOLATED_ANON),
@@ -5397,7 +5397,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
global_zone_page_state(NR_BOUNCE),
global_zone_page_state(NR_FREE_PAGES),
free_pcp,
- global_zone_page_state(NR_FREE_CMA_PAGES));
+ global_zone_page_state(NR_FREE_CMA_PAGES),
+ global_node_page_state(NR_SOCK));
for_each_online_pgdat(pgdat) {
if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
@@ -5425,6 +5426,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
#ifdef CONFIG_SHADOW_CALL_STACK
" shadow_call_stack:%lukB"
#endif
+ " sock:%lukB"
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -5450,6 +5452,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
#ifdef CONFIG_SHADOW_CALL_STACK
node_page_state(pgdat, NR_KERNEL_SCS_KB),
#endif
+ K(node_page_state(pgdat, NR_SOCK)),
pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
"yes" : "no");
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b05dec387557..ceaf6f85c155 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1220,6 +1220,7 @@ const char * const vmstat_text[] = {
#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
"nr_shadow_call_stack",
#endif
+ "nr_sock",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
diff --git a/net/core/sock.c b/net/core/sock.c
index 5972d26f03ae..1661b423802b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1780,10 +1780,8 @@ static void __sk_destruct(struct rcu_head *head)
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
+ if (put_page_frag(&sk->sk_frag))
sk->sk_frag.page = NULL;
- }
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
@@ -2456,7 +2454,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
}
if (pfrag->offset + sz <= pfrag->size)
return true;
- put_page(pfrag->page);
+ put_page_frag(pfrag);
}
pfrag->offset = 0;
@@ -2469,12 +2467,14 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
SKB_FRAG_PAGE_ORDER);
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
+ inc_sock_node_page_state(pfrag->page);
return true;
}
}
pfrag->page = alloc_page(gfp);
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE;
+ inc_sock_node_page_state(pfrag->page);
return true;
}
return false;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..583761844b4f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2751,8 +2751,7 @@ int tcp_disconnect(struct sock *sk, int flags)
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
+ if (put_page_frag(&sk->sk_frag)) {
sk->sk_frag.page = NULL;
sk->sk_frag.offset = 0;
}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 69520ad3d83b..0f7c16679e49 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -495,8 +495,7 @@ static void ___xfrm_state_destroy(struct xfrm_state *x)
x->type->destructor(x);
xfrm_put_type(x->type);
}
- if (x->xfrag.page)
- put_page(x->xfrag.page);
+ put_page_frag(&x->xfrag);
xfrm_dev_state_free(x);
security_xfrm_state_free(x);
xfrm_state_free(x);
--
2.20.1
Hi,
On 10/10/20 3:38 AM, Muchun Song wrote:
> The amount of memory allocated to sockets buffer can become significant.
> However, we do not display the amount of memory consumed by sockets
> buffer. In this case, knowing where the memory is consumed by the kernel
> is very difficult. On our server with 500GB RAM, sometimes we can see
> 25GB disappear through /proc/meminfo. After our analysis, we found the
> following memory allocation path which consumes the memory with page_owner
> enabled.
>
> 849698 times:
> Page allocated via order 3, mask 0x4052c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP)
> __alloc_pages_nodemask+0x11d/0x290
> skb_page_frag_refill+0x68/0xf0
> sk_page_frag_refill+0x19/0x70
> tcp_sendmsg_locked+0x2f4/0xd10
> tcp_sendmsg+0x29/0xa0
> sock_sendmsg+0x30/0x40
> sock_write_iter+0x8f/0x100
> __vfs_write+0x10b/0x190
> vfs_write+0xb0/0x190
> ksys_write+0x5a/0xd0
> do_syscall_64+0x5d/0x110
> entry_SYSCALL_64_after_hwframe+0x44/0xa9
>
> Signed-off-by: Muchun Song <[email protected]>
> ---
> drivers/base/node.c | 2 ++
> drivers/net/virtio_net.c | 3 +--
> fs/proc/meminfo.c | 1 +
> include/linux/mmzone.h | 1 +
> include/linux/skbuff.h | 43 ++++++++++++++++++++++++++++++++++++++--
> kernel/exit.c | 3 +--
> mm/page_alloc.c | 7 +++++--
> mm/vmstat.c | 1 +
> net/core/sock.c | 8 ++++----
> net/ipv4/tcp.c | 3 +--
> net/xfrm/xfrm_state.c | 3 +--
> 11 files changed, 59 insertions(+), 16 deletions(-)
Thanks for finding that.
Please update Documentation/filesystems/proc.rst "meminfo" section also.
--
~Randy
On Sat, Oct 10, 2020 at 06:38:54PM +0800, Muchun Song wrote:
> The amount of memory allocated to sockets buffer can become significant.
> However, we do not display the amount of memory consumed by sockets
> buffer. In this case, knowing where the memory is consumed by the kernel
> is very difficult. On our server with 500GB RAM, sometimes we can see
> 25GB disappear through /proc/meminfo. After our analysis, we found the
> following memory allocation path which consumes the memory with page_owner
> enabled.
I have a high lelel question.
There is accounting of the socket memory for memcg that gets called from
the networking layer. Did you check if the same call sites can be used
for the system-wide accounting as well?
> 849698 times:
> Page allocated via order 3, mask 0x4052c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP)
> __alloc_pages_nodemask+0x11d/0x290
> skb_page_frag_refill+0x68/0xf0
> sk_page_frag_refill+0x19/0x70
> tcp_sendmsg_locked+0x2f4/0xd10
> tcp_sendmsg+0x29/0xa0
> sock_sendmsg+0x30/0x40
> sock_write_iter+0x8f/0x100
> __vfs_write+0x10b/0x190
> vfs_write+0xb0/0x190
> ksys_write+0x5a/0xd0
> do_syscall_64+0x5d/0x110
> entry_SYSCALL_64_after_hwframe+0x44/0xa9
>
> Signed-off-by: Muchun Song <[email protected]>
> ---
> drivers/base/node.c | 2 ++
> drivers/net/virtio_net.c | 3 +--
Is virtio-net the only dirver that requred an update?
> fs/proc/meminfo.c | 1 +
> include/linux/mmzone.h | 1 +
> include/linux/skbuff.h | 43 ++++++++++++++++++++++++++++++++++++++--
> kernel/exit.c | 3 +--
> mm/page_alloc.c | 7 +++++--
> mm/vmstat.c | 1 +
> net/core/sock.c | 8 ++++----
> net/ipv4/tcp.c | 3 +--
> net/xfrm/xfrm_state.c | 3 +--
> 11 files changed, 59 insertions(+), 16 deletions(-)
>
On Sun, Oct 11, 2020 at 9:53 PM Mike Rapoport <[email protected]> wrote:
>
> On Sat, Oct 10, 2020 at 06:38:54PM +0800, Muchun Song wrote:
> > The amount of memory allocated to sockets buffer can become significant.
> > However, we do not display the amount of memory consumed by sockets
> > buffer. In this case, knowing where the memory is consumed by the kernel
> > is very difficult. On our server with 500GB RAM, sometimes we can see
> > 25GB disappear through /proc/meminfo. After our analysis, we found the
> > following memory allocation path which consumes the memory with page_owner
> > enabled.
>
> I have a high lelel question.
> There is accounting of the socket memory for memcg that gets called from
> the networking layer. Did you check if the same call sites can be used
> for the system-wide accounting as well?
I also think about this. But we did not pass the `struct page` parameter to
the sock accounting memcg API. So we did not know the NUMA node
which allocated the socket buffer memory and cannot do node-level
statistics. In addition, there is another problem. If the user sends a 4096-byte
message, we only charge one page to the memcg but the system allocates 8
pages. So if we reuse the same call sites for the system-wide accounting,
the statistical count we get is always smaller than the actual situation.
>
> > 849698 times:
> > Page allocated via order 3, mask 0x4052c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP)
> > __alloc_pages_nodemask+0x11d/0x290
> > skb_page_frag_refill+0x68/0xf0
> > sk_page_frag_refill+0x19/0x70
> > tcp_sendmsg_locked+0x2f4/0xd10
> > tcp_sendmsg+0x29/0xa0
> > sock_sendmsg+0x30/0x40
> > sock_write_iter+0x8f/0x100
> > __vfs_write+0x10b/0x190
> > vfs_write+0xb0/0x190
> > ksys_write+0x5a/0xd0
> > do_syscall_64+0x5d/0x110
> > entry_SYSCALL_64_after_hwframe+0x44/0xa9
> >
> > Signed-off-by: Muchun Song <[email protected]>
> > ---
> > drivers/base/node.c | 2 ++
> > drivers/net/virtio_net.c | 3 +--
>
> Is virtio-net the only dirver that requred an update?
Yeah, only virtio-net needs an update. Because only it uses the
skb_page_frag_refill() API.
>
> > fs/proc/meminfo.c | 1 +
> > include/linux/mmzone.h | 1 +
> > include/linux/skbuff.h | 43 ++++++++++++++++++++++++++++++++++++++--
> > kernel/exit.c | 3 +--
> > mm/page_alloc.c | 7 +++++--
> > mm/vmstat.c | 1 +
> > net/core/sock.c | 8 ++++----
> > net/ipv4/tcp.c | 3 +--
> > net/xfrm/xfrm_state.c | 3 +--
> > 11 files changed, 59 insertions(+), 16 deletions(-)
> >
--
Yours,
Muchun
On Sun, Oct 11, 2020 at 12:37 AM Randy Dunlap <[email protected]> wrote:
>
> Hi,
>
> On 10/10/20 3:38 AM, Muchun Song wrote:
> > The amount of memory allocated to sockets buffer can become significant.
> > However, we do not display the amount of memory consumed by sockets
> > buffer. In this case, knowing where the memory is consumed by the kernel
> > is very difficult. On our server with 500GB RAM, sometimes we can see
> > 25GB disappear through /proc/meminfo. After our analysis, we found the
> > following memory allocation path which consumes the memory with page_owner
> > enabled.
> >
> > 849698 times:
> > Page allocated via order 3, mask 0x4052c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP)
> > __alloc_pages_nodemask+0x11d/0x290
> > skb_page_frag_refill+0x68/0xf0
> > sk_page_frag_refill+0x19/0x70
> > tcp_sendmsg_locked+0x2f4/0xd10
> > tcp_sendmsg+0x29/0xa0
> > sock_sendmsg+0x30/0x40
> > sock_write_iter+0x8f/0x100
> > __vfs_write+0x10b/0x190
> > vfs_write+0xb0/0x190
> > ksys_write+0x5a/0xd0
> > do_syscall_64+0x5d/0x110
> > entry_SYSCALL_64_after_hwframe+0x44/0xa9
> >
> > Signed-off-by: Muchun Song <[email protected]>
> > ---
> > drivers/base/node.c | 2 ++
> > drivers/net/virtio_net.c | 3 +--
> > fs/proc/meminfo.c | 1 +
> > include/linux/mmzone.h | 1 +
> > include/linux/skbuff.h | 43 ++++++++++++++++++++++++++++++++++++++--
> > kernel/exit.c | 3 +--
> > mm/page_alloc.c | 7 +++++--
> > mm/vmstat.c | 1 +
> > net/core/sock.c | 8 ++++----
> > net/ipv4/tcp.c | 3 +--
> > net/xfrm/xfrm_state.c | 3 +--
> > 11 files changed, 59 insertions(+), 16 deletions(-)
>
> Thanks for finding that.
>
> Please update Documentation/filesystems/proc.rst "meminfo" section also.
Will do. Thanks for your suggestions.
>
> --
> ~Randy
>
--
Yours,
Muchun
On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
>
> The amount of memory allocated to sockets buffer can become significant.
> However, we do not display the amount of memory consumed by sockets
> buffer. In this case, knowing where the memory is consumed by the kernel
We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
rather than /proc/meminfo?
> static inline void __skb_frag_unref(skb_frag_t *frag)
> {
> - put_page(skb_frag_page(frag));
> + struct page *page = skb_frag_page(frag);
> +
> + if (put_page_testzero(page)) {
> + dec_sock_node_page_state(page);
> + __put_page(page);
> + }
> }
You mix socket page frag with skb frag at least, not sure this is exactly
what you want, because clearly skb page frags are frequently used
by network drivers rather than sockets.
Also, which one matches this dec_sock_node_page_state()? Clearly
not skb_fill_page_desc() or __skb_frag_ref().
Thanks.
On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
>
> On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
> >
> > The amount of memory allocated to sockets buffer can become significant.
> > However, we do not display the amount of memory consumed by sockets
> > buffer. In this case, knowing where the memory is consumed by the kernel
>
> We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
> rather than /proc/meminfo?
If the system has little free memory, we can know where the memory is via
/proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
know it when the Sock is not shown in the /proc/meminfo. If the unaware user
can't think of the socket buffer, naturally they will not `ss -m`. The
end result
is that we still don’t know where the memory is consumed. And we add the
Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
>
> > static inline void __skb_frag_unref(skb_frag_t *frag)
> > {
> > - put_page(skb_frag_page(frag));
> > + struct page *page = skb_frag_page(frag);
> > +
> > + if (put_page_testzero(page)) {
> > + dec_sock_node_page_state(page);
> > + __put_page(page);
> > + }
> > }
>
> You mix socket page frag with skb frag at least, not sure this is exactly
> what you want, because clearly skb page frags are frequently used
> by network drivers rather than sockets.
>
> Also, which one matches this dec_sock_node_page_state()? Clearly
> not skb_fill_page_desc() or __skb_frag_ref().
Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
So if someone gets the page returned by skb_page_frag_refill(), it must
put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
to indicate that we need to dec the node page state when the refcount of
page reaches zero.
Thanks.
>
> Thanks.
--
Yours,
Muchun
On Mon, Oct 12, 2020 at 6:22 AM Muchun Song <[email protected]> wrote:
>
> On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
> >
> > On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
> > >
> > > The amount of memory allocated to sockets buffer can become significant.
> > > However, we do not display the amount of memory consumed by sockets
> > > buffer. In this case, knowing where the memory is consumed by the kernel
> >
> > We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
> > rather than /proc/meminfo?
>
> If the system has little free memory, we can know where the memory is via
> /proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
> know it when the Sock is not shown in the /proc/meminfo. If the unaware user
> can't think of the socket buffer, naturally they will not `ss -m`. The
> end result
> is that we still don’t know where the memory is consumed. And we add the
> Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
> v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
>
> >
> > > static inline void __skb_frag_unref(skb_frag_t *frag)
> > > {
> > > - put_page(skb_frag_page(frag));
> > > + struct page *page = skb_frag_page(frag);
> > > +
> > > + if (put_page_testzero(page)) {
> > > + dec_sock_node_page_state(page);
> > > + __put_page(page);
> > > + }
> > > }
> >
> > You mix socket page frag with skb frag at least, not sure this is exactly
> > what you want, because clearly skb page frags are frequently used
> > by network drivers rather than sockets.
> >
> > Also, which one matches this dec_sock_node_page_state()? Clearly
> > not skb_fill_page_desc() or __skb_frag_ref().
>
> Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
> So if someone gets the page returned by skb_page_frag_refill(), it must
> put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
> to indicate that we need to dec the node page state when the refcount of
> page reaches zero.
>
Pages can be transferred from pipe to socket, socket to pipe (splice()
and zerocopy friends...)
If you want to track TCP memory allocations, you always can look at
/proc/net/sockstat,
without adding yet another expensive memory accounting.
On Mon, Oct 12, 2020 at 3:42 PM Eric Dumazet <[email protected]> wrote:
>
> On Mon, Oct 12, 2020 at 6:22 AM Muchun Song <[email protected]> wrote:
> >
> > On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
> > >
> > > On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
> > > >
> > > > The amount of memory allocated to sockets buffer can become significant.
> > > > However, we do not display the amount of memory consumed by sockets
> > > > buffer. In this case, knowing where the memory is consumed by the kernel
> > >
> > > We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
> > > rather than /proc/meminfo?
> >
> > If the system has little free memory, we can know where the memory is via
> > /proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
> > know it when the Sock is not shown in the /proc/meminfo. If the unaware user
> > can't think of the socket buffer, naturally they will not `ss -m`. The
> > end result
> > is that we still don’t know where the memory is consumed. And we add the
> > Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
> > v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
> >
> > >
> > > > static inline void __skb_frag_unref(skb_frag_t *frag)
> > > > {
> > > > - put_page(skb_frag_page(frag));
> > > > + struct page *page = skb_frag_page(frag);
> > > > +
> > > > + if (put_page_testzero(page)) {
> > > > + dec_sock_node_page_state(page);
> > > > + __put_page(page);
> > > > + }
> > > > }
> > >
> > > You mix socket page frag with skb frag at least, not sure this is exactly
> > > what you want, because clearly skb page frags are frequently used
> > > by network drivers rather than sockets.
> > >
> > > Also, which one matches this dec_sock_node_page_state()? Clearly
> > > not skb_fill_page_desc() or __skb_frag_ref().
> >
> > Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
> > So if someone gets the page returned by skb_page_frag_refill(), it must
> > put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
> > to indicate that we need to dec the node page state when the refcount of
> > page reaches zero.
> >
>
> Pages can be transferred from pipe to socket, socket to pipe (splice()
> and zerocopy friends...)
>
> If you want to track TCP memory allocations, you always can look at
> /proc/net/sockstat,
> without adding yet another expensive memory accounting.
The 'mem' item in the /proc/net/sockstat does not represent real
memory usage. This is just the total amount of charged memory.
For example, if a task sends a 10-byte message, it only charges one
page to memcg. But the system may allocate 8 pages. Therefore, it
does not truly reflect the memory allocated by the above memory
allocation path. We can see the difference via the following message.
cat /proc/net/sockstat
sockets: used 698
TCP: inuse 70 orphan 0 tw 617 alloc 134 mem 13
UDP: inuse 90 mem 4
UDPLITE: inuse 0
RAW: inuse 1
FRAG: inuse 0 memory 0
cat /proc/meminfo | grep Sock
Sock: 13664 kB
The /proc/net/sockstat only shows us that there are 17*4 kB TCP
memory allocations. But apply this patch, we can see that we truly
allocate 13664 kB(May be greater than this value because of per-cpu
stat cache). Of course the load of the example here is not high. In
some high load cases, I believe the difference here will be even
greater.
--
Yours,
Muchun
On 10/12/20 10:39 AM, Muchun Song wrote:
> On Mon, Oct 12, 2020 at 3:42 PM Eric Dumazet <[email protected]> wrote:
>>
>> On Mon, Oct 12, 2020 at 6:22 AM Muchun Song <[email protected]> wrote:
>>>
>>> On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
>>>>
>>>> On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
>>>>>
>>>>> The amount of memory allocated to sockets buffer can become significant.
>>>>> However, we do not display the amount of memory consumed by sockets
>>>>> buffer. In this case, knowing where the memory is consumed by the kernel
>>>>
>>>> We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
>>>> rather than /proc/meminfo?
>>>
>>> If the system has little free memory, we can know where the memory is via
>>> /proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
>>> know it when the Sock is not shown in the /proc/meminfo. If the unaware user
>>> can't think of the socket buffer, naturally they will not `ss -m`. The
>>> end result
>>> is that we still don’t know where the memory is consumed. And we add the
>>> Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
>>> v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
>>>
>>>>
>>>>> static inline void __skb_frag_unref(skb_frag_t *frag)
>>>>> {
>>>>> - put_page(skb_frag_page(frag));
>>>>> + struct page *page = skb_frag_page(frag);
>>>>> +
>>>>> + if (put_page_testzero(page)) {
>>>>> + dec_sock_node_page_state(page);
>>>>> + __put_page(page);
>>>>> + }
>>>>> }
>>>>
>>>> You mix socket page frag with skb frag at least, not sure this is exactly
>>>> what you want, because clearly skb page frags are frequently used
>>>> by network drivers rather than sockets.
>>>>
>>>> Also, which one matches this dec_sock_node_page_state()? Clearly
>>>> not skb_fill_page_desc() or __skb_frag_ref().
>>>
>>> Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
>>> So if someone gets the page returned by skb_page_frag_refill(), it must
>>> put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
>>> to indicate that we need to dec the node page state when the refcount of
>>> page reaches zero.
>>>
>>
>> Pages can be transferred from pipe to socket, socket to pipe (splice()
>> and zerocopy friends...)
>>
>> If you want to track TCP memory allocations, you always can look at
>> /proc/net/sockstat,
>> without adding yet another expensive memory accounting.
>
> The 'mem' item in the /proc/net/sockstat does not represent real
> memory usage. This is just the total amount of charged memory.
>
> For example, if a task sends a 10-byte message, it only charges one
> page to memcg. But the system may allocate 8 pages. Therefore, it
> does not truly reflect the memory allocated by the above memory
> allocation path. We can see the difference via the following message.
>
> cat /proc/net/sockstat
> sockets: used 698
> TCP: inuse 70 orphan 0 tw 617 alloc 134 mem 13
> UDP: inuse 90 mem 4
> UDPLITE: inuse 0
> RAW: inuse 1
> FRAG: inuse 0 memory 0
>
> cat /proc/meminfo | grep Sock
> Sock: 13664 kB
>
> The /proc/net/sockstat only shows us that there are 17*4 kB TCP
> memory allocations. But apply this patch, we can see that we truly
> allocate 13664 kB(May be greater than this value because of per-cpu
> stat cache). Of course the load of the example here is not high. In
> some high load cases, I believe the difference here will be even
> greater.
>
This is great, but you have not addressed my feedback.
TCP memory allocations are bounded by /proc/sys/net/ipv4/tcp_mem
Fact that the memory is forward allocated or not is a detail.
If you think we must pre-allocate memory, instead of forward allocations,
your patch does not address this. Adding one line per consumer in /proc/meminfo looks
wrong to me.
If you do not want 9.37 % of physical memory being possibly used by TCP,
just change /proc/sys/net/ipv4/tcp_mem accordingly ?
On Sun, Oct 11, 2020 at 9:22 PM Muchun Song <[email protected]> wrote:
>
> On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
> >
> > On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
> > >
> > > The amount of memory allocated to sockets buffer can become significant.
> > > However, we do not display the amount of memory consumed by sockets
> > > buffer. In this case, knowing where the memory is consumed by the kernel
> >
> > We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
> > rather than /proc/meminfo?
>
> If the system has little free memory, we can know where the memory is via
> /proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
> know it when the Sock is not shown in the /proc/meminfo. If the unaware user
> can't think of the socket buffer, naturally they will not `ss -m`. The
> end result
Interesting, we already have a few counters related to socket buffers,
are you saying these are not accounted in /proc/meminfo either?
If yes, why are page frags so special here? If not, they are more
important than page frags, so you probably want to deal with them
first.
> is that we still don’t know where the memory is consumed. And we add the
> Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
> v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
It looks like actually the socket page frag is already accounted,
for example, the tcp_sendmsg_locked():
copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
>
> >
> > > static inline void __skb_frag_unref(skb_frag_t *frag)
> > > {
> > > - put_page(skb_frag_page(frag));
> > > + struct page *page = skb_frag_page(frag);
> > > +
> > > + if (put_page_testzero(page)) {
> > > + dec_sock_node_page_state(page);
> > > + __put_page(page);
> > > + }
> > > }
> >
> > You mix socket page frag with skb frag at least, not sure this is exactly
> > what you want, because clearly skb page frags are frequently used
> > by network drivers rather than sockets.
> >
> > Also, which one matches this dec_sock_node_page_state()? Clearly
> > not skb_fill_page_desc() or __skb_frag_ref().
>
> Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
How is skb_page_frag_refill() possibly paired with __skb_frag_unref()?
> So if someone gets the page returned by skb_page_frag_refill(), it must
> put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
> to indicate that we need to dec the node page state when the refcount of
> page reaches zero.
skb_page_frag_refill() is called on frags not within an skb, for instance,
sk_page_frag_refill() uses it for a per-socket or per-process page frag.
But, __skb_frag_unref() is specifically used for skb frags, which are
supposed to be filled by skb_fill_page_desc() (page is allocated by driver).
They are different things you are mixing them up, which looks clearly
wrong or at least misleading.
Thanks.
On Tue, Oct 13, 2020 at 5:47 AM Cong Wang <[email protected]> wrote:
>
> On Sun, Oct 11, 2020 at 9:22 PM Muchun Song <[email protected]> wrote:
> >
> > On Mon, Oct 12, 2020 at 2:39 AM Cong Wang <[email protected]> wrote:
> > >
> > > On Sat, Oct 10, 2020 at 3:39 AM Muchun Song <[email protected]> wrote:
> > > >
> > > > The amount of memory allocated to sockets buffer can become significant.
> > > > However, we do not display the amount of memory consumed by sockets
> > > > buffer. In this case, knowing where the memory is consumed by the kernel
> > >
> > > We do it via `ss -m`. Is it not sufficient? And if not, why not adding it there
> > > rather than /proc/meminfo?
> >
> > If the system has little free memory, we can know where the memory is via
> > /proc/meminfo. If a lot of memory is consumed by socket buffer, we cannot
> > know it when the Sock is not shown in the /proc/meminfo. If the unaware user
> > can't think of the socket buffer, naturally they will not `ss -m`. The
> > end result
>
> Interesting, we already have a few counters related to socket buffers,
> are you saying these are not accounted in /proc/meminfo either?
Yeah, these are not accounted for in /proc/meminfo.
> If yes, why are page frags so special here? If not, they are more
> important than page frags, so you probably want to deal with them
> first.
>
>
> > is that we still don’t know where the memory is consumed. And we add the
> > Sock to the /proc/meminfo just like the memcg does('sock' item in the cgroup
> > v2 memory.stat). So I think that adding to /proc/meminfo is sufficient.
>
> It looks like actually the socket page frag is already accounted,
> for example, the tcp_sendmsg_locked():
>
> copy = min_t(int, copy, pfrag->size - pfrag->offset);
>
> if (!sk_wmem_schedule(sk, copy))
> goto wait_for_memory;
>
Yeah, it is already accounted for. But it does not represent real memory
usage. This is just the total amount of charged memory.
For example, if a task sends a 10-byte message, it only charges one
page to memcg. But the system may allocate 8 pages. Therefore, it
does not truly reflect the memory allocated by the page frag memory
allocation path.
>
> >
> > >
> > > > static inline void __skb_frag_unref(skb_frag_t *frag)
> > > > {
> > > > - put_page(skb_frag_page(frag));
> > > > + struct page *page = skb_frag_page(frag);
> > > > +
> > > > + if (put_page_testzero(page)) {
> > > > + dec_sock_node_page_state(page);
> > > > + __put_page(page);
> > > > + }
> > > > }
> > >
> > > You mix socket page frag with skb frag at least, not sure this is exactly
> > > what you want, because clearly skb page frags are frequently used
> > > by network drivers rather than sockets.
> > >
> > > Also, which one matches this dec_sock_node_page_state()? Clearly
> > > not skb_fill_page_desc() or __skb_frag_ref().
> >
> > Yeah, we call inc_sock_node_page_state() in the skb_page_frag_refill().
>
> How is skb_page_frag_refill() possibly paired with __skb_frag_unref()?
>
> > So if someone gets the page returned by skb_page_frag_refill(), it must
> > put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_private
> > to indicate that we need to dec the node page state when the refcount of
> > page reaches zero.
>
> skb_page_frag_refill() is called on frags not within an skb, for instance,
> sk_page_frag_refill() uses it for a per-socket or per-process page frag.
> But, __skb_frag_unref() is specifically used for skb frags, which are
> supposed to be filled by skb_fill_page_desc() (page is allocated by driver).
>
> They are different things you are mixing them up, which looks clearly
> wrong or at least misleading.
Yeah, it looks a little strange. I just want to account for page frag
allocations. So I have to use PG_private to distinguish the page
from page frag or others in the __skb_frag_unref(). If the page is
allocated from skb_page_frag_refill, we should decrease the
statistics.
Thanks.
>
> Thanks.
--
Yours,
Muchun