From: Hideo AOKI <haoki@redhat.com>
To: David Miller <davem@davemloft.net>, netdev <netdev@vger.kernel.org>
Cc: Satoshi Oshima <satoshi.oshima.fk@hitachi.com>,
Herbert Xu <herbert@gondor.apana.org.au>,
Andi Kleen <andi@firstfloor.org>,
Stephen Hemminger <shemminger@linux-foundation.org>,
Evgeniy Polyakov <johnpol@2ka.mipt.ru>,
yoshfuji@linux-ipv6.org,
Yumiko Sugita <yumiko.sugita.yf@hitachi.com>
Subject: [PATCH 2/5] accounting unit and variable
Date: Mon, 29 Oct 2007 17:23:10 -0400 [thread overview]
Message-ID: <47264F3E.3080306@redhat.com> (raw)
In-Reply-To: <47264E2D.4080109@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 139 bytes --]
This patch introduces global variable for UDP memory accounting.
The unit is page.
--
Hideo Aoki
Hitachi Computer Products (America) Inc.
[-- Attachment #2: udp_memory_account_common.patch --]
[-- Type: text/x-patch, Size: 2960 bytes --]
Signed-off-by: Satoshi Oshima <satoshi.oshima.fk@hitachi.com>
Signed-off-by: Hideo Aoki <haoki@redhat.com>
include/net/sock.h | 7 +++++++
include/net/udp.h | 2 ++
net/ipv4/proc.c | 3 ++-
net/ipv4/udp.c | 2 ++
4 files changed, 13 insertions(+), 1 deletion(-)
diff -pruN linux-2.6.24-rc1-mem003-ipv4-dev-p1/include/net/sock.h linux-2.6.24-rc1-mem003-ipv4-dev-p2/include/net/sock.h
--- linux-2.6.24-rc1-mem003-ipv4-dev-p1/include/net/sock.h 2007-10-24 11:34:32.000000000 -0400
+++ linux-2.6.24-rc1-mem003-ipv4-dev-p2/include/net/sock.h 2007-10-24 11:47:51.000000000 -0400
@@ -727,6 +727,13 @@ static inline int sk_stream_wmem_schedul
sk_stream_mem_schedule(sk, size, 0);
}
+#define SK_DATAGRAM_MEM_QUANTUM ((int)PAGE_SIZE)
+
+static inline int sk_datagram_pages(int amt)
+{
+ return DIV_ROUND_UP(amt, SK_DATAGRAM_MEM_QUANTUM);
+}
+
/* Used by processes to "lock" a socket state, so that
* interrupts and bottom half handlers won't change it
* from under us. It essentially blocks any incoming
diff -pruN linux-2.6.24-rc1-mem003-ipv4-dev-p1/include/net/udp.h linux-2.6.24-rc1-mem003-ipv4-dev-p2/include/net/udp.h
--- linux-2.6.24-rc1-mem003-ipv4-dev-p1/include/net/udp.h 2007-10-10 11:49:42.000000000 -0400
+++ linux-2.6.24-rc1-mem003-ipv4-dev-p2/include/net/udp.h 2007-10-24 11:47:51.000000000 -0400
@@ -65,6 +65,8 @@ extern rwlock_t udp_hash_lock;
extern struct proto udp_prot;
+extern atomic_t udp_memory_allocated;
+
struct sk_buff;
/*
diff -pruN linux-2.6.24-rc1-mem003-ipv4-dev-p1/net/ipv4/proc.c linux-2.6.24-rc1-mem003-ipv4-dev-p2/net/ipv4/proc.c
--- linux-2.6.24-rc1-mem003-ipv4-dev-p1/net/ipv4/proc.c 2007-10-24 11:34:34.000000000 -0400
+++ linux-2.6.24-rc1-mem003-ipv4-dev-p2/net/ipv4/proc.c 2007-10-24 11:47:51.000000000 -0400
@@ -67,7 +67,8 @@ static int sockstat_seq_show(struct seq_
fold_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count),
tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated),
atomic_read(&tcp_memory_allocated));
- seq_printf(seq, "UDP: inuse %d\n", fold_prot_inuse(&udp_prot));
+ seq_printf(seq, "UDP: inuse %d mem %d\n", fold_prot_inuse(&udp_prot),
+ atomic_read(&udp_memory_allocated));
seq_printf(seq, "UDPLITE: inuse %d\n", fold_prot_inuse(&udplite_prot));
seq_printf(seq, "RAW: inuse %d\n", fold_prot_inuse(&raw_prot));
seq_printf(seq, "FRAG: inuse %d memory %d\n",
diff -pruN linux-2.6.24-rc1-mem003-ipv4-dev-p1/net/ipv4/udp.c linux-2.6.24-rc1-mem003-ipv4-dev-p2/net/ipv4/udp.c
--- linux-2.6.24-rc1-mem003-ipv4-dev-p1/net/ipv4/udp.c 2007-10-24 11:34:35.000000000 -0400
+++ linux-2.6.24-rc1-mem003-ipv4-dev-p2/net/ipv4/udp.c 2007-10-24 12:27:37.000000000 -0400
@@ -114,6 +114,8 @@ DEFINE_SNMP_STAT(struct udp_mib, udp_sta
struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);
+atomic_t udp_memory_allocated;
+
static inline int __udp_lib_lport_inuse(__u16 num,
const struct hlist_head udptable[])
{
next prev parent reply other threads:[~2007-10-29 21:27 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-29 21:18 [PATCH 0/5] UDP memory accounting and limitation (take 6) Hideo AOKI
2007-10-29 21:22 ` [PATCH 1/5] fix send buffer check Hideo AOKI
2007-11-09 12:24 ` Herbert Xu
2007-11-14 3:25 ` Hideo AOKI
2007-10-29 21:23 ` Hideo AOKI [this message]
2007-11-09 12:34 ` [PATCH 2/5] accounting unit and variable Herbert Xu
2007-11-14 3:27 ` Hideo AOKI
2007-11-14 3:45 ` Herbert Xu
2007-11-14 3:55 ` David Miller
2007-11-14 15:32 ` Hideo AOKI
2007-11-14 23:30 ` Hideo AOKI
2007-11-15 1:09 ` Herbert Xu
2007-11-15 21:37 ` Hideo AOKI
2007-10-29 21:23 ` [PATCH 3/5] memory accounting Hideo AOKI
2007-11-09 13:07 ` Herbert Xu
2007-10-29 21:23 ` [PATCH 4/5] memory limitation by using udp_mem Hideo AOKI
2007-10-29 21:23 ` [PATCH 5/5] introduce udp_rmem and udp_wmem Hideo AOKI
2007-10-30 4:52 ` Bill Fink
2007-11-02 15:42 ` Hideo AOKI
-- strict thread matches above, loose matches on Subject: below --
2007-11-14 2:39 [PATCH 0/5] UDP memory accounting and limitation (take 7) Hideo AOKI
2007-11-14 2:48 ` [PATCH 2/5] accounting unit and variable Hideo AOKI
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=47264F3E.3080306@redhat.com \
--to=haoki@redhat.com \
--cc=andi@firstfloor.org \
--cc=davem@davemloft.net \
--cc=herbert@gondor.apana.org.au \
--cc=johnpol@2ka.mipt.ru \
--cc=netdev@vger.kernel.org \
--cc=satoshi.oshima.fk@hitachi.com \
--cc=shemminger@linux-foundation.org \
--cc=yoshfuji@linux-ipv6.org \
--cc=yumiko.sugita.yf@hitachi.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).