Re: [PATCHv 2] tcp: properly initialize tcp memory limits part 2 (fix nfs regression)

[Jason Wang <jasowang@redhat.com>]

On 03/02/2012 03:59 PM, Sergei Trofimovich wrote:
> From: Sergei Trofimovich<slyfox@gentoo.org>
>
> The commit c43b874d5d7 introduced NFS file transfer hangup (proved by bisection).
>> Commit 4acb4190 tries to fix the using uninitialized value
>> introduced by commit 3dc43e3,  but it would make the
>> per-socket memory limits too small.
>>
>> This patch fixes this and also remove the redundant codes
>> introduced in 4acb4190.
> The change looks like a typo (division flipped to multiplication):
>> limit = nr_free_buffer_pages() / 8;
>> limit = nr_free_buffer_pages()<<  (PAGE_SHIFT - 10);

Hi, thanks for the reporting. It's not a typo. It was previously: 
sysctl_tcp_mem[1] << (PAGE_SHIFT -  7). Looks like we need to do the 
limit check before shift the value. Please try the following patch, thanks.

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 22ef5f9..4035aab 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3299,8 +3299,8 @@ void __init tcp_init(void)

         tcp_init_mem(&init_net);
         /* Set per-socket limits to no more than 1/128 the pressure 
threshold */
-       limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10);
-       limit = max(limit, 128UL);
+       limit = nr_free_buffer_pages() / 8;
+       limit = max(limit, 128UL) << (PAGE_SHIFT - 7);
         max_share = min(4UL*1024*1024, limit);

         sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;