Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+no\s+more\s+rwlock_t\s+inside\s+tcp_ehash

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+no\s+more\s+rwlock_t\s+inside\s+tcp_ehash_bucket\s*$/: 4 ]

Total 4 documents matching your query.

1. eterion/S2io 10GbE Adapters (score: 1): Author: ian Bunk <bunk@xxxxxxxxx>; Date: Tue, 15 Mar 2005 17:13:11 +0100; A machine with large tcp_ehash uses half the size of the hash to store rwlocks. That seems not really necessary : - Most accesses to tcp_ehash[] are done with read_locks(), so dirtying the memory (be; /archives/netdev/2005-03/msg00922.html (22,905 bytes)
2. /fc.c: remove fc_type_trans (score: 1): Author: 明 <yoshfuji@xxxxxxxxxxxxxx>; Date: Tue, 15 Mar 2005 10:32:53 -0800; I'm generally in support of this change, however 2 suggestions: 1) Please allocate the rwlock table dynamically. You can put we don't do silly things like allocate a zero sized table on non-SMP build; /archives/netdev/2005-03/msg00932.html (9,113 bytes)
3. [PATCH] no more rwlock_t inside tcp_ehash_bucket (score: 1): Author: Eric Dumazet <dada1@xxxxxxxxxxxxx>; Date: Tue, 15 Mar 2005 17:13:11 +0100; A machine with large tcp_ehash uses half the size of the hash to store rwlocks. That seems not really necessary : - Most accesses to tcp_ehash[] are done with read_locks(), so dirtying the memory (be; /archives/netdev/2005-03/msg02845.html (21,542 bytes)
4. Re: [PATCH] no more rwlock_t inside tcp_ehash_bucket (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Tue, 15 Mar 2005 10:32:53 -0800; I'm generally in support of this change, however 2 suggestions: 1) Please allocate the rwlock table dynamically. You can put we don't do silly things like allocate a zero sized table on non-SMP build; /archives/netdev/2005-03/msg02855.html (9,161 bytes)

Current List: 1 - 4
Page: [1]