Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\.6\.11\-rc4\-mm1\]\s+connector\:\s+Add\s+a\s+fork\s+connector\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\.6\.11\-rc4\-mm1\]\s+connector\:\s+Add\s+a\s+fork\s+connector\s*$/: 16 ]

Total 16 documents matching your query.

1. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: rzik@xxxxxxxxx>; Date: Wed, 02 Mar 2005 09:48:12 +0100; - Add parenthesis around sizeof(struct cn_msg) + CN_FORK_INFO_SIZE in the CN_FORK_MSG_SIZE macro - fork_cn_lock is declareed with DEFINE_SPINLOCK() - fork_cn_lock is defined as static and local to f; /archives/netdev/2005-03/msg00052.html (18,090 bytes)
2. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: bunk@xxxxxxxxx>; Date: Wed, 2 Mar 2005 06:51:52 -0800; Good. If I read this code right: then the code executed if the fork connector is off is a call to an inline function that tests an integer, finds it zero, and returns. This is sufficiently little cod; /archives/netdev/2005-03/msg00068.html (10,029 bytes)
3. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: on <pj@xxxxxxx>; Date: Wed, 2 Mar 2005 07:50:55 -0800; In addition to worrying about performance and scaling, with accounting enabled or disabled, one should also try to minimize code clutter in key kernel files, such as fork.c For example, one might, in; /archives/netdev/2005-03/msg00071.html (10,328 bytes)
4. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: .grossman@xxxxxxxxxxxx>; Date: Wed, 2 Mar 2005 09:48:26 -0800; But if it *is* enabled, it takes a global lock on every fork. That can't scale on a big multiprocessor if lots of CPUs are doing lots of forks... Jesse; /archives/netdev/2005-03/msg00077.html (10,433 bytes)
5. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: el Wu <flamingice@xxxxxxxxxxxx>; Date: Thu, 03 Mar 2005 12:18:25 +0900; I tried to measure the process-creation/destruction performance on 2.6.11-rc4-mm1 plus some extensiton(Normal/with PAGG/with Fork-Connector). But I received a following messages endlessly on system; /archives/netdev/2005-03/msg00118.html (14,201 bytes)
6. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: ai Kohei <kaigai@xxxxxxxxxxxxx>; Date: Thu, 3 Mar 2005 08:46:56 +0300; On Thu, Mar 03, 2005 at 12:18:25PM +0900, Kaigai Kohei (kaigai@xxxxxxxxxxxxx) No, lengths are correct, but skb can be dropped due to misaligned sizes check. I've sent that patch to Guillaume and upst; /archives/netdev/2005-03/msg00119.html (16,820 bytes)
7. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: x>; Date: Thu, 03 Mar 2005 14:51:29 +0300; Simple program to test fork() performance. include <sys/signal.h> include <sys/time.h> int main(int argc, char *argv[]) { int pid; int i = 0, max = 100000; struct timeval tv0, tv1; struct timezone tz; /archives/netdev/2005-03/msg00124.html (11,214 bytes)
8. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Polyakov <johnpol@xxxxxxxxxxx>; Date: Thu, 03 Mar 2005 15:20:44 +0300; ... In a bit more advanced version it checks for error value, but it never happend. It can also have more fine grained measurment, but IMHO the picture is clear for small systems. Actually sometimes; /archives/netdev/2005-03/msg00125.html (11,624 bytes)
9. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Guillaume Thouvenin <guillaume.thouvenin@xxxxxxxx>; Date: Wed, 02 Mar 2005 09:48:12 +0100; ChangeLog: - Add parenthesis around sizeof(struct cn_msg) + CN_FORK_INFO_SIZE in the CN_FORK_MSG_SIZE macro - fork_cn_lock is declareed with DEFINE_SPINLOCK() - fork_cn_lock is defined as static and; /archives/netdev/2005-03/msg01975.html (18,212 bytes)
10. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Paul Jackson <pj@xxxxxxx>; Date: Wed, 2 Mar 2005 06:51:52 -0800; Good. If I read this code right: then the code executed if the fork connector is off is a call to an inline function that tests an integer, finds it zero, and returns. This is sufficiently little cod; /archives/netdev/2005-03/msg01991.html (10,156 bytes)
11. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Paul Jackson <pj@xxxxxxx>; Date: Wed, 2 Mar 2005 07:50:55 -0800; In addition to worrying about performance and scaling, with accounting enabled or disabled, one should also try to minimize code clutter in key kernel files, such as fork.c For example, one might, in; /archives/netdev/2005-03/msg01994.html (10,455 bytes)
12. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Jesse Barnes <jbarnes@xxxxxxxxxxxx>; Date: Wed, 2 Mar 2005 09:48:26 -0800; But if it *is* enabled, it takes a global lock on every fork. That can't scale on a big multiprocessor if lots of CPUs are doing lots of forks... Jesse; /archives/netdev/2005-03/msg02000.html (10,595 bytes)
13. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Kaigai Kohei <kaigai@xxxxxxxxxxxxx>; Date: Thu, 03 Mar 2005 12:18:25 +0900; Hello, Guillaume I tried to measure the process-creation/destruction performance on 2.6.11-rc4-mm1 plus some extensiton(Normal/with PAGG/with Fork-Connector). But I received a following messages endl; /archives/netdev/2005-03/msg02041.html (14,328 bytes)
14. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Evgeniy Polyakov <johnpol@xxxxxxxxxxx>; Date: Thu, 3 Mar 2005 08:46:56 +0300; On Thu, Mar 03, 2005 at 12:18:25PM +0900, Kaigai Kohei (kaigai@xxxxxxxxxxxxx) wrote: No, lengths are correct, but skb can be dropped due to misaligned sizes check. I've sent that patch to Guillaume a; /archives/netdev/2005-03/msg02042.html (17,000 bytes)
15. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Evgeniy Polyakov <johnpol@xxxxxxxxxxx>; Date: Thu, 03 Mar 2005 14:51:29 +0300; Simple program to test fork() performance. include <sys/signal.h> include <sys/time.h> int main(int argc, char *argv[]) { int pid; int i = 0, max = 100000; struct timeval tv0, tv1; struct timezone tz; /archives/netdev/2005-03/msg02047.html (11,388 bytes)
16. Re: [PATCH 2.6.11-rc4-mm1] connector: Add a fork connector (score: 1): Author: Evgeniy Polyakov <johnpol@xxxxxxxxxxx>; Date: Thu, 03 Mar 2005 15:20:44 +0300; ... In a bit more advanced version it checks for error value, but it never happend. It can also have more fine grained measurment, but IMHO the picture is clear for small systems. Actually sometimes; /archives/netdev/2005-03/msg02048.html (11,893 bytes)

Current List: 1 - 16
Page: [1]