Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+\"lockless\s+loopback\"\s+patch\s+for\s+2\.6\.6\s*$/: 8 ]

Total 8 documents matching your query.

1. ty. (score: 1)
Author: xxxxxxx>
Date: Fri, 21 May 2004 14:04:09 -0700
Lock contention on the loopback device can lead to poor performance, even an essentially hung system, on systems with many processors. For the loopback device, the only purpose that locking serves is
/archives/netdev/2004-05/msg00223.html (10,493 bytes)

2. ess (score: 1)
Author: x>
Date: Fri, 21 May 2004 14:45:36 -0700
The problem is more general than just loopback. This kind of special case hack is the right thing. Really fast network devices will have the same issues. Either do per-cpu stats or don't this seems c
/archives/netdev/2004-05/msg00226.html (18,636 bytes)

3. 6.6 (score: 1)
Author: Stephen Hemminger <shemminger@xxxxxxxx>
Date: Fri, 21 May 2004 14:45:57 -0700
It is legal to attach queueing disciplines to the loopback device but your patch makes that impossible. I don't think it is worth worrying about things like this especially if you're going to be addi
/archives/netdev/2004-05/msg00227.html (9,399 bytes)

4. mer (score: 1)
Author: erbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Date: Sat, 22 May 2004 14:20:55 +0200
[...] It looks quite ugly. How about you just create multiple loopback devices and use these preferably from specific CPUs ? One loopback device per CPU would be probably overkill, but maybe one per
/archives/netdev/2004-05/msg00243.html (9,180 bytes)

5. [PATCH] "lockless loopback" patch for 2.6.6 (score: 1)
Author: Arthur Kepner <akepner@xxxxxxx>
Date: Fri, 21 May 2004 14:04:09 -0700
Lock contention on the loopback device can lead to poor performance, even an essentially hung system, on systems with many processors. For the loopback device, the only purpose that locking serves is
/archives/netdev/2004-05/msg00741.html (10,658 bytes)

6. Re: [PATCH] "lockless loopback" patch for 2.6.6 (score: 1)
Author: Stephen Hemminger <shemminger@xxxxxxxx>
Date: Fri, 21 May 2004 14:45:36 -0700
The problem is more general than just loopback. This kind of special case hack is the right thing. Really fast network devices will have the same issues. Either do per-cpu stats or don't this seems c
/archives/netdev/2004-05/msg00744.html (18,845 bytes)

7. Re: [PATCH] "lockless loopback" patch for 2.6.6 (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Fri, 21 May 2004 14:45:57 -0700
It is legal to attach queueing disciplines to the loopback device but your patch makes that impossible. I don't think it is worth worrying about things like this especially if you're going to be addi
/archives/netdev/2004-05/msg00745.html (9,608 bytes)

8. Re: [PATCH] "lockless loopback" patch for 2.6.6 (score: 1)
Author: Andi Kleen <ak@xxxxxxx>
Date: Sat, 22 May 2004 14:20:55 +0200
[...] It looks quite ugly. How about you just create multiple loopback devices and use these preferably from specific CPUs ? One loopback device per CPU would be probably overkill, but maybe one per
/archives/netdev/2004-05/msg00761.html (9,389 bytes)


This search system is powered by Namazu