Re: [PATCH] Execute tasklets in the same order they were queued

2008-02-12 Thread Andrew Morton
On Mon, 11 Feb 2008 16:28:13 -0600 Olof Johansson <[EMAIL PROTECTED]> wrote: > I noticed this when looking at an openswan issue. Openswan (ab?)uses > the tasklet API to defer processing of packets in some situations, > with one packet per tasklet_action(). I started noticing sequences of >

Re: [PATCH] Execute tasklets in the same order they were queued

2008-02-12 Thread Andrew Morton
On Mon, 11 Feb 2008 16:28:13 -0600 Olof Johansson [EMAIL PROTECTED] wrote: I noticed this when looking at an openswan issue. Openswan (ab?)uses the tasklet API to defer processing of packets in some situations, with one packet per tasklet_action(). I started noticing sequences of

Re: [PATCH] Execute tasklets in the same order they were queued

2008-02-11 Thread Andrew Morton
On Mon, 11 Feb 2008 16:28:13 -0600 Olof Johansson <[EMAIL PROTECTED]> wrote: > I noticed this when looking at an openswan issue. Openswan (ab?)uses > the tasklet API to defer processing of packets in some situations, > with one packet per tasklet_action(). I started noticing sequences of >

[PATCH] Execute tasklets in the same order they were queued

2008-02-11 Thread Olof Johansson
I noticed this when looking at an openswan issue. Openswan (ab?)uses the tasklet API to defer processing of packets in some situations, with one packet per tasklet_action(). I started noticing sequences of reverse-ordered sequence numbers coming over the wire, since new tasklets are always queued

Re: [PATCH] Execute tasklets in the same order they were queued

2008-02-11 Thread Andrew Morton
On Mon, 11 Feb 2008 16:28:13 -0600 Olof Johansson [EMAIL PROTECTED] wrote: I noticed this when looking at an openswan issue. Openswan (ab?)uses the tasklet API to defer processing of packets in some situations, with one packet per tasklet_action(). I started noticing sequences of

[PATCH] Execute tasklets in the same order they were queued

2008-02-11 Thread Olof Johansson
I noticed this when looking at an openswan issue. Openswan (ab?)uses the tasklet API to defer processing of packets in some situations, with one packet per tasklet_action(). I started noticing sequences of reverse-ordered sequence numbers coming over the wire, since new tasklets are always queued