| To: | Andreas Henriksson <andreas@xxxxxxxxxxxx> |
|---|---|
| Subject: | Re: fealnx oopses |
| From: | Denis Vlasenko <vda@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> |
| Date: | Mon, 29 Mar 2004 09:52:01 +0200 |
| Cc: | Francois Romieu <romieu@xxxxxxxxxxxxx>, Jeff Garzik <jgarzik@xxxxxxxxx>, Andreas Henriksson <andreas@xxxxxxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <20040328232707.GA17524@scream.fjortis.info> |
| References: | <200403261214.58127.vda@port.imtp.ilyichevsk.odessa.ua> <200403282219.56799.vda@port.imtp.ilyichevsk.odessa.ua> <20040328232707.GA17524@scream.fjortis.info> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Monday 29 March 2004 01:27, Andreas Henriksson wrote: > On Sun, Mar 28, 2004 at 10:19:56PM +0200, Denis Vlasenko wrote: > > I tested on 2.4.25, patch applied with minimal manual correction > > in last hunk (rediffed patch attached). > > I tested on 2.6.5-rc2-bk7 ... with both jeffs (which was exactly the > same patch I had except for removing the return at the end of the void > function) and francis patches... > > Btw. I haven't seen any panics at all because of rx, just tx, and that > problem seems solved. But I thought testing additional patches that > is supposed to cure other problems won't hurt me.. ;) Thank you, you verified that _I_ did not caused it. (I could, I was a bit tired at the time) You need to make your box very RAM starved for this. I boot with mem=16M and load all iptables NAT/conntrack modules to make network processing more CPU/RAM intensive. -- vda |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH 2.6] sock_put() on a TIMEWAIT socket, David S. Miller |
|---|---|
| Next by Date: | IPsec 2.6 fragmentation issue(s), Valentijn Sessink |
| Previous by Thread: | Re: fealnx oopses (with [PATCH]), Francois Romieu |
| Next by Thread: | Re: fealnx oopses, Francois Romieu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |