| To: | Harald Welte <laforge@xxxxxxxxxxxx> |
|---|---|
| Subject: | Re: "dst cache overflow" |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Tue, 21 Sep 2004 15:24:11 -0700 |
| Cc: | Robert.Olsson@xxxxxxxxxxx, cd@xxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <20040921215501.GE3236@xxxxxxxxxxxxxxxxxxxxxxx> |
| References: | <16719.13095.369830.547715@xxxxxxxxxxxx> <20040921215501.GE3236@xxxxxxxxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 21 Sep 2004 23:55:02 +0200 Harald Welte <laforge@xxxxxxxxxxxx> wrote: > I bet that something inside the kernel forgets dst_release().. IMQ is > just compiled, not used (so I don't see how it should come from this). > > Any comments, suggestions? Most likely it is a leak like that, yes. Here is my suggstion for debugging this: 1) Boot with profile=2 or similar. 2) Disable the platform code that bumps the profiling counters at the timer interrupt. 3) Make every piece of which gets or puts a dst entry reference pass it's PC to some function which increments the profile buffer entry. (use current_text_addr()) Then after running for some time use readprofile to figure out what subsystem or area is causing the references. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH] [ATM]: [he] make code more readable with list_for_each_entry (from Domen Puncer <domen@xxxxxxxxxxxx>), David S. Miller |
|---|---|
| Next by Date: | [PATCH 2.6 NET] Fix ifmap alignment issues over rtnetlink, Thomas Graf |
| Previous by Thread: | Re: "dst cache overflow", Harald Welte |
| Next by Thread: | Re: "dst cache overflow", Patrick McHardy |
| Indexes: | [Date] [Thread] [Top] [All Lists] |