| To: | root@xxxxxxxxxxxxxxxxxx, Andreas Dilger <adilger@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: Kernel stack overflow on 2.6.9-rc2 |
| From: | Denis Vlasenko <vda@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> |
| Date: | Tue, 14 Sep 2004 22:43:55 +0300 |
| Cc: | Linux kernel <linux-kernel@xxxxxxxxxxxxxxx>, Trond Myklebust <trond.myklebust@xxxxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <Pine.LNX.4.53.0409141340540.4262@chaos> |
| References: | <200409141723.35009.vda@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> <20040914163347.GE3197@xxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.53.0409141340540.4262@chaos> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
| User-agent: | KMail/1.5.4 |
On Tuesday 14 September 2004 20:55, Richard B. Johnson wrote: > Has anybody ever explained why there is an attempt to > minimize the size of the kernel stack? Temporary data > allocation on the stack is FREE! The compiler just > adjusts offsets for data. Even dynamic data-allocation > takes only one instruction, (subl %reg, %esp). IIRC it is done in order to be able to support large number of threads on 32-bit machines and to avoid needing to do a order-1 allocation at fork(). -- vda |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Kernel stack overflow on 2.6.9-rc2, Richard B. Johnson |
|---|---|
| Next by Date: | Re: [PATCH 2.6] Add NAPI support to sungem.c, David S. Miller |
| Previous by Thread: | Re: Kernel stack overflow on 2.6.9-rc2, Richard B. Johnson |
| Next by Thread: | Re: Kernel stack overflow on 2.6.9-rc2, Denis Vlasenko |
| Indexes: | [Date] [Thread] [Top] [All Lists] |