Messages in this thread | | | Date | Thu, 17 Sep 1998 18:15:41 +0200 (CEST) | From | Andrea Arcangeli <> | Subject | Re: showstopper race condition in sync() ??? [2.1.119|120] |
| |
On Thu, 17 Sep 1998, Cyrille Chepelov wrote:
>On Thu, 17 Sep 1998, Andrea Arcangeli wrote: > >> If you have a K6 as you said putting a spinlock can' t help you to avoid >> the dquota deadlock. > >???? Isn't the K6 supposed to behave like a Pentium, at least >interface-wise ?
As a Pentium _UP_. At least if something is not changed recently (usually I am not in sync with harware news).
>(I may have employed the wrong terminology, if by 'spinlock' you (and the >others) mean a hardware helper device for SMP machines. Sorry, I'm a >rather recent convert. I meant bracketing the dquota [and the bdflush] >with whatever Win32's EnterCriticalSection()/LeaveCriticalSection() >translates to in Linux kernel code. Something to guarantee that only one >thread can enter a particular piece of code at a time).
The point is that you are getting troubles with dquota on an UP hardware. Yes? If so you can' t fix _your_ problem spinlokking some piece of code. The kernel is not preemptive so you don' t need to care about nothig other irq handlers in UP.
Andrea[s] Arcangeli
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |