Messages in this thread | | | Date | Thu, 2 Jan 2003 22:52:20 -0800 | From | William Lee Irwin III <> | Subject | Re: [PATCH] generic device DMA (dma_pool update) |
| |
Adam J. Richter wrote: >> mempool_alloc does. That's the point of it. You calculate >> how many objects you need in order to guarantee no deadlocks and >> reserve that number in advance (the initial reservation can fail).
On Thu, Jan 02, 2003 at 10:46:43PM -0800, David Brownell wrote: > To rephrase that so it illustrates my point: the whole reason to > use mempool is to try adding __GFP_NEVERFAIL when __GFP_WAIT is > given ... because __GFP_WAIT doesn't otherwise mean NEVERFAIL.
Well, it's not quite that general. There is a constraint of the objects allocated with a mempool having a finite lifetime. And non-waiting mempool allocations are also available, but may fail.
So long as the queueing is fair everyone eventually gets their turn.
Bill - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |