| To: | christoph@xxxxxxxxxxx |
|---|---|
| Subject: | Re: [PATCH] NUMA aware allocation of transmit and receive buffers for e1000 |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Tue, 17 May 2005 19:57:03 -0700 (PDT) |
| Cc: | akpm@xxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <Pine.LNX.4.62.0505171941340.21153@xxxxxxxxxx> |
| References: | <Pine.LNX.4.62.0505171854490.20408@xxxxxxxxxx> <20050517190343.2e57fdd7.akpm@xxxxxxxx> <Pine.LNX.4.62.0505171941340.21153@xxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
From: Christoph Lameter <christoph@xxxxxxxxxxx> Subject: Re: [PATCH] NUMA aware allocation of transmit and receive buffers for e1000 Date: Tue, 17 May 2005 19:52:38 -0700 (PDT) > > > - txdr->buffer_info = vmalloc(size); > > > + txdr->buffer_info = kmalloc_node(size, GFP_KERNEL, node); > > > > How come that this is safe to do > > Because physically contiguous memory is usually better than virtually > contiguous memory? Any reason that physically contiguous memory will > break the driver? The issue is whether size can end up being too large for kmalloc() to satisfy, whereas vmalloc() would be able to handle it. |
| Previous by Date: | Re: [PATCH] NUMA aware allocation of transmit and receive buffers for e1000, Christoph Lameter |
|---|---|
| Next by Date: | Re: [PATCH] TSO Reloaded, David S. Miller |
| Previous by Thread: | Re: [PATCH] NUMA aware allocation of transmit and receive buffers for e1000, Christoph Lameter |
| Next by Thread: | Re: [PATCH] NUMA aware allocation of transmit and receive buffers for e1000, Christoph Lameter |
| Indexes: | [Date] [Thread] [Top] [All Lists] |