Re: tcp_sendpage and page allocation lifetime vs. iscsi
From: Olivier Galibert
Date: Mon Apr 25 2005 - 17:10:04 EST
On Mon, Apr 25, 2005 at 12:19:53PM -0700, David S. Miller wrote:
> Or, he could simply not try to reuse the private buffer he is
> giving to TCP.
'cept the buffer is managed by scsi/st.c, not the iscsi driver. So
it's either changing the read/write buffer control rules scsi uses, or
systematically copying the data before sending. Not that good
performance-wise, especially since most of the time tcp_sendpage does
not want to grab the page.
Do you think possible to extent the sendpage api to add some kind of
"don't get the pages, copy them if you need them" flag?
OG.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/