Messages in this thread | | | Date | Tue, 15 Jul 2008 11:40:45 +0900 | Subject | Re: [SUGGESTION]: drop virtual merge accounting in I/O requests | From | FUJITA Tomonori <> |
| |
On Mon, 14 Jul 2008 10:03:29 -0400 (EDT) Mikulas Patocka <mpatocka@redhat.com> wrote:
> On Mon, 14 Jul 2008, David Miller wrote: > > > From: Mikulas Patocka <mpatocka@redhat.com> > > Date: Mon, 14 Jul 2008 08:16:13 -0400 (EDT) > > > >> As you mentioned ESP driver, it declares .sg_tablesize = SG_ALL, so > >> BIO_VMERGE_BOUNDARY has no effect on the operation of this driver. Any > >> other driver where BIO_VMERGE_BOUNDARY does matter? > > > > When BIO_VMERGE_BOUNDARY is turned on, requests that would not > > otherwise fit into the device's limits, can. > > Why would someone want to overshoot SG_ALL? ... and, shouldn't the > constant be increased then --- instead of making buggy BIO_VMERGE_BOUNDARY > expectations?
'buggy' is a wrong word. VMERGE works for some IOMMUs (though I think that we need to fix it about max_segment_size).
| |