On Wed, 27 Jan 2010 11:57:35 -0500Ah - ok... will poke around there... if you have any suggestions, diagnostics, whatever, let me know. Also, just an FYI - before rebooting with copybreak back to defaults, I tried mtu=9000 again. That hung the server immediately - no diagnostic output - system froze until watchdog rebooted. Don't know right now if the copybreak had anything to do with this, but when I've tried in the past I've had errors on sky2, but never crashed the system like this. Only two things different were copybreak and the length of time the system had been up. I'll try later with copybreak default and copybreak=1 to see if that affects mtu behavior.
Michael Breuer<mbreuer@xxxxxxxxxx> wrote:
On 1/27/2010 11:50 AM, Stephen Hemminger wrote:Setting it to 1 causes driver to never go through the dma_sync_single/memcpy
On Wed, 27 Jan 2010 10:34:51 -0500Ok - but I'm wondering under what circumstances size would be<
Michael Breuer<mbreuer@xxxxxxxxxx> wrote:
On 01/23/2010 06:21 PM, Jarek Poplawski wrote:This code is where driver decides how much data will be received in skb
On Fri, Jan 22, 2010 at 06:50:21PM -0500, Michael Breuer wrote:Ok - now up 80+ hours with copybreak=1. I'm going to redo w/o copybreak
When the packets were dropped, there was a different sequence in theAnyway, I'd be intersted if the switch matters here.
log - DISCOVER/OFFER repeated. The "normal" is that the sequence
appeared correct and complete - DISCOVER/OFFER/REQUEST/ACK - or
INFORM/ACK (vs. INFORM repeatedly sans ACK) as the case may be.
Plus one more test: could you try to load sky2 with the parameter:
"copybreak=1" (the rest as in any recent test, which gave you dmar
errors; any switch).
Thanks,
Jarek P.
to confirm that I haven't inadvertently fixed something. However, given
that it might be copybreak-related, I looked at sky2.c again and I'm
wondering about the copybreak max size in sky2_rx_start:
size = roundup(sky2->netdev->mtu + ETH_HLEN + VLAN_HLEN, 8);
/* Stopping point for hardware truncation */
thresh = (size - 8) / sizeof(u32);
sky2->rx_nfrags = size>> PAGE_SHIFT;
BUG_ON(sky2->rx_nfrags> ARRAY_SIZE(re->frag_addr));
/* Compute residue after pages */
size -= sky2->rx_nfrags<< PAGE_SHIFT;
/* Optimize to handle small packets and headers */
if (size< copybreak)
size = copybreak;
if (size< ETH_HLEN)
size = ETH_HLEN;
Why would increasing size to copybreak be valid here?
Guessing a bit as I'm not sure about rx_nfrags, but if I read this
correctly, if size is ever less than copybreak it's because there isn't
enough space left for anything larger. If so, wouldn't increasing size
potentially corrupt something? I'd further guess that the resulting
condition manifests sooner (or at least with a more visible effect) when
using DMAR.
In any event, why "copybreak" as the minimum buffer size? I'd suggest
that if it isn't possible to allocate at least MTU + overhead that
sky2_rx_start ought to be delayed until there is room.
data area and the remaining data spills over into skb frags.
Copybreak is the threshold so that packets less than size are copied
to a new skb. The code doing the copying there assumes the data is
totally contained in the skb (not in frags). The size increase there
is to make sure that assumption is always true. I suppose you
could do something perverse like setting copybreak really huge
and confuse driver, but that is a user error.
copybreak in the first place after computing the residue. If size ends
up being unreasonably small, is simply increasing the number to whatever
copybreak is correct? Assuming my testing is correct, then the crash
I've been experiencing when using dmar (only) seems related to the value
of copybreak. I don't think the other use (skb reuse) is the issue (but
hey, I could have missed something). The crash occurs when copybreak is
the default of 128, didn't happen when I set copybreak to 1.
path. Perhaps the code for DMAR doesn't do dma_sync_single_for_cpu
properly, or the value passed to sync_single_for_cpu doesn't account for
all the overhead of padding and/or ether header.