netdev
[Top] [All Lists]

Re: RFC: NAPI packet weighting patch

To: john.ronciak@xxxxxxxxx
Subject: Re: RFC: NAPI packet weighting patch
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Mon, 06 Jun 2005 12:47:25 -0700 (PDT)
Cc: mchan@xxxxxxxxxxxx, hadi@xxxxxxxxxx, buytenh@xxxxxxxxxxxxxx, mitch.a.williams@xxxxxxxxx, jdmason@xxxxxxxxxx, shemminger@xxxxxxxx, netdev@xxxxxxxxxxx, Robert.Olsson@xxxxxxxxxxx, ganesh.venkatesan@xxxxxxxxx, jesse.brandeburg@xxxxxxxxx
In-reply-to: <468F3FDA28AA87429AD807992E22D07E0450C002@orsmsx408>
References: <468F3FDA28AA87429AD807992E22D07E0450C002@orsmsx408>
Sender: netdev-bounce@xxxxxxxxxxx
From: "Ronciak, John" <john.ronciak@xxxxxxxxx>
Date: Mon, 6 Jun 2005 08:35:26 -0700

> We are dropping packets at the HW level (FIFO errors) with 256
> descriptors and the default weight of 64.  As we said reducing the
> weight eliminates this which is understandable since the driver is being
> serviced more fequently.  We also hacked the driver to do a buffer
> allocation per packet sent up the stack.  This reduced the number of
> dropped pacekts by about 80% but it was still a significant number of
> drops (190K to 39K dropped).  So I don't think this is where the problem
> is.  This is also comfimed with the tg3 driver doing the buffer update
> to the HW every 25 descriptors.

I reach a different conclusion, sorry. :-)

Here is the invariant:

        If you force the e1000 driver to do RX replenishment every N
        packets it should reduce the packet drops the same (in the
        single NIC case) as if you reduced the dev->weight to that
        same value N.

You have two test cases, single NIC and multi-NIC, so you should
be very clear in which case your drop number applies to.  They
are two totally different problems.

> We did not up the descriptor ring size with the default weight but will
> try this today and report back.

Thanks for all of your test data and hard work so far.
It's very valuable.

<Prev in Thread] Current Thread [Next in Thread>