Date: Mon, 06 Apr 2009 23:35:51 -0700 From: Julian Elischer <julian@elischer.org> To: Sepherosa Ziehau <sepherosa@gmail.com> Cc: freebsd-net@freebsd.org, Robert Watson <rwatson@freebsd.org>, Ivan Voras <ivoras@freebsd.org> Subject: Re: Advice on a multithreaded netisr patch? Message-ID: <49DAF447.5020407@elischer.org> In-Reply-To: <ea7b9c170904062209tda44636tb9a18755ec0c5bb3@mail.gmail.com> References: <gra7mq$ei8$1@ger.gmane.org> <alpine.BSF.2.00.0904051422280.12639@fledge.watson.org> <grac1s$p56$1@ger.gmane.org> <alpine.BSF.2.00.0904051440460.12639@fledge.watson.org> <grappq$tsg$1@ger.gmane.org> <alpine.BSF.2.00.0904052243250.34905@fledge.watson.org> <grbcfg$poe$1@ger.gmane.org> <alpine.BSF.2.00.0904061238250.34905@fledge.watson.org> <ea7b9c170904062209tda44636tb9a18755ec0c5bb3@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Sepherosa Ziehau wrote:
> On Mon, Apr 6, 2009 at 7:59 PM, Robert Watson <rwatson@freebsd.org> wrote:
>> m_pullup() has to do with mbuf chain memory contiguity during packet
>> processing. The usual usage is something along the following lines:
>>
>> struct whatever *w;
>>
>> m = m_pullup(m, sizeof(*w));
>> if (m == NULL)
>> return;
>> w = mtod(m, struct whatever *);
while this is true, m_pullup ALWAYS does things so in fact you
want to always put it in a test to see if it is really needed..
from memory it is something like:
if (m->m_len < headerlen && (m = m_pullup(m, headerlen)) == NULL) {
log(LOG_WARNING,
"nglmi: m_pullup failed for %d bytes\n", headerlen);
return (0);
}
header = mtod(m, struct header *);
>>
>> m_pullup() here ensures that the first sizeof(*w) bytes of mbuf data are
>> contiguously stored so that the cast of w to m's data will point at a
>> complete structure we can use to interpret packet data. In the common case
>> in the receipt path, m_pullup() should be a no-op, since almost all drivers
>> receive data in a single cluster.
>>
>> However, there are cases where it might not happen, such as loopback traffic
>> where unusual encapsulation is used, leading to a call to M_PREPEND() that
>> inserts a new mbuf on the front of the chain, which is later m_defrag()'d
>> leading to a higher level header crossing a boundary or the like.
>>
>> This issue is almost entirely independent from things like the cache line
>> miss issue, unless you hit the uncommon case of having to do work in
>> m_pullup(), in which case life sucks.
>>
>> It would be useful to use DTrace to profile a number of the workfull m_foo()
>> functions to make sure we're not hitting them in normal workloads, btw.
>
> I highly suspect m_pullup will take any real effect on RX path, given
> how most of drivers allocate the mbuf for RX ring (all RX mbufs should
> be mclusters).
>
> Best Regards,
> sephe
>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?49DAF447.5020407>