After installing freebsd as a gateway, natd use 100% cpu without any network load, I am using em interfaces. I updated kernel and recompiled but nothing changed. em0@pci0:1:0:0: class=0x020000 card=0x00008086 chip=0x10d38086 rev=0x00 hdr=0x00 vendor = 'Intel Corporation' class = network subclass = ethernet cap 01[c8] = powerspec 2 supports D0 D3 current D0 cap 05[d0] = MSI supports 1 message, 64 bit enabled with 1 message cap 10[e0] = PCI-Express 1 endpoint max data 128(256) link x1(x1) cap 11[a0] = MSI-X supports 5 messages in map 0x1c top PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND 1592 root 1 112 0 3348K 1316K RUN 0 0:38 85.09% natd 1899 postfix 1 4 0 24600K 21336K kqread 0 0:06 0.00% qmgr 1762 root 1 44 0 39132K 36772K select 0 0:03 0.00% perl How-To-Repeat: Always
Responsible Changed From-To: freebsd-bugs->freebsd-net Over to maintainer(s).
So, use current code, this is ancient, its actually a 82575 which is now supported by the igb driver rather than em. Try the prerelease code for 8.2 or 7.4. Should also point out that the bug is mistitled, natd uses 100%, it does not follow its em, although that might be a likely suspect, it could be an internal natd bug too afterall... Jack On Mon, Dec 20, 2010 at 6:25 AM, Yusuf Ozbilgin <yusuf@gunes.net> wrote: > > >Number: 153308 > >Category: misc > >Synopsis: em interface use 100% cpu > >Confidential: no > >Severity: serious > >Priority: high > >Responsible: freebsd-bugs > >State: open > >Quarter: > >Keywords: > >Date-Required: > >Class: sw-bug > >Submitter-Id: current-users > >Arrival-Date: Mon Dec 20 14:30:11 UTC 2010 > >Closed-Date: > >Last-Modified: > >Originator: Yusuf Ozbilgin > >Release: Freebsd 7.3 > >Organization: > Gunes Bilg. A.S > >Environment: > FreeBSD firewall.test.local 7.3-RELEASE-p2 FreeBSD 7.3-RELEASE-p2 #0: Wed > Sep 22 17:41:32 EEST 2010 root@firewall.test.local:/usr/obj/usr/src/sys/GATEWAY-FW > i386 > >Description: > After installing freebsd as a gateway, natd use 100% cpu without any > network load, I am using em interfaces. I updated kernel and recompiled but > nothing changed. > > > > em0@pci0:1:0:0: class=0x020000 card=0x00008086 chip=0x10d38086 rev=0x00 > hdr=0x00 > vendor = 'Intel Corporation' > class = network > subclass = ethernet > cap 01[c8] = powerspec 2 supports D0 D3 current D0 > cap 05[d0] = MSI supports 1 message, 64 bit enabled with 1 message > cap 10[e0] = PCI-Express 1 endpoint max data 128(256) link x1(x1) > cap 11[a0] = MSI-X supports 5 messages in map 0x1c > > top > > PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND > 1592 root 1 112 0 3348K 1316K RUN 0 0:38 85.09% natd > 1899 postfix 1 4 0 24600K 21336K kqread 0 0:06 0.00% qmgr > 1762 root 1 44 0 39132K 36772K select 0 0:03 0.00% perl > > > > >How-To-Repeat: > Always > >Fix: > > > >Release-Note: > >Audit-Trail: > >Unformatted: > _______________________________________________ > freebsd-bugs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-bugs > To unsubscribe, send any mail to "freebsd-bugs-unsubscribe@freebsd.org" >
On Mon, Dec 20, 2010 at 02:25:29PM +0000, Yusuf Ozbilgin wrote: Y> >Synopsis: em interface use 100% cpu ... Y> em0@pci0:1:0:0: class=0x020000 card=0x00008086 chip=0x10d38086 rev=0x00 hdr=0x00 Y> vendor = 'Intel Corporation' Y> class = network Y> subclass = ethernet Y> cap 01[c8] = powerspec 2 supports D0 D3 current D0 Y> cap 05[d0] = MSI supports 1 message, 64 bit enabled with 1 message Y> cap 10[e0] = PCI-Express 1 endpoint max data 128(256) link x1(x1) Y> cap 11[a0] = MSI-X supports 5 messages in map 0x1c Y> Y> top Y> Y> PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND Y> 1592 root 1 112 0 3348K 1316K RUN 0 0:38 85.09% natd Y> 1899 postfix 1 4 0 24600K 21336K kqread 0 0:06 0.00% qmgr Y> 1762 root 1 44 0 39132K 36772K select 0 0:03 0.00% perl This doesn't seem related to em(4). Do you mind if I change synopsis of PR to "natd consumes 100% CPU"? Have you tried same setup on 8-STABLE? -- Totus tuus, Glebius.
No feedback from submitter in over 4 years.