Date: Sat, 14 Mar 2015 11:42:25 -0400 From: Paul Mather <paul@gromit.dlib.vt.edu> To: Ian Lepore <ian@freebsd.org> Cc: freebsd-arm <freebsd-arm@freebsd.org> Subject: Re: BeagleBone slow inbound net I/O Message-ID: <807E4289-EC2E-49F9-A909-4D2A2A149302@gromit.dlib.vt.edu> In-Reply-To: <1426339400.52318.3.camel@freebsd.org> References: <20150311165115.32327c5a@ivory.wynn.com> <89CEBFCA-6B94-4F48-8DFD-790E4667632D@kientzle.com> <20150314031542.439cdee3@ivory.wynn.com> <1426339400.52318.3.camel@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mar 14, 2015, at 9:23 AM, Ian Lepore <ian@freebsd.org> wrote: > On Sat, 2015-03-14 at 03:15 -0400, Brett Wynkoop wrote: >> On Fri, 13 Mar 2015 23:02:25 -0700 >> Tim Kientzle <tim@kientzle.com> wrote: >>=20 >>>=20 >>>> On Mar 11, 2015, at 1:51 PM, Brett Wynkoop <freebsd-arm@wynn.com> >>>> wrote: >>>>=20 >>>> Have I managed to find a network driver issue? Any ideas how to >>>> gather more information to help get to the bottom of things? >>>>=20 >>>=20 >>> $ sysctl dev.cpsw >>>=20 >>> This will dump detailed statistics from the Ethernet hardware and >>> driver. >>>=20 >>> Tim >>>=20 >>=20 >> After a short time while doing nfs i/o >>=20 >>=20 >> [wynkoop@beaglebone ~]$ sysctl dev.cpsw | grep -i error >> dev.cpsw.0.stats.RxCrcErrors: 40 >> dev.cpsw.0.stats.RxAlignErrors: 32 >> dev.cpsw.0.stats.CarrierSenseErrors: 0 > [...] >> [wynkoop@beaglebone ~]$ sysctl dev.cpsw | grep -i error >> dev.cpsw.0.stats.RxCrcErrors: 262 >> dev.cpsw.0.stats.RxAlignErrors: 231 >> dev.cpsw.0.stats.CarrierSenseErrors: 0 >> [wynkoop@beaglebone ~]$=20 >>=20 >> So we can see climbing errors. I am not sure how this compares to = the >> results of others. The above was during the first few minutes of a >> buildworld from an nfs share. >>=20 >> At the same time on the console: >>=20 >> Mar 14 03:07:47 beaglebone amd[1163]: mountd rpc failed: RPC: Can't >> decode result Mar 14 03:11:48 beaglebone amd[1399]: mountd rpc = failed: >> RPC: Can't decode result >>=20 >> which makes sense with the above errors I think. >=20 > On mine: >=20 > root@bb:/usr/ports/benchmarks/iperf # sysctl dev.cpsw | grep Err > dev.cpsw.0.stats.RxCrcErrors: 0 > dev.cpsw.0.stats.RxAlignErrors: 0 > dev.cpsw.0.stats.CarrierSenseErrors: 0 >=20 > That's after 3 days of uptime including doing builds over nfs, and all > the iperf testing I was doing yesterday (no errors after megabytes of > transfers). Here is another data point from my BBB: pmather@beaglebone:~ % sysctl dev.cpsw dev.cpsw.%parent:=20 dev.cpsw.0.%desc: 3-port Switch Ethernet Subsystem dev.cpsw.0.%driver: cpsw dev.cpsw.0.%location:=20 dev.cpsw.0.%pnpinfo: name=3Dethernet@4A100000 compat=3Dti,cpsw dev.cpsw.0.%parent: simplebus0 dev.cpsw.0.attachedSecs: 135771 dev.cpsw.0.uptime: 135750 dev.cpsw.0.stats.GoodRxFrames: 4200799 dev.cpsw.0.stats.BroadcastRxFrames: 8326 dev.cpsw.0.stats.MulticastRxFrames: 132766 dev.cpsw.0.stats.PauseRxFrames: 0 dev.cpsw.0.stats.RxCrcErrors: 0 dev.cpsw.0.stats.RxAlignErrors: 0 dev.cpsw.0.stats.OversizeRxFrames: 0 dev.cpsw.0.stats.RxJabbers: 0 dev.cpsw.0.stats.ShortRxFrames: 0 dev.cpsw.0.stats.RxFragments: 0 dev.cpsw.0.stats.RxOctets: 6141208229 dev.cpsw.0.stats.GoodTxFrames: 2064557 dev.cpsw.0.stats.BroadcastTxFrames: 111 dev.cpsw.0.stats.MulticastTxFrames: 0 dev.cpsw.0.stats.PauseTxFrames: 0 dev.cpsw.0.stats.DeferredTxFrames: 0 dev.cpsw.0.stats.CollisionsTxFrames: 0 dev.cpsw.0.stats.SingleCollisionTxFrames: 0 dev.cpsw.0.stats.MultipleCollisionTxFrames: 0 dev.cpsw.0.stats.ExcessiveCollisions: 0 dev.cpsw.0.stats.LateCollisions: 0 dev.cpsw.0.stats.TxUnderrun: 0 dev.cpsw.0.stats.CarrierSenseErrors: 0 dev.cpsw.0.stats.TxOctets: 203621590 dev.cpsw.0.stats.RxTx64OctetFrames: 82180 dev.cpsw.0.stats.RxTx65to127OctetFrames: 2054745 dev.cpsw.0.stats.RxTx128to255OctetFrames: 10086 dev.cpsw.0.stats.RxTx256to511OctetFrames: 50051 dev.cpsw.0.stats.RxTx512to1024OctetFrames: 303 dev.cpsw.0.stats.RxTx1024upOctetFrames: 4067992 dev.cpsw.0.stats.NetOctets: 6344829819 dev.cpsw.0.stats.RxStartOfFrameOverruns: 1708 dev.cpsw.0.stats.RxMiddleOfFrameOverruns: 0 dev.cpsw.0.stats.RxDmaOverruns: 0 dev.cpsw.0.queue.tx.totalBuffers: 128 dev.cpsw.0.queue.tx.activeBuffers: 2 dev.cpsw.0.queue.tx.maxActiveBuffers: 7 dev.cpsw.0.queue.tx.availBuffers: 126 dev.cpsw.0.queue.tx.maxAvailBuffers: 128 dev.cpsw.0.queue.tx.totalEnqueued: 2128785 dev.cpsw.0.queue.tx.totalDequeued: 2128783 dev.cpsw.0.queue.tx.longestChain: 4 dev.cpsw.0.queue.rx.totalBuffers: 384 dev.cpsw.0.queue.rx.activeBuffers: 384 dev.cpsw.0.queue.rx.maxActiveBuffers: 384 dev.cpsw.0.queue.rx.availBuffers: 0 dev.cpsw.0.queue.rx.maxAvailBuffers: 55 dev.cpsw.0.queue.rx.totalEnqueued: 4201184 dev.cpsw.0.queue.rx.totalDequeued: 4200800 dev.cpsw.0.queue.rx.longestChain: 0 dev.cpsw.0.watchdog.resets: 0 pmather@beaglebone:~ % sysctl dev.cpsw | grep -i error dev.cpsw.0.stats.RxCrcErrors: 0 dev.cpsw.0.stats.RxAlignErrors: 0 dev.cpsw.0.stats.CarrierSenseErrors: 0 pmather@beaglebone:~ % uptime 11:19AM up 1 day, 13:43, 1 users, load averages: 0.93, 0.88, 0.81 The above is also after doing some iperf and inbound transfer tests = yesterday. > I wonder if your power supply is failing and injecting transient > glitches under heavy load or something? Hopefully, the OP is not powering the system via the OTG connector. I = always found my BBB to be somewhat flaky when powered that way. Cheers, Paul.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?807E4289-EC2E-49F9-A909-4D2A2A149302>