lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120314223343.23dc9df3@vostro>
Date:	Wed, 14 Mar 2012 22:33:43 +0200
From:	Timo Teras <timo.teras@....fi>
To:	Eric Dumazet <eric.dumazet@...il.com>
Cc:	Ben Hutchings <bhutchings@...arflare.com>, netdev@...r.kernel.org,
	Francois Romieu <romieu@...zoreil.com>
Subject: Re: linux-3.0.18+r8169+ipv4/tcp forwarding = tso/gso weirdness and
 performance degration

On Wed, 14 Mar 2012 13:12:45 -0700 Eric Dumazet
<eric.dumazet@...il.com> wrote:

> On Wed, 2012-03-14 at 21:51 +0200, Timo Teras wrote:
> 
> > Very good point. I thought gso also enabled gro, but seems that my
> > ethtool was old.
> > 
> > And GRO was enabled along with some other stuff. Turning GRO off
> > made my tcp performance immediately a lot better; jumped from 2MB/s
> > to 8MB/s or so (not ideal yet, though; but the remainder of the
> > difference could be related to other issue).
> > 
> > So something is definitely broke in 3.0.x with GRO enabled, but GSO
> > off.
> 
> "ifconfig eth2 ; netstat -s" can really help, I suspect tcp stack
> drops

After doing several wget's that have "bad performance".

# ifconfig eth2
eth2      Link encap:Ethernet  HWaddr 00:30:18:AB:6B:56  
          inet addr:10.26.0.2  Bcast:0.0.0.0  Mask:255.255.255.252
          inet6 addr: fe80::230:18ff:feab:6b56/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:32334060 errors:0 dropped:0 overruns:0 frame:0
          TX packets:18520452 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000 
          RX bytes:1775070027 (1.6 GiB)  TX bytes:1962364861 (1.8 GiB)
          Interrupt:16 Base address:0xc000 

# ethtool -S eth2
NIC statistics:
     tx_packets: 2069391193
     rx_packets: 3245815642
     tx_errors: 0
     rx_errors: 645238
     rx_missed: 31414
     align_errors: 0
     tx_single_collisions: 0
     tx_multi_collisions: 0
     unicast: 3245815640
     broadcast: 2
     multicast: 0
     tx_aborted: 0
     tx_underrun: 0

netstat is busybox, so no -s. But /proc/net/netstat as parsed looks
like:
SyncookiesSent 0 
SyncookiesRecv 0 
SyncookiesFailed 3 
EmbryonicRsts 0 
PruneCalled 0 
RcvPruned 0 
OfoPruned 0 
OutOfWindowIcmps 0 
LockDroppedIcmps 0 
ArpFilter 0 
TW 15 
TWRecycled 0 
TWKilled 0 
PAWSPassive 0 
PAWSActive 0 
PAWSEstab 0 
DelayedACKs 564 
DelayedACKLocked 5 
DelayedACKLost 0 
ListenOverflows 0 
ListenDrops 0 
TCPPrequeued 73 
TCPDirectCopyFromBacklog 605264 
TCPDirectCopyFromPrequeue 15961 
TCPPrequeueDropped 0 
TCPHPHits 191774 
TCPHPHitsToUser 425 
TCPPureAcks 19228 
TCPHPAcks 112359 
TCPRenoRecovery 0 
TCPSackRecovery 2 
TCPSACKReneging 0 
TCPFACKReorder 0 
TCPSACKReorder 4 
TCPRenoReorder 0 
TCPTSReorder 2 
TCPFullUndo 2 
TCPPartialUndo 107 
TCPDSACKUndo 0 
TCPLossUndo 0 
TCPLoss 0 
TCPLostRetransmit 0 
TCPRenoFailures 0 
TCPSackFailures 0 
TCPLossFailures 0 
TCPFastRetrans 2 
TCPForwardRetrans 2 
TCPSlowStartRetrans 0 
TCPTimeouts 0 
TCPRenoRecoveryFail 0 
TCPSackRecoveryFail 0 
TCPSchedulerFailed 0 
TCPRcvCollapsed 0 
TCPDSACKOldSent 0 
TCPDSACKOfoSent 0 
TCPDSACKRecv 4 
TCPDSACKOfoRecv 0 
TCPAbortOnSyn 0 
TCPAbortOnData 6 
TCPAbortOnClose 4 
TCPAbortOnMemory 0 
TCPAbortOnTimeout 0 
TCPAbortOnLinger 0 
TCPAbortFailed 0 
TCPMemoryPressures 0 
TCPSACKDiscard 0 
TCPDSACKIgnoredOld 0 
TCPDSACKIgnoredNoUndo 0 
TCPSpuriousRTOs 0 
TCPMD5NotFound 0 
TCPMD5Unexpected 0 
TCPSackShifted 0 
TCPSackMerged 0 
TCPSackShiftFallback 4484 
TCPBacklogDrop 0 
TCPMinTTLDrop 0 
TCPDeferAcceptDrop 0 
IPReversePathFilter 4 
TCPTimeWaitOverflow 0 
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ