Re: tcp ethernet RX overrun

From: Riyaj Shamsudeen <riyaj.shamsudeen_at_gmail.com>
Date: Tue, 22 May 2012 13:56:54 -0500
Message-ID: <CAA2DszwYg9WoMsCgp8+AA3kEZGur2aWO5R_H-n4=T9zvwXBfzQ_at_mail.gmail.com>



Hello Vamshi

   You can't completely eliminate dropped packets. There will be drops and errors due to issues in the host and outside the host. In your case, 3 million packets are dropped out of 91 Billion packets received, merely 0.0033%. I doubt, this is an issue.

    But, if you are in Linux platform, use ethtool -S eth4 to see where the failures occurred.

    What problem are you trying to solve?

Cheers

Riyaj Shamsudeen
Principal DBA,
Ora!nternals - http://www.orainternals.com - Specialists in Performance, RAC and EBS
Blog: http://orainternals.wordpress.com
OakTable member http://www.oaktable.com and Oracle ACE Director

Co-author of the books: Expert Oracle
Practices<http://tinyurl.com/book-expert-oracle-practices/>, Pro Oracle SQL, Expert PL/SQL
Practices<http://tinyurl.com/book-expert-plsql-practices>

Join me for next RAC training in March
2012<http://www.orainternals.com/services/training/advanced-rac-training/>:

<http://tinyurl.com/book-expert-plsql-practices>

On Tue, May 22, 2012 at 1:21 PM, Vamshi Damidi <dbaprimatics_at_gmail.com>wrote:

> To all network masters:
> Can you please throw some light on how to debug ethernet errors and
> overruns.
> below is network interface.
>
> eth4 Link encap:Ethernet HWaddr 00:10:18:98:D7:18
> inet6 addr: fe80::210:18ff:fe98:d718/64 Scope:Link
> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
> RX packets:91675115854 errors:3057985 dropped:0 overruns:3057245
> frame:740
> TX packets:20876846657 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:118442063462040 (107.7 TiB) TX bytes:21442788961564
> (19.5 TiB)
> Interrupt:40 Memory:dc800000-dcffffff
>
> We are using 10G broadcom dual nics with tcp buffersize
> #SCSI TCP buffer fix
> net.core.rmem_max = 1073741824
> net.core.wmem_max = 1073741824
> net.ipv4.tcp_rmem = 1048576 16777216 1073741824
> net.ipv4.tcp_wmem = 1048576 16770216 1073741824
> net.ipv4.tcp_mem = 1048576 16770216 1073741824
>
> and iscsi config as below.
>
> node.startup = automatic
> node.session.timeo.replacement_timeout = 120
> node.conn[0].timeo.login_timeout = 15
> node.conn[0].timeo.logout_timeout = 15
> node.conn[0].timeo.noop_out_interval = 10
> node.conn[0].timeo.noop_out_timeout = 15
> node.session.initial_login_retry_max = 4
> node.session.cmds_max = 128
> node.session.queue_depth = 128
> node.session.iscsi.InitialR2T = No
> node.session.iscsi.ImmediateData = Yes
> node.session.iscsi.FirstBurstLength = 16776192
> node.session.iscsi.MaxBurstLength = 16776192
> # the default is 131072
> node.conn[0].iscsi.MaxRecvDataSegmentLength = 16776192
> # the default is 32768
> discovery.sendtargets.iscsi.MaxRecvDataSegmentLength = 16776192
> node.conn[0].iscsi.HeaderDigest = None
> node.session.iscsi.FastAbort = No
>
>
> Thanks,
> Vamshi .D
>
>
> --
> http://www.freelists.org/webpage/oracle-l
>
>
>

--
http://www.freelists.org/webpage/oracle-l
Received on Tue May 22 2012 - 13:56:54 CDT

Original text of this message