http://www.allegro.com/?page_id=1391 - d
---
Donna Hofmeister
Allegro Consultants, Inc.
408-252-2330
> -----Original Message-----
> From: HP-3000 Systems Discussion [mailto:[log in to unmask]] On Behalf Of Kevin Smeltzer
> Sent: Thursday, July 28, 2011 3:56 PM
> To: [log in to unmask]
> Subject: Re: [HP3000-L] Deteriorating Network response times
>
> NMMGR TCP setting:
> [Y] Checksum Enabled (Y For Yes, N For No)
>
> [1024 ] Maximum Number of Connections
>
> [4 ] Retransmission Interval Lower Bound (Secs)
> [480 ] Maximum Time to Wait For Remote Response (Sec)
> [5 ] Initial Retransmission Interval (Secs)
> [8 ] Maximum Retransmissions per Packet
>
> [600 ] Connection Assurance Interval (Secs)
> [4 ] Maximum Connection Assurance Retransmissions
>
> Craig, you might have identified the issue: Change ports or switch to one
> not hardcoded as 100 mbit full duplex
> I sat though a two hour status of the account meeting today. One of the
> presenters discussed network consolidation efforts, and commented on the
> fact that the network consolidation effort has not been as stable as
> desired.
> _________________
> Kevin Smeltzer
> IT Specialist - HP MPE systems
> 804-354-7950
> Cell: 804-651-5428
> [log in to unmask]
>
>
>
> From: Craig Lalley <[log in to unmask]>
> To: [log in to unmask], Kevin Smeltzer/Richmond/IBM@IBMUS
> Date: 07/28/2011 06:35 PM
> Subject: Re: Deteriorating Network response times
>
>
>
>
> Kevin,
>
> Given the output, I would agree with donna. How are your tcp timers set?
> (This is in NMMGR)
>
> Given that you probably have not changed them. Is there any chance
> someone on the network team moved the 3000 to a different port or switch?
> Perhaps a port that is not hardcoded as 100 mbit full duplex?
>
> Just a guess.
>
> -Craig
>
>
> --- On Thu, 7/28/11, Kevin Smeltzer <[log in to unmask]> wrote:
>
> From: Kevin Smeltzer <[log in to unmask]>
> Subject: Re: Deteriorating Network response times
> To: [log in to unmask]
> Date: Thursday, July 28, 2011, 2:45 PM
>
> Thanks Craig, forgot to include Resource:
>
> [2]RESOURCE>>>display
> THU, JUL 28, 2011, 5:41:45 PM
> Item Subsystem Name G/N Description Used High Max
> ____________________________________________________________________
>
> 1 NS XPORT CP_POOL_ (G) Control Buf Pool 0 1 300 :)
> 2 NS XPORT 1536___D (G) Inbound Buf Pool 87 207 682 :)
> 3 NS XPORT LOOP____ (N) Outbnd Buf Pool 0 0 128 :)
> 4 NS XPORT FASTNET_ (N) Outbnd Buf Pool 0 85 2048 :)
> 5 NS XPORT FASTNET2 (N) Outbnd Buf Pool 0 1 2048 :)
> 6 NS XPORT FASTNET_ (N) StrFwd Buf Pool 0 0 20 :)
> 7 NS XPORT FASTNET2 (N) StrFwd Buf Pool 0 0 20 :)
> 8 NS XPORT UDP (G) GProt Msg Pool 0 N/A 512 :)
> 9 NS XPORT PXP (G) GProt Msg Pool 0 N/A 660 :)
> 10 NS XPORT PROBE (G) CM Prot Msg Pool 0 N/A 677 :)
> 11 NS XPORT PROBE (G) CM Prot Msg Pool 0 N/A 677 :)
> 12 NS XPORT IP_NI (G) IP-NI Msg Pool 0 N/A 2048 :)
> 13 NS XPORT IP_NI (G) IP-NI Msg Pool 0 N/A 2048 :)
> 14 NS XPORT IP_NI (G) IP-NI Msg Pool 0 N/A 2048 :)
> 15 NS XPORT (G) Node Name Cache 0 5 360 :)
> 16 NS XPORT (G) TCP Control pool 0 27 2048 :)
> 17 TELNET PTOD (G) Write Buf Pool 10 38 2048 :)
> 18 TELNET PTID (G) Outbnd Buf Pool 0 10 2048 :)
> 19 TELNET PTID (G) Inbound Buf Pool 1 10 2048 :)
> 20 TELNET PTOD (G) Negot Buf Pool 0 1 2048 :)
> [3]RESOURCE>>>
>
> New linkcontrol listing:
> sys:linkcontrol @,a
> Linkname: DTSLINK Linktype: PCI 100BT Linkstate: CONNECTED
> Physical Path: 0/0/0/0
> Current Station Address: 00-30-6E-C3-E3-CB
> Default Station Address: 00-30-6E-C3-E3-CB
> Current Multicast Addresses:
> 09-00-09-00-00-01 09-00-09-00-00-03 09-00-09-00-00-04
> 09-00-09-00-00-06
>
> Transmit bytes 18000437 Receive bytes 7430235
> Transmits 22961 Receives unicast 18761
> Transmits no error 22961 Receives broadcast 5772
> Transmits dropped 0 Receives multicast 0
> Transmits deferred 0 Receives no error 24533
> Transmits 1 retry 0 Recv CRC error 0
> Transmits >1 retry 0 Recv Maxsize error 0
> Trans 16 collisions 0 Recv dropped: addr 0
> Trans late collision 0 Recv dropped: buffer 0
> Trans underruns 0 Recv dropped: descr 0
> Carrier losses 0 Recv dropped: other 0
> Trans jabber timeout 0 Recv watchdg timeout 0
> Link disconnects 0 Recv collisions 0
> Link speed 100 Recv overruns 0
> Link duplex Full Link auto sensed No
> Link mode 100Base-TX Core Secs since clear 10024
>
> Linkname: FASTLNK2 Linktype: PCI 100BT Linkstate: CONNECTED
> Physical Path: 1/8/0/0
> Current Station Address: 00-30-6E-EA-85-0F
> Default Station Address: 00-30-6E-EA-85-0F
> Current Multicast Addresses:
> 09-00-09-00-00-01
>
> Transmit bytes 2460 Receive bytes 18098338
> Transmits 41 Receives unicast 1375
> Transmits no error 41 Receives broadcast 198205
> Transmits dropped 0 Receives multicast 0
> Transmits deferred 0 Receives no error 27190
> Transmits 1 retry 0 Recv CRC error 0
> Transmits >1 retry 0 Recv Maxsize error 0
> Trans 16 collisions 0 Recv dropped: addr 172390
> Trans late collision 0 Recv dropped: buffer 0
> Trans underruns 0 Recv dropped: descr 0
> Carrier losses 0 Recv dropped: other 0
> Trans jabber timeout 0 Recv watchdg timeout 0
> Link disconnects 0 Recv collisions 0
> Link speed 100 Recv overruns 0
> Link duplex Full Link auto sensed No
> Link mode 100Base-TX Addon Secs since clear 10024
>
> sys:
> _________________
> Kevin Smeltzer
> IT Specialist - HP MPE systems
> 804-354-7950
> Cell: 804-651-5428
> [log in to unmask]
>
>
>
> From: Craig Lalley <[log in to unmask]>
> To: [log in to unmask], Kevin Smeltzer/Richmond/IBM@IBMUS
> Date: 07/28/2011 05:17 PM
> Subject: Re: Deteriorating Network response times
>
>
>
>
> Keven,
>
> Just the usual,
>
> NETTOOL.NET.SYS --> RESOURCE --> DISPLAY
>
> LINKCONTROL @,a
>
> Would help determine any issues.
>
> -Craig
>
>
> --- On Thu, 7/28/11, Kevin Smeltzer <[log in to unmask]> wrote:
>
> From: Kevin Smeltzer <[log in to unmask]>
> Subject: Deteriorating Network response times
> To: [log in to unmask]
> Date: Thursday, July 28, 2011, 2:09 PM
>
> I have a steadily deteriorating response time condition with a development
> HP3000. System is a N-class, with 3 CPU. Running 7.5 PP6. Started about
> two months ago. Today so bad test programs can not stay connected to
> Quick application. Jinetd shows no issues. Stopped and restarted job
> anyway. No help. Linkcontrol only shows an issue with Recv dropped: addr
> on one path. This is a known issue with some enterprise network
> monitoring software that sends a packet that the HP3000 can not handle.
> Even HP last year had no solutions for that issue. The linkcontrol stats
> were reset about an hour ago. No issues reported before the reset either.
> No memory dump files. No jobs aborting. No hardware alerts.
>
> The system has three network connects. Two 100BT cards, and ldev 20 is
> network cabled. All three have issues with ping response times. Ping
> from laptop reports 4 for 4 most of the time. Have seen as bad as 2
> failed out of 4. Have seen response times of >75ms. Ping from
> development system to another HP3000 will also sometimes report dropped
> packets. Ping from another HP3000 to development system will also
> sometimes report dropped packets. Glance shows no issues, except
> sometimes 'TERM' wait when running Glance from two different sessions.
> This happens even when CPU and Memory are 1% with Glance the only active
> pin.
>
> What am I missing, before dragging network personal back into issue?
>
>
>
> linkcontrol @,all
> Linkname: DTSLINK Linktype: PCI 100BT Linkstate: CONNECTED
> Physical Path: 0/0/0/0
> Current Station Address: 00-30-6E-C3-E3-CB
> Default Station Address: 00-30-6E-C3-E3-CB
> Current Multicast Addresses:
> 09-00-09-00-00-01 09-00-09-00-00-03 09-00-09-00-00-04
> 09-00-09-00-00-06
>
> Transmit bytes 16110734 Receive bytes 1587070
> Transmits 15963 Receives unicast 12033
> Transmits no error 15963 Receives broadcast 3494
> Transmits dropped 0 Receives multicast 0
> Transmits deferred 0 Receives no error 15527
> Transmits 1 retry 0 Recv CRC error 0
> Transmits >1 retry 0 Recv Maxsize error 0
> Trans 16 collisions 0 Recv dropped: addr 0
> Trans late collision 0 Recv dropped: buffer 0
> Trans underruns 0 Recv dropped: descr 0
> Carrier losses 0 Recv dropped: other 0
> Trans jabber timeout 0 Recv watchdg timeout 0
> Link disconnects 0 Recv collisions 0
> Link speed 100 Recv overruns 0
> Link duplex Full Link auto sensed No
> Link mode 100Base-TX Core Secs since clear 6106
>
> Linkname: FASTLNK2 Linktype: PCI 100BT Linkstate: CONNECTED
> Physical Path: 1/8/0/0
> Current Station Address: 00-30-6E-EA-85-0F
> Default Station Address: 00-30-6E-EA-85-0F
> Current Multicast Addresses:
> 09-00-09-00-00-01
>
> Transmit bytes 1500 Receive bytes 11069670
> Transmits 25 Receives unicast 1088
> Transmits no error 25 Receives broadcast 121123
> Transmits dropped 0 Receives multicast 0
> Transmits deferred 0 Receives no error 17159
> Transmits 1 retry 0 Recv CRC error 0
> Transmits >1 retry 0 Recv Maxsize error 0
> Trans 16 collisions 0 Recv dropped: addr 105052
> Trans late collision 0 Recv dropped: buffer 0
> Trans underruns 0 Recv dropped: descr 0
> Carrier losses 0 Recv dropped: other 0
> Trans jabber timeout 0 Recv watchdg timeout 0
> Link disconnects 0 Recv collisions 0
> Link speed 100 Recv overruns 0
> Link duplex Full Link auto sensed No
> Link mode 100Base-TX Addon Secs since clear 6106
>
> * To join/leave the list, search archives, change list settings, *
> * etc., please visit http://raven.utc.edu/archives/hp3000-l.html *
>
>
> * To join/leave the list, search archives, change list settings, *
> * etc., please visit http://raven.utc.edu/archives/hp3000-l.html *
>
>
> * To join/leave the list, search archives, change list settings, *
> * etc., please visit http://raven.utc.edu/archives/hp3000-l.html *
* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *
|
