we have several servers on same rack and servers are all inside firewall. Centos version from 4.X to 5.X. sometime the connection are very slow (compare to servers on other racks also inside firewall). we discuss with network engineer he ask us use "ping" and traceroute" to check. Both tools response time are good but if we connect through application like Web browser, database, or DELL OPMN tool. The response time is very very slow. This situation normally last 4 to 5 hours then it back to normal. Does there has way to check "real" network response time so we can show to network engineer. Otherwise they always say "no problem". Thanks.
On Tue, 2011-03-29 at 05:13 +0800, mcclnx mcc wrote:> we have several servers on same rack and servers are all inside firewall. Centos version from 4.X to 5.X. sometime the connection are very slow (compare to servers on other racks also inside firewall). > > we discuss with network engineer he ask us use "ping" and traceroute" to check. Both tools response time are good but if we connect through application like Web browser, database, or DELL OPMN tool. The response time is very very slow. > > This situation normally last 4 to 5 hours then it back to normal. Does there has way to check "real" network response time so we can show to network engineer. Otherwise they always say "no problem".miitool and ethtool Check that you're running at the right speed; sometimes bad cables will make the negotiation go bad. Sometimes you just connect to the wrong switch port. You may also note if the switch has hard-set values about the negotiation such as duplex settings. Make sure they match on both ends. You should be full duplex unless there's a very very good network reason not to. Lastly, check ifconfig output. Make sure there's no errors reported. If you have a high error count, it's a good bet the cable is bad or the sync settings are wrong. -- Best Regards Peter Larsen Wise words of the day: Showing up is 80% of life. -- Woody Allen -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 198 bytes Desc: This is a digitally signed message part URL: <http://lists.centos.org/pipermail/centos/attachments/20110328/5b2ec841/attachment-0001.sig>
On 3/29/11, mcclnx mcc <mcclnx at yahoo.com.tw> wrote:> we have several servers on same rack and servers are all inside firewall. > Centos version from 4.X to 5.X. sometime the connection are very slow > (compare to servers on other racks also inside firewall). > > we discuss with network engineer he ask us use "ping" and traceroute" to > check. Both tools response time are good but if we connect through > application like Web browser, database, or DELL OPMN tool. The response > time is very very slow.Are you connecting to the servers from within the same network/building or via Internet? If the ping times are good, it could be the servers are too heavily loaded, whether due to too many users or inefficient applications. So they would respond very slowly to requests although there is no network problem.
On Mon, Mar 28, 2011 at 5:13 PM, mcclnx mcc <mcclnx at yahoo.com.tw> wrote:> we have several servers on same rack and servers are all inside firewall. ?Centos version from 4.X to 5.X. ?sometime the connection are very slow (compare to servers on other racks also inside firewall). > > we discuss with network engineer he ask us use "ping" and traceroute" to check. ?Both tools response time are good but if we connect through application like Web browser, database, or DELL OPMN tool. ?The response time is very very slow. > > This situation normally last 4 to 5 hours then it back to normal. ?Does there has way to check "real" network response time so we can show to network engineer. ?Otherwise they always say "no problem". > > Thanks.If you run 'iperf' between the 2 servers you will be able to check the bandwidth at that time. It could be that you have another application using all the bandwidth, or the network has slowed down for some other reason. you could also try using Cacti to monitor the bandwidth through the switch. Also install the sysstat package on all servers and let it run every minute. You can graph the data using ksar on your local system. The graphs may show you that something else is going on. Check the crontabs as well. Does the time window line up with when you are running backups or something else over the network? Ping an traceroute are going to be mostly useless for this problem. They can help determine connectivity, but even a 56k modem can be "connected" and pass. Iperf will stress the bandwidth portion of the equation.
I don't think it is cable problem. The reason are: 1. it happen every 3 to 4 weeks once. 2. problem last 4 to 5 hours then back to normal. 3. not one server has this problem, several servers on that rack all have problem at same time. --- 11/3/28 (?)?Peter Larsen <plarsen at famlarsen.homelinux.com> ???> ???: Peter Larsen <plarsen at famlarsen.homelinux.com> > ??: Re: [CentOS] centos server network speed check??? > ???: centos at centos.org > ??: 2011?3?28?,?,??5:41 > On Tue, 2011-03-29 at 05:13 +0800, > mcclnx mcc wrote: > > we have several servers on same rack and servers are > all inside firewall.? Centos version from 4.X to > 5.X.? sometime the connection are very slow (compare to > servers on other racks also inside firewall). > > > > we discuss with network engineer he ask us use "ping" > and traceroute" to check.? Both tools response time are > good but if we connect through application like Web browser, > database, or DELL OPMN tool.? The response time is very > very slow.? > > > > This situation normally last 4 to 5 hours then it back > to normal.? Does there has way to check "real" network > response time so we can show to network engineer.? > Otherwise they always say "no problem". > > miitool and ethtool > > Check that you're running at the right speed; sometimes bad > cables will > make the negotiation go bad. Sometimes you just connect to > the wrong > switch port. You may also note if the switch has hard-set > values about > the negotiation such as duplex settings. Make sure they > match on both > ends. You should be full duplex unless there's a very very > good network > reason not to. > > Lastly, check ifconfig output. Make sure there's no errors > reported. If > you have a high error count, it's a good bet the cable is > bad or the > sync settings are wrong. > > -- > Best Regards > ? Peter Larsen > > Wise words of the day: > Showing up is 80% of life. > ??? ??? -- Woody Allen > > -----????????----- > > _______________________________________________ > CentOS mailing list > CentOS at centos.org > http://lists.centos.org/mailman/listinfo/centos >