hmm.. i've been suspecting a network issue, but haven't been able to find sumthing concrete to support this fact....<br><br>the stats have been jumping <br>from <br>STAT bytes_read 18542344217<br>STAT bytes_written 64761742795
<br>to <br>STAT bytes_read 18549625582<br>STAT bytes_written 64790479458<br><br>during consecutive runs, and it is off peak time for my site.. will be running it again during peak hours to check that out....<br> <br>i plan on running a network sniffer , like ntop or any other on a machine in the network to analyze the traffic flowing between the machines ....to see the amount of traffic in the network, so i can estimate whether there is a bottle neck sumwhere in the network....
<br>or is there a better way of doing that :)<br><br><br><div><span class="gmail_quote">On 5/24/06, <b class="gmail_sendername">Steven Grimm</b> <<a href="mailto:sgrimm@facebook.com">sgrimm@facebook.com</a>> wrote:</span>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">I can tell you that when we've seen failures to connect to memcached,<br>the problem has always turned out to be a network issue -- most often a
<br>flaky switch or loose cable. But in this case it sounds like a simple<br>capacity problem.<br><br>How much data do you run through memcached? You say you moved from a<br>gigabit network to a 100Mbps network; that's an order of magnitude less
<br>available bandwidth for memcached traffic and you may simply be<br>saturating the network. You could be saturating your switch, rather than<br>maxing out any one machine's capacity; that is even more likely if<br>you're sharing a switch with other customers at your hosting provider,
<br>who might have bursts in traffic that overwhelm the switch without you<br>knowing about it.<br><br>Look at your memcached stats and see how fast the "bytes_in" and<br>"bytes_out" numbers change. If you're pushing a few tens of megabits a
<br>second, then periodic spikes in traffic could easily overwhelm your network.<br><br>In any event, if you're seeing 7ms ping times on your local switched<br>network, something is definitely wrong there. You should never see that
<br>on a network that's not pushing up against its capacity limits.<br><br>-Steve<br><br><br>Kamran Nisar wrote:<br>><br>> got zero tx/rx errors...<br>><br>><br>> even the ping returned 0% packet loss, though there was sum random
<br>> sharp jumps in repsonse time<br><br></blockquote></div><br><br clear="all"><br>-- <br>Regards<br>M Kamran Nisar,