The effect of latency and packet loss on effective throughput

Posted on January 31, 2008 by rbocchinfuso

One of my customers who was running three replication technologies, XOsoft, PlateSpin and EMC MirrorView started experiencing issue when we relocated their DR equipment from the production facility where we staged and tested the applications to their DR location.

While having the Producion and DR environments on the LAN we successfully replicated Exchange with XOsoft, Operating Systems with PlateSpin and Data with MirrorView, once we moved DR infrastructure these components all failed. This prompted us to perform network remediation. The following are the results of a simple ping test that was performed using WinMTR.

The above chart shows the output from output from a simple test which shows packets, hops, latency and % packet loss. We ran this tests a number of times from different source and destination hosts with similar results. The originating host for this for this host was 192.168.123.6 in the chart below 192.168.120.1 is the first hop.

NOTE: the destination 192.168.121.52 was sent 414 packets but only received 384 (NOTE: this number worsens over time). This is consistent with the behavior that XOsoft, PlateSpin and MV are experiencing.

The graph below represent the impact of packet loss on bandwidth. As you can see 1% packet loss has a dramatic affect on relative bandwidth.

Using a bandwidth calculator found here http://www.wand.net.nz/~perry/max_download.php, we calculated the relative bandwidth using the metrics we observed.

An effective speed of ~ 30KB/s was calculated using 7% packet loss, a 10Mbit link and 90ms RTT
- with 15ms RTT the effective speed is ~ 185 KB/s
An effective speed of ~ 128KB/s was calculated using 1% packet loss, a 10Mbit link and 90ms RTT
- with 15ms RTT the effective speed is ~ 700 KB/s

These number are dramatic when compared to the expected 9 Mbit or 1152 KB/s

In conclusion a clean network is critical, especially with technologies like replication that rely on little or to no packet loss and the use of all the bandwidth available. Interestingly enough we seem to be seeing these sort of problems more and more often. My hypothesis is that more and more organizations are looking to implement DR strategies and data replication in a critical component to these strategies, understanding this I believe this problem will get worse before it gets better. For years many of these organizations have used applications and protocols which are tolerant of packet loss, congestion, collisions, etc… protocols like http, ftp, etc… Data replication technologies are far less forgiving so network issues that have most likely existed for sometime are rearing their head at inopportune times.

Share and Enjoy

My perspective on VMW

Posted on January 30, 2008 by rbocchinfuso

So the blog has bee a bit quiet lately but I promise I have a few meaty posts which I have been working on. In my typical fashion I will most likely post them in rapid succession. Anyway on to this mornings post… Yesterday I read a fairly well know storage analyst’s take on the royal a$$ pounding that VMware has been taking over the past few days.

This analyst points out a number of good points like while VMW missed the top line revenue goal by only 10 million dollars they increased revenue by 80% and grew profit margins. This particular analyst takes the position of screw the street, CEO should ignore the street and just run their business. While I enjoy the idealism, let’s face it when the company went public (a choice they freely made) they relinquished control and the ultimate destiny of their company to the street, running the company has now morphed from building great products to keeping the street happy, a very different paradigm for VMW I am sure. From a different perspective I agree with the public flogging that VMW has been taking, this virtualization market while hot is still in it’s embryonic stage with < 5% of the servers in the market virtualized. VMW by no means owns the market, there is still plenty of green field. So, if I am looking at the market and companies like Microsoft and Citrix are targeting VMW doing business is going to get harder not easier. With > 95% of the market up for grabs and Microsoft’s already dominant OS position how hard do we really believe it is going to be for the "market leader" in this space. There is no doubt this is a land grab which means that VMware needs to grow top line revenues (which BTW I understand that they did by 80%) to demonstrate to the street that they are widening the gap. A companies valuation is all about the streets perception of this companies value in the future. IMO VMware has enjoyed a overly inflated valuation based on their present day value and market hype, their value in the future will be greatly diminished as players like Microsoft and Citrix truly compete for this business. At ~ 54 with a P/E of ~109 I think the price correction will continue.