Noisetor is showing a significant, sustained drop in bandwidth usage starting approximately February 7-8. We've checked our setup and logs and there doesn't appear to be any sign of a causative factor here.
Throughout January and the first week of February we were averaging 400-500 Mbps. There was a pretty smooth decline down on the 8th, stabilizing at a "new normal" of 200-300 Mbps which we've maintained since then. (All these numbers are based on Munin graphs of eth0 throughput using the if_ plugin.)
I have some hacky Python that summarizes the torstatus.blutmagie.de data, and it appears that other exits didn't see a similar drop; but our drop came a few hours to days after torservers added a significant amount of new bandwidth. (However, total exit BW reported in torstatus did not increase much; if anything it seems to have gone down slightly.) Around the same time, Amunet rose from ~150 Mbps to ~450 Mbps and has remained in that range since.
Thoughts?
-andy
On Tue, Feb 14, 2012 at 4:40 PM, Andy Isaacson adi@hexapodia.org wrote:
Noisetor is showing a significant, sustained drop in bandwidth usage starting approximately February 7-8. We've checked our setup and logs and there doesn't appear to be any sign of a causative factor here.
Throughout January and the first week of February we were averaging 400-500 Mbps. There was a pretty smooth decline down on the 8th, stabilizing at a "new normal" of 200-300 Mbps which we've maintained since then. (All these numbers are based on Munin graphs of eth0 throughput using the if_ plugin.)
I have some hacky Python that summarizes the torstatus.blutmagie.de data, and it appears that other exits didn't see a similar drop; but our drop came a few hours to days after torservers added a significant amount of new bandwidth. (However, total exit BW reported in torstatus did not increase much; if anything it seems to have gone down slightly.) Around the same time, Amunet rose from ~150 Mbps to ~450 Mbps and has remained in that range since.
Thoughts?
Its probably the new blockade on SSL in Iran https://blog.torproject.org/blog/iran-partially-blocks-encrypted-network-tra...
On 02/14/2012 08:40 PM, Andy Isaacson wrote:
Noisetor is showing a significant, sustained drop in bandwidth usage starting approximately February 7-8. We've checked our setup and logs and there doesn't appear to be any sign of a causative factor here.
Throughout January and the first week of February we were averaging 400-500 Mbps. There was a pretty smooth decline down on the 8th, stabilizing at a "new normal" of 200-300 Mbps which we've maintained since then. (All these numbers are based on Munin graphs of eth0 throughput using the if_ plugin.)
this is traffic data for my (non-exit) relay during the first 10 days of February
(6.1 GB IN / 6.23 GB OUT / 12.33 GB TOTAL) (6.74 GB IN / 6.84 GB OUT / 13.58 GB TOTAL) (8.73 GB IN / 8.84 GB OUT / 17.56 GB TOTAL) (6.57 GB IN / 6.7 GB OUT / 13.27 GB TOTAL) (10.58 GB IN / 10.53 GB OUT / 21.12 GB TOTAL) (4.23 GB IN / 4.28 GB OUT / 8.5 GB TOTAL) (5.09 GB IN / 5.15 GB OUT / 10.24 GB TOTAL) (5.77 GB IN / 5.88 GB OUT / 11.65 GB TOTAL) (5.21 GB IN / 5.29 GB OUT / 10.5 GB TOTAL) (7.23 GB IN / 7.24 GB OUT / 14.48 GB TOTAL)
theres a marked drop on the 6th. (not quite sure what happened on the 5th tho)
On Wed, Feb 15, 2012 at 09:32:24AM +0100, krugar wrote:
On 02/14/2012 08:40 PM, Andy Isaacson wrote:
Noisetor is showing a significant, sustained drop in bandwidth usage starting approximately February 7-8. We've checked our setup and logs and there doesn't appear to be any sign of a causative factor here.
Throughout January and the first week of February we were averaging 400-500 Mbps. There was a pretty smooth decline down on the 8th, stabilizing at a "new normal" of 200-300 Mbps which we've maintained since then. (All these numbers are based on Munin graphs of eth0 throughput using the if_ plugin.)
We've seen some recovery since February 15th, with sustained stretches over 400 Mbps the last three days.
The daily low points are still lower than was normal before February 7.
So there were about 6 days that we were much slower than expected, then back up to a more normal usage.
Very puzzling, but I guess we'll just keep an eye on it.
-andy
tor-relays@lists.torproject.org
-
Andy Isaacson -
Javier Bassi -
krugar