Wandering Thoughts archives


10G Ethernet is a sea change for my assumptions

We're soon going to migrate a bunch of filesystems to a SSD-based new fileserver, all at once. Such migrations force us to do full backups of migrated filesystems (to the backup system they appear as new filesystems), so a big move means a sudden surge in backup volume. As part of how to handle this surge, I had the obvious thought: we should upgrade the backup server that will handle the migrated filesystems to 10G Ethernet now. The 10G transfer speeds plus the source data being on SSDs would make it relatively simple to back up even this big migration overnight during our regular backup period.

Except I realized that this probably wasn't going to be the case. Our backup system writes backups to disk, specifically to ordinary SATA disks that are not aggregated together in any sort of striped setup, and an ordinary SATA disk might write at 160 Mbytes per second on a good day. This is only slightly faster than 1G Ethernet and certainly nowhere near the reasonable speeds of 10G Ethernet in our environment. We can read data off the SSD-based fileserver and send it over the network to the backup server very fast, but that doesn't really do us anywhere near as much good as it looks when the entire thing is then going to come to a screeching halt by the inconvenient need to write the data to disk on the backup server. 10G will probably help the backup servers a bit, but it isn't going to be anywhere near a great speedup.

What this points out is that my reflexive assumptions are calibrated all wrong for 10G Ethernet. I'm used to thinking of the network as slower than the disks, often drastically, but this is no longer even vaguely true. Even so-so 10G Ethernet performance (say 400 to 500 Mbytes/sec) utterly crushes single disk bandwidth for anything except SSDs. If we get good 10G speeds, we'll be crushing even moderate multi-disk bandwidth (and that's assuming we get full speed streaming IO rates and we're not seek limited). Suddenly the disks are the clear limiting factor, not the network. In fact even a single SSD can't keep up with a 10G Ethernet at full speed; we can see this from the mere fact that SATA interfaces themselves currently max out at 6 Gbits/sec on any system we're likely to use.

(I'd run into this before even for 1G Ethernet, eg here, but it evidently hadn't really sunk into my head.)

PS: I don't know what this means for our backup servers and any possible 10G networking in their future. 10G is likely to improve things somewhat, but the dual 10G-T Intel cards we use don't grow on trees and maybe it's not quite cost effective for them right now. Or maybe the real answer is working out how to give them striped staging disks for faster write speeds.

tech/HDsVs10GEthernet written at 23:42:12; Add Comment

My spam is (mostly) boring

I've mentioned a couple of times that I'm doing an experiment with a sinkhole SMTP server to handle email for some old addresses of mine that have become nothing but spam. When I started the experiment, what I think I expected to find was a bunch of industrial spam operations, places that had my addresses firmly anchored in spam lists and were sending their 'legitimate' email to them on a persistent basis, and maybe some interesting spammer behavior otherwise.

While there has been some of this and there are a few persistent and sometimes very aggressive mailing list places trying to send me spam, almost all of what I get now is surprisingly boring. Specifically, most of what I get is now advance fee fraud with a bit of phish spam mixed in.

(Admittedly I blocked the aggressive sending places once I identified them as persistent repeat senders. When I already have enough samples of their spam, I don't particularly need more.)

This 'boring' spam comes from all over and has at best vague patterns to it. It's clear that there's a lot of people doing it, a lot of hosts being abused as senders, a great variety of origin addresses being forged onto the email, and the contents vary a lot at a mechanical level. But at the level of learning interesting things about spammer behavior there's no real variation, which is why I call it boring. Advance fee fraud spam is advance fee fraud spam; I don't think I've spotted anyone doing anything particularly ingenious, but then I haven't been paying much attention.

All of this kind of makes my sinkhole SMTP server a failed experiment. If I'm not going to get interesting spam there's very little point in running it at all, so I'm probably going to shut it down entirely soon and let all the spammers just have their email time out.

(I sometimes toy with running it with absolutely no restrictions for a limited time, say a week, and seeing what I collect in that week and how things break down and so on. But I'm not sure I have the energy for that particular experiment.)

spam/MySpamIsBoring written at 00:59:37; Add Comment

Page tools: See As Normal.
Login: Password:
Atom Syndication: Recent Pages, Recent Comments.

This dinky wiki is brought to you by the Insane Hackers Guild, Python sub-branch.