time to pull the plug

I'm shamefully late in doing a real writeup of how to build one of those things. Soon, I promise.

Equipment: Orion Skyview 6 Deluxe EQ, using the 32, 25, 15, and 4 mm eyepieces. New object observed: M94, M44, M67, M41, Saturn, Titan, Tethys, Phoebe Rhea Previous objects observed: M81, M82, Mars Possibly glimpsed (but likely not): M51, M65 Notes: It's been a brutal couple of months. The night of the 18th was the first clear night in about a month or so, and the first good night since December.

And working quite nicely, too. This is a mod_mcpage patch for lighttpd 1.5. (There's a tarball too.) This is the long awaited mod_mcpage where you can add a local memcached instance as a fast local cache with a quick timeout. From README.mod_mcpage in the tarball: This patch adds the ability to add a local fast memcached with a quick time-out for extra quick serving. It tiers with the other memcached servers (which you can have an array of) so that data from the remote memcached servers gets put into the fast local memcached server, where it will live for a few seconds until it times out and gets fetched from the remote again.

Equipment: Orion Skyview 6 Deluxe EQ, using the 32, 15, 6, and 4 mm eyepieces.

New object observed: Mars

Previous objects observed: M42, M81, M82

Possibly glimpsed: NGC 3077 or NGC 2976

Notes:

It was still a cold night, but not quite as brutal as the last night out. It was a fairly short session as well, since the sky clouded up, but after using the eyepatch before I went out I was able to see both M81 and M82 again (also, I looked in the right place for M82 this time -- d'oh!). I may have also seen one of the nearby NGC galaxies, either NGC 3077 or NGC 2976, but I ended up not being able to find it again so I'm not claiming it as seen at this point.

Other than that, I looked at the always lovely Orion Nebula, and just as the clouds were starting to come in I moved the telescope and looked at Mars briefly. Unfortunately between the transparency issues that night, the clouds that were showing up, and poor seeing, I couldn't get much out of it.

Using the hair dryer for the purposes of defogging worked pretty well though this night, though. That was nice.

Equipment: Orion Skyview 6 Deluxe EQ, using the 32, 15, 6, and 4 mm eyepieces and the ultrablock & OIII filters.

New object observed: NGC 2392 (Eskimo Nebula)

Previous objects observed: M42, M81, M45

Notes:

It was a brutally cold night, at about 12°F, but I was able to stay out for about an hour or so until my feet were too cold to go on. It turns out that at that temperature, extension cords (for hair dryers) are extremely stiff, and my stool that I sit on was frozen stiff. Couldn't turn it or make it go up and down.

At the beginning of my observing session, I was able to find M81, but not M82. I think, in the future, when I try to find them I'm going to need to make sure that I put my eyepatch on ahead of time to give myself a fighting chance of seeing them better. I would have gone back to it later, but didn't find the time before I was freezing too much.

The big find of the night, and an appropriate one given the weather conditions, was seeing the Eskimo Nebula. While the OIII filter didn't help with it at all (not sure because of conditions or what), the ultrablock did some. They weren't really very necessary, though; just looking at it with the naked eye, though, was enough, and I was even able to discern some detail from it, in that I could see the center being brighter than the dimmer outside. It didn't look like the pictures, of course, but I could see how it looks like that from what I saw. Not too bad.

The Pleiades and Orion Nebula were, as usual, stunning. Mars was not quite far enough over the house to look at last night; by the time it was high enough that I could see it standing up but still too low to get with the telescope, I was having to defog my eyepieces with the hair dryer (which worked nicely) and the oddly frozen extension cord, and I couldn't feel my toes anymore. At that point, I elected to go back in.

Apparently I'll be able to get the patch ready sooner than I expected. I had been experimenting with using localmemcache's C API to store pages in the fast local cache, assuming that it would be faster than using a local instance of memcached running on the server, and that I'd just have to add expiration and LRU removal to localmemcache (not the smallest task, but certainly quite doable). After converting mod_mcpage to use the binary protocol, I got a bit of a speed boost, so that mod_mcpage serves stuff up about as quickly as it lighttpd serves a static file (sometimes a few microseconds faster, sometimes a few microseconds slower).

No patch yet, but I added a local memcached instance that only stores stuff for a few seconds to mod_mcpage to see how it worked, and got some very interesting benchmarks. My original plan had been to craft up a cache with POSIX shared memory (which is pretty sweet), semaphores, and Glib hashes, but I thought about it some and decided to just let memcached handle the housekeeping stuff, since with a custom shared mem cache I'd have to worry about expiring older stuff and removing unused entries myself.

In summary, though, being served from a paravirtualized one proc Xen VM with 128MB RAM, a local memcached instance of 16MB, and a remote memcached server with 64MB running on a fully virtualized one proc Xen VM with 128MB RAM (processor-wise, the Xen host has a Intel Core2 Duo E8500 @ 3.16GHz):

Running 1000 requests with a concurrency of 1 had 95% of all requests served in 3ms with both local and remote memcacheds, 95% within 17ms with just the remote memcached, and 95% within 780ms with no memcached at all.

Running 1000 requests with a concurrency of 5, with both 95% were within 135ms (80% within 9ms, 50% within 7ms), with just the remote 95% were within 90ms (80% were within 69ms and 50% were within 63ms), and no memcaching at all 95% were within 3766ms (80% were within 3621ms and 50% were within 3554ms).

Mean times for concurrency of one with both, remote only, and no memcached: 4.004ms, 13.878ms, and 778.267ms.

Mean times (across all requests) for concurrency of five with both, remote only, and no memcached: 3.926ms, 13.359ms, and 718.912ms.

Update: As I was cleaning up mod_mcpage to make a patch out of it in the relatively near future, I took out a bunch of random debugging stuff that was going into the log and re-ran ab again, this time with the index page of the site I was testing with using the tiered local + remote caches against the same file being served statically. Over 10,000 requests at a concurrency of one, the tiered cache had a mean time per request of 2.216ms. The static file had a mean time of 2.110ms. Over 10,000 requests with a concurrency of five, the tiered cache had a mean time per request of 1.120ms across all requests. The static file had a mean time of 1.025ms across all requests.

Not too bad. Doing it in shared memory would be blazingly fast, but who knows when I'll have time to get all the little bits of that done. Something worth shooting for down the road though.

Full benchmarks (including the update) below the fold.

Equipment: Orion Skyview 6 Deluxe EQ and Celestron Astromaster 76 EQ, using the 32, 25, 15, and 9 mm eyepieces and the ultrablock filter.

New objects observed: dew

Previously observed objects: M31, M32, M42

Notes:

I had had great hopes for this night - the sky was going to be clear for a long time for the first time in ages, with halfway decent transparency to boot. I went and set up my shelter and scope early in the night, but found that there wasn't a whole lot out that I could look at early on, so I went back inside, leaving my stuff out for later.

When I came back out, I was a bit surprised to find that massive amounts of dew had settled on everything. Still, it wasn't the end of the world. I started looking around, but found that I was having a really hard time finding anything in my finder scope. Then I noticed that I was having a tough time seeing anything at all. Finally I shined my red flashlight on my eyepiece, and saw that it was fogged up. Oh no!

I tried swapping other eyepieces in, but that didn't help. The primary mirror was fine, at least, but I still couldn't see anything. Eventually I noticed that the secondary mirror was fogged up, so I packed everything up and took it back into the garage. I pointed the 6" upside down to dry out and left the lens case open so that could fully dry out as well. I took the 3" out for a spin for a while and was able to see M31 (but not M32) and M42, but not with the same detail as with the 6" of course. I am not, however, sure how much of the difference was from the size of the mirrors and how much was from any dewing on the 3".

After a while, I brought the 6" back out and was able to observe M31, M32, and M42 briefly, but it dewed up again within a few minutes and I gave up. I have begun researching anti-dewing solutions and will try them out next time the weather permits observation.

I'm going to be speaking at Ignite Seattle 8 on December 1st. Normally if I go talk somewhere (which hasn't happened all that often), it would be on Daily Kos related issues, but not this time. I'll be speaking on building an astronomical viewing shelter (which I need to write up for here too) on the cheap, coming in at about $100. You can buy a viewing tent for several hundred, or spend thousands on a dome.

Equipment: Orion Skyview 6 Deluxe EQ, using the 32, 15, and 10 mm eyepieces and the broadband,  ultrablock, and OIII filters. New objects observed: M42, Betelgeuse Previous objects observed: M81, M82, M31, M32 Notes: The Moon was not out, and the clouds parted, for the first time in weeks, so I went out for a brief unplanned session with the telescope. Unfortunately transparency wasn't real great and skyglow was fairly bad, so it wasn't the best night.