I’m realizing that we simply cannot count on our leaders to do it all – or for that matter, to do much at all. Although I think things must change at a very basic institutional level, and therefore we must keep pressuring governments to act, we can’t wait for that. There are things we all can, and must, do – now. I am pretty damned sure that it is in our best interest to do so, in the most fundamental way. 20-50 years from now, will our actions be forgiveable?
Added a new mobile plugin/theme for WordPress, WPtouch. If you have a mobile device, give the site a browse and see what you think, I think it’s swanky.
I’ve been an eMusic subscribe since 2003. Have generally liked it, but they just revamped things and I can’t tell now. They’ve made changes before, but this is pretty sweeping. They got more labels & artists signed up – yay! It costs more per track now – boo. Some albums with > 12 tracks (hardcore!) cost only 12 track credits now – yay! Some 3-track albums now cost 12 credits – boo. Still no DRM – yay! Still no way to get lossless encoding – boo.
Yeah, I dunno. Make this stuff too hard and/or expensive and/or frustrating and people will go elsewhere.
From the latest “filesystem test” of btrfs, nilfs, ext4 and xfs:
It took 20 seconds for this database test to complete under EXT3, 34 seconds under NILFS2, but 870 seconds for EXT4! XFS was at 1312 seconds and Btrfs was at 1472 seconds! These results are a bit shocking, but the Phoronix Test Suite does run these tests multiple times to ensure accuracy and statistical significance.
Ok, but the issue here is not statistical noise or averaging problems. ext4 & xfs & btrfs are flushing the drive’s write cache to be sure fsync is on disk; ext3 is not. This came up on their own list, and I explained that it was related to barriers etc. Short memories I guess. Phoronix could be useful if the tests were more meaningful & transparent, and if they engaged in a bit of communication with the experts in the subsystems they are testing. It could have been a teachable moment, but it’s just noise this way. :(
How many times has this played out …
[17:30] * gnude (~email@example.com) has joined #ext4
[17:31] <gnude> hello
[17:33] <sandeen> hey
[17:35] <gnude> hello sandeen
... wait ...
[18:01] * gnude (~firstname.lastname@example.org) has left #ext4 (Verlassend)
If you join an irc channel, you don’t have to say hello, really. It makes people wait around to see if you have a question, and then blog about it when you don’t. ;)
Jack Aboutboul’s blog has an interview with me about ext4 in Fedora 11.
I’m turning over a new decade tomorrow, and got an early birthday present:
Rode it to work today, works just fine… I like the simplicity of the single speed, it’s pretty light & quick, and seems solid. I had been looking at the Masis but in the end decided against it. The Fixed was a bit too stripped down, and the Commuter was too much like a family sedan. This one seems like a good compromise between them. I got it at The Alt in Minneapolis. Chuck at Behind Bars carries Masis and Konas, but didn’t have the 2008 Konas, just 2009, and I couldn’t handle the yellow rims. But I was very impressed with Behind Bars, nice place, nice people, extremely helpful … check them out (or heck, both) if you’re in the market.
The O_PONIES thing came up in the context of how ext3 behaves, how app writers wish that every filesystem behaved like ext3 (in the good ways , of course, not in the bad ways, oh no!) and how generally they’d like a pony with that, too, please. In other words, open your files with O_PONIES and the world is your oyster; the filesystem will grant your every wish.
It’s become the running joke among the filesystem developers I know, but as it turns out I was the one who coined it (I think?) Jeff thinks so too, which is what reminded me. Ted T’so thought it was Jeff, but he was 2 weeks behind the curve. Who knew I’d leave such a lasting impression.
$ grep O_PONIES OFTC-#linuxfs.txt | head -n 1
<sandeen> Mar 15 23:34:10 open(my_configfile, O_PONIES);
I made a tshirt, too:
But it was Val, with her impeccable sense of style, timing, and politics, who had the good sense to make a t-shirt with an extra inkjet t-shirt transfer I gave her, and wear it on photo day at LSF:
I wore mine on day 1, and other than a photo Matt Mackall took, there is no record.
But now you know the secret of the man behind the O_PONIES curtain!
ext4 recently grew a feature to run without journalling, which is kinda neat.
While thinking about what it might take to do such a thing for xfs, because running without a log is certainly interesting for benchmarking if nothing else, I realized there’s a pretty simple way to do this without requiring any disruptive code changes:
# echo "0 67108864 zero" | dmsetup create zero1
# mkfs.xfs -l logdev=/dev/mapper/zero1 /dev/sdb1
# mount -o logdev=/dev/mapper/zero1 /dev/sdb1 /mnt/test
voila, most log overhead is gone. The zero dm target soaks up the log writes w/o much overhead, and when mounting, xfs handles a zeroed log just fine. In case it’s not obvious, of course this doesn’t give you any sort of filesystem integrity when you crash…