|
| Greg's diary |
| August 2004 |
|
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
|
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Sunday, 1 August 2004 | Echunga | |
| Top of page | ||
| next day | ||
| last day |
Another day spent almost entirely brewing beer. There must be an easier way.
Took a look at the xine port I made yesterday. It's difficult to say whether it will do slow motion: all I got was three different SIGBUS crashes in a couple of minutes. Not very promising. It also has a configuration screen that looks like it has a web site in its ancestry, to judge by the poor layout:
|
|
||||||||
| Monday, 2 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Back to work today, and managed to get my program working as intended, more or less. I have an important demo to do next week, requiring about 6 weeks of work to be done first, so spent some time looking at that.
Also looked a little bit at mplayer to see what would be required to do slow motion and frame advance. Very little, it seems. Within a couple of minutes I was able to influence the frame rate and do something approximating to a very poor slow motion. It seems that it should be relatively trivial (a couple of hours, as opposed to minutes) to get it to work properly. Why do people prefer to invent “skins” rather than implement basic functionality?
Just when I thought the air conditioner problems were over, the external unit failed completely this evening. Looks like the compressor has failed. sigh.
| Tuesday, 3 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
More slog today. Came to the realization that my attempt to do 6 weeks' work in one was not likely to succeed, and gave up, spending time filing down rough edges instead, with what looked like good results.
Call from Chris Butler of Multi-Tech today: one of the Fedora CDs David Newall sent him last week was marginal. This is a real pain! Asked him to recover it and compare it with the first ones we sent. Didn't hear back from him.
Phil from Mount Barker Air Conditioning came along in the evening and took a look at the air conditioner. Diagnosis: defective starter capacitor:
That was quickly changed, and the system was back up and running within 24 hours. A far cry from the times we've had to endure in the past.
| Wednesday, 4 August 2004 | Echunga | Images for 4 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Just when I thought we finally had our CDs sorted out! Got a CD in the mail from Multi-Tech: Chris had made a copy of the first Fedora CD I had sent, which had been OK in the first place, except that, once it had installed itself from it, Fedora couldn't read it. Confirmed that the same applied to the copy that Chris made. It's looking more and more like a bug in Fedora and less and less like a bug in FreeBSD, though I can't completely exonerate FreeBSD.
Continued with tidy-up work today, and got some good results. Looks like things are in good shape.
| Thursday, 5 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
More work on my program today, and compared storage requirements with an existing product. The result: my program required 30 times more disk, and so of course was also a lot slower (though not by the same factor). There's obviously room for improvement there, which in the first instance will involve reassessing tradeoffs.
Still more problems with the CDs. It seems that the one I sent off yesterday was marginal as well. About the only ones that are not marginal are the ones I burnt on the CD-R burner on my Dell Inspiron 5150, but Fedora doesn't want to know about them. What a pain!
| Friday, 6 August 2004 | Echunga | Images for 6 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
After a flash of inspiration last night, set to rewriting large parts of my program. That's non-trivial, but I don't really have a choice if I want to have anything at all worth showing by Monday. Looks like a busy weekend.
Still no confirmation that the CDs are OK. What a pain.
| Saturday, 7 August 2004 | Echunga | Images for 7 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Had to do some scanning this morning, so installed the Canon software on my new machine and did so. Then decided to try out the “workaround” that they had claimed that would allow reliable scanning of 6 slides every time (it should do 8): leave out top left and bottom right slides, and the rest should be recognized correctly. Well, they're not:
Only one of the 6 slides is correctly framed; numbers 1 and 3 have a black bar on the right, number 4 has one at the bottom, and the software thinks that 5 and 6 are the wrong way round. This is no exception: it gets most of them wrong.
I've had enough with this thing. It's clear that Canon are not going to honour more than their absolute minimum legal obligations—given the inability of this software to scan slides and their continuing advertisements that it can, even this is in doubt—I'm going to return it. Now to find a scanner worth using.
| Sunday, 8 August 2004 | Echunga | Images for 8 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Exceptionally (for recent times, anyway) did some work today to fix up the problems in my program ahead of a demo tomorrow. That was a resounding success, so much so that I'm left wondering what I've forgotten: I exceeded my performance figures by about 60%. Things are looking good.
There's finally been a break in the rain, so we loaded our horses into the float and headed off to Kuitpo Forest to go riding. We weren't fast enough; it started raining on the way, so we just turned around and came back. It must dry up soon.
| Monday, 9 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Jim Johnson along today to look at the work I've been doing and to discuss where the company's going. We're living in interesting times. At least the deadline is gone, and in a few days I can relax a bit. Maybe.
Received a brochure for AUUG2004 in the mail today. Grrr. That was what I was going to pad AUUGN with. Now I need to find 11 more pages by yesterday.
| Tuesday, 10 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Finally a breather! A good thing too: in the morning I has 10,000 mail messages in my inbox, and it was threatening to overflow. By the evening I hadn't quite made it below 1,000 (but it was below 1,023).
Finally also got AUUGN out of the way, after finding another article to print. Thank God for that! Now I have to start with the next one almost immediately. Mikal Still also found an article about AUUG based on my diary entry for 30 July. I wish people would contact me before quoting my diary in the press.
Still more interest in my performance figures. I don't understand myself why they're so (comparatively) good, but I suspect it's not of my making.
| Wednesday, 11 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Ross Williams out here today for a discussion of the work I've been doing and our future direction. A long discussion, but we came out with some useful stuff.
While talking, had a minor mail disaster. Five days ago, I tried to forward over 5,000 spam messages to abuse@ctbcnetsuper.com.br. I've never seen anything but spam from ctbcnetsuper.com.br (and, in fact, in my experience the Brasilians are currently very heavy spam senders, probably not the impression that the country wants to make in the rest of the world), but this one was extreme: the messages came in in less than a day. I should have been more careful, though: this seems to be a send-only site, and there's no way to send mail to them. As a result, I ended up with them all expiring today—and being returned to me with multiple error messages. Took me over half an hour just to delete them all again.
Call from Sam Varghese of The Age. This story in ZDNet has obviously aroused some interest. Sam wrote a much more accurate article.
| Thursday, 12 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
The results of yesterday's mail crisis were evident today:
On 11 August 2004 you received 35771 mail messages and sent 28 mail messages.
I still can't dump a FreeBSD -CURRENT system, but I now have the Fedora CDs back, the ones that David Newall sent in. They worked fine, and I was able to install Fedora on eucla with no particular problem. Then decided to update FreeBSD on a third partition, which proved very frustrating: the disk partitioning tools seem to be broken, probably as a result of GEOM changes, and at one point I thought I would have to restore the entire existing FreeBSD partition. Installed FreeBSD 5.2.1 from CD-ROM onto the spare partition, and miraculously the existing partition came back to life.
Was just starting an installation of CURRENT on the new partition when I got a message from Brett Lymn that a number of older SPARC machines were available for grabs from his company, so up to Edinburgh to take a look, and ended up coming back with 9 SPARC machines ranging from an IPX to a SPARCStation 20, as well as a couple of old DEC Alpha servers. None of them have disks, which makes things a little more complicated, but they could be useful as diskless workstations. I'm prepared to give some of them away to anybody who's interested and has an interesting use for them.
| Friday, 13 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Testing went on in the background today, which was a good way to do it: I had some strangeness which only showed up after fifteen minutes of running; setting conditional breakpoints managed to get gdb to use twice as much CPU time as the program, making things even slower.
In the meantime, updated the kernel on eucla, in the process showing that my system upgrade procedure works relatively well. Dumping a processor from ddb, however, doesn't. at least not with the panic command; you need to use call doadump instead. It's been like that for I don't know how long.
Running a tcpdump on my right-hand monitor has proved useful on multiple occasions. This afternoon I saw a whole line of this on the screen:
16:22:35.753430 < 213.180.193.68.56911 > 192.109.197.80.27953: S 2706038967:2706038967(0) win 3072 16:22:35.770356 < 213.180.193.68.56911 > 192.109.197.80.48381: S 2706038967:2706038967(0) win 1024 16:22:35.770439 < 213.180.193.68.56911 > 192.109.197.80.2658: S 2706038967:2706038967(0) win 4096 16:22:35.770530 < 213.180.193.68.56911 > 192.109.197.80.2124: S 2706038967:2706038967(0) win 3072
This carried on at a rate of about 50 probes per second for nearly an hour, by which time I had received (and firewalled) about 200,000 packets, or 10 MB. It was relatively easy to find out who was doing it:
$ host 213.180.193.68 68.193.180.213.IN-ADDR.ARPA domain name pointer proxychecker.yandex.net
Sent a message to abuse@yandex.net, after which the bombardment stopped. Some time later I received a reply to my message stating:
Some things leave me at a loss for words.
| Saturday, 14 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
My loss for words continues. This time it's a journalist. After the misinterpretation of my diary entry of last month and my response, Iain Ferguson, another ZDNet reporter took up the story, performing no further investigation and deliberately ignoring the context or my request to contact me first. It's not surprising that he got things wrong. But then, he couldn't even read what I had written. Reluctantly, I'm going to have to put a copyright on this diary to minimize the number of people quoting me out of context. I don't want to stop people quoting me, but it doesn't help anybody if people go and invent things because they're too lazy to do their research.
In the afternoon, spent some time scanning the old cookbook that Yvonne had started in her time in France, and in which she collected recipes for nearly 20 years. The recipes are not very sophisticated, but they're interesting ideas, and the format is interesting. I suppose we should find a way to put the better ones in web page format.
| Sunday, 15 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
More working on web pages today. In the lead-up to the AUUG 2004 national conference, I tried to find the photos of the last conference in Melbourne, only to find that they weren't there. On further investigation discovered a large number of photos that I hadn't converted to web pages, so spent some time doing that; ended up uploading nearly 200 MB of images to the web site.
Also processed Yvonne's old cookbook, which I had scanned in yesterday. Had some fun writing a shell script to create a framework around the images; for such a simple thing, it worked surprisingly well, and left me wondering to what extent people have thrown out control in the sake of ease of use when creating modern software.
| Monday, 16 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Things are starting to little more normal again, but somehow I didn't have much to show for today. Spent some time debugging my program; as suspected, some of the blame was with the gdb debugging scripts. It's a slow business.
Also looked at the SPARC hardware that I got on Thursday. It's a good reminder of how quickly hardware becomes obsolete. The SPARCStation 10, the fastest machine, only had 32 MB of memory, and the SPARCStation 20 only had 64 MB, but it also had 2 CPUs. The SS 10 had a defective power supply (well, at least it had been removed), so took the memory out of it and put it into the SS 20, making just enough memory to install Solaris 9. Also had to find a disk to install on. The disks from my Sun Disk Array have the correct connectors, but they're full height drives, and their construction means that they'll only fit the top slot: the top slot obstructs the disk if you try to install into the bottom slot. That also means, of course, that I need to prop it up, and that I won't be able to put the cover on. Finally I've found a use for my old Fujitsu magneto-optical disks:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
How slow this installation is!
| Tuesday, 17 August 2004 | Echunga | Images for 17 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Finally got round to looking at the tutorial notes for the debugging tutorial I'm doing in two weeks' time. Hopefully by then I'll get them finished and in better shape than previously.
Carried on with my program debugging and found another bug, interestingly apparently a day one bug in code over 10 years old. It'll take a bit of thinking to fix it, not because it's so difficult to find a solution (that's obvious), but it'll be difficult to prove that it's fixed.
| Wednesday, 18 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
What a hectic day! It started off normally enough, installing a new version of FreeBSD on sydney and NetBSD on the SPARCstation 20. The latter proved to be almost impossible with the CDs I had (1.5.2 from Wasabi), so downloaded an ISO.
In the meantime, Alan Kennington showed up for a technical discussion about networking, about which I know nothing, so spent most of our time talking about file systems.
That time was somewhat curtailed by a phone call from Ollivier Robert, who was due to arrive from Melbourne by car this evening. He had discovered that the distances in Australia were larger than in Europe (he had expected the distance to be about 300 km, although Élodie told me had originally thought about 100 km; the real distance is about 750). As a result he had decided to fly instead, so he was arriving at 14:50. Reluctantly curtailed the discussion with Alan (which we wouldn't have finished today anyway) and into town to pick them up.
Back home, ran into more trouble on multiple fronts: updating DNS for Ollivier's monster laptop didn't update the secondary properly, building the software for sydney failed, the disk I had put in the SPARCstation 20 proved (after significant checking) to be defective (wouldn't even probe), and sat-gw, my satellite downlink and firewall box, developed not one but at least three problems: it wouldn't let data through for Olliver's IP, I couldn't get an ssh connection, couldn't get a console display (the video board seemed to have lost sync), and to add insult to injury the g key on the keyboard failed. Ended up crashing the machine and rebooting, after which Ollivier's machine was on the net, but I still couldn't get an ssh; looks like that one is my fault, probably a broken firewall config.
Pam Hay along on her way from OliVaylle to Perth, spending the night here. Pleasant evening.
| Thursday, 19 August 2004 | Echunga | Images for 19 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Somehow another day where I got nothing done. The news of the day was the breaking of the MD5 algorithm, which we have been using. Looks like we're going to have to find something else. SHA1 is a possibility, but the hashes are even longer, and it's marginally slower. Also fixed (hopefully) the complicated program bug that I found last week.
Apart from that, got NetBSD installed on the SPARCstation 20, which I've decided to call dumpty. Some day I must write a web page describing the crazy ideas that lead to my system names. What I didn't get done was any further work on my tutorial; that's now becoming urgent.
| Friday, 20 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
ADUUG lunch today, with Ollivier and Élodie, of course, but also with Andy Johnstone of the Australian Democrats for the first time; Andy's the real reason for Ian Gilfillan's recent Open Source Bill, and he aroused some interested discussion.
ADUUG lunches are always fun, and this time we had a total of 13 people show up, more than usual; but somehow it cuts the day in half, and I didn't get much done in the remainder of the day, just enough to confirm that, though I had fixed the bug I had been dancing around all week, it wasn't the one that was causing the corruption I saw last week. sigh
| Saturday, 21 August 2004 | Echunga | Images for 21 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Up early this morning and out to Clarendon with Ollivier and Élodie to meet Michael Hickinbotham, who showed us round his Clarendon vineyard:
|
|||||||||||||||||||||||
A nice place. They grow most of their fruit for big-name vintners, and I discovered that they're the owner of the “Old vine” Grenache vines (70 years old) from which Normans produced a wine of the same name some years ago, and which I had found particularly good.
After that to McLaren Vale to visit the same old wineries: Chapel Hill was closed, but went to Rosemount, Tatachilla and Wirra Wirra, none of which I have visited in over two years. Interestingly, the good wines they presented to us at Rosemount and Tatachilla were the same ones, same year, as last time, and I ended up buying more than I had intended. Things seem to be going well in the wine country, though. Wirra Wirra has just opened a new, much larger cellar door facility.
Catchup time in the afternoon. Building a NetBSD kernel for the SPARCstation 20 proves more difficult than I had expected: the kernel finally built, but crashed immediately on booting. Did some puzzling over that, but given the speed of the machine, didn't finish.
| Sunday, 22 August 2004 | Echunga | Images for 22 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Another barbecue today. They're a lot of fun, but somehow they tear the day apart. It's really difficult to calculate how much food to buy: if we assume they'll be hungry, they won't be, and we end up eating barbecued meat for the rest of the week. If we buy a little less, we run out and people go hungry. That would have been the case today, except that a number of people (five) didn't show up, so we did have enough. Took a number of photos.
| Monday, 23 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Ollivier and Élodie left for Kangaroo Island this morning, leaving me to catch up on the work that has accumulated in the last couple of days. Somehow I didn't have much to show for it. Made some progress on the tutorial notes for the AUUG conference, though not as much as I wanted; it seems that the kernel debugger really is still broken, which is a real nuisance. Tried to repeat the crashes I had experienced last month, without success. As I've noticed elsewhere, never rely on a bug. Even firewire debugging wouldn't work properly, which is disappointing.
| Tuesday, 24 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Into town this morning for the inaugural meeting of the Board of Management of the IT Council of South Australia, again with Yana. There's something strange about these board meetings: I've been to about six of them, and today for the third time we encountered kangaroos while bypassing Hahndorf. It's the second time Yana was with me, but every time I was on the way to an IT council meeting. You'd think that there would be some connection, but the only one I can think of is that Adelaide is a town not far from the bush.
The changes have made a big difference in the size of the meetings, which makes them more manageable, especially since not all positions on the board have been filled. On the other hand, that leaves fewer people to do the work, and I found myself chairing a membership subcommittee. That'll be interesting.
In the afternoon, more work on my tutorial, but also found enough time to find the next bug in my program; possibly it, too, is a day-one bug, but I'll have to investigate that more carefully, probably after the AUUG conference.
| Wednesday, 25 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
More work on the tutorial notes today, and finally got something worth submitting. It's really amazing how much work they are. Hopefully they're better than they have been. Didn't get much else done. Even managed to miss an AUUG board teleconference—the first time I've ever missed an AUUG board meeting, which left me less than happy.
| Thursday, 26 August 2004 | Echunga | Images for 26 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Spent most of the day working on my tutorial slides. It's difficult to know how to present this kind of material. In Taipei, as last year at AUUG and BSDCon, I presented directly from the tutorial notes, but particularly in the large lecture theatre in Taipei that was a problem. On the other hand, slides don't contain much information, and there are so many details to consider here.
Finally got our Digitrex DVD recorder back from “repair”, after being away for nearly a month. According to the service report, they changed the fan, and indeed it's a lot quieter. The other matters are allegedly “USUAL FOR THIS MODEL”. What now?
| Friday, 27 August 2004 | Echunga | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Relatively quiet day today, spent preparing for tomorrow's journey. It wasn't made any easier by the fact that zaphod paniced during the night; it's not clear whether the new replacement disk is not in fact also defective.
Ollivier and Élodie back in the evening, and we drank the bottle of Gevrey-Chambertin 1995 that he brought with him. A good reminder how heavy the Australian wines have become.
| Saturday, 28 August 2004 | Echunga –> Warrnambool | Images for 28 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
zaphod paniced again during the night with some file system consistency issue. Why do these things always happen when I'm leaving for a conference? Took a dump and put all the information, including the source and object trees and yesterday's dump, on eucla to look at when I get to Melbourne. Looks like there's something happening during the night to trigger it.
Off relatively early along the Princes Highway, through Mount Gambier towards the Great Ocean Road. Stopped at Beachport for lunch, reminding myself of the last time I was down this way; from memory this would have been on 9 or 16 November 1985. We left from the Semmens' place in Adelaide far too late in the morning, and we had a dinner invitation to John Donelan's place somewhere in the East of Melbourne, which meant that we basically had to hurry all the way. It seems that the road has changed since then, but I recall the T junction near Beachport: it came on me as such a surprise that I had to break heavily, throwing Yana, then 5 months old, and her baby bed off the back seat onto the floor (without injury, fortunately).
On to Mount Gambier, where in the intervening years I have discovered my grandfather was born (in 1893 or 1894), but wasn't able to establish where. Took a brief look at the Blue Lake and then on to Warrnambool, where we stopped for the night. Had dinner at the “Beach Babylon”, a mixed blessing. The food was quite good, but the service was terrible: a three course meal took over three hours, and the timing was all over the place. I think the real issue is that they're understaffed. I told the maître d'hôtel of my concerns on leaving, but instead of apologizing, he just took offence to my statement that it would be in my diary. It seems that I should just have put up with the service. What a pity. With a little more attention to the issues it would be quite a nice restaurant.
The food was not only good, it was also very plentiful. I took the following photo, which I later sold to Weight Watchers for a TV commercial against gluttony. They cut Ollivier out of the photo, though: he was far too skinny.
|
|||||||||||||||||||||||
| Sunday, 29 August 2004 | Warrnambool –> Melbouurne | Images for 29 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
The weather hasn't held, unfortunately. Up through the rain this morning to look for some breakfast and some petrol, then picked up Ollivier and Élodie and to Flagstaff Hill, an open-air maritime museum, where we got slightly moist. Much of the area has to do with a Bass Strait port of 150 years ago, and it looks much less authentic than Old Tailem Town; it was just too tidy.
Then to Logan's Beach and was rewarded by the sight of a number of Southern Right Whales swimming in mid-distance. Certainly impressive by their size, but unfortunately not by their detail. What an idiot I was to forget to bring the binoculars.
On to the Twelve Apostles, by which time it was raining so heavily that we took a quick look, a couple of photos, and swam back to the car. On to Melbourne, stopping only for lunch, and got to the Duxton Hotel through very heavy traffic shortly before 6 pm. Out for dinner with Steve Bellovin, Jeffrey Hsu and Carl Makin; Theo Deraadt was there too, but declined to join us: he had apparently already eaten.
| Monday, 30 August 2004 | Melbourne | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Today was my all-day kernel debugging tutorial, which went smoothly enough. Five participants (got to remember that that corresponds to about 75 in America), all of whom were primarily interested in Linux. It looks like I'm going to have to add more Linux-related material. Deviated somewhat from the course notes, and spent some time looking at the zaphod dumps, which seem to be due to a vnode being marked VBAD and being caught in an INVARIANTS section because a pointer hadn't been recycled; possibly a harmless omission.
In the evening to Lygon Street for dinner, at a place on the South-East corner of Lygon and Grattan Streets, where we somehow managed to get all the drinks for free. Considering they charged $10.50 for a basket of garlic bread, I don't think they suffered too much, though.
| Tuesday, 31 August 2004 | Melbourne | Images for 31 August 2004 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
Jeffrey Hsu's tutorial today, a Linux code walkthrough. I've been in this sort of thing before, but it seems that it's a relatively unusual thing in the Linux world. It was also Jeffrey's first tutorial of this nature, and he somewhat overestimated the time it took people to read and understand the code. From my viewpoint, things were different. After the pain of the code reading I did in April and May, I found it refreshingly easy to follow.
Jeffrey also had a number of interesting tools and methods. He brought a number of books, most of which I had, though not Comaen, Leiserson and Rivest: “Algorithms”,McGraw-Hill 1989, which I think I'm going to have to buy. In addition he showed a new tool called Source Navigator, in the style of cscope and etags, but ostensibly more powerful. Spent quite some time trying to install the FreeBSD port, showing all the weaknesses of the Ports Collection in the process: pkg-add -r didn't work (claimed it couldn't find the URI), dependencies were wrong, and when I finally got everything installed, I didn't know how to start it, and there was no obvious documentation. When I finally got it started, discovered that it would generate about 2 GB of cross-reference data (TAGS is 1.3 MB), and I didn't have space. Jeffrey used it during his talk, and I found I was consistently faster with etags than Jeffrey was with Source Navigator. It's doubtless of use, but the menu pushing slows it down too much for a number of uses.
Speakers' drinks at the Royal Melbourne Hotel in the evening, after which down to the other end of Bourke St to a NetBSD beer drinking evening. Late to bed.
Do you have a comment about something I have written? This is a diary, not a “blog”, and there is deliberately no provision for directly adding comments. It's also not a vehicle for third-party content. But I welcome feedback and try to reply to all messages I receive. See the diary overview for more details. If you do send me a message relating to something I have written, please indicate whether you'd prefer me not to mention your name. Otherwise I'll assume that it's OK to do so.
| Top of page | Previous month | Greg's home page | Today's diary entry | Next month | Greg's photos | Copyright information |
