sitting here at Patterson station, where i was early for the train. then get told it’s running 12 minutes late. suck
i’m on way into city to look more closely at facities at RMIT.
at least the weather is nice.
back in town later tonight for luv too. going to drive for that as it’s just so much more efficient.
I normally read Planet MySQL from RSS, but for some reason I ended up on the actual site today in a Web Browser (Epiphany to be exact) and saw this:
And thought, “wow, ugly”. I don’t keep my browser “maximised” because I think it’s a stupid way to work – I often switch between tasks or like to have an editor open while referring to something in a browser (e.g. some tech details of some source module), or monitor IRC or IM. I remembered that Epiphany has an Ad Blocking extension, so in an effort to de-uglify, I enabled it. I now see:
Hrrm… much better. Notice how the links on the left to the most active are actually useful now (I can read them).
Note that this isn’t a rant on adverts on web sites – I can handle them (the google ones which aren’t obtrusive) – I’m against the uglyweb.
Spoke with Brian the other day on what was required to get NDB to be a pluggable engine – and started hacking.
The tricky bits invole dependencies of things like mysqldump and ndb_restore on some headers to determine what tables shouldn’t be dumped (hint: the cluster database used for replication).
Also, all those command line parameters and global variables – they’re fun too. It turns out InnoDB and PBXT are also waiting on this. In the meantime, I’ve done a hack that puts config options in a table.
Currently blocked on getting the embedded server (libmysqld) to build properly – but i now have a sql/mysqld binary with pluggable NDB. All libtool foo too.
Hopefully i’ll be able to post soon with a “it works” post
Inspired by PeterZ’s Opening Tables scalability post, I decided to try a little benchmark. This benchmark involved the following:
I wanted to test file system impact on this benchmark. So, I created a new LVM volume, 10GB in size. I extracted a ‘make bin-dist’ of a recent MySQL 5.1 tree, did a “mysql-test-run.pl –start-and-exit” and ran my script, timing real time with time.
For a default ext3 file system creating MyISAM tables, the test took 15min 8sec.
For a default xfs file sytem creating MyISAM tables, the test took 7min 20sec.
For an XFS file system with a 100MB Version 2 log creating MyISAM tables, the test took 7min 32sec – which is within repeatability of the default XFS file system. So log size and version made no real difference.
For a default reiserfs (v3) file system creating MyISAM tables, the test took 9m 44sec.
For a ext3 file system with the dir_index option enabled creating MyISAM tables, the test took 14min 21sec.
For an approximate measure of the CREATE performance…. ext3 and reiserfs averaged about 100 tables/second (although after the 20,000 mark, reiserfs seemed to speed up a little). XFSÂ averaged about 333 tables/second. I credit this to the check for if the files exist being performed by a b-tree lookup in XFS once the directory reached a certain size.
Interestingly, DROPPING the tables was amazingly fast on ext3 – about 2500/sec. XFS about 1000/sec. So ext3 can destroy easier than it can create while XFS keeps up to speed with itself.
What about InnoDB tables? Well…
ext3(default): 21m 11s
xfs(default): 12m 48s
ext3(dir_index): 21m 11s
Interestingly the create rate for XFS was around 500 tables/second – half that of MyISAM tables.
These are interesting results for those who use a lot of temporary tables or do lots of create/drop tables as part of daily life.
All tests performed on a Western Digital 250GB 7200rpm drive in a 2.8Ghz 800Mhz FSB P4 with 2GB memory running Ubuntu 6.10 with HT enabled.
At the end of the test, the ibdata1 file had grown to a little over 800MB – still enough to fit in memory. If we increased this to maybe 200,000 tables (presumably about a 3.2GB file) that wouldn’t fit in cache, then the extents of XFS would probably make it perform better when doing INSERT and SELECT queries as opposed to the list of blocks that ext3 uses. This is because the Linux kernel caches the mapping of in memory block to disk block lookup making the efficiency of this in the file system irrelevant for data sets less than memory size.
So go tell your friends: XFS is still the coolest kid on the block.
If you tar my Maildir, it comes out at about 8.6GB currently. That’s about all my mail since October 2001. Notable exceptions are most of the Spam I’ve received and any messages from LKML.
Doing a first time sync with offlineimap takes an amount of time that is truly scary. Over 8 hours. When connected directly to the IMAP server with 100base.
With only 2.7GB synced so far (on one of my machines), there’s been about 210,000 messages transfered. There are about 500,000 messages to go. So a total time of around 24hrs. eep.
Thunderbird did an offline download of the 700MB of my INBOX very quickly (i.e. at a speed that was encouraging and made me not stop it before it completed). Evolution seemed to be really slow, and want to put header and body in separate files (hrrm… that’s going to be a lot of files). However, I am not ready to switch mail clients to Thunderbird (a variety of reasons).
I tried switching to dovecot over the weekend – didn’t turn out so great. The sync speed was even slower, and syncing from remote dovecot to local dovecot was horrifically slow (probably would have completed by the end of the week). key word, probably.
I don’t consider my Maildir to be big. I don’t get many large attachments.
The fact that Evolution uses about 250MB of memory when I start it up, and 300MB now after sending a few mails is sort of disturbing. Although this does seem to be down from previous versions – so horray Evolution team for that.
I wonder why such a key piece of infrastructure seems to be so neglected.
I’ve talked about disk space allocation previously, mainly revolving around XFS (namely because it’s what I use, a sensible choice for large file systems and large files and has a nice suite of tools for digging into what’s going on).Most people write software that just calls write(2) (or libc things like fwrite or fprintf) to do file IO – including space allocation. Probably 99% of file io is fine to do like this and the allocators for your file system get it mostly right (some more right than others). Remember, disk seeks are really really expensive so the less you have to do, the better (i.e. fragmentation==bad).
I recently (finally) wrote my patch to use the xfsctl to get better allocation for NDB disk data files (datafiles and undofiles).
patch at:
http://lists.mysql.com/commits/15088
This actually ends up giving us a rather nice speed boost in some of the test suite runs.
The problem is:
– two cluster nodes on 1 host (in the case of the mysql-test-run script)
– each node has a complete copy of the database
– ALTER TABLESPACE ADD DATAFILE / ALTER LOGFILEGROUP ADD UNDOFILE creates files on *both* nodes. We want to zero these out.
– files are opened with O_SYNC (IIRC)
The patch I committed uses XFS_IOC_RESVSP64 to allocate (unwritten) extents and then posix_fallocate to zero out the file (the glibc implementation of this call just writes zeros out).
Now, ideally it would be beneficial (and probably faster) to have XFS do this in kernel. Asynchronously would be pretty cool too.. but hey :)
The reason we don’t want unwritten extents is that NDB has some realtime properties, and futzing about with extents and the like in the FS during transactions isn’t such a good idea.
So, this would lead me to try XFS_IOC_ALLOCSP64 – which doesn’t have the “unwritten extents” warning that RESVSP64 does. However, with the two processes writing the files out, I get heavy fragmentation. Even with a RESVSP followed by ALLOCSP I get the same result.
So it seems that ALLOCSP re-allocates extents (even if it doesn’t have to) and really doesn’t give you much (didn’t do too much timing to see if it was any quicker).
I’ve asked if this is expected behaviour on the XFS list… we’ll see what the response is (i haven’t had time yet to go read the code… i should though).
So what improvement does this patch make? well, i’ll quote my commit comments:
BUG#24143 Heavy file fragmentation with multiple ndbd on single fs If we have the XFS headers (at build time) we can use XFS specific ioctls (once testing the file is on XFS) to better allocate space. This dramatically improves performance of mysql-test-run cases as well: e.g. number of extents for ndb_dd_basic tablespaces and log files BEFORE this patch: 57, 13, 212, 95, 17, 113 WITH this patch : ALL 1 or 2 extents (results are consistent over multiple runs. BEFORE always has several files with lots of extents). As for timing of test run: BEFORE ndb_dd_basic [ pass ] 107727 real 3m2.683s user 0m1.360s sys 0m1.192s AFTER ndb_dd_basic [ pass ] 70060 real 2m30.822s user 0m1.220s sys 0m1.404s (results are again consistent over various runs) similar for other tests (BEFORE and AFTER): ndb_dd_alter [ pass ] 245360 ndb_dd_alter [ pass ] 211632
So what about the patch? It’s actually really tiny:
--- 1.388/configure.in 2006-11-01 23:25:56 +11:00 +++ 1.389/configure.in 2006-11-10 01:08:33 +11:00 @@ -697,6 +697,8 @@ sys/ioctl.h malloc.h sys/malloc.h sys/ipc.h sys/shm.h linux/config.h \ sys/resource.h sys/param.h) +AC_CHECK_HEADERS([xfs/xfs.h]) + #-------------------------------------------------------------------- # Check for system libraries. Adds the library to $LIBS # and defines HAVE_LIBM etc --- 1.36/storage/ndb/src/kernel/blocks/ndbfs/AsyncFile.cpp 2006-11-03 02:18:41 +11:00 +++ 1.37/storage/ndb/src/kernel/blocks/ndbfs/AsyncFile.cpp 2006-11-10 01:08:33 +11:00 @@ -18,6 +18,10 @@ #include #include +#ifdef HAVE_XFS_XFS_H +#include +#endif + #include "AsyncFile.hpp" #include @@ -459,6 +463,18 @@ Uint32 index = 0; Uint32 block = refToBlock(request->theUserReference); +#ifdef HAVE_XFS_XFS_H + if(platform_test_xfs_fd(theFd)) + { + ndbout_c("Using xfsctl(XFS_IOC_RESVSP64) to allocate disk space"); + xfs_flock64_t fl; + fl.l_whence= 0; + fl.l_start= 0; + fl.l_len= (off64_t)sz; + if(xfsctl(NULL, theFd, XFS_IOC_RESVSP64, &fl) < 0) + ndbout_c("failed to optimally allocate disk space"); + } +#endif #ifdef HAVE_POSIX_FALLOCATE posix_fallocate(theFd, 0, sz); #endif
So get building your MySQL Cluster with the XFS headers installed and run on XFS for sweet, sweet disk allocation.
Drivl.com | The Seven Phases of Owning an iPod – An Illustrated Journey
Awesome. Simply Awesome. Oh so true too.
class Guard {
public:
Guard(NdbMutex *mtx) : m_mtx(mtx) { NdbMutex_Lock(m_mtx); };
Guard(NdbLockable & l) : m_mtx(l.m_mutex) { NdbMutex_Lock(m_mtx);
};
~Guard() { NdbMutex_Unlock(m_mtx); };
private:
NdbMutex *m_mtx;
};
The Programme for linux.conf.au 2007 has hit the streets (err.. web) and it’s looking pretty neat.
I’m glad to see the MySQL and PostgreSQL miniconfs on different days – means I should be able to pop into the PostgreSQL one as well. Kernel could be interesting too… I guess it can depend on the sessions and stuff though.
Greg Banks’ session on “Making NFS Suck Faster” should be interesting. Tridge’s session on “clustering tdb – a little database meets big iron” should be really interesting (after all, I hack on a clustered database for a crust). After lunch, I’m a bit torn between a few sessions – but Matthew Garrett‘s “Fixing suspend for fun and profit” could be a laugh.
The next session will involve last minute jitters for my session (which is next: “eat my data: how everybody gets file IO wrong” – which will be great fun as there will no doubt be a bunch of smart people about ready to expand and clarify things.
By the end of the day I’ll be torn between Keith Packard’s “X Monitor Hotplugging Sweetness” (Hopefully the extension will be called XBLING – as I keep tryning to convince him to call an X extension that) and Garbage Collection in LogFS by Jorn Engel.
On Thursday, I’ll want to be in all the sessions at once – including Practical MythTV as presented by Mikal Still and myself. If you’re not in our session (and damn you for not being :) you should check out the no doubt other great things on: Dave Miller on Routing and IPSEC Lookup scaling in the linux kernel should be great fun, OzDMCA by Kim Weatherall will no doubt bring a tear to the eye, Rasmus on Faster and Richer Web Apps with PHP 5 (aparrently the aim when coding PHP is to not suck… so a lot of PHP “programmers” should take note – and ask to see how fast he can down a beer in), Andrew Cowie is talking on writing rad GTK apps (always fun when you can see something from your coding efforts). My photographer side of my brain is telling me to go to the GIMP Tutorial too. Hrrm… busy day (but our MythTV tute will ROCK – so show up and be converted).
After a morning berocca (err… tea), the NUMA sessions sound interesting (especially on memory mapped files – going to be thinking about this and databases odly enough). Lunch, then the Heartbeat tutorial sounds interesting (from a “we have an internal one and i wonder what this does” PoV).
Ted Ts’o is on enterprise real time… could be interesting as Ted’s a fun guy.
On Friday, Ted’s ext4 talk is a must see – especially from a poking him in the ribs about what would be neat from a DB PoV (and the reminder of the real numbers in a benchmark boost to performance we see with XFS versus ext3).
While wanting to be a cool kid like Rusty, Disk Encryption also sounds interesting, and Robert Collins could be talking about some interesting stuff (although the title “do it our way” isn’t giving much away).
So, I’ve pretty much just planned a week in January down to the hour. If you’re not already going – get booked for linux.conf.au 2007 now – sure to sell out quickly. Going to be totally kick-ass.
one thing i love about the weather getting warmer is the fact that the price of a Mango becomes reasonable (and they taste better). Just had (another) amazing one. Possibly the best fruit in the world.
If you head over here: mysql on bkbits.net you can get a copy of the NDB team trees. This is where we push stuff before it hits the main MySQL trees so that we can get some extra testing in (also for when pulling from the main tree). So you can be relatively assured that this is going to work fairly well for NDB and have the latest bug fixes.
Of course, if anything is going to break here – it’s going to be NDB :)
This should allow you to get easy access to the latest-and-greatest NDB code.
At some point soon I’ll update my scripts that generate doxygen output (and builds) to do the -ndb trees.
enjoy!
$ svn ci Connection closed by $MAGIC_IP_ADDR svn: Commit failed (details follow): svn: Connection closed unexpectedly svn: Your commit message was left in a temporary file: svn: '/full/path/to/parent/directory/where/no/changed/files/svn-commit.tmp' $ svn ci Log message unchanged or not specified a)bort, c)ontinue, e)dit a
could have at least saved the commit message somewhere useful. like, say, somewhere so when i type “svn ci” again it reads the commit message.
grrr
Listening to JJJ’s Hack from Monday 16th October and the interview with BDO people in regards to scalping, balloting tickets and stuff and woah, talk about agressive.
Although Tool being the reason that things sold out quickly…. quite likely.
I cannot wait until those few days in January that will be Tool filled.
Saturn’s autoweb
I’ve hacked my scripts that generate doxygen docs to also build MySQL 4.1, 5.0 and 5.1 for AMD64 (the box that it’s running on) with Cluster. This is to help my idea of running Gallery at home with NDB disk data tables in very recent MySQL builds.
How’s it going so far? Well… I’ve found some bugs and some seemingly strange behaviour here and there. However, bug reports will come, and I’m currently running a bit of an older build.
I’ll make the URL of the Gallery public at some point too
LA meeting in the day, LA beers at night, LA food followed by catching up with Timmeah! and co. for awesome drinks.
All I can say is Awesome Night – that is all.
MemberDB – A Membership Database
Released 0.5. Pretty much the same as 0.4 but with a bunch of bug fixes. As used for the recent(ish) LUV election. This is what will probably be used for the next LA election too.
Slashdot | MySQL CEO MÃ¥rten Mickos Answers Your Questions
I’m pretty sure this is the first time I’ve been mentioned by name in the 1st commet to a /. article. Yay me!? :)
Made it to the Honbu today for the first time in a while. I really need to train more – have a Judo competition on Monday night (would be Saturday, but I have the LA face2face, so I’m going to the alternate).
The good thing about training on Thursday evenings is that there tends to be a lot of people on the mat – often more than at any other time. A lot of black belts show up too… some I don’t see too often (but that could be due to me generally not training as much this year).
At the end of November is gradings… so better be prepared. That, and I need to build up some fitness again.
Didn’t stay for the Sword class though, was quite knackered after the 1.5hrs of jiujitsu (well… more Judo style today). The class was good too – Kancho was on the mat and doing things for a while.
I feel I fixed some problems with my 5th and 6th hip throws today (or at least learnt where I tend to go wrong). My 5th leg still isn’t the best… but practice, practice. I think it’s more a consistency issue – sometimes I can just hammer in for the hip throws and execute them beautifully (at least for my grade…. nothing like a 3rd, 4th, 6th or 10th Dan or so throwing you around for a bit to see how far you can still go).
I totally vote we open a Melbourne MySQL office right near there (which is actually further from home for me.. which would be rather annoying, but means I could train every day :)
So a bunch of stuff has happenned (or happenning) that I’ve been wanting to blog about for a bit. Some stuff had to wait, others it’s just been me being slack.
Anyway, anyone who hangs closely around the MySQL circles probably now knows about MySQL Enterprise. There’s been a fair bit of talk about this internally for a little while now. When it was being talked about a bit wider within the company some of the initial communication was (in my mind) rather unclear. So I took the “what’s the worst way somebody could interpret this” viewpoint and replied with my thoughts. The idea behind this was to simulate what some of the loud-mouthed trolls of the non-shifted question mark e on a qwerty keyboard mapped to dvorak kind may do.
After a few phone calls (some at strange hours) my worst fears were not realised – we were still not being insane.
So I hope I’ve been of some use in making sure that communication has been clear and any possible fears put to rest.
There is also an increased willingness to make things saner for getting non-MySQL AB authored code into the main trees (err… now labelled Community).
We’re also getting geared up for another 5.1 release – the Cluster team has recently chased down some failures: from out-of-disk on build machine (why is it us who had to find that out?) to an “actual bug”.
Kudos goes out to Jonas who has recently found a few bugs that have been Can’t Repeat since about the year 2000 – ones that were real hard to hit, but naturally, somebody has.
I also added some new things to the Cluster Management Server (ndb_mgmd) in 5.1 that should help with debugging in the future. I basically just exposed the MgmApiSession stuff a bit, giving each session a unique id (64 bit int) that you could then check if the session had gone away or not (or list all sessions). This gives us a test case for bug 13987 which is pretty neat.
I also have geared up a change to the handler API to fix bug 19914 – and being a good boy, I’ve mailed out to the public internals list so that people are ready for the building of outside of tree storage engines to break (on 4.1 and up!). The good news is, however, that this is a real fix and that any errors on COUNT(*) will be reported back to the user (a customer was affected by this).
Also, I updated how engines fill out the INFORMATION_SCHEMA.FILES table to make it a bit nicer (Brian wants to add support for it to some of the other engines). He also pointed out a really obvious bug of mine in a recent push to that code (that probably showed up in a compiler warning come to think of it…). Paul is looking at it for PBXT too (or at least thinks it’s cool :).
Also had a bit of a ask-around the cluster team about if making the team trees (VERSION-ndb) public (up on bkbits.net etc) was good. Nobody seems to have any objections, so will (as soon as I get a minute) persue that. Basically it’ll let people get access to the latest NDB bug fixes in source-tree form (certainly not recommended for production, but could be useful in testing environments).
I’ve also been thinking about talks for the MySQL UC next year as Cluster tends to be a popular topic (had a rather full room this year).
There’s probably more to talk about too, but i’m getting sleepy.
As email is *sooo* non-“Web 2.0”, i reply in blog form….
Rusty’s Bleeding Edge Page talks about a “Writing an x86 hypervisor: all the cool kids are doing it!” session that sounds really cool (better not be on at the same time as my talk… :)
I don’t (currently) intend to be one of the cool kids though.
He also mentions a session entitled “First-timer’s Introduction to LCA”. A couple of possible suggestions (or thoughts, and stuff I’ve seen):
I wonder what should/could be written about going all fanboy/fangirl over favourite hackers? and taking/asking to get taken photos?
The last thing Rusty talks about is the “Hacking in groups” tutorial. I really liked his and Robert Love’s tutorial in Canberra (Kernel Hacking – where you wrote a PCI driver for the excellent Love Rusty 3000. A device with real specifications, coffee cup stain and all). I’ve had a bit of a mixed feeling about it from Rusty since then, but I reckon it was seriously one of the best tutorials I have ever attended. I also took the hands-on approach as great inspiration for various MySQL Cluster Tutorials I’ve given since (and people have commented on how the hands-on part is great).
I guess the thing about the kernel hacking tute was that not everybody in the room was at the same skill level (which is something you totally run the risk of with hands-on). Also, if you hadn’t done the prep material, you were probably going to be in trouble.
But anyway, the idea of having 20 talented coders with 5 people in the tute for each of them and working on some project could be interesting – although rather ambitious. I worry that people without a good enough skillset would rock up and not get much out of it. Although those with adequate skill would do well.
Picking a project that could be doable in a handful of hours (or a day) is tricky – as it’d probably be an extension to some existing project, which requires learning of it. Or, starting something from scratch can be equally as hard (to end up anywhere useful).
Some ideas for projects could include:
These have the benefit of being able to run existing good test suites against the software and see how well people did. They’d probably also help people land jobs :)
Another interesting one would be implementing a library for journaling writes to a file. i.e. instead of write to temp, sync, rename – do journaling. This would let people easily write apps that did safe updates to large files. You could then use this to implement other things (like a really simple crash-safe storage engine, FUSE file system or something).
I’m just not sure how much “cool tricks” could really happpen in that time (instead of just getting the job done). 20 coders talking about their neat tricks would probably make a good book though…