Kerneltrap has spoken with Linux kernel hacker, Andrew Morton. His contributions cover a wide range of kernel components, including ext3 on 2.4 and the low-latency patch. Currently he works for moxi.com.
Jeremy Andrews:
Please share a little about yourself and your background...
JA:
What is your current involvement withmoxi.com?
JA:
When did you get started with Linux?
JA:
We spoke with Robert Love last October, learning about his preempt patch. How
does your low-latency patch differ from his?
JA:
In other words, the low-latency patch should have a much more noticeable affect
than the preempt patch?
JA:
Have you worked with Robert to combine efforts?
JA:
Is the low-latency patch compatible with the Ingo's new O(1) scheduler, in 2.5
as well as with the patch for 2.4?
JA:
Do you have plans to get your low-latency patch into the 2.5 kernel?
JA:
What are some of the most outstanding issues that still need to be addressed
in 2.4?
JA:
Do you have any predictions as to when 2.4 will reach a stable state?
JA:
How will we know when it's there?
JA:
How did you get involved with the ext3 filesystem?
JA:
What was the problem?
JA:
How does the performance compare between ext3 on 2.2, and on 2.4?
JA:
I've been happily using ext3 without problems since it was first introduced
into the -ac kernels. How stable do you consider this filesystem to be? How
much does the code base differ from ext2?
JA:
What about resierfs? XFS? JFS? It seems there are several journaling
alternatives to ext3, though none of the others have the convenience of
compatibility with ext2.
JA:
What is it about ext3 that causes it to start the disk up frequently?
JA:
How does your fix solve the problem?
JA:
What's wrong with your solution, that you won't publish it?
JA:
What comparison can you make between the current 2.4.x VM, and Rik van Riel's
VM?
JA:
Are you happy with Linus' choice with the new VM?
JA:
What other contributions have you made to Linux?
JA:
What main tools do you use when developing?
JA:
Linus has refused to include a debugger with the standard Linux kernel. What
do you think of this?
JA:
Do you use other operating systems besides Linux?
JA:
Have you met Linus? Alan? Other kernel hackers?
JA:
Do you care to elaborate more on this humorous comment?
JA:
What do you enjoy doing when you're not hacking on or otherwise using your
computer?
JA:
What advice can you offer to people just learning to become kernel hackers?
JA:
Can you offer any examples of botched fixes you've intentionally proposed?
JA:
Is there anything else you'd like to add?
JA:
Thank you for all your time! Your Linux contributions are much appreciated by
myself and many others!
About the interviewer:
Jeremy Andrews was born and raised in Southeast Alaska. Currently he lives and works in South Florida. He maintains KernelTrap as a hobby.
There is a very good interview w/ some of the Beos developers in which they cover latency and it is nowhere near this 3 microseconds that you claim (but you only off by a factor of 80). You've also conveniently skirt around the rt os stuff available in linux.
http://technetcast.ddj.com/tnc_program.html?program_id=35
-----
DDJ: BeOS is promoted as a media OS. What OS features make it well-adapted to the types of resource-intensive, mixed-media applications that you want Be developers to write?
DG: There's a number of things that conspire to make it that way. At the lowest level, the kernel provides very low scheduling latency services. When a driver event [occurs], [the kernel] releases a semaphore which causes a thread to run. That [elapsed] time is very small, measured on the order of microseconds. In this upcoming release we've worked to bring this scheduling latency down to the point where real-time threads' latencies can be [measured at around] 250 microseconds.
-----
Andrew mentioned above development of an 802.11a driver. Anyone know what is happening in that department.
Andrew Morton will be speaking atSCALE 2x on Novemer 22, 2003.
Thank You for another very interesting article. It's really good written and I fully agree with You on main issue, btw. I must say that I really enjoyed reading all of Your posts. It’s interesting to read ideas, and observations from someone else’s point of view… it makes you think more. So please try to keep up the great work all the time. Greetings
I am SO glad I read this interview. Mr. Morton's comments were a lot of fun to read. It was a lark I decided to read this, interest in patch sets (Wolk, etc.)led me here. The "noatime" comment is MUCH appreciated. I had noticed a "ticking" sound from my laptop just about every five seconds. I put the suggestion in my /etc/fstab file and voila! Thank you!
Andrew Morton works in Google as far as I know.
True. But since this interview is dated February 14th 2002 ...
Though it's not nice to link such an old interview without any comment to an article from May 3rd 2007. It creates quite some confusion.
| Wireless card to buy | 2 hours, 55 minutes ago | Linux 2.6 kernel |
| Creating macros for function definitions && calls | 5 hours, 13 minutes ago | GCC |
| Resetting the bios password for Toshiba Laptop | 6 hours, 15 minutes ago | KernelTrap help |
| how to configure tun device | 10 hours, 26 minutes ago | Linux 2.6 kernel |
| Need help cross-compiling MIG | 10 hours, 51 minutes ago | GNU/Hurd help |
| Boot up problem: "Cannot open root device 306 or hda6" | 13 hours, 41 minutes ago | Linux 2.6 kernel |
| DMA xmit from kernel space to pci device memory | 14 hours, 27 minutes ago | Linux 2.6 kernel |
| Zetera Z-San Filesystem and Devices - Any Linux Interest? | 18 hours, 21 minutes ago | Linux 2.6 kernel |
| windows folder creation surprise | 1 day, 2 hours ago | Windows |
| what is "callback function"?.can anyone explain me please.. | 1 day, 16 hours ago | Linux help |
