Re: Poll and Select not scaling

2001-01-11 Thread dean gaudet
On Wed, 10 Jan 2001, Dan Kegel wrote: select() is usually limited to 1024 file descriptors oh hey, this limit is only a libc limit these days. you can do this: #define MY_FD_SETSIZE (16384) typedef struct { __fd_mask __fds_bits[MY_FD_SETSIZE / __NFDBITS]; } my_fd_set; #define

Re: khttpd beats boa with persistent patch

2001-01-12 Thread dean gaudet
a few comments... - localhost is a meaningless benchmark. it's useful to catch some low hanging fruit, but it really doesn't help in the long run. - contrast the max connection times between kHTTPd and Boa. if that 9 second maximum for kHTTPd is any indication of its latency performance on a

Re: Is sendfile all that sexy?

2001-01-15 Thread dean gaudet
On Mon, 15 Jan 2001, Jonathan Thackray wrote: (Linux, FreeBSD, HP-UX, AIX, Tru64). The next cool feature to add to Linux is sendpath(), which does the open() before the sendfile() all combined into one system call. how would sendpath() construct the Content-Length in the HTTP header? it's

Re: Is sendfile all that sexy?

2001-01-15 Thread dean gaudet
On Mon, 15 Jan 2001, Jonathan Thackray wrote: TCP_CORK is useful for FAR more than just sendfile() headers and footers. it's arguably the most correct way to write server code. Agreed -- the hard-coded Nagle algorithm makes no sense these days. hey, actually a little more thinking this

Re: [patch] sendpath() support, 2.4.0-test3/-ac9

2001-01-16 Thread dean gaudet
On Tue, 16 Jan 2001, Ingo Molnar wrote: On Mon, 15 Jan 2001, dean gaudet wrote: just for kicks i've implemented sendpath() support. _syscall4 (int, sendpath, int, out_fd, char *, path, off_t *, off, size_t, size) hey so how do you implement transmit timeouts with sendpath

Re: 'native files', 'object fingerprints' [was: sendpath()]

2001-01-16 Thread dean gaudet
On Tue, 16 Jan 2001, Ingo Molnar wrote: But even user-space code could use 'native files', via the following, safe mechanizm: so here's an alternative to ingo's proposal which i think solves some of the other objections raised. it's something i've proposed in the past under the name

Re: Is sendfile all that sexy?

2001-01-17 Thread dean gaudet
On Tue, 16 Jan 2001, David L. Parsley wrote: Felix von Leitner wrote: close (0); close (1); close (2); open ("/dev/console", O_RDWR); dup (); dup (); So it's not actually part of POSIX, it's just to get around fixing legacy code? ;-) it's part of POSIX.

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-17 Thread dean gaudet
On Wed, 17 Jan 2001, Rick Jones wrote: The fact that I understand _why_ it is done that way doesn't mean that I don't think it's a hack. It doesn't allow you to sendfile multiple files etc without having nagle boundaries, and the header/trailer stuff really isn't a generic solution.

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-18 Thread dean gaudet
On Wed, 17 Jan 2001, Rick Jones wrote: actually the problem isn't nagle... nagle needs to be turned off for efficient servers anyhow. i'm not sure I follow that. could you expand on that a bit? the problem which caused us to disable nagle in apache is documented in this paper

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-18 Thread dean gaudet
(because they're being pretty ambitious); and nobody has decided to just forge forward and layer HTTP/1.1 on top of WebMUX yet. (the subversive in me wants to see WebMUX patches for apache, squid, and mozilla ;) -dean On Thu, 18 Jan 2001, dean gaudet wrote: On Wed, 17 Jan 2001, Rick Jones w

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-18 Thread dean gaudet
On Thu, 18 Jan 2001, Zach Brown wrote: We set TCP_CORK on the socket we handed to external programs that were being run via 'site exec' in an ftp server. It resulted in much nicer packets being spit out, especially in the 'ls' case where it likes to write() on really goofy boundaries.

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-18 Thread dean gaudet
huh -- i think with this apache could solve the problem documented in heidemann's paper while also leaving nagle on... which would solve the CGI dribbler vs. bulk problem i just posted about. at the end of a request apache would check first if it can get another request without blocking; if it

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-18 Thread dean gaudet
nly i had a portable version of this :) -dean On Thu, 18 Jan 2001, dean gaudet wrote: huh -- i think with this apache could solve the problem documented in heidemann's paper while also leaving nagle on... which would solve the CGI dribbler vs. bulk problem i just posted about. at the end of a

Re: [Fwd: [Fwd: Is sendfile all that sexy? (fwd)]]

2001-01-22 Thread dean gaudet
On 20 Jan 2001, Kai Henningsen wrote: [EMAIL PROTECTED] (dean gaudet) wrote on 18.01.01 in [EMAIL PROTECTED]: i'm pretty sure the actual use of pipelining is pretty disappointing. the work i did in apache preceded the widespread use of HTTP/1.1 and we What widespread use of HTTP/1.1

Re: 2.2.20pre2aa1

2001-05-15 Thread dean gaudet
On Tue, 15 May 2001, Andrea Arcangeli wrote: o fixed race in wake-one LIFO in accept(2). Apache must be compiled with -DSINGLE_LISTEN_UNSERIALIZED_ACCEPT to take advantage of that. 00_wake-one-4 Backport 2.4 waitqueues and in turn fixes an hanging condition in accept(2).

Re: 2.2.20pre2aa1

2001-05-16 Thread dean gaudet
On Wed, 16 May 2001, Andrea Arcangeli wrote: On Tue, May 15, 2001 at 08:33:05PM -0700, dean gaudet wrote: apache since 1.3.15 has defined SINGLE_LISTEN_UNSERIALIZED_ACCEPT ... That's definitely a good thing. hmm, i'm not so sure -- 1.3.x is our stable release, and it sounds like

Re: [CHECKER] large stack variables (=1K) in 2.4.4 and 2.4.4-ac8

2001-05-25 Thread dean gaudet
On Fri, 25 May 2001, Andi Kleen wrote: On Fri, May 25, 2001 at 04:03:57PM +0200, Oliver Neukum wrote: Is there a reason for the task structure to be at the bottom rather than the top of these two pages ? This way you save one addition for every current access; which adds to quite a few

Re: [CHECKER] large stack variables (=1K) in 2.4.4 and 2.4.4-ac8

2001-05-25 Thread dean gaudet
On Sat, 26 May 2001, Keith Owens wrote: On Fri, 25 May 2001 08:31:24 -0700 (PDT), dean gaudet [EMAIL PROTECTED] wrote: another possibility for a debugging mode for the kernel would be to hack gcc to emit something like the following in the prologue of every function (after the frame

Re: [CHECKER] large stack variables (=1K) in 2.4.4 and 2.4.4-ac8

2001-05-25 Thread dean gaudet
On Fri, 25 May 2001, Jonathan Lundell wrote: At 8:45 AM -0700 2001-05-25, dean gaudet wrote: i think it really depends on how you use current -- here's an alternative usage which can fold the extra addition into the structure offset calculations, and moves the task struct to the top

Re: POSIX/1003.b/whatever docs free?

2001-05-30 Thread dean gaudet
if you go to opengroup.org you can read the single-unix standard for free... you need to register though. (it's not quite the same as POSIX...) -dean On Wed, 30 May 2001 [EMAIL PROTECTED] wrote: Is there somewhere I can download the collection of POSIX standards docs free of charge? ;-)

Re: zero-copy TCP

2000-09-05 Thread dean gaudet
On Mon, 4 Sep 2000, Linus Torvalds wrote: On Mon, 4 Sep 2000, Jamie Lokier wrote: Linus Torvalds wrote: Basically any copy = 4 cache lines is "free" compared to trying to be clever. We're obviously interested in larger packets than 128 bytes. "obviously"? Take a look at

Re: zero-copy TCP

2000-09-05 Thread dean gaudet
On Mon, 4 Sep 2000, Jamie Lokier wrote: Alan Cox wrote: It's not faster than card-card DMA, which falls out naturally from my zero-copy proposal :-) We already support card-card DMA for routing with fastrouting ..but not for user space proxies which was the above's context.

Re: [ANNOUNCE] Withdrawl of Open Source NDS Project/NTFS/M2FS forLinux

2000-09-05 Thread dean gaudet
On Sun, 3 Sep 2000, Andre Hedrick wrote: But there is no Copyright license in patch code. On Mon, 4 Sep 2000, Mike A. Harris wrote: I was under the understanding a "patch" to something GPL, means the "patch" is also GPL. when IBM started working with the apache group their lawyers did a

Re: GPL violations: make it harder

2000-09-05 Thread dean gaudet
On Tue, 5 Sep 2000, Mike A. Harris wrote: If even one file in the kernel source gets modified, then the entire patch is GPL via the GPL assimilation rules in COPYING - regardless of what the author of the patch says. IANAL. i know this is what the GPL wants, but AFAIK it's never been tested

Re: Linux-2.4.0-test8-pre6

2000-09-07 Thread dean gaudet
On Wed, 6 Sep 2000, Linus Torvalds wrote: Yeah. Maybe we fixed truncate, and maybe we didn't. I've thought that we fixed it now several times, and I was always wrong. obpainintheass: haven't you anti-debugger-religion folks been claiming that if you don't have a debugger you're forced to

Re: Linux-2.4.0-test8-pre6

2000-09-07 Thread dean gaudet
On Thu, 7 Sep 2000, Bill Wendling wrote: Also sprach dean gaudet: } On Wed, 6 Sep 2000, Linus Torvalds wrote: } } Yeah. Maybe we fixed truncate, and maybe we didn't. I've thought that we } fixed it now several times, and I was always wrong. } } obpainintheass: haven't you anti

Re: 2.2 generating odd TCP resets?

2000-10-19 Thread dean gaudet
On Wed, 18 Oct 2000, Brian Craft wrote: In the code below, I removed the shutdown() and added the block after do_scan() to eliminate the RST. The read() never finds any data. If there's no data pending, why does read() have any affect? EOF is considered pending data... and has to be read.

Re: strange nonmonotonic behavior of gettimeoftheday -- seen similar problem on PPC

2001-03-03 Thread dean gaudet
On Fri, 2 Mar 2001, Richard B. Johnson wrote: Note that two subsequent calls to gettimeofday() must not return the same time even if your CPU runs infinitely fast. I haven't seen any kernel in the past few years that fails this test. i don't see any requirement for this in SuS.

Re: scsi vs ide performance on fsync's

2001-03-06 Thread dean gaudet
On Tue, 6 Mar 2001, Jonathan Morton wrote: Pathological shutdown pattern: assuming scatter-gather is not allowed (for IDE), and a 20ms full-stroke seek, write sectors at alternately opposite ends of the disk, working inwards until the buffer is full. 512-byte sectors, 2MB of them, is 4000

Re: scsi vs ide performance on fsync's

2001-03-06 Thread dean gaudet
On Tue, 6 Mar 2001, dean gaudet wrote: i assume you meant to time the xlog.c program? (or did i miss another program on the thread?) i've an IBM-DJSA-210 (travelstar 10GB, 5411rpm) which appears to do *something* with the write cache flag -- it gets 0.10s elapsed real time in default

Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:Strangeperformance behavior of 2.4.0-test9)

2000-11-04 Thread dean gaudet
On Sat, 4 Nov 2000, Andrew Morton wrote: Dean, neither flock() nor fcntl() serialisation are effective on linux 2.2 or linux 2.4. i have to admit the last time i timed any of the methods on linux was in 2.0.x days. thanks for the updated data! For kernel 2.2 I recommend that Apache

Re: [PATCH] Re: Negative scalability by removal of

2000-11-07 Thread dean gaudet
: Mon, 6 Nov 2000 21:23:57 -0800 (PST) From: dean gaudet [EMAIL PROTECTED] apache is about correctness first, and performance second. Which is why we say it is "incorrect" for apache to try and work around kernel performance problems. :-))) Later, David S. Mill

Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:Strange

2000-11-04 Thread dean gaudet
On Sat, 4 Nov 2000, Alan Cox wrote: sysv semaphores have a very unfortunate negative feature -- if the admin kill -9's the server (impatient admins do this all the time) then you end up leaving a semaphore lying around. sysvsem don't have the usual unix Umm they have SEM_UNDO. Its a

Re: how to capture long oops w/o having second machine

2000-12-12 Thread dean gaudet
i've always been curious why none of the crash dump patches are default. an oops dumper alone would seem to be most useful. (i know anything more would be unacceptable 'cause linus isn't into debuggers ;) -dean On Tue, 12 Dec 2000, Miles Lane wrote: Try reading:

Re: linux 2.2.19pre and thttpd (VM-global problem?)

2000-12-29 Thread dean gaudet
On Fri, 29 Dec 2000, Andrea Arcangeli wrote: On Fri, Dec 29, 2000 at 06:50:18PM +, Alan Cox wrote: Your cgi will keep the other CPU occupied, or run two of them. thttpd has superb scaling properties compared to say apache. I think with 8 CPUs and 8 NICs (usual benchmark setup) you

storage over IP (was Re: [PLEASE-TESTME] Zerocopy networking patch,2.4.0-1)

2001-01-09 Thread dean gaudet
On Tue, 9 Jan 2001, Ingo Molnar wrote: On Mon, 8 Jan 2001, Rik van Riel wrote: Having proper kiobuf support would make it possible to, for example, do zerocopy network-disk data transfers and lots of other things. i used to think that this is useful, but these days it isnt. this seems

Re: storage over IP (was Re: [PLEASE-TESTME] Zerocopy networkingpatch, 2.4.0-1)

2001-01-09 Thread dean gaudet
On Tue, 9 Jan 2001, David S. Miller wrote: Date: Tue, 9 Jan 2001 18:56:33 -0800 (PST) From: dean gaudet [EMAIL PROTECTED] is NFS receive single copy today? With the zerocopy patches, NFS client receive is "single cpu copy" if that's what you mean. yeah sorry, i mea

Re: select() bug

2000-11-02 Thread dean gaudet
Semantic issues aside, since Apache does the test I mentionned earlier to determine child status and since it could be misled, should this feature be turned off? Or made smarter yes i'm scratching my head wondering what i was thinking when i wrote that code. the specific thing the

Re: Can EINTR be handled the way BSD handles it? -- a plea from a user-land programmer...

2000-11-03 Thread dean gaudet
On Fri, 3 Nov 2000 [EMAIL PROTECTED] wrote: I don't mean this to sound like a rant. It's just that I can't possibly ascertain why someone in their right mind would want any behaviour different than SA_RESTART. study apache 1.3's child_main code, you'll see an example of EINTR in use. it's

Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:Strangeperformance behavior of 2.4.0-test9)

2000-11-04 Thread dean gaudet
On Fri, 3 Nov 2000, Linus Torvalds wrote: Please use unserialized accept() _always_, because we can fix that. i can unserialise the single socket case, but the multiple socket case is not so simple. the executive summary is that when you've got multiple sockets you have to use select().

Re: [PATCH] Re: Negative scalability by removal of

2000-11-05 Thread dean gaudet
the numbers didn't look that bad for the small numbers of concurrent clients on 2.2... a few % slower without the serialisation. compared to orders of magnitude slower with large numbers of concurrent client. oh, someone reminded me of the other reason sysvsems suck: a cgi can grab the

Re: Can EINTR be handled the way BSD handles it? -- a plea from auser-land programmer...

2000-11-06 Thread dean gaudet
On Mon, 6 Nov 2000, George Talbot wrote: I respectfully disagree that programs which don't surround some of the most common system calls with do { rv = __some_system_call__(...); } while (rv == -1 errno == EINTR); welcome to Unix. this is how it is, and

Re: X15 alpha release: as fast as TUX but in user space (fwd)

2001-04-29 Thread dean gaudet
can't find the original. http://www.mail-archive.com/linux-kernel@vger.kernel.org/msg13584.html Initiated by a post from (iirc) Dean Gaudet, we found out that gettimeofday was one particular system call in the Apache fast path that couldn't be optimized well, or moved out of the fast path

Re: X15 alpha release: as fast as TUX but in user space

2001-04-29 Thread dean gaudet
On Sun, 29 Apr 2001, Fabio Riccardi wrote: I can disable header caching and see what happens, I'll add an option for this in the next X15 release. heh, well to be honest, i'd put the (permanent) caching of the Date header into the very slimy, benchmark-only trick category. (right up there

Re: X15 alpha release: as fast as TUX but in user space

2001-04-30 Thread dean gaudet
On Mon, 30 Apr 2001, Fabio Riccardi wrote: Ok I fixed it, the header date timestamp is updated with every request. Performance doesn't seem to have suffered significantly (less than 1%). rad! BTW: Don't call me slime, I wasn't trying to cheat, I just didn't know that the date stamp was

Re: X15 alpha release: as fast as TUX but in user space (fwd)

2001-05-04 Thread dean gaudet
um, presumably this new magic page won't eliminate the old syscall entry points. so just use those for UML. -dean On Fri, 4 May 2001, Pavel Machek wrote: Hi! That means that for fooling closed-source statically-linked binary, If they are using glibc then you have the right to the

Re: [PATCH] arp_filter patch for 2.4.4 kernel.

2001-05-05 Thread dean gaudet
On Sat, 5 May 2001, David S. Miller wrote: How difficult is it to compose netfilter rules that do this? what's the performance impact of doing that? i've got multiple ip networks on the same gigabit link... i'm pretty happy with this tiny patch i've posted before, which is not on any

Re: [PATCH] arp_filter patch for 2.4.4 kernel.

2001-05-05 Thread dean gaudet
also -- isn't it kind of wrong for arp to respond with addresses from other interfaces? what if ip_forward is 0? or if there's some other sort of routing policy in effect? -dean On Sat, 5 May 2001, dean gaudet wrote: i've got multiple ip networks on the same gigabit link... p.s

Re: [Question] Explanation of zero-copy networking

2001-05-07 Thread dean gaudet
On Mon, 7 May 2001, Alan Cox wrote: documented so far) detailed description of the newly implemented zero-copy mechanisms in the network-stack. We are interested in how to use it (changed network-API?) and also in the internal architecture. It is built around sendfile. Trying to do

Re: [Question] Explanation of zero-copy networking

2001-05-07 Thread dean gaudet
On Mon, 7 May 2001, Richard B. Johnson wrote: when the hardware I/O is used. This shows that the network code, alone, cannot be improved very much to provide an improvement in throughput. doesn't your analysis assume that we've got nothing else interesting to do while doing the network i/o?

Re: [Question] Explanation of zero-copy networking

2001-05-07 Thread dean gaudet
On Mon, 7 May 2001, Richard B. Johnson wrote: When we get to media that can sink data as fast as we can generate them (it), then we have to worry about memory copy speed. However, these new devices are actually an IP subsystem. They generate and receive entire datagrams. To fully utilize

Re: Break 2.4 VM in five easy steps

2001-06-06 Thread dean gaudet
On Wed, 6 Jun 2001, Dr S.M. Huen wrote: If you can afford 4GB RAM, you certainly can afford 8GB swap. this is a completely crap argument. you should study the economics of managing a farm of thousands of machines some day. when you do this, you'll also learn to consider the power

Re: Break 2.4 VM in five easy steps

2001-06-06 Thread dean gaudet
On Wed, 6 Jun 2001, Alexander Viro wrote: On Wed, 6 Jun 2001, Sean Hunter wrote: This is completely bogus. I am not saying that I can't afford the swap. What I am saying is that it is completely broken to require this amount of swap given the boundaries of efficient use. Funny. I can

Re: Client receives TCP packets but does not ACK

2001-06-17 Thread dean gaudet
On Sun, 17 Jun 2001, Dan Podeanu wrote: Is there any logical reason why if, given fd is a connected, AF_INET, SOCK_STREAM socket, and one does a write(fd, buffer, len); close(fd); to the peer, over a rather slow network (read modem, satelite link, etc), the data gets lost (the remote

Re: Client receives TCP packets but does not ACK

2001-06-18 Thread dean gaudet
On Mon, 18 Jun 2001, Jan Hudec wrote: Btw: can the aplication somehow ask the tcp/ip stack what was actualy acked? (ie. how many bytes were acked). no, but it's not necessarily a useful number anyhow -- because it's possible that the remote end ACKd bytes but the ACK never arrives. so you

Re: Client receives TCP packets but does not ACK

2001-06-18 Thread dean gaudet
On Mon, 18 Jun 2001, Jonathan Morton wrote: Btw: can the aplication somehow ask the tcp/ip stack what was actualy acked? (ie. how many bytes were acked). no, but it's not necessarily a useful number anyhow -- because it's possible that the remote end ACKd bytes but the ACK never

Re: Client receives TCP packets but does not ACK

2001-06-18 Thread dean gaudet
On Tue, 19 Jun 2001, Jonathan Morton wrote: Btw: can the aplication somehow ask the tcp/ip stack what was actualy acked? (ie. how many bytes were acked). no, but it's not necessarily a useful number anyhow -- because it's possible that the remote end ACKd bytes but the

dentry cache order 7 is broken

2001-02-07 Thread dean gaudet
this looks to be a problem going back all the way to at least 2.2. if you've got 512Mb of RAM you end up with a dentry cache of order 7 -- 65536 entries. this results in a D_HASHBITS of 16. if you look at d_hash it contains this code: hash = hash ^ (hash D_HASHBITS) ^ (hash

ARP out the wrong interface

2001-02-08 Thread dean gaudet
this appears to occur with both 2.2.16 and 2.4.1. server: eth0 is 192.168.250.11 netmask 255.255.255.0 eth1 is 192.168.251.11 netmask 255.255.255.0 they're both connected to the same switch. client: eth0 is 192.168.251.11 netmask 255.255.255.0 connected to the same switch as both of

Re: ARP out the wrong interface

2001-02-08 Thread dean gaudet
oops typo. On Thu, 8 Feb 2001, dean gaudet wrote: this appears to occur with both 2.2.16 and 2.4.1. server: eth0 is 192.168.250.11 netmask 255.255.255.0 eth1 is 192.168.251.11 netmask 255.255.255.0 they're both connected to the same switch. client: eth0 is 192.168.251.11 netmask

Re: ARP out the wrong interface

2001-02-21 Thread dean gaudet
On Fri, 9 Feb 2001, Matthew Kirkwood wrote: On Thu, 8 Feb 2001, dean gaudet wrote: responses come back from both eth0 and eth1, listing each of their respective MAC addresses... it's essentially a race condition at this point as to whether i'll get the right MAC address. ("right&q

Re: Broken ARP (was Re: ARP responses broken!)

2001-04-17 Thread dean gaudet
On Tue, 17 Apr 2001, Eric Weigle wrote: Ok, I was ignorant of the arp filter functionality in 2.2. I found an old (probably painfully out-of-date) posting the patch Andi Kleen was referring to in the archive, but I've not used it.

Re: console scroll lock causes DOS

2007-02-18 Thread dean gaudet
On Wed, 7 Feb 2007, Andy wrote: If the scroll lock is on and there is a bunch of console output, the machine will eventually stop responding to the network, until scroll lock is turned off (at sometimes that doesn't even help). Easy test: hit scroll lock do a few echo t

Re: Raid 10 Problems?

2007-03-07 Thread dean gaudet
On Mon, 5 Mar 2007, Marc Perkel wrote: --- Jan Engelhardt [EMAIL PROTECTED] wrote: On Mar 4 2007 19:37, Marc Perkel wrote: -b internal -- seems like a good idea to speed up resynchronization. I'm trying to figure out what the default is. -b none, meaning the

Re: CPA patchset

2008-01-11 Thread dean gaudet
On Fri, 11 Jan 2008, Ingo Molnar wrote: * Andi Kleen [EMAIL PROTECTED] wrote: Cached requires the cache line to be read first before you can write it. nonsense, and you should know it. It is perfectly possible to construct fully written cachelines, without reading the cacheline

Re: CPA patchset

2008-01-11 Thread dean gaudet
On Fri, 11 Jan 2008, dean gaudet wrote: On Fri, 11 Jan 2008, Ingo Molnar wrote: * Andi Kleen [EMAIL PROTECTED] wrote: Cached requires the cache line to be read first before you can write it. nonsense, and you should know it. It is perfectly possible to construct fully

nosmp/maxcpus=0 or 1 - TSC unstable

2008-01-12 Thread dean gaudet
if i boot an x86 64-bit 2.6.24-rc7 kernel with nosmp, maxcpus=0 or 1 it still disables TSC :) Marking TSC unstable due to TSCs unsynchronized this is an opteron 2xx box which does have two cpus and no clock-divide in halt or cpufreq enabled so TSC should be fine with only one cpu. pretty sure

Re: [perfmon] Re: [perfmon2] perfmon2 merge news

2007-11-14 Thread dean gaudet
On Wed, 14 Nov 2007, Andi Kleen wrote: Later a syscall might be needed with event multiplexing, but that seems more like a far away non essential feature. actually multiplexing is the main feature i am in need of. there are an insufficient number of counters (even on k8 with 4 counters) to do

Re: [perfmon] Re: [perfmon2] perfmon2 merge news

2007-11-14 Thread dean gaudet
On Thu, 15 Nov 2007, Paul Mackerras wrote: dean gaudet writes: actually multiplexing is the main feature i am in need of. there are an insufficient number of counters (even on k8 with 4 counters) to do complete stall accounting or to get a general overview of L1d/L1i/L2 cache hit

Re: [PATCHv2 4/4] first use of sys_indirect system call

2007-11-16 Thread dean gaudet
On Fri, 16 Nov 2007, Ulrich Drepper wrote: dean gaudet wrote: honestly i think there should be a per-task flag which indicates whether fds are by default F_CLOEXEC or not. my reason: third party libraries. Only somebody who thinks exclusively about applications as opposed to runtimes

Re: perfmon2 merge news

2007-11-16 Thread dean gaudet
On Fri, 16 Nov 2007, Andi Kleen wrote: I didn't see a clear list. - cross platform extensible API for configuring perf counters - support for multiplexed counters - support for virtualized 64-bit counters - support for PC and call graph sampling at specific intervals - support for reading

Re: [PATCHv2 4/4] first use of sys_indirect system call

2007-11-16 Thread dean gaudet
you know... i understand the need for FD_CLOEXEC -- in fact i tried petitioning for CLOEXEC options to all the fd creating syscalls something like 7 years ago when i was banging my head against the wall trying to figure out how to thread apache... but even still i'm not convinced that

Re: [PATCHv3 0/4] sys_indirect system call

2007-11-20 Thread dean gaudet
On Mon, 19 Nov 2007, Ingo Molnar wrote: * Eric Dumazet [EMAIL PROTECTED] wrote: I do see a problem, because some readers will take your example as a reference, as it will probably sit in a page that google^Wsearch_engines will bring at the top of search results for next ten years

Re: [patch][v2] x86, ptrace: support for branch trace store(BTS)

2007-11-20 Thread dean gaudet
On Tue, 20 Nov 2007, dean gaudet wrote: On Tue, 20 Nov 2007, Metzger, Markus T wrote: +__cpuinit void ptrace_bts_init_intel(struct cpuinfo_x86 *c) +{ + switch (c-x86) { + case 0x6: + switch (c-x86_model) { +#ifdef __i386__ + case 0xD: + case

Re: [patch][v2] x86, ptrace: support for branch trace store(BTS)

2007-11-20 Thread dean gaudet
On Tue, 20 Nov 2007, Metzger, Markus T wrote: +__cpuinit void ptrace_bts_init_intel(struct cpuinfo_x86 *c) +{ + switch (c-x86) { + case 0x6: + switch (c-x86_model) { +#ifdef __i386__ + case 0xD: + case 0xE: /* Pentium M */ +

Re: [RFC] Documentation about unaligned memory access

2007-11-22 Thread dean gaudet
On Fri, 23 Nov 2007, Alan Cox wrote: Its usually faster if you don't misalign on x86 as well. i'm not sure if i agree with usually... but i know you (alan) are probably aware of the exact requirements of the hw. for everyone else: on intel x86 processors an access is unaligned only if it

Re: [RFC] Documentation about unaligned memory access

2007-11-26 Thread dean gaudet
On Fri, 23 Nov 2007, Arne Georg Gleditsch wrote: dean gaudet [EMAIL PROTECTED] writes: on AMD x86 pre-family 10h the boundary is 8 bytes, and on fam 10h it's 16 bytes. the penalty is a mere 3 cycles if an access crosses the specified boundary. Worth noting though, is that atomic

Re: RFC: permit link(2) to work across --bind mounts ?

2007-12-28 Thread dean gaudet
On Wed, 19 Dec 2007, David Newall wrote: Mark Lord wrote: But.. pity there's no mount flag override for smaller systems, where bind mounts might be more useful with link(2) actually working. I don't see it. You always can make hard link on the underlying filesystem. If you need to make

Re: RFC: permit link(2) to work across --bind mounts ?

2007-12-28 Thread dean gaudet
On Sat, 29 Dec 2007, Jan Engelhardt wrote: On Dec 28 2007 18:53, dean gaudet wrote: p.s. in retrospect i probably could have arranged it more like this: mount /dev/md1 $tmpmntpoint mount --bind $tmpmntpoint/var /var mount --bind $tmpmntpoint/home /home umount $tmpmntpoint

Re: RFC: permit link(2) to work across --bind mounts ?

2007-12-29 Thread dean gaudet
On Sat, 29 Dec 2007, David Newall wrote: dean gaudet wrote: On Wed, 19 Dec 2007, David Newall wrote: Mark Lord wrote: But.. pity there's no mount flag override for smaller systems, where bind mounts might be more useful with link(2) actually working. I

Re: RFC: permit link(2) to work across --bind mounts ?

2007-12-29 Thread dean gaudet
On Sun, 30 Dec 2007, David Newall wrote: dean gaudet wrote: Pffuff. That's what volume managers are for! You do have (at least) two independent spindles in your RAID1 array, which give you less need to worry about head-stack contention. this system is write intensive

Re: RFC: permit link(2) to work across --bind mounts ?

2007-12-29 Thread dean gaudet
On Sat, 29 Dec 2007, [EMAIL PROTECTED] wrote: On Sat, 29 Dec 2007 12:40:47 PST, dean gaudet said: the main worry i have is some user maliciously hardlinks everything under /var/log somewhere else and slowly fills up the file system with old rotated logs. Doctor, it hurts when I do

Re: Interaction between Xen and XFS: stray RW mappings

2007-10-21 Thread dean gaudet
On Mon, 15 Oct 2007, Nick Piggin wrote: Yes, as Dave said, vmap (more specifically: vunmap) is very expensive because it generally has to invalidate TLBs on all CPUs. why is that? ignoring 32-bit archs we have heaps of address space available... couldn't the kernel just burn address space

Re: Interaction between Xen and XFS: stray RW mappings

2007-10-21 Thread dean gaudet
On Sun, 21 Oct 2007, Jeremy Fitzhardinge wrote: dean gaudet wrote: On Mon, 15 Oct 2007, Nick Piggin wrote: Yes, as Dave said, vmap (more specifically: vunmap) is very expensive because it generally has to invalidate TLBs on all CPUs. why is that? ignoring 32-bit archs we

Re: [patch 5/5] x86: Set PCI config space size to extended for AMD Barcelona

2007-09-03 Thread dean gaudet
it's so very unfortunate the PCI standard has no feature bit to indicate the presence of ECS. FWIW in my testing on a range of machines spanning 7 or 8 years i could read config space reg 256... and get 0x when the device didn't support ECS, and get valid data when the device did

Re: Intel Memory Ordering White Paper

2007-09-08 Thread dean gaudet
On Sun, 9 Sep 2007, Nick Piggin wrote: I've also heard that string operations do not follow the normal ordering, but that's just with respect to individual loads/stores in the one operation, I hope? And they will still follow ordering rules WRT surrounding loads and stores? see section 7.2.3

Re: Intel Memory Ordering White Paper

2007-09-08 Thread dean gaudet
On Sat, 8 Sep 2007, Petr Vandrovec wrote: dean gaudet wrote: On Sun, 9 Sep 2007, Nick Piggin wrote: I've also heard that string operations do not follow the normal ordering, but that's just with respect to individual loads/stores in the one operation, I hope

Re: [PATCH] [1/12] x86: Work around mmio config space quirk on AMD Fam10h

2007-08-12 Thread dean gaudet
On Sun, 12 Aug 2007, Linus Torvalds wrote: On Sun, 12 Aug 2007, Dave Jones wrote: This does make me wonder, why these weren't caught in -mm ? I'm worried that -mm isn't getting a lot of exposure these days. People do run it, but I wonder how many.. andrew caught it in -mm and reverted

Re: [PATCH] hugetlbfs read() support

2007-07-30 Thread dean gaudet
On Thu, 19 Jul 2007, Bill Irwin wrote: On Thu, Jul 19, 2007 at 10:07:59AM -0700, Nishanth Aravamudan wrote: But I do think a second reason to do this is to make hugetlbfs behave like a normal fs -- that is read(), write(), etc. work on files in the mountpoint. But that is simply my

Re: TLB sizes among x86 CPUs?

2007-07-31 Thread dean gaudet
http://sandpile.org/ On Wed, 18 Jul 2007, Rene Herman wrote: Good day. Would anyone happen to have a list of TLB sizes for some selected x86{,-64} CPUs? I know it goes from a few entries on a 386 to a lot on Opteron but I have a real hard time finding specific data. Rene. - To

Re: [PATCH] i386: Selectable Frequency of the Timer Interrupt

2005-07-13 Thread dean gaudet
On Wed, 13 Jul 2005, Chris Wedgwood wrote: On Wed, Jul 13, 2005 at 01:48:57PM -0700, Andrew Morton wrote: My expectation is if we want to beat the competition, we'll want the ability to go *under* 100Hz. What does Windows do here? windows xp base rate is 100Hz... but multimedia apps can

Re: [PATCH] i386: Selectable Frequency of the Timer Interrupt

2005-07-13 Thread dean gaudet
On Wed, 13 Jul 2005, Chris Wedgwood wrote: On Wed, Jul 13, 2005 at 04:41:41PM -0700, dean gaudet wrote: windows xp base rate is 100Hz... but multimedia apps can ask for almost any rate they want (depends on the hw capabilities). i recall seeing rates 1200Hz when you launch some

Re: Power consumption HZ250 vs. HZ1000

2005-07-26 Thread dean gaudet
On Mon, 25 Jul 2005, Marc Ballarin wrote: Hmm, just did. I even tried the rather minimalistic configuration below. Still no C3. (And what seems even stranger: no C1.) there's no point to going into C1 if the C2 entry/exit latencies are acceptable. (winxp generally never uses C1 if C2 is

Re: IBM HDAPS things are looking up

2005-07-04 Thread dean gaudet
On Mon, 4 Jul 2005, Alejandro Bonilla wrote: Do you think that the kernel will STOP, HOLD and park the head in less than a second? OR on the time we need? this is why the windows driver uses heuristics to decide when the laptop is possibly unstable and *may* fall soon... because it takes

Re: [patch 1/2] fork_connector: add a fork connector

2005-03-25 Thread dean gaudet
On Fri, 25 Mar 2005, Guillaume Thouvenin wrote: ... The lmbench shows that the overhead (the construction and the sending of the message) in the fork() routine is around 7%. ... + /* + * size of data is the number of characters + * printed plus one

Re: [patch 1/2] fork_connector: add a fork connector

2005-03-29 Thread dean gaudet
On Tue, 29 Mar 2005, Jay Lan wrote: The fork_connector is not designed to solve accounting data collection problem. The accounting data collection must be done via a hook from do_exit(). by the time do_exit() occurs the parent may have disappeared... you do need to record something at

TCP_DEFER_ACCEPT

2001-07-07 Thread dean gaudet
i was digging around for info on TCP_DEFER_ACCEPT and found this claim in the thttpd mailing list archive: Alexey Kuznestov mentioned to me that on SMP servers, this option may not be desired as it creates a new contention point is this still the case? i haven't played with it yet, but i was

Re: RFC: i386: kill !4KSTACKS

2005-09-04 Thread dean gaudet
On Mon, 5 Sep 2005, Adrian Bunk wrote: How do you put pressure on hardware manufacturers for getting them to release the specs? If they are able to write supported by Linux on their products anyway because there's a driver that runs under NdisWrapper? that's specious... they can put

Re: Question about SO_LINGER

2005-08-13 Thread dean gaudet
On Wed, 10 Aug 2005, steve roussey wrote: socket to shut down. Apache has a workaround called lingering_close() that tries to address broken SO_LINGER implementations, but it also blocks. apache 1.x is single threaded / forked, so yeah it blocks. the implementation is there because very few

Re: zero-copy read() interface

2005-08-18 Thread dean gaudet
On Thu, 18 Aug 2005, Folkert van Heusden wrote: Doesn't that one also use copying? I've also heard that using mmap is expensive due to pagefaulting. I've found, for example, that copying a 1.3GB file using read/write instead of mmap memcpy is seconds faster. why would you memcpy if you're

  1   2   3   4   >