brian [Tue, 10 Apr 2001 23:16:55 +0000 (23:16 +0000)]
o The -s limit is ARG_MAX - 4K, not ARG_MAX - 2K.
o Mention that the current environment is part of the -s calculation.
o Add a BUGS section that warns against executing a program that increases
the size of the argument list or the size of the environment.
I have wondered for a while what the difference is between
get a big list | xargs sudo command
which fails and
get a big list | sudo xargs command
which succeeds. The answer is that in the first case, sudo expands
the environment and pushes the amount of data passed into execve over
the E2BIG threshold.
Remove the old APIC I/O higher level IPI API in favor of the newer MI
API for IPI's that isn't tied to the Intel APIC. MD code can still use
the apic_ipi() function or dink with the apic directly if needed to send
MD IPI's.
Catch up to the dirpref changes by copying new fields in the alternate
superblock from the original superblock so that differences in those new
fields are ignored.
Split out all the RPC code into a separate function and address a
number of issues:
- Fix background mounts; these were broken in revision 1.40.
- Don't give up before trying all addresses returned by getaddrinfo().
- Use protocol-independent routines where possible.
- Improve error reporting for RPC errors.
- In non-background mode, give up after trying all protocols once.
- Use daemon(3) instead of rolling our own version.
- Never go ahead with the mount() syscall until we have received
a reply from the remote nfsd; this is especially important with
non-interruptible mounts, as otherwise a mistyped command might
require a reboot to correct.
Add an MI API for sending IPI's. I used the same API present on the alpha
because:
- it used a better namespace (smp_ipi_* rather than *_ipi),
- it used better constant names for the IPI's (IPI_* rather than
X*_OFFSET), and
- this API also somewhat exists for both alpha and ia64 already.
Add another card to the list of Neomagic 256AV's which don't have AC97
codecs. Also, add some additional code to check for future cards without
this feature - attempting to initialise them as AC97 cards will hang the
machine.
Add information about the new options to newfs and tunefs which set the
expected average file size and number of files per directory. Could do
with some fleshing out.
Directory layout preference improvements from Grigoriy Orlov <gluk@ptci.ru>.
His description of the problem and solution follow. My own tests show
speedups on typical filesystem intensive workloads of 5% to 12% which
is very impressive considering the small amount of code change involved.
------
One day I noticed that some file operations run much faster on
small file systems then on big ones. I've looked at the ffs
algorithms, thought about them, and redesigned the dirpref algorithm.
First I want to describe the results of my tests. These results are old
and I have improved the algorithm after these tests were done. Nevertheless
they show how big the perfomance speedup may be. I have done two file/directory
intensive tests on a two OpenBSD systems with old and new dirpref algorithm.
The first test is "tar -xzf ports.tar.gz", the second is "rm -rf ports".
The ports.tar.gz file is the ports collection from the OpenBSD 2.8 release.
It contains 6596 directories and 13868 files. The test systems are:
1. Celeron-450, 128Mb, two IDE drives, the system at wd0, file system for
test is at wd1. Size of test file system is 8 Gb, number of cg=991,
size of cg is 8m, block size = 8k, fragment size = 1k OpenBSD-current
from Dec 2000 with BUFCACHEPERCENT=35
2. PIII-600, 128Mb, two IBM DTLA-307045 IDE drives at i815e, the system
at wd0, file system for test is at wd1. Size of test file system is 40 Gb,
number of cg=5324, size of cg is 8m, block size = 8k, fragment size = 1k
OpenBSD-current from Dec 2000 with BUFCACHEPERCENT=50
You can get more info about the test systems and methods at:
http://www.ptci.ru/gluk/dirpref/old/dirpref.html
Test Results
tar -xzf ports.tar.gz rm -rf ports
mode old dirpref new dirpref speedup old dirprefnew dirpref speedup
First system
normal 667 472 1.41 477 331 1.44
async 285 144 1.98 130 14 9.29
sync 768 616 1.25 477 334 1.43
softdep 413 252 1.64 241 38 6.34
Second system
normal 329 81 4.06 263.5 93.5 2.81
async 302 25.7 11.75 112 2.26 49.56
sync 281 57.0 4.93 263 90.5 2.9
softdep 341 40.6 8.4 284 4.76 59.66
"old dirpref" and "new dirpref" columns give a test time in seconds.
speedup - speed increasement in times, ie. old dirpref / new dirpref.
------
Algorithm description
The old dirpref algorithm is described in comments:
/*
* Find a cylinder to place a directory.
*
* The policy implemented by this algorithm is to select from
* among those cylinder groups with above the average number of
* free inodes, the one with the smallest number of directories.
*/
A new directory is allocated in a different cylinder groups than its
parent directory resulting in a directory tree that is spreaded across
all the cylinder groups. This spreading out results in a non-optimal
access to the directories and files. When we have a small filesystem
it is not a problem but when the filesystem is big then perfomance
degradation becomes very apparent.
What I mean by a big file system ?
1. A big filesystem is a filesystem which occupy 20-30 or more percent
of total drive space, i.e. first and last cylinder are physically
located relatively far from each other.
2. It has a relatively large number of cylinder groups, for example
more cylinder groups than 50% of the buffers in the buffer cache.
The first results in long access times, while the second results in
many buffers being used by metadata operations. Such operations use
cylinder group blocks and on-disk inode blocks. The cylinder group
block (fs->fs_cblkno) contains struct cg, inode and block bit maps.
It is 2k in size for the default filesystem parameters. If new and
parent directories are located in different cylinder groups then the
system performs more input/output operations and uses more buffers.
On filesystems with many cylinder groups, lots of cache buffers are
used for metadata operations.
My solution for this problem is very simple. I allocate many directories
in one cylinder group. I also do some things, so that the new allocation
method does not cause excessive fragmentation and all directory inodes
will not be located at a location far from its file's inodes and data.
The algorithm is:
/*
* Find a cylinder group to place a directory.
*
* The policy implemented by this algorithm is to allocate a
* directory inode in the same cylinder group as its parent
* directory, but also to reserve space for its files inodes
* and data. Restrict the number of directories which may be
* allocated one after another in the same cylinder group
* without intervening allocation of files.
*
* If we allocate a first level directory then force allocation
* in another cylinder group.
*/
My early versions of dirpref give me a good results for a wide range of
file operations and different filesystem capacities except one case:
those applications that create their entire directory structure first
and only later fill this structure with files.
My solution for such and similar cases is to limit a number of
directories which may be created one after another in the same cylinder
group without intervening file creations. For this purpose, I allocate
an array of counters at mount time. This array is linked to the superblock
fs->fs_contigdirs[cg]. Each time a directory is created the counter
increases and each time a file is created the counter decreases. A 60Gb
filesystem with 8mb/cg requires 10kb of memory for the counters array.
The maxcontigdirs is a maximum number of directories which may be created
without an intervening file creation. I found in my tests that the best
performance occurs when I restrict the number of directories in one cylinder
group such that all its files may be located in the same cylinder group.
There may be some deterioration in performance if all the file inodes
are in the same cylinder group as its containing directory, but their
data partially resides in a different cylinder group. The maxcontigdirs
value is calculated to try to prevent this condition. Since there is
no way to know how many files and directories will be allocated later
I added two optimization parameters in superblock/tunefs. They are:
int32_t fs_avgfilesize; /* expected average file size */
int32_t fs_avgfpdir; /* expected # of files per directory */
These parameters have reasonable defaults but may be tweeked for special
uses of a filesystem. They are only necessary in rare cases like better
tuning a filesystem being used to store a squid cache.
I have been using this algorithm for about 3 months. I have done
a lot of testing on filesystems with different capacities, average
filesize, average number of files per directory, and so on. I think
this algorithm has no negative impact on filesystem perfomance. It
works better than the default one in all cases. The new dirpref
will greatly improve untarring/removing/coping of big directories,
decrease load on cvs servers and much more. The new dirpref doesn't
speedup a compilation process, but also doesn't slow it down.
alfred [Tue, 10 Apr 2001 05:29:26 +0000 (05:29 +0000)]
Add more diagnostic output for failure.
s/1518/ETHER_MAX_LEN
Some style changes, add some braces, mostly residual from having
a lot of debug hooks added while working on this driver.
Bring in a plethora of changes from NetBSD:
revision 1.58
date: 2001/03/08 11:07:08; author: ichiro; state: Exp; lines: +17 -1
it wait until busy flag disappears.
it was able to prevent some cards with late initializing faling in wi_reset().
revision 1.41
date: 2000/10/13 19:15:08; author: jonathan; state: Exp; lines: +4 -2
Fix wi_intr() to avoid touching card registers during insert/remove events,
when sharing an interrupt with other devices:
check sc->sc_enabled, and drop the interrupt if its' off.
revision 1.30
date: 2000/08/18 04:11:48; author: jhawk; state: Exp; lines: +4 -4
Copy wi_{dst,src}_addr from struct wi_frame into faked-up ether_header
instead of addr1 and addr2. THis means that tcpdump -e will show the
correct MAC address for communications with access points instead of showing
the BSSID.
In the future there should be 802.11 support for bpf/libpcap/tcpdump,
but that is aways down the road.
Clean up a bit. Use the correct TAILQ link when walking the thread
lists to free thread resources after a fork (in the child). Also
remember to free the dead thread list.
To be consistent, use the __weak_reference macro from <sys/cdefs.h>
instead of #pragma weak to create weak definitions. This macro is
improperly named, though, since a weak definition is not the same
thing as a weak reference.
Make the list in the DIAGNOSTICS section "-tag" instead of "-diag":
the former makes it more obvious as to there the error message starts
and the explanation begins.
Maintain a reference count on the witness struct. When the reference
count drops to 0 in witness_destroy, set the w_name and w_file pointers
to point to the string "(dead)" and the w_line field to 0. This way,
if a mutex of a given name is used only in a module, then as long as
all mutexes in the module are destroyed when the module is unloaded,
witness will not maintain stale references to the mutex's name in the
module's data section causing a panic later on when the w_name or w_file
field's are examined.
- One can now specify the decimal pid of a process to trace as a parameter.
Since pid's are not in the kernel address space, this doesn't conflict
with the funcionality of specifying an arbitrary frame pointer to the
trace command.
- If the first function of a backtrace maps to fork_trampoline, then this
is a newly fork'd process that has not been executed yet, so just print
out the first frame and then return for that case.
- Lower the default count from 65535 to 1024. ddb doesn't trace into
userland, and if the stack gets hosed and starts looping it's less
annoying.
Add Marvell PHY support for 10/100/1000 LIVENGOOD_CU Intel NIC.
Parag Patel did all of the grunt work, so he gets the credit.
Register definitions and actions inferred from a Linux driver,
so Intel also gets some 'credit'.
Allow user to omit font size specification when loading a font. In addition
the following fixes had been made:
- check the size of the font being loaded and compare it with possible sizes
to minimise possibility of loading something that is not a fontfile at all
and turning console screen into garbage;
- prevent buffer overflow (and coredump as a result ) when loading valid
uuencoded file with size that exceeds allocated buffer;
- .Fn and .Fc now print a final semicolon (`;') after a
function declaration in the SYNOPSIS
- .%I implemented
- .At outputs ``AT&T UNIX'' if called without arguments
- minor cleanup
the main benefit this gives for now is that via686 audio devices on
motherboards with ac97 codecs that do not support vra will be able to use
sample rates other than 48khz.
Add function prototypes and base module for kernel side iconv library.
Add simple "xlat" converter which performs 8to8 table based conversion.
Unicode converter will be added in the near future.
Two minor fixes:
o Change the number of init tries from 5 to a #define.
o Allow up to 5s rather than 2s for commands to complete. This
is still much less than 51 minutes, but makes my intel card init
with more reliability than before.
Correctly initialize free_ccbq so that if we fail to attach (as is
possible for some systems where the device is there, but the BIOS
hasn't allocated memory resources for it), we don't panic.
joe [Sun, 8 Apr 2001 21:35:17 +0000 (21:35 +0000)]
Don't complain about deprecated environment variables, like MUSIC_CD,
being present in the environment if the user has CDROM defined, or
has specified a device on the command line.
This avoids users of ports like 'workman' that use these variables
getting gratuitous warnings from cdcontrol.
Suggested by: John Sellens <jsellens@generalconcepts.com>
According with RFC 2330 ("Framework for IP Performance Metrics", from
Paxson et al, Status: Informational, May 1998), we should use "bits per
second" and "k" as 1000 not 1024 for throughput measures.
Submitted by: Eduardo Souza Machado da Silva <esms@acm.org>
Move the decision whether we want to request authentication from our
peer out from sppp_lcp_open() to sppp_lcp_up(). For one, this makes
things look more symmetrical to sppp_lcp_close(), and somehow it also
just occurred to me that an Up event following the open caused the
value of the authentication option to be clobbered.
The maximum RPC message size was set at 8k for UDP. This is lower
than the default buffer size in the old RPC code (8800 bytes), and
it could not be overriden by the application. This caused problems
with CFS (/usr/port/security/cfs).
Change this default back to UDPMSGSIZE (8800 bytes), but more
importantly, allow applications to use larger message sizes for
all protocols if desired. Choose an arbitrary maximum message size
of 256k instead of using the default as the maximum (which is
silly).
Reported by: ache
Reviewed by: alfred, Martin Blapp <mb@imp.ch>
insert a magical second memory barrier prior to calling draina() in
badaddr_read(). This fixes 'machine check in pal mode' halts on
ev5 2100As.
MFC candidate -- after spending 6 hours tracking this down, I checked and
discovered that it has been in NetBSD for over a year, so it should be safe
for MFC into 4.3-RELEASE
des [Sat, 7 Apr 2001 19:51:12 +0000 (19:51 +0000)]
Let pseudofs into the warmth of the FreeBSD CVS repo.
It's not finished yet (I still have to find a way to implement process-
dependent nodes without consuming too much memory, and the permission
system needs tightening up), but it's becoming hard to work on without
a repo (I've accidentally almost nuked it once already), and it works
(except for the lack of process-dependent nodes, that is).
I was supposed to commit this a week ago, but timed out waiting for jkh
to reply to some questions I had. Pass him a spoonful of bad karma :)