FreeBSD (three commits; the initial work, man page updates, and a fix
to ffs_reload()), with the following differences:
- Be consistent between newfs(8) and tunefs(8) as to the options which
set and control the tuning parameters for this work (avgfilesize & avgfpdir)
- Use u_int16_t instead of u_int8_t to keep track of the number of
contiguous directories (suggested by Chuck Silvers)
- Work within our FFS_EI framework
- Ensure that fs->fs_maxclusters and fs->fs_contigdirs don't point to
the same area of memory
The new algorithm has a marked performance increase, especially when
performing tasks such as untarring pkgsrc.tar.gz, etc.
The original FreeBSD commit messages are attached:
=====
mckusick 2001/04/10 01:39:00 PDT
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.
Obtained from: Grigoriy Orlov <gluk@ptci.ru>
=====
=====
iedowse 2001/04/23 17:37:17 PDT
Pre-dirpref versions of fsck may zero out the new superblock fields
fs_contigdirs, fs_avgfilesize and fs_avgfpdir. This could cause
panics if these fields were zeroed while a filesystem was mounted
read-only, and then remounted read-write.
Add code to ffs_reload() which copies the fs_contigdirs pointer
from the previous superblock, and reinitialises fs_avgf* if necessary.
Reviewed by: mckusick
=====
=====
nik 2001/04/10 03:36:44 PDT
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.
=====
- add CHANGEVAL() macro, which does the hard work of changing a parameter
- sort options in usage()
- use .ig [ ... ] .. to comment out sections of man pages (instead
of .\" at the start of each line
in an effort to maintain compatibility with freebsd/openbsd/whatever,
i'm attempting to get the superblock format in sync, and freebsd uses
the int32_t at this position for `fs_pendinginodes'.
if we ever decide to implement fscktime functionality, we'll:
a) make sure to liaise with the other projects to reserve the same
spare field
b) actually implement the code this time ...
(this is also preparing us for other changes, like the new dirpref code)
cylinder groups to work correctly, with minor modifications by me to work
with our FFS_EI code. From the FreeBSD commit message:
The ffs superblock includes a 128-byte region for use by temporary
in-core pointers to summary information. An array in this region
(fs_csp) could overflow on filesystems with a very large number of
cylinder groups (~16000 on i386 with 8k blocks). When this happens,
other fields in the superblock get corrupted, and fsck refuses to
check the filesystem.
Solve this problem by replacing the fs_csp array in 'struct fs'
with a single pointer, and add padding to keep the length of the
128-byte region fixed. Update the kernel and userland utilities
to use just this single pointer.
With this change, the kernel no longer makes use of the superblock
fields 'fs_csshift' and 'fs_csmask'. Add a comment to newfs/mkfs.c
to indicate that these fields must be calculated for compatibility
with older kernels.
Reviewed by: mckusick
- replace the unused fs_headswitch and fs_trkseek with fs_id[2], bringing
our struct fs closer to that in freebsd & openbsd (& solaris FWIW)
- dumpfs: improve warning message when cpc == 0
- fix round-off errors when determining the number of inodes per group,
which often resulted in the total number of inodes in the file system
being less than what the density asked for.
now you might get more inodes than requested for a given density,
rather than less.
- if the new inodes/group is <= 0, ensure that it's at least 1, preventing
a possible division by zero or other wacky problems
- use long long instead of quad_t
- reorder "special" validation to after option parsing
- use getopt(3) instead of homegrown code
- add getnum() to parse and validate a number
- clean up man page
- ansi KNF, WARNS=2
determine the endianness of the `struct fs *o' superblock from o->fs_magic
and set needswap as necessary, rather than trusting the caller to get
it right. invariably, almost every caller of ffs_sb_swap() was calling it
with ns set to the wrong value for ns anyway!
ansi KNF ffs_bswap.c declarations whilst here.
this fixes all sorts of problems when trying to use other-endian file systems,
notably the kernel trying to access memory *way* off, possibly corrupting or
panicing, and userland programs SEGVing and/or corrupting things (e.g,
"fsck_ffs -B" to swap a file system endianness).
whilst the previous rev of ffs_bswap.c (1.10, 2000/12/23) made this problem
worse, i suspect that the problem was always there and previous versions
just happened not to trash things at the wrong time.
FFS_EI should now be a lot more stable.
and exit.
Previously, combinations would produce unintended results, such as
deleting the primary IP on an interface, instead of deleting an specified
alias.
safe (since there's two separate mallocs using sbrk(2) in that case)
XXX: local malloc provided for mfs memory store allocation; need to
investigate if system (phk) malloc can be used instead.
disklabel is created as per mfs on "swap".
* add -Z option: pre-zero the -F image file before use. this is necessary if
the image is to be used with vnd(4) because by default the files created
with -F have "holes" and vnd doesn't cope with that.
* support 'k', 'm', 'g' suffixes for all options which take numeric arguments.
provide strsuftoi() which performs the parsing mechanism.
* improve man page description of various options
* replace "filesystem" with "file system"
* when displaying usage for mfs, only list mfs options
* minor KNF and WARNS=2 cleanups
- in replacement malloc(), if sbrk(2) returns (void *)-1, convert to NULL
before returning
- in replacement calloc(), check return value of malloc() before zeroing result
Kernels and tools understand both v1 and v2 filesystems; newfs_lfs
generates v2 by default. Changes for the v2 layout include:
- Segments of non-PO2 size and arbitrary block offset, so these can be
matched to convenient physical characteristics of the partition (e.g.,
stripe or track size and offset).
- Address by fragment instead of by disk sector, paving the way for
non-512-byte-sector devices. In theory fragments can be as large
as you like, though in reality they must be smaller than MAXBSIZE in size.
- Use serial number and filesystem identifier to ensure that roll-forward
doesn't get old data and think it's new. Roll-forward is enabled for
v2 filesystems, though not for v1 filesystems by default.
- The inode free list is now a tailq, paving the way for undelete (undelete
is not yet implemented, but can be without further non-backwards-compatible
changes to disk structures).
- Inode atime information is kept in the Ifile, instead of on the inode;
that is, the inode is never written *just* because atime was changed.
Because of this the inodes remain near the file data on the disk, rather
than wandering all over as the disk is read repeatedly. This speeds up
repeated reads by a small but noticeable amount.
Other changes of note include:
- The ifile written by newfs_lfs can now be of arbitrary length, it is no
longer restricted to a single indirect block.
- Fixed an old bug where ctime was changed every time a vnode was created.
I need to look more closely to make sure that the times are only updated
during write(2) and friends, not after-the-fact during a segment write,
and certainly not by the cleaner.
same configuration format that -c and -C use.
this is useful if you're using autoconfig and you've misplaced the
/etc/raidXXX.conf files
* "filesystem" -> "file system", and other man page cleanups.
Some hosts and gateways ignore record route, but not "many." Of course,
more are firewalled. But that's not what was meant here.
Expand flood-pinging admonition to include multicast addresses.
Note flags that conflict with ping under Solaris and FreeBSD.
Reorder BUGS in rough order of significance.
Currently, only Aironet ("an") driver/card can be used.
nwkey persist (IEEE 802.11 devices only) Enable WEP encryption for IEEE
802.11-based wireless network interfaces with the persis-
tent key written in the network card.
nwkey persist:key
(IEEE 802.11 devices only) Write the key to the persis-
tent memory of the network card, and enable WEP encryp-
tion for IEEE 802.11-based wireless network interfaces
with the key.
(force) is given. fsck(8) will return with a zero exit status if "fsck -p"
is used in this circumstance, but all other invocations (e.g, "fsck",
"fsck /filesystem", "fsck -p /filesystem") will return with a non-zero exit
status in this circumstance.
Per discussions with various people including Bill Sommerfeld.
- Use "file system" instead of "filesystem"
a little used server daemon which can be controlled with rc.conf in any case.
(xxx: list of files probably should be totally configurable, but that's
another story). from [bin/13061] by matthew green.
for FreeBSD project. Besides huge speed boost compared with socketpair-based
pipes, this implementation also uses pagable kernel memory instead of mbufs.
Significant differences to FreeBSD version:
* uses uvm_loan() facility for direct write
* async/SIGIO handling correct also for sync writer, async reader
* limits settable via sysctl, amountpipekva and nbigpipes available via sysctl
* pipes are unidirectional - this is enforced on file descriptor level
for now only, the code would be updated to take advantage of it
eventually
* uses lockmgr(9)-based locks instead of home brew variant
* scatter-gather write is handled correctly for direct write case, data
is transferred by PIPE_DIRECT_CHUNK bytes maximum, to avoid running out of kva
All FreeBSD/NetBSD specific code is within appropriate #ifdef, in preparation
to feed changes back to FreeBSD tree.
This pipe implementation is optional for now, add 'options NEW_PIPE'
to your kernel config to use it.
network interfaces. This works by pre-computing the pseudo-header
checksum and caching it, delaying the actual checksum to ip_output()
if the hardware cannot perform the sum for us. In-bound checksums
can either be fully-checked by hardware, or summed up for final
verification by software. This method was modeled after how this
is done in FreeBSD, although the code is significantly different in
most places.
We don't delay checksums for IPv6/TCP, but we do take advantage of the
cached pseudo-header checksum.
Note: hardware-assisted checksumming defaults to "off". It is
enabled with ifconfig(8). See the manual page for details.
Implement hardware-assisted checksumming on the DP83820 Gigabit Ethernet,
3c90xB/3c90xC 10/100 Ethernet, and Alteon Tigon/Tigon2 Gigabit Ethernet.
simonb