summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Correct u_int_64 casting to remove warnings in printf()grog1998-11-031-2/+2
|
* Remove some dead code and commentsgrog1998-11-032-20/+16
|
* Print a warning if we removed a junked drivegrog1998-11-032-2/+14
| | | | Take a drive down if it's not open
* Take drive down if the disk driver tells us it's not theregrog1998-11-032-2/+10
|
* Check for duplicate subdisk namesgrog1998-11-032-18/+18
|
* Add the Ficl (Forth Inspired Command Language) interpreter. If all goes well,msmith1998-11-0323-2/+9740
| | | | | | | | | | | | | | | | | | | this will allow us to manage bloat in the loader by using a bytecoded HLL rather than lots of C code. It also offers an opportunity for vendors or others with special applications to significantly customise the boot process without having to commit to a divergent code branch. This early commit is to allow others to experiment with the most effective mechanisms for integrating FICL with the loader as it currently stands. Ficl is distributed with the following license conditions: "Ficl is freeware. Use it in any way that you like, with the understanding that the code is not supported." All source files contain authorship attributions. Obtained from: John Sadler (john_sadler@alum.mit.edu)
* Deal with both foo.hlp and FOO.TXT files.jkh1998-11-038-34/+52
|
* Copy appropriate docs into help/ directory of boot floppy.jkh1998-11-031-2/+4
|
* Use the new doc locations.jkh1998-11-031-22/+7
|
* Stage 1: Move a bunch of docs out from under sysinstall and otherjkh1998-11-0314-0/+1541
| | | | less than accessible places.
* Don't update the screen while the cursor shape is being changedyokota1998-11-032-2/+10
| | | | | by the user-land program. PR: i386/8344
* Ok, the entry aging algorithm sucked; 1s time resolution is not enough formsmith1998-11-021-7/+16
| | | | | LRU. Use a 31-bit counter instead. If we decide to do heavy I/O through the bootloader this will have to be revisited.
* Implement a simple LRU block cache. By default this is initialised to 16k,msmith1998-11-027-13/+278
| | | | | | | | | | | | | | and will bypass transfers for more than 8k. Blocks are invalidated after 2 seconds, so removable media should not confuse the cache. The 8k threshold is a compromise; all UFS transfers performed by libstand are 8k or less, so large file reads thrash the cache. However many filesystem metadata operations are also performed using 8k blocks, so using a lower threshold gives poor performance. Those of you with an eye for cache algorithms are welcome to tell me how badly this one sucks; you can start with the 'bcachestats' command which will print the contents of the cache and access statistics.
* Revise a few comments.rnordier1998-11-022-14/+14
|
* Standardise on ';' as a component separator; it seems to be a little moremsmith1998-11-021-4/+4
| | | | common than ','.
* Include `enigma' into the list of usr.bin programs.joerg1998-11-021-1/+2
|
* Remove the "adding default route" message and replace withobrien1998-11-022-2/+4
| | | | | | "Looking up host %s". Suggested by: msmith
* spell checkobrien1998-11-022-6/+6
|
* Show revive pointer in percentage complete as well as absolute value.grog1998-11-021-4/+5
|
* Remove kludge to set subdisk states when bringing up a plexgrog1998-11-021-50/+1
|
* Change some numeric #defines to enumsgrog1998-11-022-24/+22
|
* Don't close drives when called from interrupt context, set a flag forgrog1998-11-022-46/+126
| | | | | | | | | | | | the top half to do it. Put in a dubious check for subdisk integrity when trying to bring up a plex where others are already up. This particular kludge is crying out for a rewrite of the whole state code. Add code to set_plex_state and set_volume_state to defer updates when called from an interrupt context. This doesn't happen yet, but it could do.
* Get the default revive blocksize right for striped and RAID-5 plexesgrog1998-11-022-6/+8
|
* Close any drives downed in an interrupt context.grog1998-11-022-10/+48
| | | | | | Ensure correct order of requests. Call launch_requests at splhigh to see if this stops the mysterious SMP panics
* Accept incorrect device open counts, but print a warninggrog1998-11-022-4/+34
| | | | Don't save invalid drive config information, remove the drive
* Check for maximum number of subdisks in a plexgrog1998-11-022-2/+22
| | | | Get object counts right when removing
* Only do one VOP_ACCESS() per open() instead of two. This should reducepeter1998-11-021-8/+9
| | | | | | | | | | | the NFSv3 ACCESS RPC problems a little for busy clients that do a lot of open/close. The nfs code could probably cache the results, but I'm not sure whether this would be legal or useful. The problem is that with a CPU farm, on each open there would be a lookup, getattr then access RPC then the read/write RPC activity. Caching the access results probably isn't going to help much if the clients access lots of files. Having the nfs_access() routine interpret the getattr results is a bit of a hack, but it's how NFSv2 is done and it might be OK for a mount attribute for v3.
* Optimize bzero() by unrolling the aligned quadword loop and moving the lengthalex1998-11-021-2/+14
| | | | | | manipulation away from the length comparison. Measurements on beast.cdrom.com show >3X improvement over the original code on large block sizes, putting the performance on par with the optimized assembly code in libc.
* Changed my e-mail address.abial1998-11-0139-101/+57
|
* Change my e-mail address.abial1998-11-014-10/+10
|
* Added info on Unified Configuration Interface Project. Several peopleabial1998-11-012-2/+857
| | | | | contributed their ideas to this document, among them Terry Lambert and Bryan Mann, both @whistle.com. Thanks!
* Oops forgot to remove peter's 'device iicbb0' declaration. Done.nsouch1998-11-013-6/+3
|
* Add controller iicbb (generic I2C bit-banging code) and lpbbnsouch1998-11-013-6/+48
| | | | | | (official Philips I2C parallel interface) Add comments for bktr port to the new I2C framework
* The kernel should compile even /dev/null does not exists.wosch1998-11-011-3/+2
|
* Ignore, rather than emulate, an i386 'hlt' instruction (though forrnordier1998-11-012-22/+22
| | | | | | | most practical purposes, this should be indistinguishable from a more strictly correct approach). Feedback and testing: msmith
* Write temp files with a uniq name into /var/runwosch1998-11-012-4/+4
| | | | | instead the public writable directory /tmp PR: conf/8330
* Add:msmith1998-11-015-10/+73
| | | | | | assert() setjmp()/longjmp() vsprintf()
* Ported to OpenBSD. sys/pci/smc83c170.h renamed to sys/pci/if_txvar.h to besemenu1998-11-015-1098/+2615
| | | | like others.
* Fix errors detected by -Wformat.jdp1998-11-013-6/+7
|
* Link objformat statically by default. This makes it possible tojdp1998-11-011-0/+1
| | | | | | | | | | build 2.2-stable worlds on 3.0-current systems again. objformat calls getobjformat(), which doesn't exist in 2.2's libc. Technically there should have been a version number bump when it was added in -current. But it's used in so few places that it hardly seems worth that. Besides, the objformat program is very heavily used during a make world; it won't hurt to have it load a little faster.
* Unneeded file.phk1998-10-311-93/+0
| | | | Submitted by: Mike Spengler <mks@networkcs.com>
* Set BLLI Layer 2 protocol field when using a 'User specified' protocol.phk1998-10-311-2/+4
| | | | Submitted by: Mike Spengler <mks@networkcs.com>
* Trivial stylish changes, mostly to silence gcc.phk1998-10-3185-424/+434
| | | | | Reviewed by: Mike Spengler <mks@networkcs.com> Submitted by: phk
* If the CBCP callee offsers no callback, send our configuredbrian1998-10-311-5/+7
| | | | | | response anyway. This is what Win95 does, despite it not being documented in the cbcp spec.... Reported by: Bill <petheram@acm.org>
* Allow multiple systems (config labels) on the commandbrian1998-10-316-101/+116
| | | | | | line and in the ``load'' & ``dial'' commands. The last label loaded becomes the current label name. Only require a label for -auto mode.
* Increase the size of the tx and rx rings from 10 to 20 descriptorswpaul1998-10-312-8/+8
| | | | | | | | | and increase the tx interrupt threshold to 4. This fixes performance problems on slower systems. Also fix a mind-o in the rx ring init routine: I used the TX constant instead of the RX. This isn't a problem as long as the rings are the same size, but if they aren't hijinx will ensue.
* Add John Dyson's SYSCTL descriptions, and an export of more stats topeter1998-10-315-20/+124
| | | | | a sysctl hierarchy (vm.stats.*). SYSCTL descriptions are only present in source, they do not get compiled into the binaries taking up memory.
* * Extend the memory available for the heap from 256k to 512k.dfr1998-10-318-20/+86
| | | | | | | | | * Embed the stack into the bss section for loader and netboot. This is required for netboot since otherwise the stack would be inside our heap. * Install loader and netboot in /boot by default. * Fix getbootfile so that it searches for a ',' instead of a ';' when terminating the filename.
* vm_object_page_clean() last arg changed from TRUE to OBJPC_SYNC. I'm notpeter1998-10-312-4/+4
| | | | | | sure that this is necessary to be a sync write here since a VOP_FSYNC() follows and it will schedule, sort and complete the writes that the vm_object_page_clean() started (as I think I understand things).
* Change dirty block list handling to use TAILQ macros.peter1998-10-313-24/+24
|
OpenPOWER on IntegriCloud