Re: Linux 2.4.5-ac2

Re: Linux 2.4.5-ac2

[Leeuw van der, Tim]

Alan Cox wrote:

> > Performance is back to that of 2.4.2-ac26, and stability is a lot >
better. Under 
> > heavy FS pressure 2.4.5-ac2 is about 5-10% faster than vanilla 2.4.5, >
the aa1,2 
> > kernels have the same performance of vanilla 2.4.5. 
> > 
> > Which one of your changes affected performance so much? 

> Its much more a case that the 2.4.5 tree got fixed and I picked up the >
2.4.5 
> changes. Its still not perfect (bigmem will deadlock again as in 2.4.5 >
vanilla 
> now) but its a much better basis to work from again 

But the claim was that 2.4.5-ac2 is faster than 2.4.5 plain, so which
changes are in 2.4.5-ac2 that would make it faster than 2.4.5 plain? Also, I
don't know if 2.4.5-ac1 is as fast as 2.4.5-ac2 for Fabio. If not, then it's
a change in the 2.4.5-ac2 changelog. If it is as fast, it is one of the
changes in the 2.4.5-ac1 changelog.

I haven't tried plain kernels for a long time, but 2.4.5-ac1 is definately a
lot slower for interactive use than 2.4.4-ac8 so I've gone back to using
that version. I haven't tried 2.4.5-ac2 to see if that improves upon -ac1.

The VM in 2.4.5 might be largely 'fixed' and I know that the VM changes in
-ac were considered to be but still broken, however for me they worked
better than what is in 2.4.5.

I have a rather aging P5MMX at 200MHz with 64MB RAM, and I'm only judging
interactive use (not measuring anything like compile times etc).


with greetings,

--Tim

Re: Linux 2.4.5-ac2

[Alan Cox]

> But the claim was that 2.4.5-ac2 is faster than 2.4.5 plain, so which
> changes are in 2.4.5-ac2 that would make it faster than 2.4.5 plain? Also, I
> don't know if 2.4.5-ac1 is as fast as 2.4.5-ac2 for Fabio. If not, then it's
> a change in the 2.4.5-ac2 changelog. If it is as fast, it is one of the
> changes in the 2.4.5-ac1 changelog.

ac1 to ac2 backs out some of the bits of old VM cruft. ac2 doesnt really add
much that is VM relevant but it might be the user has a VIA chipset box in
which case -ac will be faster for other reasons

Re: Linux 2.4.5-ac2

[Mike Galbraith]

On Mon, 28 May 2001, Leeuw van der, Tim wrote:

> The VM in 2.4.5 might be largely 'fixed' and I know that the VM changes in
> -ac were considered to be but still broken, however for me they worked
> better than what is in 2.4.5.

The VM changes in 2.4.5 fixed a very serious performance problem.  IMHO,
2.4.5 is a step in the right direction.  (and I hope more steps are in
the offing;)

> I have a rather aging P5MMX at 200MHz with 64MB RAM, and I'm only judging
> interactive use (not measuring anything like compile times etc).

Interactive performance became a problem here exactly at the point when
we stopped waiting for the vm to produce results.  (which rather sucks,
because that's also the spot where throughput improved [non-suprise])

	-Mike

Re: Linux 2.4.5-ac2

[Marcelo Tosatti]

On Mon, 28 May 2001, Mike Galbraith wrote:

> On Mon, 28 May 2001, Leeuw van der, Tim wrote:
> 
> > The VM in 2.4.5 might be largely 'fixed' and I know that the VM changes in
> > -ac were considered to be but still broken, however for me they worked
> > better than what is in 2.4.5.
> 
> The VM changes in 2.4.5 fixed a very serious performance problem.  IMHO,
> 2.4.5 is a step in the right direction.  (and I hope more steps are in
> the offing;)

It did not fixed any interactivity problem. 

Re: Linux 2.4.5-ac2

[André Dahlqvist]

Marcelo Tosatti <marcelo@conectiva.com.br> wrote:

> It did not fixed any interactivity problem. 

I agree. Kernels after 2.4.4 uses a *lot* more swap for me, which I guess
might be part of the reason for the slowdown.
-- 

André Dahlqvist <anedah-9@sm.luth.se>

Re: Linux 2.4.5-ac2

[André Dahlqvist]

André Dahlqvist <anedah-9@sm.luth.se> wrote:

> I agree. Kernels after 2.4.4 uses a *lot* more swap for me, which I guess
> might be part of the reason for the slowdown.

Following up on myself, here are some numbers:

Freshly booted 2.4.4 with X and Mozilla running, 'free' outputs this:

             total       used       free     shared    buffers     cached
Mem:         62716      61280       1436          0       1820      28704
-/+ buffers/cache:      30756      31960
Swap:       160608          0     160608

Freshly booted 2.4.5-ac2 with X and Mozilla running, 'free' outputs this:

             total       used       free     shared    buffers     cached
Mem:         62784      61784       1000        380       1824      35748
-/+ buffers/cache:      24212      38572
Swap:       160608       7128     153480

After running 2.4.5-ac2 (and other kernels after vanilla 2.4.4) for a while
the swap usage grows a lot, to around 60 MB. Older kernels didn't swap out
this aggressively in my experience.

This is on a 233 Mhz box with 64 megs of RAM.
-- 

André Dahlqvist <anedah-9@sm.luth.se>

Re: Linux 2.4.5-ac2

[Marcelo Tosatti]

On Tue, 29 May 2001, André Dahlqvist wrote:

> André Dahlqvist <anedah-9@sm.luth.se> wrote:
> 
> > I agree. Kernels after 2.4.4 uses a *lot* more swap for me, which I guess
> > might be part of the reason for the slowdown.
> 
> Following up on myself, here are some numbers:
> 
> Freshly booted 2.4.4 with X and Mozilla running, 'free' outputs this:
> 
>              total       used       free     shared    buffers     cached
> Mem:         62716      61280       1436          0       1820      28704
> -/+ buffers/cache:      30756      31960
> Swap:       160608          0     160608
> 
> Freshly booted 2.4.5-ac2 with X and Mozilla running, 'free' outputs this:
> 
>              total       used       free     shared    buffers     cached
> Mem:         62784      61784       1000        380       1824      35748
> -/+ buffers/cache:      24212      38572
> Swap:       160608       7128     153480
> 
> After running 2.4.5-ac2 (and other kernels after vanilla 2.4.4) for a while
> the swap usage grows a lot, to around 60 MB. Older kernels didn't swap out
> this aggressively in my experience.

Well, they probably did. Its just that the kernel released unused swap
cache pages (thus releasing swap space) "more often".

Just to confirm this is what happening in your case:  Can you please try
2.4.4-ac5 and see if the _swap usage_ is still as badly?

This kernel contains a workaround to make the VM release unused swap cache
pages more often. (note: newer 2.4.4-ac do not contain the patch because
it could cause locks under some cases. Specially swap to files)

Back to the interactivity issue, I suppose you've "felt" bad interactivity
with 2.4.* kernels, right ?

I am asking that because I do not believe this swap usage issue is the
main reason for the problem.

Re: Linux 2.4.5-ac2

[André Dahlqvist]

Marcelo Tosatti <marcelo@conectiva.com.br> wrote:

> Just to confirm this is what happening in your case:  Can you please try
> 2.4.4-ac5 and see if the _swap usage_ is still as badly?

2.4.4-ac5 seams to use the swap about as much as 2.4.4, which is less than
2.4.5-ac2. In my simple "freesly boot kernel, start X and Mozilla" test
2.4.4-ac5 showed almost identical 'free' output as 2.4.4:

             total       used       free     shared    buffers     cached
Mem:         62760      61368       1392          0       1828      28760
-/+ buffers/cache:      30780      31980
Swap:       160608          0     160608

> Back to the interactivity issue, I suppose you've "felt" bad interactivity
> with 2.4.* kernels, right ?

Yes, I feel bad interactivety with later 2.4.4-acX kernels, and 2.4.5
kernels. Switching between apps and such feels a lot slower.

Let me know if you want me to do more tests.
-- 

André Dahlqvist <anedah-9@sm.luth.se>

Re: Linux 2.4.5-ac2

[Mike Galbraith]

On Mon, 28 May 2001, Marcelo Tosatti wrote:

> On Mon, 28 May 2001, Mike Galbraith wrote:
>
> > On Mon, 28 May 2001, Leeuw van der, Tim wrote:
> >
> > > The VM in 2.4.5 might be largely 'fixed' and I know that the VM changes in
> > > -ac were considered to be but still broken, however for me they worked
> > > better than what is in 2.4.5.
> >
> > The VM changes in 2.4.5 fixed a very serious performance problem.  IMHO,
> > 2.4.5 is a step in the right direction.  (and I hope more steps are in
> > the offing;)
>
> It did not fixed any interactivity problem.

Yes, I know.  I mentioned that interactivity went south here back
when we stopped waiting.  The performance problem I was refering to
was the cache collapsing as soon as you hit a load spike.  You and
Rik killed that longstanding problem.

	-Mike

Re: Linux 2.4.5-ac2

[Fabio Riccardi]

"Leeuw van der, Tim" wrote:

> But the claim was that 2.4.5-ac2 is faster than 2.4.5 plain, so which
> changes are in 2.4.5-ac2 that would make it faster than 2.4.5 plain? Also, I
> don't know if 2.4.5-ac1 is as fast as 2.4.5-ac2 for Fabio. If not, then it's
> a change in the 2.4.5-ac2 changelog. If it is as fast, it is one of the
> changes in the 2.4.5-ac1 changelog.

2.4.5-ac1 crashed on my machine, vanilla 2.4.5 worked but slower than 2.4.2

2.4.5-ac2 is _a lot_ faster than all the 2.4.4 and of vanilla 2.4.5

please notice that I have a 4G machine, dual proc, and I run a very
memory/IO/CPU intensive test, so your mileage may vary with different
applications.

I have no swapping in my case, it is the filesystem cache that works better in
my case. In the 2.4.4-ac series the machine would slowdown by a good 5-10%
(fluctuating) when the filesystem cache would hit the size of the physical RAM.

I have observed the same behaviour on three different brands (HP, Dell and
Compaq), I don't think that it depends on a specific chipset.

 - Fabio

Re: Linux 2.4.5-ac2

[Jens Axboe]

On Tue, May 29 2001, Fabio Riccardi wrote:
> "Leeuw van der, Tim" wrote:
> 
> > But the claim was that 2.4.5-ac2 is faster than 2.4.5 plain, so which
> > changes are in 2.4.5-ac2 that would make it faster than 2.4.5 plain? Also, I
> > don't know if 2.4.5-ac1 is as fast as 2.4.5-ac2 for Fabio. If not, then it's
> > a change in the 2.4.5-ac2 changelog. If it is as fast, it is one of the
> > changes in the 2.4.5-ac1 changelog.
> 
> 2.4.5-ac1 crashed on my machine, vanilla 2.4.5 worked but slower than 2.4.2
> 
> 2.4.5-ac2 is _a lot_ faster than all the 2.4.4 and of vanilla 2.4.5
> 
> please notice that I have a 4G machine, dual proc, and I run a very
> memory/IO/CPU intensive test, so your mileage may vary with different
> applications.

Could you try the 4GB I/O patches and see if they boost performance of
such cases?

*.kernel.org/pub/linux/kernel/people/axboe/patches/2.4.5/

-- 
Jens Axboe

Re: Linux 2.4.5-ac2

[Fabio Riccardi]

yes I get a performance improvement of about 5%

could you port your patches to the 2.4.5-ac4 kernel? I'd love to see if the ac
improvements and yours add to each other.

 Thanks,

 - Fabio

Jens Axboe wrote:

> On Tue, May 29 2001, Fabio Riccardi wrote:
> > "Leeuw van der, Tim" wrote:
> >
> > > But the claim was that 2.4.5-ac2 is faster than 2.4.5 plain, so which
> > > changes are in 2.4.5-ac2 that would make it faster than 2.4.5 plain? Also, I
> > > don't know if 2.4.5-ac1 is as fast as 2.4.5-ac2 for Fabio. If not, then it's
> > > a change in the 2.4.5-ac2 changelog. If it is as fast, it is one of the
> > > changes in the 2.4.5-ac1 changelog.
> >
> > 2.4.5-ac1 crashed on my machine, vanilla 2.4.5 worked but slower than 2.4.2
> >
> > 2.4.5-ac2 is _a lot_ faster than all the 2.4.4 and of vanilla 2.4.5
> >
> > please notice that I have a 4G machine, dual proc, and I run a very
> > memory/IO/CPU intensive test, so your mileage may vary with different
> > applications.
>
> Could you try the 4GB I/O patches and see if they boost performance of
> such cases?
>
> *.kernel.org/pub/linux/kernel/people/axboe/patches/2.4.5/
>
> --
> Jens Axboe
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

Re: Linux 2.4.5-ac2

[Jens Axboe]

On Tue, May 29 2001, Fabio Riccardi wrote:
> yes I get a performance improvement of about 5%

Nice

> could you port your patches to the 2.4.5-ac4 kernel? I'd love to see if the ac
> improvements and yours add to each other.

Sure:

*.kernel.org/pub/linux/kernel/people/axboe/patches/2.4.5-ac4/

-- 
Jens Axboe

Linux 2.4.5-ac2

[Alan Cox]

	ftp://ftp.kernel.org/pub/linux/kernel/people/alan/2.4/

		 Intermediate diffs are available from
			http://www.bzimage.org

In terms of going through the code audit almost all the sound drivers still 
need fixing to lock against format changes during a read/write. Poll creating 
and starting a buffer as write does and also mmap during write, write during
an mmap.

2.4.5-ac2
o	Restore lock_kernel on umount			(Al Viro)
	| Should cure Reiserfs crash in 2.4.5
o	Fix additional scsi_ioctl leak			(John Martin)
o	Clean up scsi_ioctl error handling		(me)
o	Configure.help typo fixes			(Nerijus Baliunas)
o	Fix hgafb problems with logos			(Ferenc Bakonyi)
o	Fix lock problems in the rio driver		(Rasmus Andersen)
o	Make new cmpci SMP safe				(Carlos E Gorges)
o	Fix missing restore flags in soundmodem		(Rasmus Andersen)
o	Set max sectors in ps2esdi			(Paul Gortmaker)
o	Fix interrupt restore problems in mixcom	(Rasmus Andersen)
o	Fix alpha compile on dp264/generic		(Andrea Arcangeli)
o	Fix irda irport locking restores		(Rasmus Andersen)
o	Fix failed kmalloc handling in hisax		(Kai Germaschewski)
o	Add missing memory barrier in qlogicisp		(?)
o	Fix missing restore_flags in eata_dma		(Rasmus Andersen)
o	Fix procfs locking in irttp			(Rasmus Andersen)
o	Winbond updates					(Manfred Spraul)
o	Stop network eating PF_MEMALLOC ram		(Manfred Spraul)
o	Drop fs/buffer.c low mem flush changes		(me)
o	Drop changes to mm/highmem.c			(me)
	| I don't think the Linus one is quite right but its easier
	| for everyone to be working off one base
o	Revert GFP_FAIL and some other alloc bits	(me)
o	Hopefully fix initrd problem			(me)
o	Fix kmalloc check in ide-tape			(Rasmus Andersen)
o	Fix irda irtty locking				(Rasmus Andersen)
o	Fix missing irq restore in qla1280		(Rasmus Andersen)
o	Fix proc/pid/mem cross exec behaviour		(Arjan van de Ven)
o	Fix direct user space derefs in eicon		(me)
	| From Stanford checker
o	Fix direct user space derefs in ipddp		(me)
	| From Stanford checker
o	Fix direct user space derefs in ixj		(me)
	| From Stanford checker
o	Fix direct user space derefs in decnet		(me)
	| From Stanford checker

2.4.5-ac1
o	Merge Linus 2.4.5 tree

Summary of changes for Linux 2.4.5-ac versus Linus 2.4.5

o	Fix memory leak in wanrouter
o	Fix memory leak in wanmain
o	Use non atomic memory for linearising NFS buffers as they are 
	done in task context
o	Fix dereference of freed memory in NetROM drivers
o	Fix writing to freed memory in ax25_ip
o	Support debugging of slab pools
o	NinjaSCSI pcmcia scsi driver
o	Raw HID device for USB peripheral buttons/controllers
o	Updated NTFS
o	RAMfs with resource limits
o	NMI watchdog available on uniprocessor x86
o	Update CMPCI drivers (not yet SMP safe)
o	Configurable max_map_count
o	Dynamic sysctl key registration
o	SE401 USB camera driver
o	Updated Zoran ZR3606x driver (replaces buz)
o	w9966 parallel port camera driver (partially merged with Linus)
o	Include headers in etags
o	Don't delete empty directories on make distclean
o	Fix halt/reboot handling on Alcor Alpha
o	IDE driver support for Etrax E100
o	IDE infrastructure support for IDE using non standard data transfers
o	Run ~/bin/installkernel if present
o	Support for out of order stores on x86 with this mode (IDT Winchip)
	- worth 20% performance on them
o	Configure level debugging menu
o	Make BUG() default to an oops only - saves 70K
o	Power management help for UP-APIC
o	Work around 440BX APIC hang (eg the ne2000 SMP hang)
o	Run time configurable APM behaviour (interrupts, psr etc)
o	Smarter DMI parser - handles multiple use of names
o	DMI layer has blacklist tables fixing Dell Inspiron 5000e crashes,
	PowerEdge reboot problems , and IBM laptop APM problems
o	PNPBios support
o	Fix atomicity of IRQ error count
o	Handle PCI/ISA boxes that don't list edge levels but have an ELCR
o	Don't erroneously mangle settings on all VIA bridges - cures the 
	horrible performance problem in 2.4.5 vanilla with VIA
o	Fix bootmem corruption on x86 boot
o	Scan and retrieve multipliers for processors (not yet used to handle
	the SMP cases where we need to disable tsc use)
o	Support machine check on Athlon and Pentium
o	Fix SUS violation with signal stacks
o	Handle boxes where firmware resets the timer to 18Hz (this should
	now not show false positives)
o	Better OOPS formatting on x86
o	Fix nasty problems with interrupts being disabled for long periods
	in frame buffer drivers
o	PAE mode alignment assumption fixes
o	32bit UID clean quota
o	Fix quota deadlocks
o	Fix TLB shootdown races
o	Experimental merge of usermode Linux
o	Fix memory leaks and othe rproblems with the iphase driver
o	IBM AS/400 iSeries virtual drivers
o	DAC960 null pointer checks
o	CCISS driver leak fixes
o	MPT fusion drivers for scsi and networking
o	Handle out of memory allocating request queue entries and avoid oops
o	Free the initial ramdisk correctly
o	Small CD-ROM layer updates
o	AGP power management hooks
o	First basic applicom driver fixes
o	Fix copy_from_user with interrupts off in cyclades driver
o	Fix out of memory handling in DRM
o	Clean up dsp56K driver
o	Update generic serial driver with break support
o	Clean up h8 driver namespace
o	Fix keymap changing problems in console drivers
o	Fix locking in machzwd
o	Updated rio serial driver
o	A2232 driver
o	Fix serial driver mangling of some clone uarts
o	Handle xircom serial port setup delay bug
o	Updated sx driver for newer generic_serial
o	W83877F watchdog driver
o	ITE8172 IDE driver support
o	Q40/Q60 IDE support
o	Fix nodma handling bug in alim15x3
o	hpt366 DMA blacklist
o	IDE-CD updates
o	Updated IDE DMA blacklist
o	OOPS catch for sg reuse in IDE driver
o	Support formatting of IDE floppies
o	Support PIIX4U4 (851EM)
o	Enable second port on promise pseudo raid
o	Support nodma on pmac
o	Support more PCI irq sharing on IDE
o	IDE tape updates - DI-50 support, 
o	Much updated VIA IDE support
o	video1394 updated to newer module API
o	Support write on the input event driver
o	Quieten mouse and keyboard input drivers
o	Fix compile problem with pc110pad
o	Fix memory leak in isdnppp
o	LVM updates
o	Fix plan b locking
o	Fix saa5249 locking
o	Fix stradis locking
o	Acenic driver updates
o	aironet4500 cleanups, probe tables
o	Ariadne updated to newer API
o	Don't limit mtu to 68+ in arlan drivers
o	Updated eepro100 driver
o	Fix potential crash on downing a bpqether port
o	Updated nsc-ircc driver
o	Updated toshoboe driver
o	Intel Panther LP486e ethernet driver
o	Remove erroneous check in eth_change_mtu
o	Alternative xircom_cb driver
o	Avoid ibm tr being rebuilt each make
o	Updated ibm token ring drivers
o	Add 'static' to bits of ppp code
o	Add pci probe table to roadrunner
o	Fix memory leak in sk_ge
o	sk_g16 updates
o	sk_mca updates
o	Add tools to generate starfire firmware
o	Synclink driver can be compiled in
o	Fix possible oops in lapbether
o	Fix memory leak in lanmedia driver
o	Fix SDLA_X25 warnings
o	Fix syncppp negotiation loop bug
o	GSC parallel port support
o	PCMCIA parallel port support
o	Support PnPBIOS probing for PC parallel ports
o	Fix leak in PCMCIA bulkmem driver
o	Fix leak in PCMCIA ds driver
o	Add more cards to the ti list for the yenta pcmcia
o	Updated 3ware scsi driver
o	NCR 53c700 and 53c700/66 driver core
o	Fix pci_enable/resource read order on buslogic
o	Updated NCR53c8xx driver
o	Updated SYM53c8xx driver
o	Fix NCR53c406 warnings
o	NCR dual MCA driver
o	AIC7xxx pci probe table for hotplug
o	Updated aic7xxx_old
o	Fix resource leaks in dec esp driver
o	Fix printk levels in dmx3191 driver
o	Allow per device max sector counts. (2.4 workaround until 2.5 does
	this in the block layer per device)
o	Support SCSI2/SCSI3 extended LUN numbering
o	Limit qlogicisp and qlogicpti to 64 sectors/write
o	Fix missing EFAULT return in scsi proc
o	Fix locking of scsi_unregister_host
o	Fix leaks in scsi_ioctl
o	Fix potential lost requests in scsi merges
o	Fix leak on write when scsi driver has no proc write op
o	Extend the scsi black/whitelist
o	Fix locking/eject/rescan on removable scsi disk media
o	Updated scsi generic driver
o	Updated scsi cdrom driver
o	Correct ac97 handling on sparc
o	Fix use after kfree in cs4281
o	Update ess solo to new PCI style and PM
o	Update maestro to new PCI style and PM
o	Add docking station support to maestro
o	Update sonicvies to new PCI api
o	Fix trident locking problems
o	Fix buzzing on ymfpci
o	Power management for ymfpci
o	Fix leak/missized copy on xjack driver
o	CDCEther driver
o	ACM driver with fixed CLOCAL
o	Updated USB audio drivers
o	Fix locking/reporting in USB device list
o	Allow dsbr100 to take a radio_nr option
o	HP5300 series USB scanner driver
o	Updated IBM cam driver
o	Fix USB inode locking
o	Driver for Kawasaki based USB ethernet
o	Small ov511 fixes
o	Updated USB storage drivers
o	Entries for Sony MSC-U01N memory stick, Fujifilm FinePix 1400Zoom,
	Casio QV Digial Camera
o	USB Ultracam driver
o	Fix derefence of freed memory in the USB code
o	Generic USB host->host drivers for anchorchip 2270, ipaq, netchip
	1080, and Prolific PL-2301/2
o	Updated ATI frame buffer drivers
o	Updated clgen and control frame buffer drivers
o	Updated cyber2000 driver
o	Documentation for fbcon driver
o	Additional modes for titanium powerbook (1152x768)
o	Updated matrxofb drivers
o	Support __setup in mdacon
o	Radeon console driver
o	Handle out of memory on sun3 fb
o	Updated tga/vesa fb
o	CMS file system (basic R/O)
o	JFFS journalling flash file system with compression
o	Updated AFFS file system
o	Threaded core dumps
o	Fix security holes in binfmt_misc
o	Allow flushing of low buffers only when we need bounce buffers
o	Use brelse in cramfs
o	Fix memory leaks in freevxfs
o	Updated isofs
o	Small lockd updates (experimental)
o	Fix nfs alignment funnies
o	Report correct SuS errors on some opens
o	Add generic_file_open to get 64bit stuff right
o	Locking on make_inode_number for procfs
o	Report shmem size in shared memory proc field
o	Fail lseek outside of allowed range for filesystem
o	Fix select race with fdset growth
o	Kernel message levels and handle oom on superblock/mount ops
o	Updated frame buffer logos
o	Prefetch support for AMD Athlon
o	Support out of order stores in spinlocks on x86
o	m68k bitop compile fixes
o	Add truncatepage op to address operations
o	shmem filesystem cleanups and updates
o	Fix off by one on real time pre-emption in scheduler
o	Use prefetches in scheduler and wakeups
o	Support GFP_FAIL to avoid highmem deadlocks
 
---
Alan Cox <alan@lxorguk.ukuu.org.uk>
Red Hat Kernel Hacker
& Linux 2.2 Maintainer                        Brainbench MVP for TCP/IP
http://www.linux.org.uk/diary                 http://www.brainbench.com

Re: Linux 2.4.5-ac2

[Tom Vier]

i haven't had any reiserfs crashes on my alpha, but restoring a backup of a
debian installation to a reiserfs partition doesn't quite work. untarring a
linux kernel tarball to the fs works, does work though. i get these kernel
messages:

May 27 23:28:47 zero kernel: is_leaf: free space seems wrong: level=1, nr_items=17, free_space=132 rdkey 
May 27 23:28:47 zero kernel: vs-5150: search_by_key: invalid format found in block 11693. Fsck?
May 27 23:28:47 zero kernel: vs-13070: reiserfs_read_inode2: i/o failure occurred trying to find stat data of [1361 1362 0x0 SD]
May 27 23:28:47 zero kernel: vs-13048: reiserfs_iget: bad_inode. Stat data of (1361 1362) not found
May 27 23:28:47 zero last message repeated 2 times
May 27 23:28:48 zero kernel: is_leaf: free space seems wrong: level=1, nr_items=18, free_space=568 rdkey 
May 27 23:28:48 zero kernel: vs-5150: search_by_key: invalid format found in block 14392. Fsck?
May 27 23:28:48 zero kernel: vs-13070: reiserfs_read_inode2: i/o failure occurred trying to find stat data of [3215 3216 0x0 SD]
May 27 23:28:48 zero kernel: vs-13048: reiserfs_iget: bad_inode. Stat data of (3215 3216) not found
May 27 23:28:48 zero last message repeated 2 times
May 27 23:28:49 zero kernel: is_leaf: free space seems wrong: level=1, nr_items=18, free_space=568 rdkey 
May 27 23:28:49 zero kernel: vs-5150: search_by_key: invalid format found in block 14392. Fsck?
May 27 23:28:49 zero kernel: vs-13070: reiserfs_read_inode2: i/o failure occurred trying to find stat data of [3208 3210 0x0 SD]
May 27 23:28:49 zero kernel: vs-13048: reiserfs_iget: bad_inode. Stat data of (3208 3210) not found
May 27 23:28:49 zero last message repeated 2 times
May 27 23:28:49 zero kernel: is_leaf: free space seems wrong: level=1, nr_items=18, free_space=568 rdkey 
May 27 23:28:49 zero kernel: vs-5150: search_by_key: invalid format found in block 14392. Fsck?
May 27 23:28:49 zero kernel: vs-13070: reiserfs_read_inode2: i/o failure occurred trying to find stat data of [3208 3211 0x0 SD]
May 27 23:28:49 zero kernel: vs-13048: reiserfs_iget: bad_inode. Stat data of (3208 3211) not found
May 27 23:28:49 zero last message repeated 8 times

On Mon, May 28, 2001 at 01:33:42AM +0100, Alan Cox wrote:
> 2.4.5-ac2
> o	Restore lock_kernel on umount			(Al Viro)
> 	| Should cure Reiserfs crash in 2.4.5

-- 
Tom Vier <tmv5@home.com>
DSA Key id 0x27371A2C

Re: Linux 2.4.5-ac2

[Tom Vier]

actually, it happens on ext2, also. it was fun trying to switch back to 2.2
after converting raid devs for 2.4 and trashing my emergency boot disk. i
was finally able to restore from tape by mounting -o sync. there was still
some minor corruption caught by fsck, though.

the new sym53c875 driver seems to have fixed the pci_map_sg() problem i was
having, but now it complains about scsi script errors. changing the TCQ
defaults from 32 to 8 fixes that. though, the corruption (even with TCQ max
8 and -o sync) may be related.

anyone else tried 2.4.5-ac2 on a miata or other alpha?

On Sun, May 27, 2001 at 11:38:01PM -0400, Tom Vier wrote:
> i haven't had any reiserfs crashes on my alpha, but restoring a backup of a
> debian installation to a reiserfs partition doesn't quite work. untarring a
> linux kernel tarball to the fs works, does work though. i get these kernel
> messages:

-- 
Tom Vier <tmv5@home.com>
DSA Key id 0x27371A2C

Re: Linux 2.4.5-ac2

[Fabio Riccardi]

Ok, things are fast again now! :))

Performance is back to that of 2.4.2-ac26, and stability is a lot better. Under
heavy FS pressure 2.4.5-ac2 is about 5-10% faster than vanilla 2.4.5, the aa1,2
kernels have the same performance of vanilla 2.4.5.

Which one of your changes affected performance so much?

BTW: the hangs that you are talking about in the 2.4.4 series, are they total
freezes? I've sporadically observed in a few 2.4.4-acX kernels strange hung-ups
where the system is still running, but very slowly, ps and other similar
commands (top) hang and you cannot kill them anymore. I think that this is some
sort of (memory?) resource deadlock.

The only miraculous way to resurrect such a locked system is to start Mozilla...
everything goes back to normal!

For the curious, the latest Ximian Gnone has the terminal and the mozilla icons
next to each other and I clicked on the wrong icon by mistake...

 - Fabio

Alan Cox wrote:

>         ftp://ftp.kernel.org/pub/linux/kernel/people/alan/2.4/
>
>                  Intermediate diffs are available from
>                         http://www.bzimage.org
>
> In terms of going through the code audit almost all the sound drivers still
> need fixing to lock against format changes during a read/write. Poll creating
> and starting a buffer as write does and also mmap during write, write during
> an mmap.
>
> 2.4.5-ac2
> o       Restore lock_kernel on umount                   (Al Viro)
>         | Should cure Reiserfs crash in 2.4.5
> o       Fix additional scsi_ioctl leak                  (John Martin)
> o       Clean up scsi_ioctl error handling              (me)
> o       Configure.help typo fixes                       (Nerijus Baliunas)
> o       Fix hgafb problems with logos                   (Ferenc Bakonyi)
> o       Fix lock problems in the rio driver             (Rasmus Andersen)
> o       Make new cmpci SMP safe                         (Carlos E Gorges)
> o       Fix missing restore flags in soundmodem         (Rasmus Andersen)
> o       Set max sectors in ps2esdi                      (Paul Gortmaker)
> o       Fix interrupt restore problems in mixcom        (Rasmus Andersen)
> o       Fix alpha compile on dp264/generic              (Andrea Arcangeli)
> o       Fix irda irport locking restores                (Rasmus Andersen)
> o       Fix failed kmalloc handling in hisax            (Kai Germaschewski)
> o       Add missing memory barrier in qlogicisp         (?)
> o       Fix missing restore_flags in eata_dma           (Rasmus Andersen)
> o       Fix procfs locking in irttp                     (Rasmus Andersen)
> o       Winbond updates                                 (Manfred Spraul)
> o       Stop network eating PF_MEMALLOC ram             (Manfred Spraul)
> o       Drop fs/buffer.c low mem flush changes          (me)
> o       Drop changes to mm/highmem.c                    (me)
>         | I don't think the Linus one is quite right but its easier
>         | for everyone to be working off one base
> o       Revert GFP_FAIL and some other alloc bits       (me)
> o       Hopefully fix initrd problem                    (me)
> o       Fix kmalloc check in ide-tape                   (Rasmus Andersen)
> o       Fix irda irtty locking                          (Rasmus Andersen)
> o       Fix missing irq restore in qla1280              (Rasmus Andersen)
> o       Fix proc/pid/mem cross exec behaviour           (Arjan van de Ven)
> o       Fix direct user space derefs in eicon           (me)
>         | From Stanford checker
> o       Fix direct user space derefs in ipddp           (me)
>         | From Stanford checker
> o       Fix direct user space derefs in ixj             (me)
>         | From Stanford checker
> o       Fix direct user space derefs in decnet          (me)
>         | From Stanford checker
>
> 2.4.5-ac1
> o       Merge Linus 2.4.5 tree
>
> Summary of changes for Linux 2.4.5-ac versus Linus 2.4.5
>
> o       Fix memory leak in wanrouter
> o       Fix memory leak in wanmain
> o       Use non atomic memory for linearising NFS buffers as they are
>         done in task context
> o       Fix dereference of freed memory in NetROM drivers
> o       Fix writing to freed memory in ax25_ip
> o       Support debugging of slab pools
> o       NinjaSCSI pcmcia scsi driver
> o       Raw HID device for USB peripheral buttons/controllers
> o       Updated NTFS
> o       RAMfs with resource limits
> o       NMI watchdog available on uniprocessor x86
> o       Update CMPCI drivers (not yet SMP safe)
> o       Configurable max_map_count
> o       Dynamic sysctl key registration
> o       SE401 USB camera driver
> o       Updated Zoran ZR3606x driver (replaces buz)
> o       w9966 parallel port camera driver (partially merged with Linus)
> o       Include headers in etags
> o       Don't delete empty directories on make distclean
> o       Fix halt/reboot handling on Alcor Alpha
> o       IDE driver support for Etrax E100
> o       IDE infrastructure support for IDE using non standard data transfers
> o       Run ~/bin/installkernel if present
> o       Support for out of order stores on x86 with this mode (IDT Winchip)
>         - worth 20% performance on them
> o       Configure level debugging menu
> o       Make BUG() default to an oops only - saves 70K
> o       Power management help for UP-APIC
> o       Work around 440BX APIC hang (eg the ne2000 SMP hang)
> o       Run time configurable APM behaviour (interrupts, psr etc)
> o       Smarter DMI parser - handles multiple use of names
> o       DMI layer has blacklist tables fixing Dell Inspiron 5000e crashes,
>         PowerEdge reboot problems , and IBM laptop APM problems
> o       PNPBios support
> o       Fix atomicity of IRQ error count
> o       Handle PCI/ISA boxes that don't list edge levels but have an ELCR
> o       Don't erroneously mangle settings on all VIA bridges - cures the
>         horrible performance problem in 2.4.5 vanilla with VIA
> o       Fix bootmem corruption on x86 boot
> o       Scan and retrieve multipliers for processors (not yet used to handle
>         the SMP cases where we need to disable tsc use)
> o       Support machine check on Athlon and Pentium
> o       Fix SUS violation with signal stacks
> o       Handle boxes where firmware resets the timer to 18Hz (this should
>         now not show false positives)
> o       Better OOPS formatting on x86
> o       Fix nasty problems with interrupts being disabled for long periods
>         in frame buffer drivers
> o       PAE mode alignment assumption fixes
> o       32bit UID clean quota
> o       Fix quota deadlocks
> o       Fix TLB shootdown races
> o       Experimental merge of usermode Linux
> o       Fix memory leaks and othe rproblems with the iphase driver
> o       IBM AS/400 iSeries virtual drivers
> o       DAC960 null pointer checks
> o       CCISS driver leak fixes
> o       MPT fusion drivers for scsi and networking
> o       Handle out of memory allocating request queue entries and avoid oops
> o       Free the initial ramdisk correctly
> o       Small CD-ROM layer updates
> o       AGP power management hooks
> o       First basic applicom driver fixes
> o       Fix copy_from_user with interrupts off in cyclades driver
> o       Fix out of memory handling in DRM
> o       Clean up dsp56K driver
> o       Update generic serial driver with break support
> o       Clean up h8 driver namespace
> o       Fix keymap changing problems in console drivers
> o       Fix locking in machzwd
> o       Updated rio serial driver
> o       A2232 driver
> o       Fix serial driver mangling of some clone uarts
> o       Handle xircom serial port setup delay bug
> o       Updated sx driver for newer generic_serial
> o       W83877F watchdog driver
> o       ITE8172 IDE driver support
> o       Q40/Q60 IDE support
> o       Fix nodma handling bug in alim15x3
> o       hpt366 DMA blacklist
> o       IDE-CD updates
> o       Updated IDE DMA blacklist
> o       OOPS catch for sg reuse in IDE driver
> o       Support formatting of IDE floppies
> o       Support PIIX4U4 (851EM)
> o       Enable second port on promise pseudo raid
> o       Support nodma on pmac
> o       Support more PCI irq sharing on IDE
> o       IDE tape updates - DI-50 support,
> o       Much updated VIA IDE support
> o       video1394 updated to newer module API
> o       Support write on the input event driver
> o       Quieten mouse and keyboard input drivers
> o       Fix compile problem with pc110pad
> o       Fix memory leak in isdnppp
> o       LVM updates
> o       Fix plan b locking
> o       Fix saa5249 locking
> o       Fix stradis locking
> o       Acenic driver updates
> o       aironet4500 cleanups, probe tables
> o       Ariadne updated to newer API
> o       Don't limit mtu to 68+ in arlan drivers
> o       Updated eepro100 driver
> o       Fix potential crash on downing a bpqether port
> o       Updated nsc-ircc driver
> o       Updated toshoboe driver
> o       Intel Panther LP486e ethernet driver
> o       Remove erroneous check in eth_change_mtu
> o       Alternative xircom_cb driver
> o       Avoid ibm tr being rebuilt each make
> o       Updated ibm token ring drivers
> o       Add 'static' to bits of ppp code
> o       Add pci probe table to roadrunner
> o       Fix memory leak in sk_ge
> o       sk_g16 updates
> o       sk_mca updates
> o       Add tools to generate starfire firmware
> o       Synclink driver can be compiled in
> o       Fix possible oops in lapbether
> o       Fix memory leak in lanmedia driver
> o       Fix SDLA_X25 warnings
> o       Fix syncppp negotiation loop bug
> o       GSC parallel port support
> o       PCMCIA parallel port support
> o       Support PnPBIOS probing for PC parallel ports
> o       Fix leak in PCMCIA bulkmem driver
> o       Fix leak in PCMCIA ds driver
> o       Add more cards to the ti list for the yenta pcmcia
> o       Updated 3ware scsi driver
> o       NCR 53c700 and 53c700/66 driver core
> o       Fix pci_enable/resource read order on buslogic
> o       Updated NCR53c8xx driver
> o       Updated SYM53c8xx driver
> o       Fix NCR53c406 warnings
> o       NCR dual MCA driver
> o       AIC7xxx pci probe table for hotplug
> o       Updated aic7xxx_old
> o       Fix resource leaks in dec esp driver
> o       Fix printk levels in dmx3191 driver
> o       Allow per device max sector counts. (2.4 workaround until 2.5 does
>         this in the block layer per device)
> o       Support SCSI2/SCSI3 extended LUN numbering
> o       Limit qlogicisp and qlogicpti to 64 sectors/write
> o       Fix missing EFAULT return in scsi proc
> o       Fix locking of scsi_unregister_host
> o       Fix leaks in scsi_ioctl
> o       Fix potential lost requests in scsi merges
> o       Fix leak on write when scsi driver has no proc write op
> o       Extend the scsi black/whitelist
> o       Fix locking/eject/rescan on removable scsi disk media
> o       Updated scsi generic driver
> o       Updated scsi cdrom driver
> o       Correct ac97 handling on sparc
> o       Fix use after kfree in cs4281
> o       Update ess solo to new PCI style and PM
> o       Update maestro to new PCI style and PM
> o       Add docking station support to maestro
> o       Update sonicvies to new PCI api
> o       Fix trident locking problems
> o       Fix buzzing on ymfpci
> o       Power management for ymfpci
> o       Fix leak/missized copy on xjack driver
> o       CDCEther driver
> o       ACM driver with fixed CLOCAL
> o       Updated USB audio drivers
> o       Fix locking/reporting in USB device list
> o       Allow dsbr100 to take a radio_nr option
> o       HP5300 series USB scanner driver
> o       Updated IBM cam driver
> o       Fix USB inode locking
> o       Driver for Kawasaki based USB ethernet
> o       Small ov511 fixes
> o       Updated USB storage drivers
> o       Entries for Sony MSC-U01N memory stick, Fujifilm FinePix 1400Zoom,
>         Casio QV Digial Camera
> o       USB Ultracam driver
> o       Fix derefence of freed memory in the USB code
> o       Generic USB host->host drivers for anchorchip 2270, ipaq, netchip
>         1080, and Prolific PL-2301/2
> o       Updated ATI frame buffer drivers
> o       Updated clgen and control frame buffer drivers
> o       Updated cyber2000 driver
> o       Documentation for fbcon driver
> o       Additional modes for titanium powerbook (1152x768)
> o       Updated matrxofb drivers
> o       Support __setup in mdacon
> o       Radeon console driver
> o       Handle out of memory on sun3 fb
> o       Updated tga/vesa fb
> o       CMS file system (basic R/O)
> o       JFFS journalling flash file system with compression
> o       Updated AFFS file system
> o       Threaded core dumps
> o       Fix security holes in binfmt_misc
> o       Allow flushing of low buffers only when we need bounce buffers
> o       Use brelse in cramfs
> o       Fix memory leaks in freevxfs
> o       Updated isofs
> o       Small lockd updates (experimental)
> o       Fix nfs alignment funnies
> o       Report correct SuS errors on some opens
> o       Add generic_file_open to get 64bit stuff right
> o       Locking on make_inode_number for procfs
> o       Report shmem size in shared memory proc field
> o       Fail lseek outside of allowed range for filesystem
> o       Fix select race with fdset growth
> o       Kernel message levels and handle oom on superblock/mount ops
> o       Updated frame buffer logos
> o       Prefetch support for AMD Athlon
> o       Support out of order stores in spinlocks on x86
> o       m68k bitop compile fixes
> o       Add truncatepage op to address operations
> o       shmem filesystem cleanups and updates
> o       Fix off by one on real time pre-emption in scheduler
> o       Use prefetches in scheduler and wakeups
> o       Support GFP_FAIL to avoid highmem deadlocks
>
> ---
> Alan Cox <alan@lxorguk.ukuu.org.uk>
> Red Hat Kernel Hacker
> & Linux 2.2 Maintainer                        Brainbench MVP for TCP/IP
> http://www.linux.org.uk/diary                 http://www.brainbench.com
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

Re: Linux 2.4.5-ac2

[Alan Cox]

> Performance is back to that of 2.4.2-ac26, and stability is a lot better. Under
> heavy FS pressure 2.4.5-ac2 is about 5-10% faster than vanilla 2.4.5, the aa1,2
> kernels have the same performance of vanilla 2.4.5.
> 
> Which one of your changes affected performance so much?

Its much more a case that the 2.4.5 tree got fixed and I picked up the 2.4.5
changes. Its still not perfect (bigmem will deadlock again as in 2.4.5 vanilla
now) but its a much better basis to work from again