Re: Bugreport: Kernel 2.4.x crash

2001-04-18 Thread Jörn Engel
Hi! I have no experience with kernel debugging, but so far, I have found no log entry giving me a hint and the screen is blank after the crash Could you disable console blanking (setterm -blank 0). We really need a hint where it crashed. Over the easter weekend I took some time for

Bugreport: Kernel 2.4.x crash

2001-04-03 Thread Jörn Engel
1. Kernel crash w/out error message or logfile entry 2. A Fileserver with an ABIT Hotrod 66 (htp366) controller will crash within 5-60 minutes after boot with a 2.4.x kernel. 2.2.x works fine. No other exotic hardware. Another possibility might be Reiserfs, which I use for all partitions except

Re: [RFC] MTD driver for MMC cards

2007-04-15 Thread Jörn Engel
On Mon, 16 April 2007 01:33:17 +0200, Arnd Bergmann wrote: There is also still some need for performance testing. Jörn brought up the point that if a specific card can't have multiple open erase block simulateously, it's rather pointless for logfs. It might still be useful to use jffs2 on

Re: ZFS with Linux: An Open Plea

2007-04-16 Thread Jörn Engel
On Mon, 16 April 2007 17:46:50 +0200, Tomasz Kłoczko wrote: On Mon, 16 Apr 2007, Christoph Hellwig wrote: Numbers, please. So far in all interesting benchmarks it actually was slower. But when they're faster than XFS somewhere I'd defintly be interesting in looking at why this is true and

Re: [00/17] Large Blocksize Support V3

2007-04-24 Thread Jörn Engel
On Tue, 24 April 2007 15:21:05 -0700, [EMAIL PROTECTED] wrote: This patchset modifies the Linux kernel so that larger block sizes than page size can be supported. Larger block sizes are handled by using compound pages of an arbitrary order for the page cache instead of single pages with

Re: Documenting MS_RELATIME

2007-02-12 Thread Jörn Engel
On Mon, 12 February 2007 18:49:39 +0100, Jan Engelhardt wrote: On Feb 12 2007 10:40, Dave Jones wrote: The one problem with noatime is that mutt's 'new mail arrived' breaks Just why does not it use mtime then to check for New Mail Arrived, like bash does? Just a guess: because it has to

Re: [PATCH x86 for review III] [10/29] i386: don't include bugs.h

2007-02-12 Thread Jörn Engel
On Mon, 12 February 2007 17:51:30 +0100, Andi Kleen wrote: From: Andrew Morton [EMAIL PROTECTED] That stupid non-inlined-static function in bugs.h causes: include/asm/bugs.h:186: warning: 'check_bugs' defined but not used But fortunately the include isn't needed. Cc: Andi Kleen

Re: SATA-performance: Linux vs. FreeBSD

2007-02-13 Thread Jörn Engel
On Tue, 13 February 2007 11:27:58 +, Alan wrote: isn't yet a heavily optimised libata path. Secondly erase block size matters with flash drives so the bigger each I/O the better erase block behaviour we should get. Although that should max out somewhere between 16KiB and 128KiB,

Re: SATA-performance: Linux vs. FreeBSD

2007-02-13 Thread Jörn Engel
On Tue, 13 February 2007 11:29:18 +0100, Martin A. Fink wrote: Please Read Carefully! I talk about flash disk, not normal harddisks. There are no mechanical parts in flash disks, only flash memory. And therefore 48MB/s is excellent (compared to all other available disks) [...] Well.

Re: GPL vs non-GPL device drivers

2007-02-15 Thread Jörn Engel
On Thu, 15 February 2007 00:40:31 -0800, v j wrote: Oh, I am sorry. Seems like the German courts have spoken. I am not sure about what, but they have spoken. Sorry for the confusion. In short, there seem to be two classes of closed-source drivers: 1. ATI and nVidia. Both are well-known, in

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-15 Thread Jörn Engel
On Thu, 15 February 2007 19:38:14 +0100, Juan Piernas Canovas wrote: The patch for 2.6.11 is not still stable enough to be released. Be patient ;-) While I don't want to discourage you, this is about the point in development where most log structured filesystems stopped. Doing a little web

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-16 Thread Jörn Engel
On Thu, 15 February 2007 23:59:14 +0100, Juan Piernas Canovas wrote: Actually, the version of DualFS for Linux 2.4.19 implements a cleaner. In our case, the cleaner is not really a problem because there is not too much to clean (the meta-data device only contains meta-data blocks which

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-17 Thread Jörn Engel
On Fri, 16 February 2007 18:47:48 -0500, Bill Davidsen wrote: Actually I am interested in the common case, where the machine is not out of space, or memory, or CPU, but when it is appropriately sized to the workload. Not that I lack interest in corner cases, but the running flat out case

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-17 Thread Jörn Engel
On Sat, 17 February 2007 13:10:23 -0500, Bill Davidsen wrote: I missed that. Which corner case did you find triggers this in DualFS? This is not specific to DualFS, it applies to any log-structured filesystem. Garbage collection always needs at least one spare segment to collect valid data

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-17 Thread Jörn Engel
On Sat, 17 February 2007 15:47:01 -0500, Sorin Faibish wrote: DualFS can probably get around this corner case as it is up to the user to select the size of the MD device size. If you want to prevent this corner case you can always use a device bigger than 10% of the data device which is

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-18 Thread Jörn Engel
Maybe this is a decent approach to deal with the problem. First some definitions. T is the target segment to be cleaned, S is the spare segment that valid data is written to, O are other segments that contain indirect blocks I for valid data D in T. Have two different GC mechanisms to choose

Re: [PATCH 41/44 take 2] [UBI] gluebi unit header

2007-02-19 Thread Jörn Engel
On Sat, 17 February 2007 21:02:17 -0600, Josh Boyer wrote: That just sounds like we need Jörn to get off his butt and finish logfs ;) He's working on it this very moment. Help in debugging would be appreciated, if progress is too slow for people. That part seems to consume a lot of time and

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-19 Thread Jörn Engel
On Tue, 20 February 2007 00:57:50 +0100, Juan Piernas Canovas wrote: I understand the problem that you describe with respect to the GC, but let me explain why I think that it has a small impact on DualFS. Actually, the GC may become a problem when the number of free segments is 50% or

Re: [PATCH] slab: deal with NULL pointers passed to kmem_cache_free

2007-03-19 Thread Jörn Engel
On Mon, 19 March 2007 14:10:38 -0700, Andrew Morton wrote: Would prefer to do: static inline void kmem_cache_free_if_not_null(struct kmem_cache *cachep, void *objp) { if (objp) kmem_cache_free(cachep, objp); } so that

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-21 Thread Jörn Engel
On Tue, 20 March 2007 01:42:46 +0100, Thomas Gleixner wrote: On Mon, 2007-03-19 at 17:32 -0500, Matt Mackall wrote: 4. JFFS2 has its own wear-leving scheme, as do several other filesystems, so they probably want to bypass this piece of the stack. JFFS2 on top of UBI delegates

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-21 Thread Jörn Engel
On Wed, 21 March 2007 12:25:34 +0100, Thomas Gleixner wrote: On Wed, 2007-03-21 at 12:05 +0100, Jörn Engel wrote: Ok, now we have reached the absurd. UBI quite fundamentally cannot do wear leveling as good as LogFS can. Simply because UBI has zero knowledge of the _contents_ of its

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-21 Thread Jörn Engel
On Wed, 21 March 2007 12:57:42 +0100, Thomas Gleixner wrote: On Wed, 2007-03-21 at 12:35 +0100, Jörn Engel wrote: Even if such flashes still contain a bootloader and a kernel, that will occupy less than 1% of the device. Wear leveling across the device is fairly pointless here

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-21 Thread Jörn Engel
*sigh* I really did not want to become involved in this. So please be nice and leave the flamethrower in your weapon closet or I will disappear again before you can say fire. On Tue, 20 March 2007 21:32:40 +, David Woodhouse wrote: On Tue, 2007-03-20 at 10:58 -0800, David Lang wrote:

Re: [PATCH] slab: deal with NULL pointers passed to kmem_cache_free

2007-03-21 Thread Jörn Engel
On Wed, 21 March 2007 08:30:27 -0800, Andrew Morton wrote: On Wed, 21 Mar 2007 16:41:19 +0200 Pekka Enberg [EMAIL PROTECTED] wrote: Yeah, I'll try to sneak a patch past Andrew. That would be sneaky. Thing is, such a patch would amount to adding a test-for-NULL to codepaths which we

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-25 Thread Jörn Engel
On Wed, 21 March 2007 12:25:34 +0100, Thomas Gleixner wrote: On Wed, 2007-03-21 at 12:05 +0100, Jörn Engel wrote: Also LogFS currently requires erasesizes of 2^n. Last time I talked to you about that, you said it would be possible and fixable. Actually, no. LogFS is not broken

Re: [2.6 patch] block2mtd_paramline[] mustn't be __initdata

2007-03-25 Thread Jörn Engel
On Sun, 25 March 2007 16:58:05 +0200, Adrian Bunk wrote: block2mtd_paramline[] is used in the non-__init block2mtd_setup() Signed-off-by: Adrian Bunk [EMAIL PROTECTED] Acked-By: Jörn Engel [EMAIL PROTECTED] Adrian, can you put me on Cc: next time? --- --- linux-2.6.21-rc4-mm1/drivers/mtd

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-25 Thread Jörn Engel
On Sun, 25 March 2007 13:49:58 -0800, David Lang wrote: On Sun, 25 Mar 2007, Jörn Engel wrote: Logical volume management can just as easily move its management information into a table, instead of having it spread across all blocks. Blocks can keep their original size. Since you have

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-25 Thread Jörn Engel
On Mon, 26 March 2007 00:46:33 +0100, David Woodhouse wrote: On Mon, 2007-03-26 at 00:55 +0200, Jörn Engel wrote: although, since you can flip bits to 1 without requireing an erase you [ vice versa. you can flip bits to 0 without erasing. ] And on NAND flash you can't just do

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-25 Thread Jörn Engel
On Mon, 26 March 2007 01:21:25 +0100, David Woodhouse wrote: On Mon, 2007-03-26 at 02:01 +0200, Jörn Engel wrote: You can on NAND. ECC is done in software. And for a data structure as simple as the 'tally', foregoing ECC is not a huge problem - most bitflips are easily detected

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-26 Thread Jörn Engel
On Mon, 26 March 2007 10:45:57 +0100, David Woodhouse wrote: No, on NAND flash it's a limitation of the hardware. The number of write cycles you can perform to a given page is limited. Exceed it and the contents of that page become undefined due to leakage, until you next erase it. Are you

Re: [PATCH 00/22 take 3] UBI: Unsorted Block Images

2007-03-26 Thread Jörn Engel
On Mon, 26 March 2007 13:49:06 +0300, Artem Bityutskiy wrote: On Sun, 2007-03-25 at 22:08 +0200, Jörn Engel wrote: Logical volume management can just as easily move its management information into a table, instead of having it spread across all blocks. Blocks can keep their original size

Re: If not readdir() then what?

2007-04-08 Thread Jörn Engel
On Sun, 8 April 2007 11:11:20 -0700, H. Peter Anvin wrote: Well, the question is if you can keep the seekdir/telldir cookie around as a pointer -- preferrably in userspace, of course. You would presumably garbage-collect them on closedir() -- there is no other point at which you could.

Re: If not readdir() then what?

2007-04-09 Thread Jörn Engel
On Sun, 8 April 2007 21:44:26 -0400, Theodore Tso wrote: Well, Joern thought that rm -rf might relying on the telldir cookie being valid in precisely that circumstance. If that is true, I'd argue that this is a BUG in GNU coreutils that should be fixed... I heard it and accepted that claim

Re: Interface for the new fallocate() system call

2007-04-09 Thread Jörn Engel
On Mon, 9 April 2007 23:01:42 +1000, Paul Mackerras wrote: Jörn Engel writes: Wouldn't that work be confined to fallocate()? If I understand Heiko correctly, the alternative would slow s390 down for every syscall, including more performance-critical ones. The alternative that Jakub

Re: Add a norecovery option to ext3/4?

2007-04-10 Thread Jörn Engel
On Mon, 9 April 2007 12:21:15 -0500, Eric Sandeen wrote: Phillip Susi wrote: When the filesystem is told to mount the disk read only, that means it should not write to it. It means the filesystem should not be writeable when it is mounted. This is not the same as saying that the

Re: Add a norecovery option to ext3/4?

2007-04-10 Thread Jörn Engel
On Tue, 10 April 2007 07:27:18 -0400, Theodore Tso wrote: I suppose what you could do is to read in the journal, and use it to create an remapping table so that when you want to read block #5126, and block number 5126 is in the journal, to read the journal version of the block instead of the

Re: [PATCH 1/13] fs: convert core functions to zero_user_page

2007-04-11 Thread Jörn Engel
On Tue, 10 April 2007 22:56:38 -0700, Andrew Morton wrote: And I'm surprised that this: +static inline void memclear_highpage_flush(struct page *page, unsigned int offset, unsigned int size) +{ + return zero_user_page(page, offset, size); +} compiled. zero_user_page() returns

Re: If not readdir() then what?

2007-04-11 Thread Jörn Engel
On Wed, 11 April 2007 16:23:21 -0700, H. Peter Anvin wrote: David Lang wrote: On Thu, 12 Apr 2007, Neil Brown wrote: For the second. You say that you would need at least 96 bits in order to make that guarantee; 64 bits of hash, plus a 32-bit count value in the hash collision chain. I

Re: If not readdir() then what?

2007-04-11 Thread Jörn Engel
On Thu, 12 April 2007 11:46:41 +1000, Neil Brown wrote: I could argue that nfs came before ext3+dirindex, so ext3 should have been designed to work properly with NFS. You could argue that fixing it in nfsd fixes it for all filesystems. But I'm not sure either of those arguments are likely

Re: If not readdir() then what?

2007-04-12 Thread Jörn Engel
On Thu, 12 April 2007 15:57:41 +1000, Neil Brown wrote: However, the collision chain gives me quite a bit of headache. One would have to store each entry's position on the chain, deal with older entries getting deleted, newer entries getting removed, etc. All this requires a lot of

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-21 Thread Jörn Engel
On Wed, 21 February 2007 05:36:22 +0100, Juan Piernas Canovas wrote: I don't see how you can guarantee 50% free segments. Can you explain that bit? It is quite simple. If 50% of your segments are busy, and the other 50% are free, and the file system needs a new segment, the cleaner starts

Re: [PATCH] [MTD] CHIPS: oops in cfi_amdstd_sync

2007-02-21 Thread Jörn Engel
On Tue, 20 February 2007 17:46:13 -0800, Vijay Sampath wrote: The files cfi_cmdset_0002.c and cfi_cmdset_0020.c do not initialize their wait queues like is done in cfi_cmdset_0001.c. This causes an oops when the wait queue is accessed. I have copied the code from cfi_cmdset_0001.c that is

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-21 Thread Jörn Engel
On Wed, 21 February 2007 19:31:40 +0100, Juan Piernas Canovas wrote: I do not understand. Do you mean that if I have 10 segments, 5 busy and 5 free, after cleaning I could need 6 segments? How? Where the extra blocks come from? This is a fairly complicated subject and I have trouble

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-22 Thread Jörn Engel
On Thu, 22 February 2007 05:30:03 +0100, Juan Piernas Canovas wrote: DualFS writes meta-blocks in variable-sized chunks that we call partial segments. The meta-data device, however, is divided into segments, which have the same size. A partial segment can be as large a a segment, but a

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-23 Thread Jörn Engel
On Thu, 22 February 2007 20:57:12 +0100, Juan Piernas Canovas wrote: I do not agree with this picture, because it does not show that all the indirect blocks which point to a direct block are along with it in the same segment. That figure should look like: Segment 1: [some data] [ DA D1'

Re: SLUB: The unqueued Slab allocator

2007-02-24 Thread Jörn Engel
On Sat, 24 February 2007 09:32:49 -0800, Christoph Lameter wrote: If that is a problem for particular object pools then we may be able to except those from the merging. How much of a gain is the merging anyway? Once you start having explicit whitelists or blacklists of pools that can be

Re: [ANNOUNCE] DualFS: File System with Meta-data and Data Separation

2007-02-25 Thread Jörn Engel
On Sun, 25 February 2007 03:41:40 +0100, Juan Piernas Canovas wrote: Well, our experimental results say another thing. As I have said, the greatest part of the files are written at once, so their meta-data blocks are together on disk. This allows DualFS to implement an explicit

Re: SLUB: The unqueued Slab allocator

2007-02-25 Thread Jörn Engel
On Sat, 24 February 2007 16:14:48 -0800, Christoph Lameter wrote: It eliminates 50% of the slab caches. Thus it reduces the management overhead by half. How much management overhead is there left with SLUB? Is it just the one per-node slab? Is there runtime overhead as well? In a slightly

Re: [RFC] Heads up on sys_fallocate()

2007-03-04 Thread Jörn Engel
On Sun, 4 March 2007 14:38:13 -0800, Ulrich Drepper wrote: When you do it like this, who can the kernel/filesystem *guarantee* that when the data is written there actually is room on the harddrive? What you described seems like using truncate/ftruncate to increase the file's size. That is

Re: [RFC] Heads up on sys_fallocate()

2007-03-05 Thread Jörn Engel
On Mon, 5 March 2007 01:36:36 +0100, Arnd Bergmann wrote: Using the current glibc implementation on a compressed file system ideally should be a very expensive no-op because you won't actually allocate much space for a file when writing zeroes to it. You also don't benefit of a contiguous

Re: [RFC] Heads up on sys_fallocate()

2007-03-05 Thread Jörn Engel
On Mon, 5 March 2007 00:32:14 +, Anton Altaparmakov wrote: I don't know how your compression algorithm works [...] LogFS is designed for flash media, so it does not have to worry much about reducing disk seeks. It is log-structured, which simplifies compression further. When writing a

Re: [RFC] Heads up on sys_fallocate()

2007-03-05 Thread Jörn Engel
On Mon, 5 March 2007 07:08:03 -0800, Ulrich Drepper wrote: Jörn Engel wrote: Does the allocation have to be persistent beyond lifetime of the file descriptor? Of course. You call posix_fallocate once for the lifetime of the file when it is created to ensure that all future uses will work

Re: [RFC] Heads up on sys_fallocate()

2007-03-07 Thread Jörn Engel
On Wed, 7 March 2007 09:51:35 +0100, Jan Kara wrote: I'll probably first write some userspace fs-reorganizer to find out how much these changes in layout are able to give you in performance (i.e. whether it's worth the effort of more complicated kernel online defragmenter). Have tried

Re: [patch] add file position info to proc

2007-03-27 Thread Jörn Engel
On Tue, 27 March 2007 21:24:20 +, Pavel Machek wrote: From: Miklos Szeredi [EMAIL PROTECTED] This patch adds support for finding out the current file position, open flags and possibly other info in the future. These new entries are added: /proc/PID/fdinfo/FD

Re: Interface for the new fallocate() system call

2007-03-30 Thread Jörn Engel
On Fri, 30 March 2007 19:15:58 +1000, Paul Mackerras wrote: Heiko Carstens writes: If possible I'd prefer the six-32-bit-args approach. It does mean extra unnecessary work for 64-bit platforms, though... Wouldn't that work be confined to fallocate()? If I understand Heiko correctly, the

Re: [PATCH 09/16] zlib-decompression-status.diff

2007-04-02 Thread Jörn Engel
On Sun, 1 April 2007 20:15:42 +0200, Jan Engelhardt wrote: +static inline void putstr(const char *s) { +printk(%s, s); +return; +} + static int __init crd_load(int in_fd, int out_fd) { int result; @@ -418,7 +423,7 @@ static int __init crd_load(int in_fd, in

Re: missing madvise functionality

2007-04-03 Thread Jörn Engel
On Tue, 3 April 2007 23:10:14 +0200, Eric Dumazet wrote: mmap()/brk() must give fresh NULL pages, but maybe madvise(MADV_DONTNEED) can relax this requirement (if the pages were reclaimed, then a page fault could bring a new page with random content) ...provided that it doesn't leak

Re: [PATCH] block2mtd lockdep_init_map warning

2008-01-07 Thread Jörn Engel
On Mon, 7 January 2008 11:05:26 +0100, Peter Zijlstra wrote: Would something like this work for people? Looks a lot better than what I thought of. However, does the #ifdef within is_module_address() make sense when afaict lockdep is the only caller of that function? Looks as if the whole

Re: [noob q. on block layer] block IO read-ahead during sequential *write*?

2008-01-07 Thread Jörn Engel
On Mon, 7 January 2008 13:25:09 +0100, Frantisek Rysanek wrote: let me start with a simple example. The following commands: cp /dev/zero /dev/hda dd if=/dev/zero of=/dev/hda [bs=512] both have one common side-effect: apart from the disk being properly overwritten with zeroes, the

Re: [PATCH] Claim maintainership for block2mtd and update email addresses

2008-01-07 Thread Jörn Engel
On Mon, 7 January 2008 15:23:00 -0800, Andrew Morton wrote: On Sun, 6 Jan 2008 14:56:01 +0100 J__rn Engel [EMAIL PROTECTED] wrote: You found a new one! That make a round dozen, I believe. http://logfs.org/logfs/joern - * Copyright (C) 2004-2006 Jörn Engel [EMAIL PROTECTED] + * Copyright

Re: [RFC PATCH] greatly reduce SLOB external fragmentation

2008-01-10 Thread Jörn Engel
On Thu, 10 January 2008 11:49:25 -0600, Matt Mackall wrote: b) grouping objects of the same -type- (not size) together should mean they have similar lifetimes and thereby keep fragmentation low (b) is known to be false, you just have to look at our dcache and icache pinning. (b) is

Re: [00/41] Large Blocksize Support V7 (adds memmap support)

2007-09-16 Thread Jörn Engel
On Sun, 16 September 2007 00:30:32 +0200, Andrea Arcangeli wrote: Movable? I rather assume all slab allocations aren't movable. Then slab defrag can try to tackle on users like dcache and inodes. Keep in mind that with the exception of updatedb, those inodes/dentries will be pinned and you

Re: [00/41] Large Blocksize Support V7 (adds memmap support)

2007-09-16 Thread Jörn Engel
On Sat, 15 September 2007 01:44:49 -0700, Andrew Morton wrote: On Tue, 11 Sep 2007 14:12:26 +0200 Jörn Engel [EMAIL PROTECTED] wrote: While I agree with your concern, those numbers are quite silly. The chances of 99.8% of pages being free and the remaining 0.2% being perfectly spread

Re: [00/41] Large Blocksize Support V7 (adds memmap support)

2007-09-16 Thread Jörn Engel
On Sun, 16 September 2007 11:15:36 -0700, Linus Torvalds wrote: On Sun, 16 Sep 2007, Jörn Engel wrote: I have been toying with the idea of having seperate caches for pinned and movable dentries. Downside of such a patch would be the number of memcpy() operations when moving dentries

Re: [00/41] Large Blocksize Support V7 (adds memmap support)

2007-09-16 Thread Jörn Engel
On Mon, 17 September 2007 00:06:24 +0200, Goswin von Brederlow wrote: How probable is it that the dentry is needed again? If you copy it and it is not needed then you wasted time. If you throw it out and it is needed then you wasted time too. Depending on the probability one of the two is

Re: [00/41] Large Blocksize Support V7 (adds memmap support)

2007-09-18 Thread Jörn Engel
On Tue, 18 September 2007 11:00:40 +0100, Mel Gorman wrote: We still lack data on what sort of workloads really benefit from large blocks Compressing filesystems like jffs2 and logfs gain better compression ratio with larger blocks. Going from 4KiB to 64KiB gave somewhere around 10% benefit

Re: x86_64: Make sparsemem/vmemmap the default memory model

2007-11-13 Thread Jörn Engel
On Mon, 12 November 2007 20:41:10 -0800, Christoph Lameter wrote: On Mon, 12 Nov 2007, Ray Lee wrote: Discontig obviously needs to die. However, FlatMem is consistently faster, averaging about 2.1% better overall for your numbers above. Is the page allocator not, erm, a fast path, where

Re: [BUG] New Kernel Bugs

2007-11-13 Thread Jörn Engel
On Tue, 13 November 2007 15:18:07 -0500, Mark Lord wrote: I just find it weird that something can be known broken for several -rc* kernels before I happen to install it, discover it's broken on my own machine, and then I track it down, fix it, and submit the patch, generally all within a

Re: [BUG] New Kernel Bugs

2007-11-13 Thread Jörn Engel
On Tue, 13 November 2007 13:56:58 -0800, Andrew Morton wrote: It's relatively common that a regression in subsystem A will manifest as a failure in subsystem B, and the report initially lands on the desk of the subsystem B developers. But that's OK. The subsystem B people are the ones

Re: x86_64: Make sparsemem/vmemmap the default memory model

2007-11-13 Thread Jörn Engel
On Tue, 13 November 2007 13:52:17 -0800, Christoph Lameter wrote: Could you run your own test to verify? You bastard! You know I'm too lazy to do that. ;) As long as the order-0 number is stable across multiple runs I don't mind. The numbers just looked suspiciously as if they were not

Re: [alsa-devel] [BUG] New Kernel Bugs

2007-11-15 Thread Jörn Engel
On Thu, 15 November 2007 13:26:51 +0100, Rene Herman wrote: Can you please just shelve this crap? You have a way of knowing that ALSA will accept you and that is knowing or assuming that the ALSA project doesn't consist of drooling retards. Well, my experience with moderation has been that

[PATCH] Document I_SYNC and I_DATASYNC

2007-11-15 Thread Jörn Engel
After some archeology (see http://logfs.org/logfs/inode_state_bits) I finally figured out what the three I_DIRTY bits do. Maybe others would prefer less effort to reach this insight. Signed-off-by: Jörn Engel [EMAIL PROTECTED] --- include/linux/fs.h |8 1 file changed, 4

Re: Treat disk space like memory space

2007-11-16 Thread Jörn Engel
On Fri, 16 November 2007 10:30:12 -0800, H. Peter Anvin wrote: This, by the way, has been discussed on and off -- often in the context of undelete (which is an identical problem.) The problem usually is that performance of real storage users suffer because of locality issues. However,

Re: [RFC] Documentation about unaligned memory access

2007-11-30 Thread Jörn Engel
On Fri, 23 November 2007 00:15:53 +, Daniel Drake wrote: What's the definition of an unaligned access? = Unaligned memory accesses occur when you try to read N bytes of data starting from an address that is not evenly divisible by N (i.e.

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-11-30 Thread Jörn Engel
On Fri, 30 November 2007 14:43:12 +0100, Ingo Molnar wrote: http://redhat.com/~mingo/latency-tracing-patches/latency-tracing-v2.6.24-rc3.combo.patch does it work any better? It compiles. It boots with a 512M RAM (384M was too little with all the other debug options on). But it seems

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-11-30 Thread Jörn Engel
On Thu, 15 November 2007 20:36:12 +0100, Ingo Molnar wrote: * Ingo Molnar [EMAIL PROTECTED] wrote: pick up the latest latency tracer patch from: sorry, wrong URLs, the correct links are: http://redhat.com/~mingo/latency-tracing-patches/latency-tracer-v2.6.24-rc2-git5-combo.patch

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-11-30 Thread Jörn Engel
On Fri, 30 November 2007 14:35:46 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: kernel/sched.c:3384: warning: ‘struct prio_array’ declared inside parameter list kernel/sched.c:3384: warning: its scope is only this definition or declaration, which is probably

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-01 Thread Jörn Engel
On Fri, 30 November 2007 19:46:25 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: It compiles. It boots with a 512M RAM (384M was too little with all the other debug options on). But it seems to lock up when running trace-cmd. On a rerun it locks up again

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-01 Thread Jörn Engel
On Sat, 1 December 2007 19:32:56 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: I have to change my qemu setup a little to see the top of those dumps... btw., if you start qemu like this: qemu -cdrom ./cdrom.iso -hda ./hda.img -boot c -full-screen -kernel ~/bzImage

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-01 Thread Jörn Engel
On Sat, 1 December 2007 21:54:56 +0100, Ingo Molnar wrote: * J??rn Engel [EMAIL PROTECTED] wrote: stopped custom tracer. BUG: spinlock recursion on CPU#0, sh/953 lock: c030f280, .magic: dead4ead, .owner: sh/953, .owner_cpu: 0 Pid: 953, comm: sh Not tainted 2.6.24-rc3-ge1cca7e8-dirty

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 09:56:08 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: ah. You should mark pit_read() function as notrace. PIT clocksource is rare. (add the 'notrace' word to the function prototype) Hardly a change at all. Apart from some offsets

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 12:31:43 +0100, Jörn Engel wrote: This time not even the offsets have changed. Dump is identical. After another ten or so notrace annotations throughout the spinlock code, the latency tracer appears to work. Not sure how many useful information is missing through all

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 14:57:11 +0100, Ingo Molnar wrote: hm, do you have CONFIG_FRAME_POINTERS=y, i.e. are the dumps reliable? I do. Went through 10odd runs and annotated the function right below mcount each time. Seems to work now. Trouble is that it doesn't solve my real problem at

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 13:31:25 +0100, Jörn Engel wrote: After another ten or so notrace annotations throughout the spinlock code, the latency tracer appears to work. Not sure how many useful information is missing through all the annotations, though. And here is a patch with the needed

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 16:47:46 +0100, Ingo Molnar wrote: well what does the trace say, where do the delays come from? To get a quick overview you can make tracing lighter weight by doing: echo 0 /proc/sys/kernel/mcount_enabled echo 1 /proc/sys/kernel/trace_syscalls I mistyped and

Re: Kernel Development Objective-C

2007-12-02 Thread Jörn Engel
On Sat, 1 December 2007 21:59:31 +0200, Avi Kivity wrote: Object orientation in C leaves much to be desired; see the huge number of void pointers and container_of()s in the kernel. While true, this isn't such a bad problem. A language really sucks when it tries to disallow something useful.

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 21:07:22 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: Result looked like a livelock and finally convinced me to abandon the latency tracer. Sorry, but it appears to be the right tool for the wrong job. hm, we routinely use it in -rt

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 21:45:59 +0100, Ingo Molnar wrote: to capture a 1 second trace of what the system is doing. I think your troubles are due to running it within a qemu guest - that is not a typical utilization so you are on unchartered waters. Looks like it. Guess I'll switch to

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 21:45:59 +0100, Ingo Molnar wrote: to capture that trace i did not use -rt, i just patched latest -git with: http://people.redhat.com/mingo/latency-tracing-patches/latency-tracing-v2.6.24-rc3.combo.patch (this has your fixes included already) have done:

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-02 Thread Jörn Engel
On Sun, 2 December 2007 22:19:00 +0100, Ingo Molnar wrote: * Jörn Engel [EMAIL PROTECTED] wrote: Maybe one more thing: can you send me the config you used for the setup above? I'd like to know whether qemu or my config is to blame. sure - attached. After an eternity of compile time

Re: [BUG] Strange 1-second pauses during Resume-from-RAM

2007-12-03 Thread Jörn Engel
On Mon, 3 December 2007 01:57:02 +0100, Jörn Engel wrote: After an eternity of compile time, this config does generate some useful output. qemu is not to blame. Or is it? The output definitely looks suspicious. Large amounts of code get processed within a microsecond, while

Re: solid state drive access and context switching

2007-12-04 Thread Jörn Engel
On Tue, 4 December 2007 13:54:21 -0800, Jared Hulbert wrote: Maybe I'm missing something but I don't see it. We want a block interface for these devices, we just need a faster slimmer interface. Maybe a new mtdblock interface that doesn't do erase would be the place for? Doesn't do erase?

Re: [x86] kernel/audit.c cleanup according to checkpatch.pl

2008-01-03 Thread Jörn Engel
On Thu, 3 January 2008 14:19:25 +0300, Cyrill Gorcunov wrote: @@ -232,7 +232,8 @@ void audit_log_lost(const char *message) if (print) { printk(KERN_WARNING -audit: audit_lost=%d audit_rate_limit=%d audit_backlog_limit=%d\n, +

[PATCH] Claim maintainership for block2mtd and update email addresses

2008-01-06 Thread Jörn Engel
to cause trouble until the end of this century. Signed-off-by: Jörn Engel [EMAIL PROTECTED] --- MAINTAINERS | 10 -- drivers/mtd/devices/block2mtd.c |4 ++-- drivers/mtd/devices/phram.c |4 ++-- drivers/mtd/maps/mtx-1_flash.c |2 +- scripts/checkstack.pl

Re: [PATCH] block2mtd lockdep_init_map warning

2008-01-06 Thread Jörn Engel
On Sun, 6 January 2008 14:11:47 -0500, Erez Zadok wrote: The problem appears to be an interaction of two components--module loading and lockdep--that's perhaps why it wasn't given enough attention. Correct. For modules lockdep depends on initializations done after module_init has finished.

Re: fix typo in mtd kconfig

2007-10-17 Thread Jörn Engel
David, will you take this patch? Signed-off-by: Dave Jones [EMAIL PROTECTED] Signed-off-by: Joern Engel [EMAIL PROTECTED] diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 8f9c3ba..246d451 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -300,7 +300,7

Re: [BLOCK2MTD] WARNING: at kernel/lockdep.c:2331 lockdep_init_map()

2007-10-19 Thread Jörn Engel
On Fri, 19 October 2007 13:53:40 -0400, Erez Zadok wrote: I've been having this problem for some time with mtd, which I use to mount jffs2 images (for unionfs testing). I've seen it in several recent major kernels, including 2.6.24. Here's the sequence of ops I perform: Since when roughly?

Re: [PATCH] eccbuf is statically defined and always evaluate to true

2007-10-19 Thread Jörn Engel
On Fri, 19 October 2007 19:26:35 +0200, Samuel Tardieu wrote: --- drivers/mtd/devices/doc2000.c |4 ++-- drivers/mtd/devices/doc2001plus.c |2 +- 2 files changed, 3 insertions(+), 3 deletions(-) Acked-by: Joern Engel [EMAIL PROTECTED] I assume you don't actually use this

Re: [BLOCK2MTD] WARNING: at kernel/lockdep.c:2331 lockdep_init_map()

2007-10-20 Thread Jörn Engel
On Fri, 19 October 2007 16:04:10 -0400, Erez Zadok wrote: In message [EMAIL PROTECTED], =?utf-8?B?SsO2cm4=?= Engel writes: Since when roughly? 2.6.20ish? Before? Yeah, I guess around that time. If you want, I could go back and test each of my backports and see if it has the lockdep

Re: [BLOCK2MTD] WARNING: at kernel/lockdep.c:2331 lockdep_init_map()

2007-10-21 Thread Jörn Engel
On Fri, 19 October 2007 20:31:29 +0200, Peter Zijlstra wrote: BUG: key f88e1340 not in .data! WARNING: at kernel/lockdep.c:2331 lockdep_init_map() [c0102bc2] show_trace_log_lvl+0x1a/0x2f [c0103692] show_trace+0x12/0x14 [c01037b2] dump_stack+0x15/0x17 [c0125432]

  1   2   3   4   5   6   >