- 16 Oct, 2007 40 commits
-
-
Nick Piggin authored
Implement new aops for some of the simpler filesystems. Signed-off-by:
Nick Piggin <npiggin@suse.de> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Nick Piggin authored
Restore the KERNEL_DS optimisation, especially helpful to the 2copy write path. This may be a pretty questionable gain in most cases, especially after the legacy 2copy write path is removed, but it doesn't cost much. Signed-off-by:
-
Dmitry Monakhov authored
Partial write can be easily supported by LO_CRYPT_NONE mode, but it is not easy in LO_CRYPT_CRYPTOAPI case, because of its block nature. I don't know who still used cryptoapi, but theoretically it is possible. So let's leave things as they are. Loop device doesn't support partial write before Nick's "write_begin/write_end" patch set, and let's it behave the same way after. Signed-off-by:
Dmitriy Monakhov <dmonakhov@openvz.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Nick Piggin authored
These are intended to replace prepare_write and commit_write with more flexible alternatives that are also able to avoid the buffered write deadlock problems efficiently (which prepare_write is unable to do). [mark.fasheh@oracle.com: API design contributions, code review and fixes] [akpm@linux-foundation.org: various fixes] [dmonakhov@sw.ru: new aop block_write_begin fix] Signed-off-by:
Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by:
-
Nick Piggin authored
New buffers against uptodate pages are simply be marked uptodate, while the buffer_new bit remains set. This causes error-case code to zero out parts of those buffers because it thinks they contain stale data: wrong, they are actually uptodate so this is a data loss situation. Fix this by actually clearning buffer_new and marking the buffer dirty. It makes sense to always clear buffer_new before setting a buffer uptodate. Signed-off-by:
-
Nick Piggin authored
Add an iterator data structure to operate over an iovec. Add usercopy operators needed by generic_file_buffered_write, and convert that function over. Signed-off-by:
-
Nick Piggin authored
Modify the core write() code so that it won't take a pagefault while holding a lock on the pagecache page. There are a number of different deadlocks possible if we try to do such a thing: 1. generic_buffered_write 2. lock_page 3. prepare_write 4. unlock_page+vmtruncate 5. copy_from_user 6. mmap_sem(r) 7. handle_mm_fault 8. lock_page (filemap_nopage) 9. commit_write 10. unlock_page a. sys_munmap / sys_mlock / others b. mmap_sem(w) c. make_pages_present d. get_user_pages e. handle_mm_fault f. lock_page (filemap_nopage) 2,8 - recursive deadlock if page is same 2,8;2,8 - ABBA deadlock is page is different 2,6;b,f - ABBA deadlock if page is same The solution is as follows: 1. If we find the destination page is uptodate, continue as normal, but use atomic usercopies which do not take pagefaults and do not zero the uncopied tail of the destination. The destination is already uptodate, so we can commit_write the full length even if there was a partial copy: it does not matter that the tail was not modified, because if it is dirtied and written back to disk it will not cause any problems (uptodate *means* that the destination page is as new or newer than the copy on disk). 1a. The above requires that fault_in_pages_readable correctly returns access information, because atomic usercopies cannot distinguish between non-present pages in a readable mapping, from lack of a readable mapping. 2. If we find the destination page is non uptodate, unlock it (this could be made slightly more optimal), then allocate a temporary page to copy the source data into. Relock the destination page and continue with the copy. However, instead of a usercopy (which might take a fault), copy the data from the pinned temporary page via the kernel address space. (also, rename maxlen to seglen, because it was confusing) This increases the CPU/memory copy cost by almost 50% on the affected workloads. That will be solved by introducing a new set of pagecache write aops in a subsequent patch. Signed-off-by: -
Nick Piggin authored
Hide some of the open-coded nr_segs tests into the iovec helpers. This is all to simplify generic_file_buffered_write, because that gets more complex in the next patch. Signed-off-by:
-
Nick Piggin authored
Quite a bit of code is used in maintaining these "cached pages" that are probably pretty unlikely to get used. It would require a narrow race where the page is inserted concurrently while this process is allocating a page in order to create the spare page. Then a multi-page write into an uncached part of the file, to make use of it. Next, the buffered write path (and others) uses its own LRU pagevec when it should be just using the per-CPU LRU pagevec (which will cut down on both data and code size cacheline footprint). Also, these private LRU pagevecs are emptied after just a very short time, in contrast with the per-CPU pagevecs that are persistent. Net result: 7.3 times fewer lru_lock acquisitions required to add the pages to pagecache for a bulk write (in 4K chunks). [this gets rid of some cond_resched() calls in readahead.c and mpage.c due to clashes in -mm. What put them there, and why? ] Signed-off-by:
-
Nick Piggin authored
If prepare_write fails with AOP_TRUNCATED_PAGE, or if commit_write fails, then we may have failed the write operation despite prepare_write having instantiated blocks past i_size. Fix this, and consolidate the trimming into one place. Signed-off-by:
-
Nick Piggin authored
Allow CONFIG_DEBUG_VM to switch off the prefaulting logic, to simulate the Makes the race much easier to hit. This is useful for demonstration and testing purposes, but is removed in a subsequent patch. Signed-off-by:
-
Andrew Morton authored
Rename some variables and fix some types. Signed-off-by:
Andrew Morton <akpm@osdl.org> Signed-off-by:
-
Andrew Morton authored
This reverts commit 6527c2bd, which fixed the following bug: When prefaulting in the pages in generic_file_buffered_write(), we only faulted in the pages for the firts segment of the iovec. If the second of successive segment described a mmapping of the page into which we're write()ing, and that page is not up-to-date, the fault handler tries to lock the already-locked page (to bring it up to date) and deadlocks. An exploit for this bug is in writev-deadlock-demo.c, in http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz. (These demos assume blocksize < PAGE_CACHE_SIZE). The problem with this fix is that it takes the kernel back to doing a single prepare_write()/commit_write() per iovec segment. So in the worst case we'll run prepare_write+commit_write 1024 times where we previously would have run it once. The other problem with the fix is that it fix all the locking problems. <insert numbers obtained via ext3-tools's writev-speed.c here> And apparently this change killed NFS overwrite performance, because, I suppose, it talks to the server for each prepare_write+commit_write. So just back that patch out - we'll be fixing the deadlock by other means. Nick says: also it only ever actually papered over the bug, because after faulting in the pages, they might be unmapped or reclaimed. Signed-off-by:
-
Andrew Morton authored
This reverts commit 81b0c871, which was a bugfix against 6527c2bd ("[PATCH] generic_file_buffered_write(): deadlock on vectored write"), which we also revert. Signed-off-by:
-
Nick Piggin authored
Revert the patch from Neil Brown to optimise NFSD writev handling. Cc: Neil Brown <neilb@suse.de> Signed-off-by:
-
Hisashi Hifumi authored
While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by:
Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by:
-
Lee Schermerhorn authored
Allow an application to query the memories allowed by its context. Updated numa_memory_policy.txt to mention that applications can use this to obtain allowed memories for constructing valid policies. TODO: update out-of-tree libnuma wrapper[s], or maybe add a new wrapper--e.g., numa_get_mems_allowed() ? Also, update numa syscall man pages. Tested with memtoy V>=0.13. Signed-off-by:
Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by:
Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by:
-
Rik van Riel authored
The current VM can get itself into trouble fairly easily on systems with a small ZONE_HIGHMEM, which is common on i686 computers with 1GB of memory. On one side, page_alloc() will allocate down to zone->pages_low, while on the other side, kswapd() and balance_pgdat() will try to free memory from every zone, until every zone has more free pages than zone->pages_high. Highmem can be filled up to zone->pages_low with page tables, ramfs, vmalloc allocations and other unswappable things quite easily and without many bad side effects, since we still have a huge ZONE_NORMAL to do future allocations from. However, as long as the number of free pages in the highmem zone is below zone->pages_high, kswapd will continue swapping things out from ZONE_NORMAL, too! Sami Farin managed to get his system into a stage where kswapd had freed about 700MB of low memory and was still "going strong". The attached patch will make kswapd stop paging out data from zones when there is more than enough memory free. We do go above zone->pages_high in order to keep pressure between zones equal in normal circumstances, but the patch should prevent the kind of excesses that made Sami's computer totally unusable. Signed-off-by:
Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Jesper Juhl authored
vmalloc() returns a void pointer, so there's no need to cast its return value in mm/page_alloc.c::zone_wait_table_init(). Signed-off-by:
Jesper Juhl <jesper.juhl@gmail.com> Signed-off-by:
-
Jeff Moyer authored
A while back, Nick Piggin introduced a patch to reduce the node memory usage for small files (commit cfd9b7df): -#define RADIX_TREE_MAP_SHIFT 6 +#define RADIX_TREE_MAP_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) Unfortunately, he didn't take into account the fact that the calculation of the maximum path was based on an assumption of having to round up: #define RADIX_TREE_MAX_PATH (RADIX_TREE_INDEX_BITS/RADIX_TREE_MAP_SHIFT + 2) So, if CONFIG_BASE_SMALL is set, you will end up with a RADIX_TREE_MAX_PATH that is one greater than necessary. The practical upshot of this is just a bit of wasted memory (one long in the height_to_maxindex array, an extra pre-allocated radix tree node per cpu, and extra stack usage in a couple of functions), but it seems worth getting right. It's also worth noting that I never build with CONFIG_BASE_SMALL. What I did to test this was duplicate the code in a small user-space program and check the results of the calculations for max path and the contents of the height_to_maxindex array. Signed-off-by:
Jeff Moyer <jmoyer@redhat.com> Acked-by:
Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Nick Piggin authored
nobh mode error handling is not just pretty slack, it's wrong. One cannot zero out the whole page to ensure new blocks are zeroed, because it just brings the whole page "uptodate" with zeroes even if that may not be the correct uptodate data. Also, other parts of the page may already contain dirty data which would get lost by zeroing it out. Thirdly, the writeback of zeroes to the new blocks will also erase existing blocks. All these conditions are pagecache and/or filesystem corruption. The problem comes about because we didn't keep track of which buffers actually are new or old. However it is not enough just to keep only this state, because at the point we start dirtying parts of the page (new blocks, with zeroes), the handling of IO errors becomes impossible without buffers because the page may only be partially uptodate, in which case the page flags allone cannot capture the state of the parts of the page. So allocate all buffers for the page upfront, but leave them unattached so that they don't pick up any other references and can be freed when we're done. If the error path is hit, then zero the new buffers as the regular buffer path does, then attach the buffers to the page so that it can actually be written out correctly and be subject to the normal IO error handling paths. As an upshot, we save 1K of kernel stack on ia64 or powerpc 64K page systems. Signed-off-by:
-
Dmitry Monakhov authored
Move duplicated code from end_buffer_read_XXX methods to separate helper function. Signed-off-by:
-
Christoph Lameter authored
A NULL pointer means that the object was not allocated. One cannot determine the size of an object that has not been allocated. Currently we return 0 but we really should BUG() on attempts to determine the size of something nonexistent. krealloc() interprets NULL to mean a zero sized object. Handle that separately in krealloc(). Signed-off-by:
Pekka Enberg <penberg@cs.helsinki.fi> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by:
-
Dean Nelson authored
The calculation of pgoff in do_linear_fault() should use PAGE_SHIFT and not PAGE_CACHE_SHIFT since vma->vm_pgoff is in units of PAGE_SIZE and not PAGE_CACHE_SIZE. At the moment linux/pagemap.h has PAGE_CACHE_SHIFT defined as PAGE_SHIFT, but should that ever change this calculation would break. Signed-off-by:
Dean Nelson <dcn@sgi.com> Acked-by:
-
Satyam Sharma authored
Considering kfree(NULL) would normally occur only in error paths and kfree(ZERO_SIZE_PTR) is uncommon as well, so let's use unlikely() for the condition check in SLUB's and SLOB's kfree() to optimize for the common case. SLAB has this already. Signed-off-by:
Satyam Sharma <satyam@infradead.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by:
-
Martin Schwidefsky authored
Move the definitions of struct mm_struct and struct vma_area_struct to include/mm_types.h. This allows to define more function in asm/pgtable.h and friends with inline assemblies instead of macros. Compile tested on i386, powerpc, powerpc64, s390-32, s390-64 and x86_64. [aurelien@aurel32.net: build fix] Signed-off-by:
Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by:
Aurelien Jarno <aurelien@aurel32.net> Signed-off-by:
-
Nick Piggin authored
Rather than sign direct radix-tree pointers with a special bit, sign the indirect one that hangs off the root. This means that, given a lookup_slot operation, the invalid result will be differentiated from the valid (previously, valid results could have the bit either set or clear). This does not affect slot lookups which occur under lock -- they can never return an invalid result. Is needed in future for lockless pagecache. Signed-off-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by:
-
Nick Piggin authored
__add_to_swap_cache unconditionally sets the page locked, which can be a bit alarming to the unsuspecting reader: in the code paths where the page is visible to other CPUs, the page should be (and is) already locked. Instead, just add a check to ensure the page is locked here, and teach the one path relying on the old behaviour to call SetPageLocked itself. [hugh@veritas.com: locking fix] Signed-off-by:
Hugh Dickins <hugh@veritas.com> Signed-off-by:
-
Nick Piggin authored
find_lock_page does not need to recheck ->index because if the page is in the right mapping then the index must be the same. Also, tree_lock does not need to be retaken after the page is locked in order to test that ->mapping has not changed, because holding the page lock pins its mapping. Signed-off-by:
-
Nick Piggin authored
Probing pages and radix_tree_tagged are lockless operations with the lockless radix-tree. Convert these users to RCU locking rather than using tree_lock. Signed-off-by:
-
Nick Piggin authored
The commit b5810039 contains the note A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. And indeed this cacheline bouncing has shown up on large SGI systems. There was a situation where an Altix system was essentially livelocked tearing down ZERO_PAGE pagetables when an HPC app aborted during startup. This situation can be avoided in userspace, but it does highlight the potential scalability problem with refcounting ZERO_PAGE, and corner cases where it can really hurt (we don't want the system to livelock!). There are several broad ways to fix this problem: 1. add back some special casing to avoid refcounting ZERO_PAGE 2. per-node or per-cpu ZERO_PAGES 3. remove the ZERO_PAGE completely I will argue for 3. The others should also fix the problem, but they result in more complex code than does 3, with little or no real benefit that I can see. Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a false optimisation: if an application is performance critical, it would not be doing many read faults of new memory, or at least it could be expected to write to that memory soon afterwards. If cache or memory use is critical, it should not be working with a significant number of ZERO_PAGEs anyway (a more compact representation of zeroes should be used). As a sanity check -- mesuring on my desktop system, there are never many mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not increase much without it. When running a make -j4 kernel compile on my dual core system, there are about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000 ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second is torn down without being COWed). So removing ZERO_PAGE will save 1,000 page faults per second when running kbuild, while keeping it only saves less than 1 page clearing operation per second. 1 page clear is cheaper than a thousand faults, presumably, so there isn't an obvious loss. Neither the logical argument nor these basic tests give a guarantee of no regressions. However, this is a reasonable opportunity to try to remove the ZERO_PAGE from the pagefault path. If it is found to cause regressions, we can reintroduce it and just avoid refcounting it. The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see much use to them except on benchmarks. All other users of ZERO_PAGE are converted just to use ZERO_PAGE(0) for simplicity. We can look at replacing them all and maybe ripping out ZERO_PAGE completely when we are more satisfied with this solution. Signed-off-by:
-
Christoph Lameter authored
This gets rid of all kmalloc caches larger than page size. A kmalloc request larger than PAGE_SIZE > 2 is going to be passed through to the page allocator. This works both inline where we will call __get_free_pages instead of kmem_cache_alloc and in __kmalloc. kfree is modified to check if the object is in a slab page. If not then the page is freed via the page allocator instead. Roughly similar to what SLOB does. Advantages: - Reduces memory overhead for kmalloc array - Large kmalloc operations are faster since they do not need to pass through the slab allocator to get to the page allocator. - Performance increase of 10%-20% on alloc and 50% on free for PAGE_SIZEd allocations. SLUB must call page allocator for each alloc anyways since the higher order pages which that allowed avoiding the page alloc calls are not available in a reliable way anymore. So we are basically removing useless slab allocator overhead. - Large kmallocs yields page aligned object which is what SLAB did. Bad things like using page sized kmalloc allocations to stand in for page allocate allocs can be transparently handled and are not distinguishable from page allocator uses. - Checking for too large objects can be removed since it is done by the page allocator. Drawbacks: - No accounting for large kmalloc slab allocations anymore - No debugging of large kmalloc slab allocations. Signed-off-by:
-
Fengguang Wu authored
Convert some 'unsigned long' to pgoff_t. Signed-off-by:
Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by:
-
Fengguang Wu authored
- remove unused local next_index in do_generic_mapping_read() - remove a redudant page_cache_read() declaration Signed-off-by:
-
Fengguang Wu authored
Remove the size limit max_sectors_kb imposed on max_readahead_kb. The size restriction is unreasonable. Especially when max_sectors_kb cannot grow larger than max_hw_sectors_kb, which can be rather small for some disk drives. Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by:
Jens Axboe <jens.axboe@oracle.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by:
-
Fengguang Wu authored
Remove VM_MAX_CACHE_HIT, MAX_RA_PAGES and MIN_RA_PAGES. Signed-off-by:
-
Fengguang Wu authored
The local copy of ra in do_generic_mapping_read() can now go away. It predates readanead(req_size). In a time when the readahead code was called on *every* single page. Hence a local has to be made to reduce the chance of the readahead state being overwritten by a concurrent reader. More details in: Linux: Random File I/O Regressions In 2.6 <http://kerneltrap.org/node/3039> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Fengguang Wu authored
This is a simplified version of the pagecache context based readahead. It handles the case of multiple threads reading on the same fd and invalidating each others' readahead state. It does the trick by scanning the pagecache and recovering the current read stream's readahead status. The algorithm works in a opportunistic way, in that it does not try to detect interleaved reads _actively_, which requires a probe into the page cache (which means a little more overhead for random reads). It only tries to handle a previously started sequential readahead whose state was overwritten by another concurrent stream, and it can do this job pretty well. Negative and positive examples(or what you can expect from it): 1) it cannot detect and serve perfect request-by-request interleaved reads right: time stream 1 stream 2 0 1 1 1001 2 2 3 1002 4 3 5 1003 6 4 7 1004 8 5 9 1005 Here no single readahead will be carried out. 2) However, if it's two concurrent reads by two threads, the chance of the initial sequential readahead be started is huge. Once the first sequential readahead is started for a stream, this patch will ensure that the readahead window continues to rampup and won't be disturbed by other streams. time stream 1 stream 2 0 1 1 2 2 1001 3 3 4 1002 5 1003 6 4 7 5 8 1004 9 6 10 1005 11 7 12 1006 13 1007 Here stream 1 will start a readahead at page 2, and stream 2 will start its first readahead at page 1003. From then on the two streams will be served right. Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by:
-
Fengguang Wu authored
Introduce radix_tree_next_hole(root, index, max_scan) to scan radix tree for the first hole. It will be used in interleaved readahead. The implementation is dumb and obviously correct. It can help debug(and document) the possible smart one in future. Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Fengguang Wu authored
Combine the file_ra_state members unsigned long prev_index unsigned int prev_offset into loff_t prev_pos It is more consistent and better supports huge files. Thanks to Peter for the nice proposal! [akpm@linux-foundation.org: fix shift overflow] Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by:
-
