summaryrefslogtreecommitdiffstats
path: root/source3/smbd/aio.c
Commit message (Collapse)AuthorAgeFilesLines
...
* s3: Work better without the aio sighandlerVolker Lendecke2010-07-181-7/+22
| | | | Refuse async I/O if we can't set up the signal handler
* Fix the build in the non WITH_AIO case (sorry).Jeremy Allison2010-06-101-0/+20
|
* Implement AIO in SMB2. Doesn't allow cancel calls yet (to be added).Jeremy Allison2010-06-101-0/+281
| | | | Jeremy.
* Make aio_ex owned by a talloc context, not neccessarily on the null context.Jeremy Allison2010-06-071-8/+12
|
* Move "write_though" into aio_ex struct.Jeremy Allison2010-06-071-5/+5
|
* wait_for_aio_completion() should return 0 on non-aio compiled case.Jeremy Allison2010-06-041-1/+1
|
* Rename req -> smbreq.Jeremy Allison2010-06-041-26/+26
|
* Change smbd_aio_complete_mid() -> smbd_aio_complete_aio_ex(). SimplifiesJeremy Allison2010-06-041-32/+4
| | | | | | the code and eliminates find_aio_ex(). Jeremy.
* Move to using a DATA_BLOB inside of struct aio_extra, not a char *.Jeremy Allison2010-06-021-16/+16
| | | | | | Will make using AIO in SMB2 easier. Jeremy.
* Don't use sigev_value.sival_int to just store the mid, use ↵Jeremy Allison2010-06-011-38/+26
| | | | | | | | | sigev_value.sival_ptr to store the private data structure. This allows easier use from SMB2. Ensure aio is initialized before the aio_pending_size check else aio will never be used. Jeremy.
* This patch looks bigger than it is. It does 2 things. 1). Renames smbpid -> ↵Jeremy Allison2010-05-071-2/+2
| | | | | | smblctx in our locking code. 2). Widens smblctx to 64-bits internally. Preparing to use the SMB2 handle as the locking context. Jeremy.
* Move to using 64-bit mid values in our internal open file database.Jeremy Allison2010-04-121-15/+23
| | | | | | | This will allow us to share logic much easier between SMB1 and SMB2 servers. Jeremy
* Fix issue with aio where r/w lock wasn't kept across aio read operations.Jeremy Allison2010-04-051-23/+56
| | | | | | | | Change schedule_aio_read_and_X/schedule_aio_write_and_X to return NTSTATUS. Move the grant and release of the lock into the aio code. Jeremy
* Move initialize_async_io_handler() inside of smbd/aio.c.Jeremy Allison2010-04-011-34/+42
| | | | | | Call from actual aio read or write. No reason to call this globally on startup. Jeremy.
* Remove use of "int ret" when we already have errcode.Jeremy Allison2009-10-131-13/+8
| | | | Jeremy.
* Catch one more erroneous use of errno.Jeremy Allison2009-10-131-1/+1
| | | | Jeremy.
* correctly handle aio_error() and errnoOlaf Flebbe2009-10-131-29/+24
|
* allow for outstanding_aio_calls to be decrementedOlaf Flebbe2009-09-301-2/+4
|
* Don't defer a talloc_move'd pointer.Jeremy Allison2009-09-281-1/+1
| | | | Jeremy.
* s3: Change fsp->fsp_name to be an smb_filename struct!Tim Prouty2009-07-201-14/+14
|
* Set SIGRTMIN to NSIGTimur I. Bakeyev2009-06-081-3/+0
| | | | | | | | | | | | | | In the includes we define SIGRTMIN to 32 if it's not defined already. This value could be fairly low and it's better to use NSIG(number of defined signals) as the lower mark for the available signals. We have similar defenition in the source3/smbd/aio.c, which can be safely removed, as it comes from includes.h then. With regards, Timur Bakeyev. Signed-off-by: Stefan Metzmacher <metze@samba.org>
* Move down the become_root()/unbecome_root() calls into the VFS modulesVolker Lendecke2009-05-181-6/+0
| | | | | | The aio_fork module does not need this, as it does not communicate via signals but with pipes. Watching a strace log with those become_root() calls in aio.c is absolutely awful, and it does affect performance.
* s3:smbd: use new simplified snb_signing code in the serverStefan Metzmacher2009-03-231-8/+5
| | | | | | | | | We keep the seqnum/mid mapping in the smb_request structure. This also moves one global variable into the smbd_server_connection struct. metze
* s3:signing: the seqnum should only be decremented by 1 for ntcancel requestsStefan Metzmacher2009-03-061-4/+4
| | | | | | | | | [MS-SMB] 3.3.5.1 Receiving Any Message says that the seqnum is incremented by only for ntcancel requests for any other request it's by incremented by 2, even if it doesn't expect a response. metze
* s3 oplocks: Make the level2 oplock contention API more granularTim Prouty2009-02-091-1/+3
| | | | | | | | | | | | | | | | | | This replaces release_level2_oplocks_on_change with contend_level2_oplock_begin/end in order to contend level2 oplocks throughout an operation rather than just at the begining. This is necessary for some kernel oplock implementations, and also lays the groundwork for better correctness in Samba's standard level2 oplock handling. The next step for non-kernel oplocks is to add additional state to the share mode lock struct that prevents any new opens from granting oplocks while a contending operation is in progress. All operations that contend level 2 oplocks are now correctly spanned except for aio and synchronous writes. The two write paths both have non-trivial error paths that need extra care to get right. RAW-OPLOCK and the rest of 'make test' are still passing with this change.
* S3: New module interface for SMB message statistics gatheringtodd stecher2009-02-091-3/+5
| | | | | | | This changelist allows for the addition of custom performance monitoring modules through smb.conf. Entrypoints in the main message processing code have been added to capture the command, subop, ioctl, identity and message size statistics.
* Remove the global variable "chain_size"Volker Lendecke2009-01-311-4/+2
|
* s3:smbd: convert aio to use tevent_signalStefan Metzmacher2009-01-271-100/+50
| | | | metze
* s3:smbd: move all globals and static variables in globals.[ch]Stefan Metzmacher2009-01-081-16/+10
| | | | | | The goal is to move all this variables into a big context structure. metze
* Remove a direct inbuf reference (should have been removed with 8987641d...)Volker Lendecke2008-11-081-1/+1
|
* Rewrite aio.c to keep the whole smb_request structure, not just the inbufVolker Lendecke2008-11-041-75/+41
|
* Add construct_reply_common_req wrapperVolker Lendecke2008-11-041-1/+1
| | | | The goal is to remove the remaining direct calls to construct_reply_common.
* Fix nonempty blank linesVolker Lendecke2008-11-041-3/+3
|
* Use talloc for struct aio_extraVolker Lendecke2008-11-041-27/+14
|
* Make a comment match its function definitionVolker Lendecke2008-11-031-1/+1
|
* Make a [un]become_root wrap a bit tighterVolker Lendecke2008-11-021-7/+11
| | | | Sooner or later this would bite us.
* Remove a bunch of direct inbuf references by adding "vwv" to smb_requestVolker Lendecke2008-11-021-3/+3
|
* Fix aio on FreeBSD.Timur2008-09-151-1/+16
|
* become root for AIO operationsAndrew Tridgell2008-08-261-1/+7
| | | | | | | We need to become root for AIO read and write to allow the AIO thread to send a completion signal to the parent process when the IO completes (This used to be commit c548e5c69f9d8bc85a654f4d29d64c735a5e780b)
* Allow "max mux" async i/o requestsVolker Lendecke2008-02-241-5/+9
| | | | | | | | | | In the negprot reply, we allowed the client to issued "max mux" concurrent requests. The OS might allow less, for example AFAIK AIX has a configurable limit of concurrent AIO requests. We will fall back to sync operation for the requests that are too many when aio_read/aio_write return an error. Jeremy, please check! (This used to be commit 8f86f7f25c4eb71bbdfcc6bf2d12eaaae9a8d9ec)
* Export aio_request_done()Volker Lendecke2008-02-241-3/+9
| | | | | | This is for external modules implementing the Posix AIO API that not necessarily depend on the signal mechanism to indicate completion. (This used to be commit 9a069d306bb6f8a2cd51b8ba87b433884942d13f)
* AIO on streams does not work (yet...)Volker Lendecke2008-02-241-0/+12
| | | | (This used to be commit 1ba223f202a070a695581e0d7161473a3ebf4332)
* Update position information also for AIOVolker Lendecke2008-02-191-0/+5
| | | | | | | Necessary to survive RAW-SEEK with AIO enabled. Jeremy, please check! (This used to be commit e2ca12c2345c0e3916dd09d097b2ba1ce2989fa8)
* Inform level II oplock holders when we write using AIOVolker Lendecke2008-02-191-0/+2
| | | | | Jeremy, please check! (This used to be commit 81d823e026fb332a88b6e1f15030fe49719f2522)
* Re-enable async I/O for non-TSM systemsVolker Lendecke2008-01-301-2/+4
| | | | | | | | The logic was wrong: A "SMB_VFS_AIO_FORCE()==False" disabled async I/O, whereas a "SMB_VFS_AIO_FORCE()==True" should enforce it regardless of other settings. Alexander, please check! (This used to be commit 46882ad9927c95caadeb7fb03c1d7491bbe1fb22)
* Remove an unused variableVolker Lendecke2008-01-121-1/+0
| | | | (This used to be commit 24e719a1d432d5de022ab903457df0dd67c24b85)
* Remove redundant parameter fd from SMB_VFS_AIO_CANCEL().Michael Adam2008-01-081-1/+1
| | | | | Michael (This used to be commit 3c997ae0002d4c50e8899600c17ddf74ac61f6f0)
* Refactor the crypto code after a very helpful conversationJeremy Allison2008-01-041-13/+14
| | | | | | | with Volker. Mostly making sure we have data on the incoming packet type, not stored in the smb header. Jeremy. (This used to be commit c4e5a505043965eec77b5bb9bc60957e8f3b97c8)
* Fix the buildVolker Lendecke2007-12-271-2/+3
| | | | (This used to be commit 7fb858b350856d626fed6f062029fcf09b8251e2)
* Add SMB encryption. Still fixing client decrypt butJeremy Allison2007-12-261-6/+11
| | | | | | negotiation works. Jeremy. (This used to be commit d78045601af787731f0737b8627450018902b104)
generated by cgit (git 2.34.1) at 2025-07-01 02:24:17 +0000