sin/samba-mirror
1
0
Fork 0
mirror of https://github.com/samba-team/samba.git synced 2025-11-21 12:23:50 +03:00
Code Activity
23,024 Commits 64 Branches 1,179 Tags
a8a33c377e38046b4103cf1d59032b97ab6bac9a
Commit Graph

19 Commits

Author SHA1 Message Date
Volker Lendecke
9ad91bd205 r24332: schedule_aio_read_and_X does not need InBuf/OutBuf 2007-10-10 12:29:30 -05:00
Volker Lendecke
f18b7a9a28 r24279: Remove reply_prep_legacy from reply_write_and_X 2007-10-10 12:29:24 -05:00
Volker Lendecke
eabe796e46 r24049: Some more 64-bit warnings 2007-10-10 12:28:59 -05:00
Andrew Tridgell
b0132e94fc r23784: use the GPLv3 boilerplate as recommended by the FSF and the license text 2007-10-10 12:28:22 -05:00
Jeremy Allison
407e6e695b r23779: Change from v2 or later to v3 or later. 
Jeremy.
 2007-10-10 12:28:20 -05:00
Jeremy Allison
cd3f7dbee8 r23508: Fix sync_file() to return NTSTATUS and return this 
on failure in the write path.
Jeremy.
 2007-10-10 12:23:23 -05:00
Michael Adam
9de1af6dc8 r22411: Fix the build: 
Prototype of create_aio_ex_read, set_message and definition of
UNIXERROR have changed in r22389 and r22391? to require an additional
"inbuf" argument. Some places in smbd/aio.c had not been adapted.

This patch fixes the build.

Michael
 2007-10-10 12:19:32 -05:00
Jeremy Allison
2d80a96120 r22391: Looks bigger than it is. Make "inbuf" available 
to all callers of smb_setlen (via set_message()
calls). This will allow the server to reflect back
the correct encryption context.
Jeremy.
 2007-10-10 12:19:30 -05:00
Jeremy Allison
b49e90335d r22389: Start preparing for multiple encryption contexts in the 
server. Allow server to reflect back to calling client
the encryption context that was sent.
Jeremy.
 2007-10-10 12:19:30 -05:00
Volker Lendecke
58bfd168b0 r21279: Get rid of 'aio write behind', this is broken. 
It should probably better be integrated with our write cache.

Volker
 2007-10-10 12:17:53 -05:00
Volker Lendecke
452d51bc6f r21278: The main goal of this was to get rid of the NetInBuffer / set_InBuffer. But it 
turns out that this patch actually speeds up the async writes considerably.

I tested writing 100.000 times 65535 bytes with the allowed 10 ops in
parallel. Without this patch it took about 32 seconds on my dual-core 1.6GHz
laptop. With this patch it dropped to about 26 seconds. I can only explain it
by better cache locality, NewInBuffer allocates more than 128k, so we jump
around in memory more.

Jeremy, please check!

Volker
 2007-10-10 12:17:53 -05:00
Volker Lendecke
8fd0ec5836 r21277: Fix an off by one error in the signal handler for aio: We can actually receive 
AIO_PENDING_SIZE signals, not one less.

Jeremy I'm not merging this to 3_0_25, I want you to look at it first!

Volker
 2007-10-10 12:17:53 -05:00
Volker Lendecke
b2eaa733c5 r21269: Reformatting 2007-10-10 12:17:53 -05:00
Volker Lendecke
36f60407ae r20541: Fix some obvious glitches in wait_for_aio_completion. Hmmm. It seems 
reply_close() at its heart is going to be an async call :-)

Volker
 2007-10-10 12:16:55 -05:00
James Peach
d6382092e7 r20237: Replace exit_server with exit_server_cleanly where appropriate. All 
send_smb failures should be clean exits. All times when we exit as
a matter of policy should also be clean exits.
 2007-10-10 12:16:34 -05:00
Jeremy Allison
f68ff32630 r11283: Move to using sival_int from sival_ptr. Part of bug #2922. 
Jeremy.
 2007-10-10 11:05:10 -05:00
James Peach
cc680bbe22 r9985: Move the all the strict sync logic into file_sync(). 2007-10-10 11:03:30 -05:00
Günther Deschner
49351d91c5 r8402: allow to build with --enable-aio-support. 
Guenther
 2007-10-10 11:00:04 -05:00
Jeremy Allison
1de27da470 r7963: Add aio support to 3.0. 
Jeremy.
 2007-10-10 10:58:05 -05:00