summaryrefslogtreecommitdiff
path: root/source4/torture/nbench
AgeCommit message (Collapse)AuthorFilesLines
2007-10-10r5298: - got rid of pstring.h from includes.h. This at least makes it a bitAndrew Tridgell2-0/+3
less likely that anyone will use pstring for new code - got rid of winbind_client.h from includes.h. This one triggered a huge change, as winbind_client.h was including system/filesys.h and defining the old uint32 and uint16 types, as well as its own pstring and fstring. (This used to be commit 9db6c79e902ec538108d6b7d3324039aabe1704f)
2007-10-10r5037: got rid of all of the TALLOC_DEPRECATED stuff. My apologies for theAndrew Tridgell1-5/+5
large commit. I thought this was worthwhile to get done for consistency. (This used to be commit ec32b22ed5ec224f6324f5e069d15e92e38e15c0)
2007-10-10r4063: - change char * -> uint8_t in struct request_bufferStefan Metzmacher1-3/+3
- change smbcli_read/write to take void * for the buffers to match read(2)/write(2) all this fixes a lot of gcc-4 warnings metze (This used to be commit b94f92bc6637f748d6f7049f4f9a30b0b8d18a7a)
2007-10-10r4055: fixed more places to use type safe allocation macrosAndrew Tridgell1-1/+1
(This used to be commit eec698254f67365f27b4b7569fa982e22472aca1)
2007-10-10r4011: get rid of rpc_secdes.h and replace it with a single sane set ofAndrew Tridgell1-5/+6
definitions for security access masks, in security.idl The previous definitions were inconsistently named, and contained many duplicate and misleading entries. I kept finding myself tripping up while using them. (This used to be commit 01c0fa722f80ceeb3f81f01987de95f365a2ed3d)
2007-10-10r3976: changed NBENCH to use the same recording method as the latest dbench,Andrew Tridgell2-66/+70
where the warmup phase continues until all clients have done some file IO. This gives more repeatable results when under high load (This used to be commit aca0658f6dfe8b7c90afcac87e8cc68965a4288d)
2007-10-10r3507: - added deferred replies on sharing violation in pvfs open. TheAndrew Tridgell2-7/+11
deferred reply is short-circuited immediately when the file is closed by another user, allowing it to be opened by the waiting user. - added a sane set of timeval manipulation routines - converted all the events code and code that uses it to use struct timeval instead of time_t, which allows for microsecond resolution instead of 1 second resolution. This was needed for doing the pvfs deferred open code, and is why the patch is so big. (This used to be commit 0d51511d408d91eb5f68a35e980e0875299b1831)
2007-10-10r3463: separated out some more headers (asn_1.h, messages.h, dlinklist.h and ↵Andrew Tridgell1-0/+1
ioctl.h) (This used to be commit b97e395c814762024336c1cf4d7c25be8da5813a)
2007-10-10r3447: more include/system/XXX.h include filesAndrew Tridgell1-0/+1
(This used to be commit 264ce9181089922547e8f6f67116f2d7277a5105)
2007-10-10r3325: missed one of the torture changes ...Andrew Tridgell1-1/+1
(This used to be commit 1629b593c6ad5a6c0a7dc0cd7588d979db887286)
2007-10-10r3324: made the smbtorture code completely warning freeAndrew Tridgell1-2/+2
(This used to be commit 7067bb9b52223cafa28470f264f0b60646a07a01)
2007-10-10r3040: Add sleeps between operations to nbench. Submitted by ↵Jim McDonough2-0/+8
aliguori@us.ibm.com. (This used to be commit b1bbf0a431a9bcfc786b773be1adf39eaccb0b6e)
2007-10-10r1654: rename cli_ -> smbcli_Stefan Metzmacher2-13/+13
rename CLI_ -> SMBCLI_ metze (This used to be commit 8441750fd9427dd6fe477f27e603821b4026f038)
2007-10-10r1123: Make all lp_ string functions return 'const char *'.Andrew Bartlett1-2/+2
Fix other 'const' warnings in the torture code. Andrew Bartlett (This used to be commit 5d39d7497f189da15d659b3f83b7314026040a15)
2007-10-10r962: convert 'unsigned' and 'unsigned int' to uint_tStefan Metzmacher1-4/+4
metze (This used to be commit 57151e80eb1090281401930c8fe25b20a8cf3a38)
2007-10-10r890: convert samba4 to use [u]int8_t instead of [u]int8Stefan Metzmacher1-1/+1
metze (This used to be commit 2986c5f08c8f0c26a2ea7b6ce20aae025183109f)
2007-10-10r889: convert samba4 to use [u]int16_t instead of [u]int16Stefan Metzmacher1-1/+1
metze (This used to be commit af6f1f8a01bebbecd99bc8c066519e89966e65e3)
2007-10-10r884: convert samba4 to use [u]int32_t instead of [u]int32Stefan Metzmacher1-1/+1
metze (This used to be commit 0e5517d937a2eb7cf707991d1c7498c1ab456095)
2004-03-26- moved some of the base tests into torture/basic/Andrew Tridgell1-1/+1
- added a CHARSET set of tests, which determines how the server deals with some specific charset issues related to UTF-16 support. Interestingly, Samba3 already passes all but one of these tests, because our incorrect UCS-2 and UTF-8 implementations where we don't check the validity of characters actually matches what Windows does! This means that adding UTF-16 support to Samba is going to be _much_ easier than we expected. (This used to be commit c8497a42364d186f08102224d5062d176ee81f5b)
2004-03-26- use a linked list for the ftable in the nbench load generator. ThisAndrew Tridgell1-35/+71
allows us to cope a little better with the async nature of open/close requests which implies a ordering on which handle to close. - request oplocks in NBENCH and add a oplock handler (This used to be commit 3bcd27e0f0a20f2d9923815a123044bda710693c)
2004-03-26use client1, client2 not client0, client1 to better match netbenchAndrew Tridgell1-1/+1
(This used to be commit 4bbc77fa0c3a91fd34e1966892782f5b2a441359)
2004-03-10nicer way of handling \clientsAndrew Tridgell2-3/+14
(This used to be commit 931138cc440f646671ec5e9b52eb3666b2ff014b)
2004-03-10as a special case don't check the status of the create of \clients -Andrew Tridgell1-1/+3
there is a race condition in the create (This used to be commit ddfddcbffd304b5ac51140dee048ead7137e293a)
2004-03-10make the warmup and execute phases clearerAndrew Tridgell1-4/+13
(This used to be commit d49e4407e59a25c8e887b552ed2a58de7a16b6d9)
2004-03-10added a 5% warmup time to NBENCH to make the results more consistentAndrew Tridgell2-10/+33
(This used to be commit df50911a9c71bf5b8a8988fdbf6c716f8343fa45)
2004-03-09don't check return fields (like search count) on an expected failureAndrew Tridgell1-4/+4
(This used to be commit 6cbe8a6bd5998c67b74b989d13d3cb7863fee75d)
2004-03-09handle incomplete load filesAndrew Tridgell2-6/+7
change default timelimit to 600 secs (This used to be commit c5c75a6adab10e35584dca760586fda333ca5308)
2004-03-09greatly improved NBENCH netbench simulatorAndrew Tridgell2-0/+771
- more accurate request simulation using Samba4 raw client library - now checks for correct status on all requests - timelimit based benchmarking, default of 600 seconds (This used to be commit a46c009c0459658784d7d7b3b0502dc20958043a)