History log of /6.0.3/moxi/src/thread.c (Results 1 - 25 of 87)
Revision (<<< Hide revision tags) (Show revision tags >>>) Date Author Comments
Revision tags: v5.0.0, v4.6.0, v4.5.0, v4.0.0, v3.1.0
# d0366df5 09-Apr-2015 Trond Norbye <trond.norbye@gmail.com>

Use cb_assert instead of assert

Change-Id: If6b3170af815c324b26ff44bea3b950deed774fd
Reviewed-on: http://review.couchbase.org/49431
Tested-by: buildbot <build@couchbase.com>
Revi

Use cb_assert instead of assert

Change-Id: If6b3170af815c324b26ff44bea3b950deed774fd
Reviewed-on: http://review.couchbase.org/49431
Tested-by: buildbot <build@couchbase.com>
Reviewed-by: Steve Yen <steve.yen@gmail.com>

show more ...


Revision tags: v3.0.2, v3.0.1, v3.0.0
# 5affe2d0 18-Mar-2014 Trond Norbye <trond.norbye@gmail.com>

Refactor: Prepare source to be squashed

Change-Id: I275dc53298b8cd14df84cb528decfe08be32f68e
Reviewed-on: http://review.couchbase.org/34635
Reviewed-by: Trond Norbye <trond.norbye@gm

Refactor: Prepare source to be squashed

Change-Id: I275dc53298b8cd14df84cb528decfe08be32f68e
Reviewed-on: http://review.couchbase.org/34635
Reviewed-by: Trond Norbye <trond.norbye@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


# c2d0114b 15-Jan-2014 Trond Norbye <trond.norbye@gmail.com>

Compile fixes for win32

Change-Id: I5dd91efa3089b1a312f96141459ad593726a66ef
Reviewed-on: http://review.couchbase.org/32428
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by

Compile fixes for win32

Change-Id: I5dd91efa3089b1a312f96141459ad593726a66ef
Reviewed-on: http://review.couchbase.org/32428
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


# ed741b63 15-Jan-2014 Trond Norbye <trond.norbye@gmail.com>

Cleanup from int to SOCKET

Change-Id: I43e3cc18c2a0c15845296ebfa82c9707482f9f96
Reviewed-on: http://review.couchbase.org/32423
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested

Cleanup from int to SOCKET

Change-Id: I43e3cc18c2a0c15845296ebfa82c9707482f9f96
Reviewed-on: http://review.couchbase.org/32423
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


# 7d4ff237 15-Jan-2014 Trond Norbye <trond.norbye@gmail.com>

Use libplatform instead of pthread

Change-Id: Id366ec26ddd2e68022e70cb6fd84a00a21a04313
Reviewed-on: http://review.couchbase.org/32422
Reviewed-by: Steve Yen <steve.yen@gmail.com>

Use libplatform instead of pthread

Change-Id: Id366ec26ddd2e68022e70cb6fd84a00a21a04313
Reviewed-on: http://review.couchbase.org/32422
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


# d824ea68 02-Jan-2014 Trond Norbye <trond.norbye@gmail.com>

Move towards C89

Change-Id: I9953891a2fa858b0a957faaa5974fbe2b7ba3ac5
Reviewed-on: http://review.couchbase.org/31537
Reviewed-by: Trond Norbye <trond.norbye@gmail.com>
Tested-by:

Move towards C89

Change-Id: I9953891a2fa858b0a957faaa5974fbe2b7ba3ac5
Reviewed-on: http://review.couchbase.org/31537
Reviewed-by: Trond Norbye <trond.norbye@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


Revision tags: 2.5.0
# db427f17 14-Nov-2013 Trond Norbye <trond.norbye@gmail.com>

Use C-stype comments

Change-Id: Ib374e49763843988b26f726220b66372c84828f5
Reviewed-on: http://review.couchbase.org/30327
Reviewed-by: Trond Norbye <trond.norbye@gmail.com>
Tested

Use C-stype comments

Change-Id: Ib374e49763843988b26f726220b66372c84828f5
Reviewed-on: http://review.couchbase.org/30327
Reviewed-by: Trond Norbye <trond.norbye@gmail.com>
Tested-by: Trond Norbye <trond.norbye@gmail.com>

show more ...


Revision tags: 2.1.1r, 2.0.1-linux, 1.8.1, 1.8.0, 1.7.2, 1.7.1, 1.7.0, 1.6.5.2, 1.6.5.1, 1.6.5, 1.6.4, 1.6.4r, 1.6.3, 1.6.1rc1, 1.6.1pre, 1.6.0, 1.6.0beta4, 1.6.0beta3.2b, 1.6.0beta4rc1
# 64890cf6 02-Sep-2010 Steve Yen <steve.yen@gmail.com>

zstored_acquire/release_downstream_conn() pass make tests

They now successfully use the thread->conn_hash to cache downstream
connections. The conn_hash is key'ed by host_ident string,

zstored_acquire/release_downstream_conn() pass make tests

They now successfully use the thread->conn_hash to cache downstream
connections. The conn_hash is key'ed by host_ident string, and the
value is a linked list of available (and fully connected) downstream
connections.

The logic for having downstreams waiting for downstream connections,
however, is still not integrated.

Change-Id: I3fe9f0528c150cefc75e5d4c6d39050efa77294b
Reviewed-on: http://review.northscale.com/2256
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Steve Yen <steve.yen@gmail.com>

show more ...


Revision tags: 1.6.0beta3
# 3dc08db6 12-Aug-2010 Steve Yen <steve.yen@gmail.com>

merged in zstored conn_hash and pooling logic

Ammongst the debris there is cproxy_downstream_conn_for_host_ident()
brought over the from zstore codeline.

Originally from: Jayesh

merged in zstored conn_hash and pooling logic

Ammongst the debris there is cproxy_downstream_conn_for_host_ident()
brought over the from zstore codeline.

Originally from: Jayesh Jose <jjose@zynga.com>, Manik Taneja <mtaneja@zynga.com>
from the zstored project.

Change-Id: I545b255e848ba7bfcc69b73c2abf01baccdb1e66
Reviewed-on: http://review.northscale.com/2242
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Steve Yen <steve.yen@gmail.com>

show more ...


Revision tags: 1.6.0beta3b
# e1ae2ef8 04-Aug-2010 Aliaksey Kandratsenka <alk@tut.by>

fixes tons of warnings produced on GNU/Linux

Change-Id: I4ffc7f259540ccc1e6c0c1410595f808c76c72b9
Reviewed-on: http://review.northscale.com/1566
Reviewed-by: Steve Yen <steve.yen@gma

fixes tons of warnings produced on GNU/Linux

Change-Id: I4ffc7f259540ccc1e6c0c1410595f808c76c72b9
Reviewed-on: http://review.northscale.com/1566
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Steve Yen <steve.yen@gmail.com>

show more ...


# b654665f 03-Aug-2010 Trond Norbye <trond.norbye@gmail.com>

Win32 support

Change-Id: Id93d2c84f6f737dd28a134c3f41a301f97ebcdec
Reviewed-on: http://review.northscale.com/1556
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Aliaksey

Win32 support

Change-Id: Id93d2c84f6f737dd28a134c3f41a301f97ebcdec
Reviewed-on: http://review.northscale.com/1556
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Aliaksey Kandratsenka <alkondratenko@gmail.com>

show more ...


# 6a48c213 27-Jul-2010 Manik Taneja <mtaneja@zynga.com>

Migrate to using moxi log
Small cleanups and addition of SIGHUP signal handler to
handle rotation of log files

Change-Id: I65f3b051d35c0701a3f099315ff6c8d66b3c0a1e
Reviewed-on: h

Migrate to using moxi log
Small cleanups and addition of SIGHUP signal handler to
handle rotation of log files

Change-Id: I65f3b051d35c0701a3f099315ff6c8d66b3c0a1e
Reviewed-on: http://review.northscale.com/1377
Reviewed-by: Steve Yen <steve.yen@gmail.com>
Tested-by: Steve Yen <steve.yen@gmail.com>

show more ...


Revision tags: 1.6.0beta3a, 1.6.0beta2, 1.6.0beta2rc1, 1.6.0beta1.1
# a995404d 27-Jun-2010 Steve Yen <steve.yen@gmail.com>

MOXI_USE_VBUCKET and MOXI_ITEM_MALLOC in configure.ac

This is so that moxi can still be conditionally compiled with
libmemcached, (libmemcached-0.40-revno839), instead of libvbucket, and

MOXI_USE_VBUCKET and MOXI_ITEM_MALLOC in configure.ac

This is so that moxi can still be conditionally compiled with
libmemcached, (libmemcached-0.40-revno839), instead of libvbucket, and
compiled to use the classic memcached slabber (instead of malloc) for
items.

This should be temporary until the unit and mock tests are updated.

Change-Id: I416bd1d54e52a0f56b225f1c0a851f9ae13b0700
Reviewed-on: http://review.northscale.com/926
Reviewed-by: Dustin Sallings <dustin@spy.net>
Tested-by: Steve Yen <steve.yen@gmail.com>

show more ...


Revision tags: 1.6.0beta1, 1.6.0a2, 1.6.0a1
# b33ce538 19-Jun-2010 Steve Yen <steve.yen@gmail.com>

moxi is faster without slabber

Using the slabber's global lock is worse than using straight malloc in
moxi. This change probably prevents moxi from working right as a
memcached serv

moxi is faster without slabber

Using the slabber's global lock is worse than using straight malloc in
moxi. This change probably prevents moxi from working right as a
memcached server, but it'll now be a faster proxy, consuming less CPU
resource.

Change-Id: I976aa01c1c1a24d665d9cadcfd3e3c8c43fbf095
Reviewed-on: http://review.northscale.com:8080/696
Tested-by: Steve Yen <steve.yen@gmail.com>
Reviewed-by: Matt Ingenthron <matt@northscale.com>
Reviewed-by: Eric Lambert <eric.d.lambert@gmail.com>

show more ...


Revision tags: 1.6.0a, 0.10.0, 0.10.0-rc1
# 6719f9d3 29-Sep-2009 Aliaksey Kandratsenka <alk@tut.by>

pass binding protocol to dispatch_conn_new

this fixes incorrect protocol values for cproxy connections


# 48eb8857 10-Sep-2009 Dustin Sallings <dustin@spy.net>

Merged in 1.4.1


# ea4d0640 02-Sep-2009 Dustin Sallings <dustin@spy.net>

Replaced glib dependency with a custom hash table.

This greatly simplifies builds where a package system that can deal
with glib is unavailable.


Revision tags: 0.9.6, 0.9.5
# 8398f5b0 28-Jun-2009 Dustin Sallings <dustin@spy.net>

add_delta should return a proper status indicator.

Before, it was returning text protocol, requiring special handling in
the binary protocol.


# a21f819a 30-Jun-2009 Trond Norbye <Trond.Norbye@sun.com>

Issue 61: reqs_per_event handling (-R) is incorrect leading to client lockups


# d044acb2 28-Jun-2009 Dustin Sallings <dustin@spy.net>

add_delta should return a proper status indicator.

Before, it was returning text protocol, requiring special handling in
the binary protocol.


Revision tags: 0.1.0
# 15ace4b5 09-Apr-2009 Eric Lambert <eric.lambert@sun.com>

fix and test for issue 38 (server does not respond to binary requests)


# 4e3a4eb8 11-Apr-2009 Steve Yen <steve.yen@gmail.com>

added work_queue to LIBEVENT_THREAD


# 9286b5f2 10-Apr-2009 Steve Yen <steve.yen@gmail.com>

latest memagent func signatures with userdata


# 489fba80 29-Mar-2009 Steve Yen <steve.yen@gmail.com>

thread_index() to find the LIBEVENT_THREAD array index for a thread.


# 86de8345 29-Mar-2009 Steve Yen <steve.yen@gmail.com>

Recording thread_id during child thread startup.

Before, only the main process thread had its LIBEVENT_THREAD.thread_id
value recorded. Now all child threads will have a recorded thread

Recording thread_id during child thread startup.

Before, only the main process thread had its LIBEVENT_THREAD.thread_id
value recorded. Now all child threads will have a recorded thread_id.
This allows us to match any thread to its corresponding
LIBEVENT_THREAD struct by comparing pthread_self()
to that recorded thread_id.

show more ...


1234