mongo_ha 1.12.4 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/LICENSE.txt +202 -0
- data/README.md +3 -121
- data/lib/mongo_ha/operation_failure.rb +34 -0
- data/lib/mongo_ha/retryable.rb +62 -0
- data/lib/mongo_ha/version.rb +1 -1
- data/lib/mongo_ha.rb +2 -27
- metadata +9 -10
- data/Rakefile +0 -28
- data/lib/mongo_ha/mongo_client.rb +0 -205
- data/test/readme.md +0 -48
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: c07613ccc0db614856311ea723d0bb980bd53113
|
4
|
+
data.tar.gz: f449fd924fd37daac5bfd82d3d13950422d895d9
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4e65723c5ba6bb1ac48c2095c353ee6ca048d49016e92db7329f8820a568b95a63949151f0831a3a3379f477b9673d1c9f999749f2e4d623e56a5a3f2651abbe
|
7
|
+
data.tar.gz: 83e9ccb94dc81194df0c87b8558def4f5d17efff66297071c43ab3ed4b48c52d019a4175921b87418fcd44e42d9543b282c765d3e88bcbb8e91c8b1e5b192e8a
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
Apache License
|
2
|
+
Version 2.0, January 2004
|
3
|
+
http://www.apache.org/licenses/
|
4
|
+
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6
|
+
|
7
|
+
1. Definitions.
|
8
|
+
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
11
|
+
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13
|
+
the copyright owner that is granting the License.
|
14
|
+
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
16
|
+
other entities that control, are controlled by, or are under common
|
17
|
+
control with that entity. For the purposes of this definition,
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
19
|
+
direction or management of such entity, whether by contract or
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22
|
+
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24
|
+
exercising permissions granted by this License.
|
25
|
+
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
27
|
+
including but not limited to software source code, documentation
|
28
|
+
source, and configuration files.
|
29
|
+
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
31
|
+
transformation or translation of a Source form, including but
|
32
|
+
not limited to compiled object code, generated documentation,
|
33
|
+
and conversions to other media types.
|
34
|
+
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
36
|
+
Object form, made available under the License, as indicated by a
|
37
|
+
copyright notice that is included in or attached to the work
|
38
|
+
(an example is provided in the Appendix below).
|
39
|
+
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46
|
+
the Work and Derivative Works thereof.
|
47
|
+
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
49
|
+
the original version of the Work and any modifications or additions
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
61
|
+
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
64
|
+
subsequently incorporated within the Work.
|
65
|
+
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
72
|
+
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78
|
+
where such license applies only to those patent claims licensable
|
79
|
+
by such Contributor that are necessarily infringed by their
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
82
|
+
institute patent litigation against any entity (including a
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
85
|
+
or contributory patent infringement, then any patent licenses
|
86
|
+
granted to You under this License for that Work shall terminate
|
87
|
+
as of the date such litigation is filed.
|
88
|
+
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
91
|
+
modifications, and in Source or Object form, provided that You
|
92
|
+
meet the following conditions:
|
93
|
+
|
94
|
+
(a) You must give any other recipients of the Work or
|
95
|
+
Derivative Works a copy of this License; and
|
96
|
+
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
98
|
+
stating that You changed the files; and
|
99
|
+
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
102
|
+
attribution notices from the Source form of the Work,
|
103
|
+
excluding those notices that do not pertain to any part of
|
104
|
+
the Derivative Works; and
|
105
|
+
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
108
|
+
include a readable copy of the attribution notices contained
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
111
|
+
of the following places: within a NOTICE text file distributed
|
112
|
+
as part of the Derivative Works; within the Source form or
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
114
|
+
within a display generated by the Derivative Works, if and
|
115
|
+
wherever such third-party notices normally appear. The contents
|
116
|
+
of the NOTICE file are for informational purposes only and
|
117
|
+
do not modify the License. You may add Your own attribution
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
120
|
+
that such additional attribution notices cannot be construed
|
121
|
+
as modifying the License.
|
122
|
+
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
124
|
+
may provide additional or different license terms and conditions
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
128
|
+
the conditions stated in this License.
|
129
|
+
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
133
|
+
this License, without any additional terms or conditions.
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135
|
+
the terms of any separate license agreement you may have executed
|
136
|
+
with Licensor regarding such Contributions.
|
137
|
+
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
140
|
+
except as required for reasonable and customary use in describing the
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
142
|
+
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
152
|
+
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
158
|
+
incidental, or consequential damages of any character arising as a
|
159
|
+
result of this License or out of the use or inability to use the
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
162
|
+
other commercial damages or losses), even if such Contributor
|
163
|
+
has been advised of the possibility of such damages.
|
164
|
+
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168
|
+
or other liability obligations and/or rights consistent with this
|
169
|
+
License. However, in accepting such obligations, You may act only
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
174
|
+
of your accepting any such warranty or additional liability.
|
175
|
+
|
176
|
+
END OF TERMS AND CONDITIONS
|
177
|
+
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
179
|
+
|
180
|
+
To apply the Apache License to your work, attach the following
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "{}"
|
182
|
+
replaced with your own identifying information. (Don't include
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
184
|
+
comment syntax for the file format. We also recommend that a
|
185
|
+
file or class name and description of purpose be included on the
|
186
|
+
same "printed page" as the copyright notice for easier
|
187
|
+
identification within third-party archives.
|
188
|
+
|
189
|
+
Copyright {yyyy} {name of copyright owner}
|
190
|
+
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192
|
+
you may not use this file except in compliance with the License.
|
193
|
+
You may obtain a copy of the License at
|
194
|
+
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
196
|
+
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200
|
+
See the License for the specific language governing permissions and
|
201
|
+
limitations under the License.
|
202
|
+
|
data/README.md
CHANGED
@@ -4,8 +4,7 @@ High availability for the mongo ruby driver. Automatic reconnects and recovery w
|
|
4
4
|
|
5
5
|
## Status
|
6
6
|
|
7
|
-
Production Ready: Used every day in an enterprise environment across
|
8
|
-
remote data centers.
|
7
|
+
Production Ready: Used every day in an enterprise environment across remote data centers.
|
9
8
|
|
10
9
|
## Overview
|
11
10
|
|
@@ -23,49 +22,9 @@ In the event of a connection failure, only one thread will attempt to re-establi
|
|
23
22
|
connectivity to the Mongo server(s). This is to prevent swamping the mongo
|
24
23
|
servers with reconnect attempts.
|
25
24
|
|
26
|
-
|
27
|
-
and then backs off to give the replica-set time to elect a new master.
|
25
|
+
Supports Ruby Mongo driver V1 and V2
|
28
26
|
|
29
|
-
|
30
|
-
|
31
|
-
`mongo_ha` transparently supports `MongoMapper` since it uses the mongo ruby driver
|
32
|
-
that is patched by loading this gem. Earlier versions of Mongoid will also benefit
|
33
|
-
from `mongo_ha`, the latest version of Mongoid uses Moped that should be avoided
|
34
|
-
since it is due to be replaced by the Ruby Mongo driver V2 when it is released.
|
35
|
-
|
36
|
-
Mongo Router processes will often return a connection failure on their side
|
37
|
-
as an OperationFailure. This code will also retry automatically when the router
|
38
|
-
has errors talking to a sharded cluster.
|
39
|
-
|
40
|
-
## Mongo Cursors
|
41
|
-
|
42
|
-
Any operations that return a cursor need to be handled in your own code
|
43
|
-
since the retry cannot be handled transparently.
|
44
|
-
For example: `find` returns a cursor, whereas `find_one` is handled because
|
45
|
-
it returns the data returned rather than a cursor
|
46
|
-
|
47
|
-
Example
|
48
|
-
|
49
|
-
```ruby
|
50
|
-
# Wrap existing cursor based calls with a retry on connection failure block
|
51
|
-
results_collection.retry_on_connection_failure do
|
52
|
-
results_collection.find({}, sort: '_id', timeout: false) do |cursor|
|
53
|
-
cursor.each do |record|
|
54
|
-
puts "Record: #{record.inspect}"
|
55
|
-
end
|
56
|
-
end
|
57
|
-
end
|
58
|
-
```
|
59
|
-
|
60
|
-
### Note
|
61
|
-
|
62
|
-
In the above example the block will be repeated from the _beginning_ of the
|
63
|
-
collection should a connection failure occur. Without appropriate handling it
|
64
|
-
is possible to read the same records twice.
|
65
|
-
|
66
|
-
If the collection cannot be processed twice, it may be better to just let the
|
67
|
-
`Mongo::ConnectionFailure` flow up into the application for it to deal with at
|
68
|
-
a higher level.
|
27
|
+
`mongo_ha` transparently supports `MongoMapper` and `Mongoid` which use the mongo ruby driver.
|
69
28
|
|
70
29
|
## Installation
|
71
30
|
|
@@ -85,70 +44,6 @@ If you are also using SemanticLogger, place `mongo_ha` below `semantic_logger`
|
|
85
44
|
and/or `rails_semantic_logger` in the `Gemfile`. This way it will create a logger
|
86
45
|
just for `Mongo::MongoClient` to improve the log output during connection recovery.
|
87
46
|
|
88
|
-
## Configuration
|
89
|
-
|
90
|
-
mongo_ha adds several new configuration options to fine tune the reconnect behavior
|
91
|
-
for any environment.
|
92
|
-
|
93
|
-
Sample mongo.yml:
|
94
|
-
|
95
|
-
```yaml
|
96
|
-
default_options: &default_options
|
97
|
-
:w: 1
|
98
|
-
:pool_size: 5
|
99
|
-
:pool_timeout: 5
|
100
|
-
:connect_timeout: 5
|
101
|
-
:reconnect_attempts: 53
|
102
|
-
:reconnect_retry_seconds: 0.1
|
103
|
-
:reconnect_retry_multiplier: 2
|
104
|
-
:reconnect_max_retry_seconds: 5
|
105
|
-
|
106
|
-
development: &development
|
107
|
-
uri: mongodb://localhost:27017/development
|
108
|
-
options:
|
109
|
-
<<: *default_options
|
110
|
-
|
111
|
-
test:
|
112
|
-
uri: mongodb://localhost:27017/test
|
113
|
-
options:
|
114
|
-
<<: *default_options
|
115
|
-
|
116
|
-
# Sample Production Settings
|
117
|
-
production:
|
118
|
-
uri: mongodb://mongo1.site.com:27017,mongo2.site.com:27017/production
|
119
|
-
options:
|
120
|
-
<<: *default_options
|
121
|
-
:pool_size: 50
|
122
|
-
:pool_timeout: 5
|
123
|
-
```
|
124
|
-
|
125
|
-
The following options can be specified in the Mongo configuration options
|
126
|
-
to tune the retry intervals during a connection failure
|
127
|
-
|
128
|
-
### :reconnect_attempts
|
129
|
-
|
130
|
-
* Number of times to attempt to reconnect.
|
131
|
-
* Default: 53
|
132
|
-
|
133
|
-
### :reconnect_retry_seconds
|
134
|
-
|
135
|
-
* Initial delay before retrying
|
136
|
-
* Default: 0.1
|
137
|
-
|
138
|
-
### :reconnect_retry_multiplier
|
139
|
-
|
140
|
-
* Multiply delay by this number with each retry to prevent overwhelming the server
|
141
|
-
* Default: 2
|
142
|
-
|
143
|
-
### :reconnect_max_retry_seconds
|
144
|
-
|
145
|
-
* Maximum number of seconds to wait before retrying again
|
146
|
-
* Default: 5
|
147
|
-
|
148
|
-
Using the above default values, will result in retry connects at the following intervals
|
149
|
-
|
150
|
-
0.1 0.2 0.4 0.8 1.6 3.2 5 5 5 5 ....
|
151
|
-
|
152
47
|
## Testing
|
153
48
|
|
154
49
|
There is really only one place to test something like `mongo_ha` and that is in
|
@@ -157,16 +52,3 @@ This gem was created and tested with MongoDB running in an
|
|
157
52
|
enterprise production environment with hundreds of connections to Mongo servers
|
158
53
|
in remote data centers across a WAN. It adds high availability to standalone
|
159
54
|
MongoDB servers, replica-sets, and sharded clusters.
|
160
|
-
|
161
|
-
## Issues
|
162
|
-
|
163
|
-
If the following output appears after adding the above connection options:
|
164
|
-
|
165
|
-
```shell
|
166
|
-
reconnect_attempts is not a valid option for Mongo::MongoClient
|
167
|
-
reconnect_retry_seconds is not a valid option for Mongo::MongoClient
|
168
|
-
reconnect_retry_multiplier is not a valid option for Mongo::MongoClient
|
169
|
-
reconnect_max_retry_seconds is not a valid option for Mongo::MongoClient
|
170
|
-
```
|
171
|
-
|
172
|
-
Then the `mongo_ha` gem was not loaded prior to connecting to Mongo
|
@@ -0,0 +1,34 @@
|
|
1
|
+
require 'mongo/error/operation_failure'
|
2
|
+
|
3
|
+
module Mongo
|
4
|
+
class Error
|
5
|
+
class OperationFailure
|
6
|
+
WRITE_RETRY_MESSAGES = [
|
7
|
+
'no master',
|
8
|
+
'not master',
|
9
|
+
'could not contact primary',
|
10
|
+
'Not primary'
|
11
|
+
]
|
12
|
+
|
13
|
+
remove_const :RETRY_MESSAGES
|
14
|
+
RETRY_MESSAGES = WRITE_RETRY_MESSAGES + [
|
15
|
+
'transport error',
|
16
|
+
'socket exception',
|
17
|
+
"can't connect",
|
18
|
+
'connect failed',
|
19
|
+
'error querying',
|
20
|
+
'could not get last error',
|
21
|
+
'connection attempt failed',
|
22
|
+
'interrupted at shutdown',
|
23
|
+
'unknown replica set',
|
24
|
+
'dbclient error communicating with server'
|
25
|
+
]
|
26
|
+
|
27
|
+
def write_retryable?
|
28
|
+
WRITE_RETRY_MESSAGES.any? { |m| message.include?(m) }
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'mongo/retryable'
|
2
|
+
|
3
|
+
module Mongo
|
4
|
+
module Retryable
|
5
|
+
|
6
|
+
def read_with_retry(attempt = 0, &block)
|
7
|
+
begin
|
8
|
+
block.call
|
9
|
+
rescue Error::SocketError, Error::SocketTimeoutError => e
|
10
|
+
retry_operation(e, &block)
|
11
|
+
rescue Error::OperationFailure => e
|
12
|
+
# TODO: Non sharded, retryable due to Replicaset primary change
|
13
|
+
|
14
|
+
if cluster.sharded? && e.retryable?
|
15
|
+
if attempt < cluster.max_read_retries
|
16
|
+
# We don't scan the cluster in this case as Mongos always returns
|
17
|
+
# ready after a ping no matter what the state behind it is.
|
18
|
+
sleep(cluster.read_retry_interval)
|
19
|
+
read_with_retry(attempt + 1, &block)
|
20
|
+
else
|
21
|
+
raise e
|
22
|
+
end
|
23
|
+
else
|
24
|
+
raise e
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def read_with_one_retry(&block)
|
30
|
+
block.call
|
31
|
+
rescue Error::SocketError, Error::SocketTimeoutError => e
|
32
|
+
Logger.logger.warn "Single retry due to: #{e.class.name} #{e.message}"
|
33
|
+
block.call
|
34
|
+
end
|
35
|
+
|
36
|
+
def write_with_retry(&block)
|
37
|
+
begin
|
38
|
+
block.call
|
39
|
+
rescue Error::SocketError => e
|
40
|
+
# During a master move in a replica-set the master closes existing client connections.
|
41
|
+
# Note: Small possibility the write occurs twice.
|
42
|
+
retry_operation(e, &block)
|
43
|
+
rescue Error::OperationFailure => e
|
44
|
+
if e.write_retryable?
|
45
|
+
retry_operation(e, &block)
|
46
|
+
else
|
47
|
+
raise e
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
private
|
53
|
+
|
54
|
+
# Log a warning on retry to prevent appearance of "hanging" during a failover.
|
55
|
+
def retry_operation(e, &block)
|
56
|
+
Logger.logger.warn "Retry due to: #{e.class.name} #{e.message}"
|
57
|
+
cluster.scan!
|
58
|
+
block.call
|
59
|
+
end
|
60
|
+
|
61
|
+
end
|
62
|
+
end
|
data/lib/mongo_ha/version.rb
CHANGED
data/lib/mongo_ha.rb
CHANGED
@@ -1,28 +1,3 @@
|
|
1
1
|
require 'mongo'
|
2
|
-
require 'mongo_ha/
|
3
|
-
require 'mongo_ha/
|
4
|
-
|
5
|
-
# Add in retry methods
|
6
|
-
Mongo::MongoClient.send(:include, MongoHA::MongoClient::InstanceMethods)
|
7
|
-
|
8
|
-
# Wrap critical Mongo methods with retry_on_connection_failure
|
9
|
-
{
|
10
|
-
# Most calls use a cursor under the covers to return the result
|
11
|
-
# If the primary is lost and it connects to a different server an expired cursor exception is raised
|
12
|
-
Mongo::Cursor => [:refresh],
|
13
|
-
|
14
|
-
# These methods do not use a Cursor
|
15
|
-
Mongo::Collection => [:insert, :remove, :update]
|
16
|
-
}.each_pair do |klass, methods|
|
17
|
-
methods.each do |method|
|
18
|
-
original_method = "#{method}_original".to_sym
|
19
|
-
klass.send(:alias_method, original_method, method)
|
20
|
-
klass.send(:define_method, method) do |*args|
|
21
|
-
@connection.retry_on_connection_failure { send(original_method, *args) }
|
22
|
-
end
|
23
|
-
end
|
24
|
-
end
|
25
|
-
|
26
|
-
# Drop the max ping time to a more respectable time. Assuming it is in ms.
|
27
|
-
Mongo::Pool.send(:remove_const, :MAX_PING_TIME)
|
28
|
-
Mongo::Pool::MAX_PING_TIME = 5_000
|
2
|
+
require 'mongo_ha/operation_failure'
|
3
|
+
require 'mongo_ha/retryable'
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: mongo_ha
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 2.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Reid Morrison
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-11-
|
11
|
+
date: 2016-11-30 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mongo
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '2.0'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '2.0'
|
27
27
|
description: Automatic reconnects and recovery when replica-set changes, or connections
|
28
28
|
are lost, with transparent recovery
|
29
29
|
email:
|
@@ -32,12 +32,12 @@ executables: []
|
|
32
32
|
extensions: []
|
33
33
|
extra_rdoc_files: []
|
34
34
|
files:
|
35
|
+
- LICENSE.txt
|
35
36
|
- README.md
|
36
|
-
- Rakefile
|
37
37
|
- lib/mongo_ha.rb
|
38
|
-
- lib/mongo_ha/
|
38
|
+
- lib/mongo_ha/operation_failure.rb
|
39
|
+
- lib/mongo_ha/retryable.rb
|
39
40
|
- lib/mongo_ha/version.rb
|
40
|
-
- test/readme.md
|
41
41
|
homepage: https://github.com/reidmorrison/mongo_ha
|
42
42
|
licenses:
|
43
43
|
- Apache-2.0
|
@@ -58,9 +58,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
58
58
|
version: '0'
|
59
59
|
requirements: []
|
60
60
|
rubyforge_project:
|
61
|
-
rubygems_version: 2.
|
61
|
+
rubygems_version: 2.6.8
|
62
62
|
signing_key:
|
63
63
|
specification_version: 4
|
64
64
|
summary: High availability for the mongo ruby driver
|
65
|
-
test_files:
|
66
|
-
- test/readme.md
|
65
|
+
test_files: []
|
data/Rakefile
DELETED
@@ -1,28 +0,0 @@
|
|
1
|
-
require 'rake/clean'
|
2
|
-
require 'rake/testtask'
|
3
|
-
|
4
|
-
$LOAD_PATH.unshift File.expand_path("../lib", __FILE__)
|
5
|
-
require 'mongo_ha/version'
|
6
|
-
|
7
|
-
task :gem do
|
8
|
-
system "gem build mongo_ha.gemspec"
|
9
|
-
end
|
10
|
-
|
11
|
-
task :publish => :gem do
|
12
|
-
system "git tag -a v#{MongoHA::VERSION} -m 'Tagging #{MongoHA::VERSION}'"
|
13
|
-
system "git push --tags"
|
14
|
-
system "gem push mongo_ha-#{MongoHA::VERSION}.gem"
|
15
|
-
system "rm mongo_ha-#{MongoHA::VERSION}.gem"
|
16
|
-
end
|
17
|
-
|
18
|
-
desc "Run Test Suite"
|
19
|
-
task :test do
|
20
|
-
Rake::TestTask.new(:functional) do |t|
|
21
|
-
t.test_files = FileList['test/*_test.rb']
|
22
|
-
t.verbose = true
|
23
|
-
end
|
24
|
-
|
25
|
-
Rake::Task['functional'].invoke
|
26
|
-
end
|
27
|
-
|
28
|
-
task :default => :test
|
@@ -1,205 +0,0 @@
|
|
1
|
-
require 'mongo'
|
2
|
-
module MongoHA
|
3
|
-
module MongoClient
|
4
|
-
CONNECTION_RETRY_OPTS = [:reconnect_attempts, :reconnect_retry_seconds, :reconnect_retry_multiplier, :reconnect_max_retry_seconds]
|
5
|
-
|
6
|
-
# The following errors occur when mongos cannot connect to the shard
|
7
|
-
# They require a retry to resolve them
|
8
|
-
# This list was created through painful experience. Add any new ones as they are discovered
|
9
|
-
# 9001: socket exception
|
10
|
-
# Operation failed with the following exception: Unknown error - Connection reset by peer:Unknown error - Connection reset by peer
|
11
|
-
# DBClientBase::findOne: transport error
|
12
|
-
# : db assertion failure
|
13
|
-
# 8002: 8002 all servers down!
|
14
|
-
# Operation failed with the following exception: stream closed
|
15
|
-
# Operation failed with the following exception: Bad file descriptor - Bad file descriptor:Bad file descriptor - Bad file descriptor
|
16
|
-
# Failed to connect to primary node.
|
17
|
-
# 10009: ReplicaSetMonitor no master found for set: mdbb
|
18
|
-
OPERATION_FAILURE_ERRORS = [
|
19
|
-
'socket exception',
|
20
|
-
'Connection reset by peer',
|
21
|
-
'transport error',
|
22
|
-
'db assertion failure',
|
23
|
-
'8002',
|
24
|
-
'stream closed',
|
25
|
-
'Bad file descriptor',
|
26
|
-
'Failed to connect',
|
27
|
-
'10009',
|
28
|
-
'no master found',
|
29
|
-
'not master',
|
30
|
-
'Timed out waiting on socket',
|
31
|
-
"didn't get writeback",
|
32
|
-
'interrupted at shutdown'
|
33
|
-
]
|
34
|
-
|
35
|
-
module InstanceMethods
|
36
|
-
# Add retry logic to MongoClient
|
37
|
-
def self.included(base)
|
38
|
-
base.class_eval do
|
39
|
-
# Give MongoClient a class-specific logger if SemanticLogger V2.12 or above is available
|
40
|
-
# to give better logging information during a connection recovery scenario
|
41
|
-
if defined?(SemanticLogger::DebugAsTraceLogger)
|
42
|
-
# Map Debug level calls to trace to reduce log file clutter
|
43
|
-
@@logger = SemanticLogger::DebugAsTraceLogger.new(self)
|
44
|
-
|
45
|
-
def self.logger
|
46
|
-
@@logger
|
47
|
-
end
|
48
|
-
|
49
|
-
def logger
|
50
|
-
self.class.logger
|
51
|
-
end
|
52
|
-
end
|
53
|
-
|
54
|
-
alias_method :valid_opts_original, :valid_opts
|
55
|
-
alias_method :setup_original, :setup
|
56
|
-
|
57
|
-
attr_accessor *CONNECTION_RETRY_OPTS
|
58
|
-
|
59
|
-
# Prevent multiple threads from trying to reconnect at the same time during
|
60
|
-
# connection failures
|
61
|
-
@@failover_mutex = Mutex.new
|
62
|
-
|
63
|
-
private
|
64
|
-
|
65
|
-
def valid_opts(*args)
|
66
|
-
valid_opts_original(*args) + CONNECTION_RETRY_OPTS
|
67
|
-
end
|
68
|
-
|
69
|
-
def setup(opts)
|
70
|
-
self.reconnect_attempts = (opts.delete(:reconnect_attempts) || 53).to_i
|
71
|
-
self.reconnect_retry_seconds = (opts.delete(:reconnect_retry_seconds) || 0.1).to_f
|
72
|
-
self.reconnect_retry_multiplier = (opts.delete(:reconnect_retry_multiplier) || 2).to_f
|
73
|
-
self.reconnect_max_retry_seconds = (opts.delete(:reconnect_max_retry_seconds) || 5).to_f
|
74
|
-
setup_original(opts)
|
75
|
-
end
|
76
|
-
|
77
|
-
end
|
78
|
-
end
|
79
|
-
|
80
|
-
# Retry the supplied block when a Mongo::ConnectionFailure occurs
|
81
|
-
#
|
82
|
-
# Note: Check for Duplicate Key on inserts
|
83
|
-
#
|
84
|
-
# Returns the result of the block
|
85
|
-
#
|
86
|
-
# Example:
|
87
|
-
# connection.retry_on_connection_failure { |retried| connection.ping }
|
88
|
-
def retry_on_connection_failure(&block)
|
89
|
-
raise 'Missing mandatory block parameter on call to Mongo::Connection#retry_on_connection_failure' unless block
|
90
|
-
# No need to double retry calls
|
91
|
-
return block.call(false) if Thread.current[:mongo_ha_active?]
|
92
|
-
retried = false
|
93
|
-
mongos_retries = 0
|
94
|
-
begin
|
95
|
-
Thread.current[:mongo_ha_active?] = true
|
96
|
-
result = block.call(retried)
|
97
|
-
retried = false
|
98
|
-
result
|
99
|
-
rescue Mongo::ConnectionFailure => exc
|
100
|
-
# Retry if reconnected, but only once to prevent an infinite loop
|
101
|
-
logger.warn "Connection Failure: '#{exc.message}' [#{exc.error_code}]"
|
102
|
-
if !retried && _reconnect
|
103
|
-
retried = true
|
104
|
-
retry
|
105
|
-
end
|
106
|
-
raise exc
|
107
|
-
rescue Mongo::AuthenticationError => exc
|
108
|
-
# Retry once due to rare failures during authentication against MongoDB V3 servers
|
109
|
-
logger.warn "Authentication Failure: '#{exc.message}' [#{exc.error_code}]"
|
110
|
-
if !retried && _reconnect
|
111
|
-
retried = true
|
112
|
-
retry
|
113
|
-
end
|
114
|
-
raise exc
|
115
|
-
rescue Mongo::OperationTimeout => exc
|
116
|
-
logger.warn "OperationTimeout: #{exc.message}"
|
117
|
-
if !retried && _reconnect
|
118
|
-
retried = true
|
119
|
-
retry
|
120
|
-
end
|
121
|
-
raise exc
|
122
|
-
rescue Mongo::OperationFailure => exc
|
123
|
-
# Workaround not master issue. Disconnect connection when we get a not master
|
124
|
-
# error message. Master checks for an exact match on "not master", whereas
|
125
|
-
# it sometimes gets: "not master and slaveok=false"
|
126
|
-
if exc.result
|
127
|
-
error = exc.result['err'] || exc.result['errmsg']
|
128
|
-
close if error && error.include?('not master')
|
129
|
-
end
|
130
|
-
|
131
|
-
# These get returned when connected to a local mongos router when it in turn
|
132
|
-
# has connection failures talking to the remote shards. All we do is retry the same operation
|
133
|
-
# since it's connections to multiple remote shards may have failed.
|
134
|
-
# Disconnecting the current connection will not help since it is just to the mongos router
|
135
|
-
# First make sure it is connected to the mongos router
|
136
|
-
raise exc unless (OPERATION_FAILURE_ERRORS.any? { |err| exc.message.include?(err) }) || (exc.message.strip == ':')
|
137
|
-
|
138
|
-
mongos_retries += 1
|
139
|
-
if mongos_retries <= 60
|
140
|
-
retried = true
|
141
|
-
Kernel.sleep(0.5)
|
142
|
-
logger.warn "[#{primary.inspect}] Router Connection Failure. Retry ##{mongos_retries}. Exc: '#{exc.message}' [#{exc.error_code}]"
|
143
|
-
retry
|
144
|
-
end
|
145
|
-
raise exc
|
146
|
-
ensure
|
147
|
-
Thread.current[:mongo_ha_active?] = false
|
148
|
-
end
|
149
|
-
end
|
150
|
-
|
151
|
-
private
|
152
|
-
|
153
|
-
# Call this method whenever a Mongo::ConnectionFailure Exception
|
154
|
-
# has been raised to re-establish the connection
|
155
|
-
#
|
156
|
-
# This method is thread-safe and ensure that only one thread at a time
|
157
|
-
# per connection will attempt to re-establish the connection
|
158
|
-
#
|
159
|
-
# Returns whether the connection is connected again
|
160
|
-
def _reconnect
|
161
|
-
logger.debug 'Going to reconnect'
|
162
|
-
|
163
|
-
# Prevent other threads from invoking reconnect logic at the same time
|
164
|
-
@@failover_mutex.synchronize do
|
165
|
-
# Another thread may have already failed over the connection by the
|
166
|
-
# time this threads gets in
|
167
|
-
begin
|
168
|
-
ping
|
169
|
-
rescue Mongo::ConnectionFailure
|
170
|
-
# Connection still not available, run code below
|
171
|
-
end
|
172
|
-
|
173
|
-
if active?
|
174
|
-
logger.info "Connected to: #{primary.inspect}"
|
175
|
-
return true
|
176
|
-
end
|
177
|
-
|
178
|
-
if reconnect_attempts > 0
|
179
|
-
# Wait for other threads to finish working on their sockets
|
180
|
-
retries = 1
|
181
|
-
retry_seconds = reconnect_retry_seconds
|
182
|
-
begin
|
183
|
-
logger.warn "Connection unavailable. Waiting: #{retry_seconds} seconds before retrying"
|
184
|
-
sleep retry_seconds
|
185
|
-
ping
|
186
|
-
rescue Mongo::ConnectionFailure => exc
|
187
|
-
if retries < reconnect_attempts
|
188
|
-
retries += 1
|
189
|
-
retry_seconds *= reconnect_retry_multiplier
|
190
|
-
retry_seconds = reconnect_max_retry_seconds if retry_seconds > reconnect_max_retry_seconds
|
191
|
-
retry
|
192
|
-
end
|
193
|
-
|
194
|
-
logger.error "Auto-reconnect giving up after #{retries} reconnect attempts"
|
195
|
-
raise exc
|
196
|
-
end
|
197
|
-
logger.info "Successfully reconnected to: #{primary.inspect}"
|
198
|
-
end
|
199
|
-
connected?
|
200
|
-
end
|
201
|
-
end
|
202
|
-
|
203
|
-
end
|
204
|
-
end
|
205
|
-
end
|
data/test/readme.md
DELETED
@@ -1,48 +0,0 @@
|
|
1
|
-
## Testing
|
2
|
-
|
3
|
-
Unfortunately the only way to properly test mongo_ha is to startup a console with connections
|
4
|
-
active and to stop / restart the mongo servers in the replicaset as follows:
|
5
|
-
|
6
|
-
|
7
|
-
#### Run the following code in a console
|
8
|
-
|
9
|
-
```ruby
|
10
|
-
collection = Cache::Identity.database['test']
|
11
|
-
collection.drop
|
12
|
-
threads = 5.times.collect do |i|
|
13
|
-
Thread.new do
|
14
|
-
100.times do |j|
|
15
|
-
1_000.times do |k|
|
16
|
-
collection.insert(_id: "#{i}-#{j}-#{k}")
|
17
|
-
collection.find_one(_id: "#{i}-#{j}-#{k}")
|
18
|
-
puts("#{i}-#{j}-#{k}") if k % 1000 == 0
|
19
|
-
end
|
20
|
-
puts "#{i}-#{j} pausing"
|
21
|
-
sleep 5
|
22
|
-
end
|
23
|
-
puts "#{i} Complete"
|
24
|
-
end
|
25
|
-
end
|
26
|
-
```
|
27
|
-
|
28
|
-
#### Steps
|
29
|
-
|
30
|
-
While running the above code in the console
|
31
|
-
|
32
|
-
* Stop 1 slave server
|
33
|
-
|
34
|
-
Nothing should appear in the logs and everything should process fine
|
35
|
-
|
36
|
-
* Stop another slave
|
37
|
-
|
38
|
-
The logs should show retries
|
39
|
-
|
40
|
-
* Start up one of the 2 slaves that were stopped
|
41
|
-
|
42
|
-
The processing should resume successfully
|
43
|
-
|
44
|
-
#### To stop the test
|
45
|
-
|
46
|
-
```ruby
|
47
|
-
threads.each(&:kill)
|
48
|
-
```
|