diff --git a/CHANGELOG.md b/CHANGELOG.md index 1199f33..9ad1b8a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,6 @@ +## 3.2.1 + - Raise the default value of `decode_size_limit_bytes` up to 512 MB. [#46](https://github.com/logstash-plugins/logstash-codec-json_lines/pull/46) + ## 3.2.0 - Add decode_size_limit_bytes option to limit the maximum size of each JSON line that can be parsed.[#43](https://github.com/logstash-plugins/logstash-codec-json_lines/pull/43) diff --git a/docs/index.asciidoc b/docs/index.asciidoc index 49a54ce..59aafc5 100644 --- a/docs/index.asciidoc +++ b/docs/index.asciidoc @@ -35,6 +35,7 @@ Therefore this codec cannot work with line oriented inputs. |======================================================================= |Setting |Input type|Required | <> |<>, one of `["ASCII-8BIT", "UTF-8", "US-ASCII", "Big5", "Big5-HKSCS", "Big5-UAO", "CP949", "Emacs-Mule", "EUC-JP", "EUC-KR", "EUC-TW", "GB2312", "GB18030", "GBK", "ISO-8859-1", "ISO-8859-2", "ISO-8859-3", "ISO-8859-4", "ISO-8859-5", "ISO-8859-6", "ISO-8859-7", "ISO-8859-8", "ISO-8859-9", "ISO-8859-10", "ISO-8859-11", "ISO-8859-13", "ISO-8859-14", "ISO-8859-15", "ISO-8859-16", "KOI8-R", "KOI8-U", "Shift_JIS", "UTF-16BE", "UTF-16LE", "UTF-32BE", "UTF-32LE", "Windows-31J", "Windows-1250", "Windows-1251", "Windows-1252", "IBM437", "IBM737", "IBM775", "CP850", "IBM852", "CP852", "IBM855", "CP855", "IBM857", "IBM860", "IBM861", "IBM862", "IBM863", "IBM864", "IBM865", "IBM866", "IBM869", "Windows-1258", "GB1988", "macCentEuro", "macCroatian", "macCyrillic", "macGreek", "macIceland", "macRoman", "macRomania", "macThai", "macTurkish", "macUkraine", "CP950", "CP951", "IBM037", "stateless-ISO-2022-JP", "eucJP-ms", "CP51932", "EUC-JIS-2004", "GB12345", "ISO-2022-JP", "ISO-2022-JP-2", "CP50220", "CP50221", "Windows-1256", "Windows-1253", "Windows-1255", "Windows-1254", "TIS-620", "Windows-874", "Windows-1257", "MacJapanese", "UTF-7", "UTF8-MAC", "UTF-16", "UTF-32", "UTF8-DoCoMo", "SJIS-DoCoMo", "UTF8-KDDI", "SJIS-KDDI", "ISO-2022-JP-KDDI", "stateless-ISO-2022-JP-KDDI", "UTF8-SoftBank", "SJIS-SoftBank", "BINARY", "CP437", "CP737", "CP775", "IBM850", "CP857", "CP860", "CP861", "CP862", "CP863", "CP864", "CP865", "CP866", "CP869", "CP1258", "Big5-HKSCS:2008", "ebcdic-cp-us", "eucJP", "euc-jp-ms", "EUC-JISX0213", "eucKR", "eucTW", "EUC-CN", "eucCN", "CP936", "ISO2022-JP", "ISO2022-JP2", "ISO8859-1", "ISO8859-2", "ISO8859-3", "ISO8859-4", "ISO8859-5", "ISO8859-6", "CP1256", "ISO8859-7", "CP1253", "ISO8859-8", "CP1255", "ISO8859-9", "CP1254", "ISO8859-10", "ISO8859-11", "CP874", "ISO8859-13", "CP1257", "ISO8859-14", "ISO8859-15", "ISO8859-16", "CP878", "MacJapan", "ASCII", "ANSI_X3.4-1968", "646", "CP65000", "CP65001", "UTF-8-MAC", "UTF-8-HFS", "UCS-2BE", "UCS-4BE", "UCS-4LE", "CP932", "csWindows31J", "SJIS", "PCK", "CP1250", "CP1251", "CP1252", "external", "locale"]`|No +| <> |<>|No | <> |<>|No | <> |<>|No | <> |<>|No @@ -58,6 +59,14 @@ actual encoding of the text and logstash will convert it for you. For nxlog users, you'll want to set this to `CP1252` +[id="plugins-{type}s-{plugin}-decode_size_limit_bytes"] +===== `decode_size_limit_bytes` + +* Value type is <> +* Default value is 512 MB + +Maximum number of bytes for a single line before stop processing. + [id="plugins-{type}s-{plugin}-delimiter"] ===== `delimiter` diff --git a/lib/logstash/codecs/json_lines.rb b/lib/logstash/codecs/json_lines.rb index 8e2256a..ef63afc 100644 --- a/lib/logstash/codecs/json_lines.rb +++ b/lib/logstash/codecs/json_lines.rb @@ -28,6 +28,8 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base config_name "json_lines" + DEFAULT_DECODE_SIZE_LIMIT_BYTES = 512 * (1024 * 1024) + # The character encoding used in this codec. Examples include `UTF-8` and # `CP1252` # @@ -43,9 +45,9 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base config :delimiter, :validate => :string, :default => "\n" # Maximum number of bytes for a single line before a fatal exception is raised - # which will stop Logsash. - # The default is 20MB which is quite large for a JSON document - config :decode_size_limit_bytes, :validate => :number, :default => 20 * (1024 * 1024) # 20MB + # which will stop Logstash. + # The default is 512MB which is quite large for a JSON document + config :decode_size_limit_bytes, :validate => :number, :default => DEFAULT_DECODE_SIZE_LIMIT_BYTES # 512MB # Defines a target field for placing decoded fields. # If this setting is omitted, data gets stored at the root (top level) of the event. @@ -55,6 +57,9 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base public def register + if decode_size_limit_bytes == DEFAULT_DECODE_SIZE_LIMIT_BYTES + deprecation_logger.deprecated "The default value for `decode_size_limit_bytes`, currently at 512Mb, will be lowered in a future version to prevent Out of Memory errors from abnormally large messages or missing delimiters. Please set a value that reflects the largest expected message size (e.g. 20971520 for 20Mb)" + end @buffer = FileWatch::BufferedTokenizer.new(@delimiter, @decode_size_limit_bytes) @converter = LogStash::Util::Charset.new(@charset) @converter.logger = @logger diff --git a/logstash-codec-json_lines.gemspec b/logstash-codec-json_lines.gemspec index 06f47e0..9d73ce7 100644 --- a/logstash-codec-json_lines.gemspec +++ b/logstash-codec-json_lines.gemspec @@ -1,7 +1,7 @@ Gem::Specification.new do |s| s.name = 'logstash-codec-json_lines' - s.version = '3.2.0' + s.version = '3.2.1' s.licenses = ['Apache License (2.0)'] s.summary = "Reads and writes newline-delimited JSON" s.description = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program" diff --git a/spec/codecs/json_lines_spec.rb b/spec/codecs/json_lines_spec.rb index 85d4361..7fc9ff5 100644 --- a/spec/codecs/json_lines_spec.rb +++ b/spec/codecs/json_lines_spec.rb @@ -119,6 +119,7 @@ end describe "decode_size_limits_bytes" do + let(:codec_options) { { "decode_size_limit_bytes" => 20 * 1024 * 1024 } } # lower the default to avoid OOM errors in tests let(:maximum_payload) { "a" * subject.decode_size_limit_bytes } it "should not raise an error if the number of bytes is not exceeded" do