diff options
Diffstat (limited to 'erts/doc')
| -rw-r--r-- | erts/doc/src/erl.xml | 47 | ||||
| -rw-r--r-- | erts/doc/src/erlang.xml | 8 | ||||
| -rw-r--r-- | erts/doc/src/erts_alloc.xml | 21 | ||||
| -rw-r--r-- | erts/doc/src/notes.xml | 2 | ||||
| -rw-r--r-- | erts/doc/src/zlib.xml | 30 |
5 files changed, 69 insertions, 39 deletions
diff --git a/erts/doc/src/erl.xml b/erts/doc/src/erl.xml index bf0d132955..e737727941 100644 --- a/erts/doc/src/erl.xml +++ b/erts/doc/src/erl.xml @@ -941,6 +941,10 @@ when schedulers frequently run out of work. When disabled, the frequency with which schedulers run out of work will not be taken into account by the load balancing logic. + <br/> <c>+scl false</c> is similar to + <seealso marker="#+sub">+sub true</seealso> with the difference + that <c>+sub true</c> also will balance scheduler utilization + between schedulers. </p> </item> <tag><marker id="+sct"><c>+sct CpuTopology</c></marker></tag> @@ -1087,6 +1091,29 @@ documentation of the <seealso marker="#+sbt">+sbt</seealso> flag. </p> </item> + <tag><marker id="+sub"><c>+sub true|false</c></marker></tag> + <item> + <p>Enable or disable + <seealso marker="erts:erlang#statistics_scheduler_wall_time">scheduler + utilization</seealso> balancing of load. By default scheduler + utilization balancing is disabled and instead scheduler + compaction of load is enabled which will strive for a load + distribution which causes as many scheduler threads as possible + to be fully loaded (i.e., not run out of work). When scheduler + utilization balancing is enabled the system will instead try to + balance scheduler utilization between schedulers. That is, + strive for equal scheduler utilization on all schedulers. + <br/> <c>+sub true</c> is only supported on + systems where the runtime system detects and use a monotonically + increasing high resolution clock. On other systems, the runtime + system will fail to start. + <br/> <c>+sub true</c> implies + <seealso marker="#+scl">+scl false</seealso>. The difference + between <c>+sub true</c> and <c>+scl false</c> is that + <c>+scl false</c> will not try to balance the scheduler + utilization. + </p> + </item> <tag><marker id="+swct"><c>+sws very_eager|eager|medium|lazy|very_lazy</c></marker></tag> <item> <p> @@ -1126,18 +1153,18 @@ <tag><marker id="+spp"><c>+spp Bool</c></marker></tag> <item> <p>Set default scheduler hint for port parallelism. If set to - <c>true</c>, the VM will schedule port tasks when it by this can - improve the parallelism in the system. If set to <c>false</c>, - the VM will try to perform port tasks immediately and by this - improve latency at the expense of parallelism. If this - flag has not been passed, the default scheduler hint for port - parallelism is currently <c>false</c>. The default used can be - inspected in runtime by calling - <seealso marker="erlang#system_info_port_parallelism">erlang:system_info(port_parallelism)</seealso>. + <c>true</c>, the VM will schedule port tasks when doing so will + improve parallelism in the system. If set to <c>false</c>, the VM + will try to perform port tasks immediately, improving latency at the + expense of parallelism. If this flag has not been passed, the + default scheduler hint for port parallelism is currently + <c>false</c>. The default used can be inspected in runtime by + calling <seealso + marker="erlang#system_info_port_parallelism">erlang:system_info(port_parallelism)</seealso>. The default can be overriden on port creation by passing the <seealso marker="erlang#open_port_parallelism">parallelism</seealso> - option to - <seealso marker="erlang#open_port/2">open_port/2</seealso></p>. + option to <seealso + marker="erlang#open_port/2">open_port/2</seealso></p>. </item> <tag><marker id="sched_thread_stack_size"><c><![CDATA[+sss size]]></c></marker></tag> <item> diff --git a/erts/doc/src/erlang.xml b/erts/doc/src/erlang.xml index 124302a2cb..ea753cfaaf 100644 --- a/erts/doc/src/erlang.xml +++ b/erts/doc/src/erlang.xml @@ -3011,11 +3011,11 @@ os_prompt% </pre> <tag><marker id="open_port_parallelism"><c>{parallelism, Boolean}</c></marker></tag> <item> <p>Set scheduler hint for port parallelism. If set to <c>true</c>, - the VM will schedule port tasks when it by this can improve the + the VM will schedule port tasks when doing so will improve parallelism in the system. If set to <c>false</c>, the VM will - try to perform port tasks immediately and by this improving the - latency at the expense of parallelism. The default can be set on - system startup by passing the + try to perform port tasks immediately, improving latency at the + expense of parallelism. The default can be set on system startup + by passing the <seealso marker="erl#+spp">+spp</seealso> command line argument to <seealso marker="erl">erl(1)</seealso>. </p> diff --git a/erts/doc/src/erts_alloc.xml b/erts/doc/src/erts_alloc.xml index fffa9f594c..c9eca39a99 100644 --- a/erts/doc/src/erts_alloc.xml +++ b/erts/doc/src/erts_alloc.xml @@ -395,16 +395,17 @@ <c><![CDATA[<utilization>]]></c> is an integer in the range <c>[0, 100]</c> representing utilization in percent. When a utilization value larger than zero is used, allocator instances - are allowed to abandon multiblock carriers. Currently the default - is zero. If <c>de</c> (default enabled) is passed instead of a - <c><![CDATA[<utilization>]]></c>, a recomended non zero utilization - value will be used. The actual value chosen depend on allocator - type and may be changed between ERTS versions. Carriers will be - abandoned when memory utilization in the allocator instance falls - below the utilization value used. Once a carrier has been abandoned, - no new allocations will be made in it. When an allocator instance - gets an increased multiblock carrier need, it will first try to - fetch an abandoned carrier from an allocator instances of the same + are allowed to abandon multiblock carriers. If <c>de</c> (default + enabled) is passed instead of a <c><![CDATA[<utilization>]]></c>, + a recomended non zero utilization value will be used. The actual + value chosen depend on allocator type and may be changed between + ERTS versions. Currently the default equals <c>de</c>, but this + may be changed in the future. Carriers will be abandoned when + memory utilization in the allocator instance falls below the + utilization value used. Once a carrier has been abandoned, no new + allocations will be made in it. When an allocator instance gets an + increased multiblock carrier need, it will first try to fetch an + abandoned carrier from an allocator instances of the same allocator type. If no abandoned carrier could be fetched, it will create a new empty carrier. When an abandoned carrier has been fetched it will function as an ordinary carrier. This feature has diff --git a/erts/doc/src/notes.xml b/erts/doc/src/notes.xml index 8c008c493e..b4ebef72f4 100644 --- a/erts/doc/src/notes.xml +++ b/erts/doc/src/notes.xml @@ -257,7 +257,7 @@ processes before the BIF returns, or fail with an exception due to the port not being open. </p><p> The synchronous port BIFs are: </p> <list> <item><seealso - marker="erlang#port_close/1/"><c>port_close/1</c></seealso></item> + marker="erlang#port_close/1"><c>port_close/1</c></seealso></item> <item><seealso marker="erlang#port_command/2"><c>port_command/2</c></seealso></item> <item><seealso diff --git a/erts/doc/src/zlib.xml b/erts/doc/src/zlib.xml index afc597b729..11a7437f5a 100644 --- a/erts/doc/src/zlib.xml +++ b/erts/doc/src/zlib.xml @@ -161,20 +161,22 @@ list_to_binary([Compressed|Last])</pre> state. <c><anno>MemLevel</anno></c>=1 uses minimum memory but is slow and reduces compression ratio; <c><anno>MemLevel</anno></c>=9 uses maximum memory for optimal speed. The default value is 8.</p> - <p>The <c><anno>Strategy</anno></c> parameter is used to tune the - compression algorithm. Use the value <c>default</c> for - normal data, <c>filtered</c> for data produced by a filter - (or predictor), or <c>huffman_only</c> to force Huffman - encoding only (no string match). Filtered data consists - mostly of small values with a somewhat random - distribution. In this case, the compression algorithm is - tuned to compress them better. The effect of - <c>filtered</c>is to force more Huffman coding and less - string matching; it is somewhat intermediate between - <c>default</c> and <c>huffman_only</c>. The <c><anno>Strategy</anno></c> - parameter only affects the compression ratio but not the - correctness of the compressed output even if it is not set - appropriately.</p> + <p>The <c><anno>Strategy</anno></c> parameter is used to tune + the compression algorithm. Use the value <c>default</c> for + normal data, <c>filtered</c> for data produced by a filter (or + predictor), <c>huffman_only</c> to force Huffman encoding + only (no string match), or <c>rle</c> to limit match + distances to one (run-length encoding). Filtered data + consists mostly of small values with a somewhat random + distribution. In this case, the compression algorithm is tuned + to compress them better. The effect of <c>filtered</c>is to + force more Huffman coding and less string matching; it is + somewhat intermediate between <c>default</c> and + <c>huffman_only</c>. <c>rle</c> is designed to be almost as + fast as <c>huffman_only</c>, but give better compression for PNG + image data. The <c><anno>Strategy</anno></c> parameter only + affects the compression ratio but not the correctness of the + compressed output even if it is not set appropriately.</p> </desc> </func> <func> |