memory management - Allocating Physically Contiguous Pages from User Space in Linux -

-

i need allocate physically contiguous pages user space , physical address. how can so? need physically contiguous because i'm working in-conjunction hardware needs that. get_free_pages understood kernel function , returns virtual address


Comments

Post a Comment

Popular posts from this blog

Capture and play voice with Asterisk ARI -

-
there channel ari demo in wich can control channel state: ring, answer, play silence, play tone or audio-file ( https://github.com/asterisk/ari-examples/tree/master/channel-state , https://wiki.asterisk.org/wiki/display/ast/ari+and+channels%3a+manipulating+channel+state ) possible receive chunks (parts, buffers, etc.) of call voice (which created remote subscriber) or write chunks of voice, example array of bytes (not file) in audio format (alaw, ulow etc). you can use asterisk eagi interface voice data. other option use record or mixmonitor app record channel(channel have put stasis allow dialplan control ari) "write chunks of voice" can done application playback also can create own application using c/c++, compile asterisk , result want. no, can't redirect voice directly using ari.
Read more

python - How to use elasticsearch.helpers.streaming_bulk -

-
can advice how use function elasticsearch.helpers.streaming_bulk instead elasticsearch.helpers.bulk indexing data elasticsearch. if change streaming_bulk instead of bulk, nothing gets indexed, guess needs used in different form. code below creates index, type , index data csv file in chunks of 500 elemens elasticsearch. working wandering possible increse prerformance. that's why want try out streaming_bulk function. currently need 10 minutes index 1 million rows csv document of 200mb. use 2 machines, centos 6.6 8 cpu-s, x86_64, cpu mhz: 2499.902, mem: 15.574g total. not sure can go faster. es = elasticsearch.elasticsearch([{'host': 'uxmachine-test', 'port': 9200}]) index_name = 'new_index' type_name = 'new_type' mapping = json.loads(open(config["index_mapping"]).read()) #read mapping json file es.indices.create(index_name) es.indices.put_mapping(index=index_name, doc_type=type_name, body=mapping) open(file_to_index, ...
Read more