{"id":53906,"date":"2019-12-13T00:00:00","date_gmt":"2019-12-12T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie"},"modified":"2020-02-18T14:01:51","modified_gmt":"2020-02-18T11:01:51","slug":"skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie","status":"publish","type":"post","link":"https:\/\/prohoster.info\/ro\/blog\/administrirovanie\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie","title":{"rendered":"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Acest articol este al doilea dintr-o serie despre comprimarea rapid\u0103 a datelor. \u00cen primul articol a fost descris un compresor care func\u021bioneaz\u0103 cu o vitez\u0103 de 10GB\/s pe un singur nucleu de procesor (compresie minim\u0103, RTT-Min). <\/p>\n<p>Acest compresor a fost implementat deja \u00een echipamentele duplicatorilor criminalistici pentru comprimarea rapid\u0103 a dump-urilor de medii informa\u021bionale \u0219i pentru \u00eent\u0103rirea rezisten\u021bei criptografiei; de asemenea, poate fi utilizat pentru comprimarea imaginilor virtuale \u0219i a fi\u0219ierelor swap din memoria RAM atunci c\u00e2nd sunt salvate pe unit\u0103\u021bi SSD de mare vitez\u0103.<\/p>\n<p>\u00cen primul articol a fost, de asemenea, anun\u021bat\u0103 dezvoltarea unui algoritm de compresie pentru comprimarea backup-urilor HDD \u0219i SSD (compresie medie, RTT-Mid) cu parametrii de comprimare semnificativ \u00eembun\u0103t\u0103\u021bi\u021bi. P\u00e2n\u0103 acum, acest compresor este complet gata \u0219i acest articol este dedicat lui. <br \/>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><br \/>\nCompresorul care implementeaz\u0103 algoritmul RTT-Mid asigur\u0103 un nivel de comprimare comparabil cu cel al arhivatorilor standard precum WinRar, 7-Zip, care func\u021bioneaz\u0103 \u00een mod rapid. \u00cen acela\u0219i timp, viteza sa de lucru este cu cel pu\u021bin un ordin de m\u0103rime mai mare. <\/p>\n<p>Viteza de comprimare\/decoperire a datelor este un parametru critic care determin\u0103 domeniul de aplicare al tehnologiilor de compresie. Este pu\u021bin probabil ca cineva s\u0103 se g\u00e2ndeasc\u0103 s\u0103 comprime un terabyte de date cu o vitez\u0103 de 10-15 MegaBiti pe secund\u0103 (acesta este viteza arhivatorilor \u00een modul standard de compresie), deoarece ar dura aproape dou\u0103zeci de ore cu procesorul complet \u00eenc\u0103rcat...<\/p>\n<p>Pe de alt\u0103 parte, acela\u0219i terabyte poate fi copiat cu viteze de aproximativ 2-3 GigaBiti pe secund\u0103 \u00een aproximativ zece minute. <\/p>\n<p>Prin urmare, comprimarea informa\u021biilor de mare volum este relevant\u0103 dac\u0103 se realizeaz\u0103 cu o vitez\u0103 de cel pu\u021bin viteza real\u0103 de intrare\/ie\u0219ire. Pentru sistemele moderne, aceasta nu este mai mic\u0103 de 100 MegaBiti pe secund\u0103. <\/p>\n<p>Aceste viteze pot fi ob\u021binute de compresoare moderne doar \u00een modul \u201erapid\u201d. Tocmai \u00een acest mod relevant vom compara algoritmul RTT-Mid cu compresoarele tradi\u021bionale.<\/p>\n<h4>Testarea comparativ\u0103 a noului algoritm de compresie<\/h4>\n<p>\n Compresorul RTT-Mid a func\u021bionat \u00een cadrul unui program de testare. \u00centr-o aplica\u021bie \u201ereal\u0103\u201d de lucru, acesta func\u021bioneaz\u0103 semnificativ mai repede, utiliz\u00e2nd corect multi-threading-ul \u0219i aplic\u00e2nd un compilator \u201enormal\u201d, nu C#. <\/p>\n<p>Deoarece compresoarele utilizate \u00een testul comparativ sunt construite pe principii diferite \u0219i diferite tipuri de date comprim\u0103 diferit, pentru obiectivitatea testului s-a folosit metoda m\u0103sur\u0103rii \u201etemperaturii medii pe spital\u201d...<\/p>\n<p>A fost creat un fi\u0219ier de dumping pe sectoare al discului logic cu sistemul de operare Windows 10, aceasta fiind cea mai natural\u0103 combina\u021bie de structuri de date disponibile pe fiecare computer. Comprimarea acestui fi\u0219ier va permite compararea vitezei \u0219i gradului de compresie al noului algoritm cu cele mai avansate compresoare utilizate \u00een arhivatoarele moderne.<\/p>\n<p>Acesta este fi\u0219ierul de dumping:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/39fc5bfe9812ac2417d6eb8ef1dde0a8.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nFi\u0219ierul de dumping a fost comprimat cu compresoare RTT-Mid, 7-zip, WinRar. Compresorul WinRar \u0219i 7-zip au fost setate pentru viteza maxim\u0103.<\/p>\n<p>Compresorul func\u021bioneaz\u0103 <b>7-zip<\/b>:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/1b088a99fb7b04d5b6ccb500ff74c73e.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nAcesta utilizeaz\u0103 procesorul la 100%, cu o vitez\u0103 medie de citire a fi\u0219ierului de dumping de aproximativ 60 MegaOcte\u021bi\/sec.<\/p>\n<p>Compresorul func\u021bioneaz\u0103 <b>WinRar<\/b>:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/462024e8304a90a885ef3857fbd119e1.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nSitua\u021bia este similar\u0103, utilizarea procesorului este aproape 100%, viteza medie de citire a dumpingului este de aproximativ 125 MegaOcte\u021bi\/sec.<\/p>\n<p>Ca \u0219i \u00een cazul anterior, viteza de lucru a arhivatorului este limitat\u0103 de capabilit\u0103\u021bile procesorului.<\/p>\n<p>Acum ruleaz\u0103 programul de testare al compresorului <b>RTT-Mid<\/b>:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/f46fabcbb362dcf99a8b55877954c3a8.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nCaptura de ecran arat\u0103 c\u0103 procesorul este utilizat la 50% \u0219i este inactiv restul timpului, deoarece nu exist\u0103 unde s\u0103 fie desc\u0103rcate datele comprimate. Discul de desc\u0103rcare a datelor (Discul 0) este practic complet \u00eenc\u0103rcat. Viteza de citire a datelor (Discul 1) fluctueaz\u0103 semnificativ, dar \u00een medie este mai mare de 200 MegaOcte\u021bi\/sec.<\/p>\n<p>Viteza de lucru a compresorului este limitat\u0103 \u00een acest caz de capabilit\u0103\u021bile de scriere a datelor comprimate pe Discul 0.<\/p>\n<p>Acum gradul de compresie al arhivelor rezultate:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/1e0740937909c6a5860ef35d15da9e7f.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/6e74c8ceab741943a59eca87f092e25b.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/3b2f8bed83ea72917f87a3a9813294fc.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nSe poate observa c\u0103 compresorul RTT-Mid a realizat cea mai bun\u0103 compresie, arhiva creat\u0103 de acesta fiind cu 1,3 GigaOcte\u021bi mai mic\u0103 dec\u00e2t arhiva WinRar \u0219i cu 2,1 GigaOcte\u021bi mai mic\u0103 dec\u00e2t arhiva 7z.<\/p>\n<p>Timpul necesar pentru crearea arhivei:<\/p>\n<ul>\n<li> 7-zip \u2013 26 minute \u0219i 10 secunde;<\/li>\n<li> WinRar \u2013 17 minute \u0219i 40 secunde;<\/li>\n<li> RTT-Mid \u2013 7 minute \u0219i 30 secunde.<\/li>\n<\/ul>\n<p>\nAstfel, chiar \u0219i programul de testare, neoptimizat, folosind algoritmul RTT-Mid, a reu\u0219it s\u0103 creeze arhiva de mai bine de dou\u0103 ori mai repede, iar arhiva rezultat\u0103 a fost semnificativ mai mic\u0103 dec\u00e2t a concuren\u021bilor...<\/p>\n<p>Cei care nu cred capturile de ecran pot verifica veridicitatea acestora de unul singur. Programul de testare este disponibil la <noindex><a rel=\"nofollow\" href=\"https:\/\/yadi.sk\/d\/9CkY30b1lRcLYw\">linkul<\/a><\/noindex>, desc\u0103rca\u021bi \u0219i verifica\u021bi.<\/p>\n<p>Dar doar pe procesoarele care suport\u0103 AVX-2; f\u0103r\u0103 suportul acestor instruc\u021biuni, compressorul nu func\u021bioneaz\u0103, iar nu testa\u021bi algoritmul pe procesoare AMD vechi, acestea sunt lente \u00een executarea comenzilor AVX...<\/p>\n<h4>Metoda de compresie utilizat\u0103<\/h4>\n<p>\nAlgoritmul utilizeaz\u0103 metoda de indexare a fragmentelor repetitive de text la granula\u021bie de byte. Aceast\u0103 metod\u0103 de comprimare este cunoscut\u0103 de mult timp, dar nu a fost folosit\u0103, deoarece opera\u021bia de c\u0103utare a coresponden\u021belor era foarte costisitoare \u00een termeni de resurse necesare \u0219i necesita mult mai mult timp dec\u00e2t construirea unui dic\u021bionar. Astfel, algoritmul RTT-Mid este un exemplu clasic al mi\u0219c\u0103rii \u201e\u00eenapoi \u00een viitor\u201d...<\/p>\n<p>\u00cen compressorul RTT se utilizeaz\u0103 un scaner de coresponden\u021be unic \u0219i rapid, care a permis accelerarea procesului de compresie. Scanerul este realizat manual, acesta fiind \u201efrumuse\u021bea mea\u2026\u201d, \u201epre\u021bul s\u0103u nu este mic, deoarece este realizat \u00een \u00eentregime manual\u201d (scris \u00een asamblare).<\/p>\n<p>Scanerul de c\u0103utare a coresponden\u021belor este realizat pe o schem\u0103 probabilistic\u0103 cu dou\u0103 niveluri: mai \u00eent\u00e2i se scaneaz\u0103 prezen\u021ba \u201esemnului\u201d de coresponden\u021b\u0103, iar abia dup\u0103 ce este identificat \u201esemnul\u201d \u00een acest loc se porne\u0219te procedura de descoperire a coresponden\u021bei reale. <\/p>\n<p>Fereastra de c\u0103utare a coresponden\u021belor are o dimensiune imprevizibil\u0103, \u00een func\u021bie de gradul de entropie din blocul de date procesat. Pentru date complet aleatorii (nesuprimabile), dimensiunea acesteia este de megabytes, iar pentru datele care au repet\u0103ri, dimensiunea este \u00eentotdeauna mai mare de un megabyte.<\/p>\n<p>\u00cens\u0103 multe formate moderne de date sunt nesuprimabile, iar utilizarea unui scaner resursiv pe acestea este inutil\u0103 \u0219i risipitoare, de aceea scanerul utilizeaz\u0103 dou\u0103 moduri de func\u021bionare. Ini\u021bial se caut\u0103 por\u021biuni din textul original cu posibile repet\u0103ri; aceast\u0103 opera\u021bie se desf\u0103\u0219oar\u0103, de asemenea, printr-o metod\u0103 probabilistic\u0103 \u0219i este realizat\u0103 foarte rapid (cu o vitez\u0103 de 4-6 Gigabytes\/sec). Apoi, por\u021biunile cu posibile coresponden\u021be sunt procesate de scanerul principal. <\/p>\n<p>Compresia prin indexare nu este foarte eficient\u0103, fiind nevoie s\u0103 se \u00eenlocuiasc\u0103 fragmentele repetate cu indici, iar matricea de indici reduce semnificativ coeficientul de compresie. <\/p>\n<p>Pentru a cre\u0219te gradul de compresie, sunt indexate nu doar coresponden\u021bele complete ale \u0219irurilor de octe\u021bi, ci \u0219i cele par\u021biale, atunci c\u00e2nd \u00een \u0219ir exist\u0103 octe\u021bi corespunz\u0103tori \u0219i necorespunz\u0103tori. Pentru aceasta, \u00een formatul indexului este inclus un c\u00e2mp de masc\u0103 a coresponden\u021belor care indic\u0103 octe\u021bii corespunz\u0103tori ai celor dou\u0103 blocuri. Pentru o compresie \u0219i mai mare, se folose\u0219te indexarea cu suprapunerea mai multor blocuri par\u021bial corespunz\u0103toare pe blocul curent. <\/p>\n<p>Toate acestea au permis ob\u021binerea \u00een compresorul RTT-Mid a unui grad de compresie comparabil cu cel al compresoarelor realizate prin metoda dic\u021bionarului, dar care func\u021bioneaz\u0103 mult mai repede.<\/p>\n<h4>Viteza de func\u021bionare a noului algoritm de compresie<\/h4>\n<p>\nDac\u0103 compresorul lucreaz\u0103 cu utilizarea monopolizat\u0103 a cache-ului de memorie (4 MegaBai\u021bi pentru un fir de execu\u021bie), atunci viteza de func\u021bionare variaz\u0103 \u00een intervalul de 700-2000 MegaBai\u021bi\/sec. pe un nucleu de procesor, \u00een func\u021bie de tipul datelor comprimate \u0219i depinde pu\u021bin de frecven\u021ba de lucru a procesorului. <\/p>\n<p>\u00cen implementarea multi-threading a compresorului, scalabilitatea eficient\u0103 este determinat\u0103 de volumul cache-ului de nivel trei. De exemplu, av\u00e2nd 9 MegaBai\u021bi de cache, nu are sens s\u0103 pornim mai mult de dou\u0103 fire de compresie, deoarece viteza nu se va \u00eembun\u0103t\u0103\u021bi. Dar cu un cache de 20 MegaBai\u021bi, se pot porni deja cinci fire de compresie.<\/p>\n<p>Un alt parametru semnificativ care determin\u0103 viteza de func\u021bionare a compresorului este laten\u021ba memoriei RAM. Algoritmul folose\u0219te accesuri aleatorii la RAM, dintre care o parte nu ajung \u00een cache (aproximativ 10%) \u0219i acesta este obligat s\u0103 a\u0219tepte datele din RAM, ceea ce reduce viteza de func\u021bionare. <\/p>\n<p>De asemenea, sistemul de intrare\/ie\u0219ire a datelor influen\u021beaz\u0103 semnificativ viteza compresorului. Cererile CPU pentru accesarea RAM de la intrare\/ie\u0219ire blocheaz\u0103 accesurile la date, ceea ce reduce, de asemenea, viteza de compresie. Aceast\u0103 problem\u0103 este semnificativ\u0103 pentru laptopuri \u0219i desktopuri, <a class=\"wpil_keyword_link\" href=\"https:\/\/prohoster.info\/ro\/server\/\"   title=\"servere\" data-wpil-keyword-link=\"linked\"  data-wpil-monitor-id=\"1458\">servere<\/a> iar aceasta devine mai pu\u021bin semnificativ\u0103 datorit\u0103 unui modul de control al accesului avansat la magistrala de sistem \u0219i a memoriei RAM multicanel.<\/p>\n<p>\u00cen \u00eentreaga text exist\u0103 referiri la compresie; decompresia este l\u0103sat\u0103 \u00een afara acestei discu\u021bii, deoarece acolo \u201etotul este \u00een regul\u0103\u201d. Decompresia se realizeaz\u0103 semnificativ mai rapid \u0219i este limitat\u0103 de viteza de citire\/scriere. Un nucleu fizic \u00eentr-un singur fir asigur\u0103 cu u\u0219urin\u021b\u0103 viteze de decompresie de 3-4 Gigabyte\/sec.<\/p>\n<p>Acest lucru se datoreaz\u0103 absen\u021bei \u00een procesul de decompresie a opera\u021biei de c\u0103utare a potrivirilor, care \u201econsum\u0103\u201d cele mai importante resurse ale procesorului \u0219i ale memoriei cache \u00een timpul compresiei. <\/p>\n<h4>Fiabilitatea stoc\u0103rii datelor comprimate<\/h4>\n<p>\nA\u0219a cum sugereaz\u0103 denumirea \u00eentregului tip de instrumente software care folosesc compresia datelor (compresoare), acestea sunt destinate stoc\u0103rii pe termen lung a informa\u021biei, nu ani, ci secole \u0219i milenii...<\/p>\n<p>Pe parcursul stoc\u0103rii, suporturile de informa\u021bii \u00ee\u0219i pierd o parte din date, iat\u0103 un exemplu:<\/p>\n<p><img decoding=\"async\" alt=\"Compresie rapid\u0103 rezistent\u0103 la defecte (continuare)\" src=\"\/wp-content\/uploads\/2019\/12\/b85564e175204e70ed7c3c3ed0fbf008.png\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nAcest suport de informa\u021bie \u201eanalogic\u201d are o mie de ani, unele fragmente au fost pierdute, dar \u00een general informa\u021bia este \u201ecitibil\u0103\u201d...<\/p>\n<p>Niciunul dintre produc\u0103torii responsabili de sistemele moderne de stocare digital\u0103 \u0219i de suporturile digitale nu ofer\u0103 garan\u021bii pentru integritatea complet\u0103 a datelor mai mult de 75 de ani.<br \/>\n\u0218i aceasta este o problem\u0103, dar o problem\u0103 am\u00e2nat\u0103; nepo\u021bii no\u0219tri o vor rezolva...<\/p>\n<p>Sistemele de stocare a datelor digitale pot pierde date nu doar dup\u0103 75 de ani; erorile \u00een date pot ap\u0103rea \u00een orice moment, chiar \u0219i \u00een timpul \u00eenregistr\u0103rii acestora; aceste distorsiuni sunt minime prin utilizarea redundan\u021bei \u0219i prin corectarea erorilor. Redundan\u021ba \u0219i sistemele de corectare nu pot restabili informa\u021bia pierdut\u0103 \u00eentotdeauna, iar dac\u0103 o fac, nu exist\u0103 garan\u021bii c\u0103 opera\u021bia de recuperare s-a desf\u0103\u0219urat corect.<\/p>\n<p>\u0218i aceasta este, de asemenea, o problem\u0103 major\u0103, dar nu am\u00e2nat\u0103, ci actual\u0103.<\/p>\n<p>Compresoarele moderne utilizate pentru arhivarea datelor digitale sunt construite pe diferite modific\u0103ri ale metodei de dic\u021bionar, iar pentru astfel de arhive, pierderea unui fragment de informa\u021bie va fi un eveniment fatal; exist\u0103 chiar un termen consacrat pentru aceast\u0103 situa\u021bie \u2014 arhiv\u0103 \u201ecorrupt\u0103\u201d...<\/p>\n<p>Fiabilitatea sc\u0103zut\u0103 a stoc\u0103rii informa\u021biilor \u00een arhivele cu comprimare prin dic\u021bionar este legat\u0103 de structura datelor comprimate. Informa\u021bia dintr-o astfel de arhiv\u0103 nu con\u021bine textul original, ci stocheaz\u0103 numerele \u00eenregistr\u0103rilor din dic\u021bionar, iar dic\u021bionarul este modificat dinamic cu textul comprimat curent. \u00cen cazul pierderii sau deform\u0103rii unui fragment din arhiv\u0103, toate \u00eenregistr\u0103rile ulterioare nu pot fi identificate nici dup\u0103 con\u021binut, nici dup\u0103 lungimea \u00eenregistr\u0103rii \u00een dic\u021bionar, deoarece nu este clar la ce corespunde num\u0103rul \u00eenregistr\u0103rii din dic\u021bionar.<\/p>\n<p>Recuperarea informa\u021biei dintr-o astfel de arhiv\u0103 \u201edeteriorat\u0103\u201d este imposibil\u0103.<\/p>\n<p>Algoritmul RTT se bazeaz\u0103 pe o metod\u0103 de stocare a datelor comprimate mai fiabil\u0103. Acesta aplic\u0103 o metod\u0103 indexat\u0103 pentru a \u021bine eviden\u021ba fragmentelor repetate. Aceast\u0103 abordare a comprim\u0103rii permite minimizarea consecin\u021belor distorsiunii informa\u021biei pe suport \u0219i, \u00een multe cazuri, corectarea automat\u0103 a distorsiunilor ap\u0103rute \u00een timpul stoc\u0103rii informa\u021biilor.<br \/>\nAceasta se datoreaz\u0103 faptului c\u0103 fi\u0219ierul arhiv\u0103 \u00een cazul comprim\u0103rii indexate con\u021bine dou\u0103 c\u00e2mpuri:<\/p>\n<ul>\n<li>c\u00e2mpul textului original, din care au fost eliminate sec\u021biunile repetate;<\/li>\n<li>c\u00e2mpul indicelui. <\/li>\n<\/ul>\n<p>\nC\u00e2mpul indicelui, critic pentru recuperarea informa\u021biei, nu este mare ca dimensiune \u0219i poate fi duplicat pentru a asigura o stocare fiabil\u0103 a datelor. Prin urmare, chiar dac\u0103 va fi pierdut un fragment din textul original sau din matricea indicelui, \u00eentreaga alt\u0103 informa\u021bie va putea fi recuperat\u0103 f\u0103r\u0103 probleme, la fel ca \u00een imaginea unui suport de informa\u021bie \u201eanalogic\u201d.<\/p>\n<h4>Dezavantajele algoritmului<\/h4>\n<p>\nF\u0103r\u0103 dezavantaje nu exist\u0103 avantaje. Metoda indexat\u0103 de comprimare nu comprim\u0103 secven\u021bele repetate de dimensiuni mici. Acest lucru se datoreaz\u0103 limit\u0103rilor metodei indexate. Indicele are o dimensiune de cel pu\u021bin 3 octe\u021bi \u0219i poate ajunge p\u00e2n\u0103 la 12 octe\u021bi. Dac\u0103 apare o repetare cu o dimensiune mai mic\u0103 dec\u00e2t indicele care o descrie, atunci aceasta nu este considerat\u0103, indiferent de c\u00e2t de frecvent se pot identifica astfel de repet\u0103ri \u00een fi\u0219ierul comprimat.<\/p>\n<p>Metoda tradi\u021bional\u0103 de compresie prin dic\u021bionar comprim\u0103 eficient multiple repeti\u021bii scurte, ating\u00e2nd astfel un coeficient de compresie mai mare comparativ cu compresia bazat\u0103 pe index. Totu\u0219i, acest lucru se realizeaz\u0103 printr-o \u00eenc\u0103rcare ridicat\u0103 a procesorului central; pentru a comprima datele mai eficient dec\u00e2t metoda de indexare, metoda prin dic\u021bionar trebuie s\u0103 reduc\u0103 viteza de procesare a datelor la 10-20 megabai\u021bi pe secund\u0103 \u00een condi\u021bii de calcul reale, atunci c\u00e2nd CPU este complet \u00eenc\u0103rcat.<\/p>\n<p>Aceste viteze reduse sunt inacceptabile pentru sistemele moderne de stocare a datelor \u0219i reprezint\u0103 mai mult un interes \u201eacademic\u201d dec\u00e2t unul practic.<\/p>\n<p>Gradul de compresie a informa\u021biilor va fi semnificativ \u00eembun\u0103t\u0103\u021bit \u00een urm\u0103toarea modificare a algoritmului RTT (RTT-Max), care este deja \u00een dezvoltare.<\/p>\n<p>A\u0219adar, ca \u00eentotdeauna, continuarea urmeaz\u0103\u2026<br \/>\n<br \/>Sursa: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/post\/479888\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0414\u0430\u043d\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u0443\u0436\u0435 \u0432\u0442\u043e\u0440\u0430\u044f \u0432 \u0442\u0435\u043c\u0435 \u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0439 \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u0438 \u0434\u0430\u043d\u043d\u044b\u0445. \u0412 \u043f\u0435\u0440\u0432\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u0431\u044b\u043b \u043e\u043f\u0438\u0441\u0430\u043d \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u043e\u0440 \u0440\u0430\u0431\u043e\u0442\u0430\u044e\u0449\u0438\u0439 \u0441\u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u044c\u044e 10\u0413\u0431\u0430\u0439\u0442\/\u0441\u0435\u043a. \u043d\u0430 \u043e\u0434\u043d\u043e \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043d\u043e\u0435 \u044f\u0434\u0440\u043e (\u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u0441\u0436\u0430\u0442\u0438\u0435, RTT-Min). \u042d\u0442\u043e\u0442 \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u043e\u0440, \u0443\u0436\u0435 \u0432\u043d\u0435\u0434\u0440\u0435\u043d \u0432 \u043e\u0431\u043e\u0440\u0443\u0434\u043e\u0432\u0430\u043d\u0438\u0435 \u043a\u0440\u0438\u043c\u0438\u043d\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0434\u0443\u0431\u043b\u0438\u043a\u0430\u0442\u043e\u0440\u043e\u0432 \u0434\u043b\u044f \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0433\u043e \u0441\u0436\u0430\u0442\u0438\u044f \u0434\u0430\u043c\u043f\u043e\u0432 \u043d\u043e\u0441\u0438\u0442\u0435\u043b\u0435\u0439 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u0438 \u0438 \u0443\u0441\u0438\u043b\u0435\u043d\u0438\u044f \u0441\u0442\u043e\u0439\u043a\u043e\u0441\u0442\u0438 \u043a\u0440\u0438\u043f\u0442\u043e\u0433\u0440\u0430\u0444\u0438\u0438, \u0442\u0430\u043a\u0436\u0435 \u043e\u043d \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0442\u044c\u0441\u044f \u0434\u043b\u044f \u0441\u0436\u0430\u0442\u0438\u044f \u043e\u0431\u0440\u0430\u0437\u043e\u0432 \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0445 \u043c\u0430\u0448\u0438\u043d \u0438 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[688],"tags":[],"class_list":["post-53906","post","type-post","status-publish","format-standard","hentry","category-administrirovanie"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u0414\u0430\u043d\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u0443\u0436\u0435 \u0432\u0442\u043e\u0440\u0430\u044f \u0432 \u0442\u0435\u043c\u0435 \u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0439 \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u0438 \u0434\u0430\u043d\u043d\u044b\u0445. \u0412 \u043f\u0435\u0440\u0432\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u0431\u044b\u043b \u043e\u043f\u0438\u0441\u0430\u043d \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u043e\u0440 \u0440\u0430\u0431\u043e\u0442\u0430\u044e\u0449\u0438\u0439 \u0441\u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u044c\u044e 10\u0413\u0431\u0430\u0439\u0442\/\u0441\u0435\u043a. \u043d\u0430 \u043e\u0434\u043d\u043e \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043d\u043e\u0435 \u044f\u0434\u0440\u043e (\u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u0441\u0436\u0430\u0442\u0438\u0435, RTT-Min).\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/ro\/blog\/administrirovanie\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2\" \/>\n\t\t<meta property=\"og:locale\" content=\"ro_RO\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u0421\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u0430\u044f \u043e\u0442\u043a\u0430\u0437\u043e\u0443\u0441\u0442\u043e\u0439\u0447\u0438\u0432\u0430\u044f \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u044f (\u041f\u0440\u043e\u0434\u043e\u043b\u0436\u0435\u043d\u0438\u0435) | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u0414\u0430\u043d\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u0443\u0436\u0435 \u0432\u0442\u043e\u0440\u0430\u044f \u0432 \u0442\u0435\u043c\u0435 \u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0439 \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u0438 \u0434\u0430\u043d\u043d\u044b\u0445. \u0412 \u043f\u0435\u0440\u0432\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u0431\u044b\u043b \u043e\u043f\u0438\u0441\u0430\u043d \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u043e\u0440 \u0440\u0430\u0431\u043e\u0442\u0430\u044e\u0449\u0438\u0439 \u0441\u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u044c\u044e 10\u0413\u0431\u0430\u0439\u0442\/\u0441\u0435\u043a. \u043d\u0430 \u043e\u0434\u043d\u043e \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043d\u043e\u0435 \u044f\u0434\u0440\u043e (\u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u0441\u0436\u0430\u0442\u0438\u0435, RTT-Min).\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/ro\/blog\/administrirovanie\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2019-12-12T21:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-02-18T11:01:51+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Compresie rapid\u0103, rezistent\u0103 la erori (Continuare) | ProHoster","description":"Acest articol este al doilea dintr-o serie despre comprimarea rapid\u0103 a datelor. \u00cen primul articol a fost descris un compresor care func\u021bioneaz\u0103 cu o vitez\u0103 de 10GB\/s pe un singur nucleu de procesor (compresie minim\u0103, RTT-Min).","canonical_url":"https:\/\/prohoster.info\/ro\/blog\/administrirovanie\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"ro_RO","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u0421\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u0430\u044f \u043e\u0442\u043a\u0430\u0437\u043e\u0443\u0441\u0442\u043e\u0439\u0447\u0438\u0432\u0430\u044f \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u044f (\u041f\u0440\u043e\u0434\u043e\u043b\u0436\u0435\u043d\u0438\u0435) | ProHoster","og:description":"\u0414\u0430\u043d\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u0443\u0436\u0435 \u0432\u0442\u043e\u0440\u0430\u044f \u0432 \u0442\u0435\u043c\u0435 \u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0439 \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u0438\u0438 \u0434\u0430\u043d\u043d\u044b\u0445. \u0412 \u043f\u0435\u0440\u0432\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u0431\u044b\u043b \u043e\u043f\u0438\u0441\u0430\u043d \u043a\u043e\u043c\u043f\u0440\u0435\u0441\u0441\u043e\u0440 \u0440\u0430\u0431\u043e\u0442\u0430\u044e\u0449\u0438\u0439 \u0441\u043e \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u044c\u044e 10\u0413\u0431\u0430\u0439\u0442\/\u0441\u0435\u043a. \u043d\u0430 \u043e\u0434\u043d\u043e \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043d\u043e\u0435 \u044f\u0434\u0440\u043e (\u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u0441\u0436\u0430\u0442\u0438\u0435, RTT-Min).","og:url":"https:\/\/prohoster.info\/ro\/blog\/administrirovanie\/skorostnaya-otkazoustojchivaya-kompressiya-prodolzhenie","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-12-12T21:00:00+00:00","article:modified_time":"2020-02-18T11:01:51+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"53906","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-02-09 18:05:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 20:15:55","updated":"2026-02-09 18:05:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/53906","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/comments?post=53906"}],"version-history":[{"count":1,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/53906\/revisions"}],"predecessor-version":[{"id":158702,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/53906\/revisions\/158702"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=53906"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=53906"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=53906"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}