{"id":184270,"date":"2026-11-15T11:45:19","date_gmt":"2026-11-15T09:45:26","guid":{"rendered":"https:\/\/prohoster.info\/blog\/news\/predstavlen-xraid-s-realizacziej-raid-dlya-xfs"},"modified":"2026-11-15T11:45:30","modified_gmt":"2026-11-15T09:45:30","slug":"xraid-introduced-with-raid-implementation-for-xfs","status":"publish","type":"post","link":"https:\/\/prohoster.info\/pl\/blog\/news\/xraid-introduced-with-raid-implementation-for-xfs","title":{"rendered":"Zaprezentowano XRAID z realizacj\u0105 RAID dla XFS","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Christoph Hellwig, maintainer of the DMA, KVM, Slab Allocator subsystems, and PowerPC architecture in the Linux kernel, introduced the first public release of XRAID, an implementation of declustered RAID with parity control integrated into the XFS file system. The project was created to add the ability to use RAID on zoned storage devices, such as SMR (Shingled Magnetic Recording) disks, and to provide a high-performance RAID implementation to maintain data integrity. In addition to zoned devices, XRAID also supports operation on standard hard drives and SSDs, demonstrating a significant performance increase on the latter compared to mdraid (up to 20 times during writes).<\/p>\n

XRAID uses declustered parity control for data distribution across drives, similar to dRAID in OpenZFS, where no separate drives are allocated for hot spares and the data, parity information, and spare space are evenly distributed across all drives. The reading, writing, and recovery processes during failures encompass all existing drives, which increases throughput, reduces load on individual disks, avoids noticeable performance drops during failures, and significantly speeds up the array rebuilding process after adding or replacing drives.<\/p>\n

Declustered RAIDs also simplify the creation of fault-tolerant arrays with a very large number of disks. During recovery from failures, XRAID dynamically determines the order of rebuilding drives, prioritizing areas with a greater loss of redundant information and rebuilding data zones before areas with parity information.<\/p>\n

XRAID zosta\u0142 pocz\u0105tkowo zaprojektowany z my\u015bl\u0105 o mo\u017cliwo\u015bci u\u017cycia z urz\u0105dzeniami zonowanymi, w kt\u00f3rych przestrze\u0144 do przechowywania jest dzielona na strefy, kt\u00f3re stanowi\u0105 grupy blok\u00f3w lub sektor\u00f3w. W takich urz\u0105dzeniach dopuszczane jest jedynie sekwencyjne dodawanie danych z aktualizacj\u0105 ca\u0142ej grupy blok\u00f3w. Na przyk\u0142ad, zonowanie zapisu stosowane jest w dyskach SMR (Shingled Magnetic Recording), w kt\u00f3rych szeroko\u015b\u0107 \u015bcie\u017cki jest mniejsza od szeroko\u015bci g\u0142owicy magnetycznej, a zapis nast\u0119puje z cz\u0119\u015bciowym nak\u0142adaniem s\u0105siednich \u015bcie\u017cek, co oznacza, \u017ce ka\u017cda ponowna zapisanie prowadzi do konieczno\u015bci przepisania ca\u0142ej grupy \u015bcie\u017cek. <\/p>\n

Aby wspiera\u0107 urz\u0105dzenia zonowane, w XRAID wykorzystano realizowany w XFS oraz j\u0105drze Linux alokator blok\u00f3w dla urz\u0105dze\u0144 zonowanych (zoned allocator), kt\u00f3ry u\u017cywa podobj\u0119to\u015bci RT (RealTime subvolume) do organizacji oddzielnego przechowywania danych i metadanych (w strefach z sekwencyjnym zapisem przechowywana jest jedynie zawarto\u015b\u0107 plik\u00f3w, natomiast metadane systemu plik\u00f3w lokalizowane s\u0105 w zwyk\u0142ych strefach lub na dodatkowych dyskach SSD). <\/p>\n

W XRAID mechanizmy kontroli parzysto\u015bci RAID stosowane s\u0105 wy\u0142\u0105cznie dla zawarto\u015bci plik\u00f3w, podczas gdy nadmiarowo\u015b\u0107 dla metadanych realizowana jest poprzez wykorzystanie ju\u017c istniej\u0105cych w j\u0105drze Linux sterownik\u00f3w, na przyk\u0142ad poprzez mirroring z wykorzystaniem MD RAID, co jest bardziej efektywne dla ma\u0142ych obiekt\u00f3w, aktualizowanych na miejscu. Realizacja RAID jest wbudowana w XFS do handler\u00f3w zonowanego wej\u015bcia\/wyj\u015bcia, reprezentuj\u0105cych fizyczne strefy le\u017c\u0105cych poni\u017cej no\u015bnik\u00f3w w formie logicznych stref, podobnie jak w wielowarstwowym urz\u0105dzeniu blokowym.<\/p>\n

Prace nad XRAID trwaj\u0105 ju\u017c od p\u00f3\u0142tora roku, a chocia\u017c implementacja nie jest jeszcze gotowa do integracji z g\u0142\u00f3wnym rdzeniem, jest ju\u017c dostosowana do testowania przez szerok\u0105 publiczno\u015b\u0107. W proponowanej realizacji wspierane s\u0105 od 0 do 2 poziom\u00f3w parzysto\u015bci (w planach jest wsparcie dla 3 i wi\u0119cej poziom\u00f3w). Do zarz\u0105dzania XRAID dodano nowe narz\u0119dzie «xraid» do zestawu xfsprogs oraz wprowadzono wsparcie dla XRAID w mkfs. Ponadto w narz\u0119dziu do inspekcji zonyzowanych no\u015bnik\u00f3w Zonar dodano mo\u017cliwo\u015bci wizualizacji mapowania logicznych stref na fizyczne strefy.<\/p>\n

Opublikowano wyniki testu wydajno\u015bci XRAID w por\u00f3wnaniu do mdraid i btrfs, przeprowadzone dla macierzy XRAID w konfiguracji z dw\u00f3ch dysk\u00f3w SSD WD DC-SN650 do metadanych (lustro oparte na mdraid), sze\u015bciu zwyk\u0142ych dysk\u00f3w SATA WD DC-HC590 26 TB oraz sze\u015bciu 21-zonowych dysk\u00f3w WD DC-HC690 30 TB (SMR).<\/p>\n

<\/center>
\n
<\/center>
\n
<\/center>
\n
<\/center>
\n
<\/center><\/p>\n

Przeprowadzono r\u00f3wnie\u017c testy XRAID na zwyk\u0142ych niezonym dyskach SSD w konfiguracji z jednym 4 TiB Samsung PM9D3a do metadanych i pi\u0119cioma 4 TiB Samsung PM9D3a dla RAID (4 + 1).<\/p>\n

<\/center>
\n
<\/center>
\n
<\/center><\/p>\n

<\/center>
\n
\u0179r\u00f3d\u0142o: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041a\u0440\u0438\u0441\u0442\u043e\u0444 \u0425\u0435\u043b\u0432\u0438\u0433 (Christoph Hellwig), \u043c\u044d\u0439\u043d\u0442\u0435\u0439\u043d\u0435\u0440 \u043f\u043e\u0434\u0441\u0438\u0441\u0442\u0435\u043c DMA, KVM, Slab Allocator \u0438 \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440\u044b PowerPC \u0432 \u044f\u0434\u0440\u0435 Linux, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b \u043f\u0435\u0440\u0432\u044b\u0439 \u043f\u0443\u0431\u043b\u0438\u0447\u043d\u044b\u0439 \u0432\u044b\u043f\u0443\u0441\u043a XRAID, \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 \u0434\u0435\u043a\u043b\u0430\u0441\u0442\u0435\u0440\u0438\u0437\u043e\u0432\u0430\u043d\u043d\u043e\u0433\u043e RAID \u0441 \u043a\u043e\u043d\u0442\u0440\u043e\u043b\u0435\u043c \u0447\u0451\u0442\u043d\u043e\u0441\u0442\u0438, \u0438\u043d\u0442\u0435\u0433\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e\u0439 \u0432 \u0444\u0430\u0439\u043b\u043e\u0432\u0443\u044e \u0441\u0438\u0441\u0442\u0435\u043c\u0443 XFS. \u041f\u0440\u043e\u0435\u043a\u0442 \u0441\u043e\u0437\u0434\u0430\u043d \u0441 \u0446\u0435\u043b\u044c\u044e \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0441\u0442\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f RAID \u043d\u0430 \u0437\u043e\u043d\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u0430\u0445 \u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0434\u0438\u0441\u043a\u0438 SMR (Shingled Magnetic Recording), \u0438 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":10,"featured_media":184272,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-184270","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Przedstawiono XRAID z implementacj\u0105 RAID dla XFS | ProHoster","description":"Christoph Hellwig, maintainer podsystem\u00f3w DMA, KVM, Slab Allocator oraz architektury PowerPC w j\u0105drze Linux, zaprezentowa\u0142 pierwsze publiczne wydanie XRAID, implementacji deklastrowanego RAID z kontrol\u0105.","canonical_url":"https:\/\/prohoster.info\/pl\/blog\/news\/xraid-introduced-with-raid-implementation-for-xfs","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"pl_PL","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\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d XRAID \u0441 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0435\u0439 RAID \u0434\u043b\u044f XFS | ProHoster","og:description":"\u041a\u0440\u0438\u0441\u0442\u043e\u0444 \u0425\u0435\u043b\u0432\u0438\u0433 (Christoph Hellwig), \u043c\u044d\u0439\u043d\u0442\u0435\u0439\u043d\u0435\u0440 \u043f\u043e\u0434\u0441\u0438\u0441\u0442\u0435\u043c DMA, KVM, Slab Allocator \u0438 \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440\u044b PowerPC \u0432 \u044f\u0434\u0440\u0435 Linux, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b \u043f\u0435\u0440\u0432\u044b\u0439 \u043f\u0443\u0431\u043b\u0438\u0447\u043d\u044b\u0439 \u0432\u044b\u043f\u0443\u0441\u043a XRAID, \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 \u0434\u0435\u043a\u043b\u0430\u0441\u0442\u0435\u0440\u0438\u0437\u043e\u0432\u0430\u043d\u043d\u043e\u0433\u043e RAID \u0441 \u043a\u043e\u043d\u0442\u0440\u043e\u043b\u0435\u043c.","og:url":"https:\/\/prohoster.info\/pl\/blog\/news\/xraid-introduced-with-raid-implementation-for-xfs","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":"2026-11-15T09:45:26+00:00","article:modified_time":"2026-11-15T09:45:30+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/posts\/184270","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/comments?post=184270"}],"version-history":[{"count":1,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/posts\/184270\/revisions"}],"predecessor-version":[{"id":184271,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/posts\/184270\/revisions\/184271"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/media\/184272"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/media?parent=184270"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/categories?post=184270"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/pl\/wp-json\/wp\/v2\/tags?post=184270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}