[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-github-qdrant-horizontal-scaling":3,"mdc-bbqwdh-key":47,"related-repo-github-qdrant-horizontal-scaling":224,"related-org-github-qdrant-horizontal-scaling":325},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":42,"sourceUrl":45,"mdContent":46},"qdrant-horizontal-scaling","guide Qdrant horizontal scaling decisions","Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"github","GitHub","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgithub.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Architecture","architecture","tag",{"name":17,"slug":18,"type":15},"Qdrant","qdrant",{"name":20,"slug":21,"type":15},"Database","database",{"name":23,"slug":24,"type":15},"Capacity Planning","capacity-planning",{"name":26,"slug":27,"type":15},"AI Infrastructure","ai-infrastructure",36978,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","2026-04-18T04:46:16.349561",null,4632,[34,35,36,37,38,39,40,41],"agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering",{"repoUrl":29,"stars":28,"forks":32,"topics":43,"description":44},[34,35,36,37,38,39,40,41],"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Ftree\u002FHEAD\u002Fskills\u002Fqdrant-scaling\u002Fscaling-data-volume\u002Fhorizontal-scaling","---\nname: qdrant-horizontal-scaling\ndescription: \"Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.\"\n---\n\n# What to Do When Qdrant Needs More Capacity\n\nVertical first: simpler operations, no network overhead, good up to ~100M vectors per node depending on dimensions and quantization. Horizontal when: data exceeds single node capacity, need fault tolerance, need to isolate tenants, or IOPS-bound (more nodes = more independent IOPS).\n\n## Most basic distributed configuration\n\n- 3 nodes, 3 shards with `replication_factor: 2` for zero-downtime scaling\n\nMinimum of 3 nodes is important for consensus and fault tolerance. With 3 nodes, you can lose 1 node without downtime. With 2 nodes, losing 1 node causes downtime for collection operations.\nReplication factor of 2 means each shard has 1 replica, so you have 2 copies of data. This allows for zero-downtime scaling and maintenance. With `replication_factor: 1`, zero-downtime is not guaranteed even for point-level operations, and cluster maintenance requires downtime.\n\n## Choosing number of shards\n\nShards are the unit of data distribution. \nMore shards allows more nodes and better distribution, but adds overhead. Fewer shards reduces overhead but limits horizontal scaling.\n\nFor cluster of 3-6 nodes the recommended shard count is 6-12. \nThis allows for 2-4 shards per node, which balances distribution and overhead. \n\n## Changing number of shards\n\nUse when: shard count isn't evenly divisible by node count, causing uneven distribution, or need to rebalance.\n\nResharding is expensive and time-consuming, it should be used as a last resort if regular data distribution is not possible.\nResharding is designed to be transparent for user operations, updates and searches should still work during resharding with some small performance impact.\n\nBut resharding operation itself is time-consuming and requires to move large amounts of data between nodes.\n\n- Available in Qdrant Cloud [Resharding](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fdistributed_deployment\u002F?s=resharding)\n- Resharding is not available for self-hosted deployments.\n\nBetter alternatives: over-provision shards initially, or spin up new cluster with correct config and migrate data.\n\n\n## What NOT to Do\n\n- Do not jump to horizontal before exhausting vertical (adds complexity for no gain)\n- Do not set `shard_number` that isn't a multiple of node count (uneven distribution)\n- Do not use `replication_factor: 1` in production if you need fault tolerance\n- Do not add nodes without rebalancing shards (use shard move API to redistribute)\n- Do not scale down RAM without load testing (cache eviction causes days-long latency incidents)\n- Do not hit the collection limit by using one collection per tenant (use payload partitioning)\n",{"data":48,"body":49},{"name":4,"description":6},{"type":50,"children":51},"root",[52,61,67,74,93,106,112,117,122,128,133,138,143,165,170,176],{"type":53,"tag":54,"props":55,"children":57},"element","h1",{"id":56},"what-to-do-when-qdrant-needs-more-capacity",[58],{"type":59,"value":60},"text","What to Do When Qdrant Needs More Capacity",{"type":53,"tag":62,"props":63,"children":64},"p",{},[65],{"type":59,"value":66},"Vertical first: simpler operations, no network overhead, good up to ~100M vectors per node depending on dimensions and quantization. Horizontal when: data exceeds single node capacity, need fault tolerance, need to isolate tenants, or IOPS-bound (more nodes = more independent IOPS).",{"type":53,"tag":68,"props":69,"children":71},"h2",{"id":70},"most-basic-distributed-configuration",[72],{"type":59,"value":73},"Most basic distributed configuration",{"type":53,"tag":75,"props":76,"children":77},"ul",{},[78],{"type":53,"tag":79,"props":80,"children":81},"li",{},[82,84,91],{"type":59,"value":83},"3 nodes, 3 shards with ",{"type":53,"tag":85,"props":86,"children":88},"code",{"className":87},[],[89],{"type":59,"value":90},"replication_factor: 2",{"type":59,"value":92}," for zero-downtime scaling",{"type":53,"tag":62,"props":94,"children":95},{},[96,98,104],{"type":59,"value":97},"Minimum of 3 nodes is important for consensus and fault tolerance. With 3 nodes, you can lose 1 node without downtime. With 2 nodes, losing 1 node causes downtime for collection operations.\nReplication factor of 2 means each shard has 1 replica, so you have 2 copies of data. This allows for zero-downtime scaling and maintenance. With ",{"type":53,"tag":85,"props":99,"children":101},{"className":100},[],[102],{"type":59,"value":103},"replication_factor: 1",{"type":59,"value":105},", zero-downtime is not guaranteed even for point-level operations, and cluster maintenance requires downtime.",{"type":53,"tag":68,"props":107,"children":109},{"id":108},"choosing-number-of-shards",[110],{"type":59,"value":111},"Choosing number of shards",{"type":53,"tag":62,"props":113,"children":114},{},[115],{"type":59,"value":116},"Shards are the unit of data distribution.\nMore shards allows more nodes and better distribution, but adds overhead. Fewer shards reduces overhead but limits horizontal scaling.",{"type":53,"tag":62,"props":118,"children":119},{},[120],{"type":59,"value":121},"For cluster of 3-6 nodes the recommended shard count is 6-12.\nThis allows for 2-4 shards per node, which balances distribution and overhead.",{"type":53,"tag":68,"props":123,"children":125},{"id":124},"changing-number-of-shards",[126],{"type":59,"value":127},"Changing number of shards",{"type":53,"tag":62,"props":129,"children":130},{},[131],{"type":59,"value":132},"Use when: shard count isn't evenly divisible by node count, causing uneven distribution, or need to rebalance.",{"type":53,"tag":62,"props":134,"children":135},{},[136],{"type":59,"value":137},"Resharding is expensive and time-consuming, it should be used as a last resort if regular data distribution is not possible.\nResharding is designed to be transparent for user operations, updates and searches should still work during resharding with some small performance impact.",{"type":53,"tag":62,"props":139,"children":140},{},[141],{"type":59,"value":142},"But resharding operation itself is time-consuming and requires to move large amounts of data between nodes.",{"type":53,"tag":75,"props":144,"children":145},{},[146,160],{"type":53,"tag":79,"props":147,"children":148},{},[149,151],{"type":59,"value":150},"Available in Qdrant Cloud ",{"type":53,"tag":152,"props":153,"children":157},"a",{"href":154,"rel":155},"https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fdistributed_deployment\u002F?s=resharding",[156],"nofollow",[158],{"type":59,"value":159},"Resharding",{"type":53,"tag":79,"props":161,"children":162},{},[163],{"type":59,"value":164},"Resharding is not available for self-hosted deployments.",{"type":53,"tag":62,"props":166,"children":167},{},[168],{"type":59,"value":169},"Better alternatives: over-provision shards initially, or spin up new cluster with correct config and migrate data.",{"type":53,"tag":68,"props":171,"children":173},{"id":172},"what-not-to-do",[174],{"type":59,"value":175},"What NOT to Do",{"type":53,"tag":75,"props":177,"children":178},{},[179,184,197,209,214,219],{"type":53,"tag":79,"props":180,"children":181},{},[182],{"type":59,"value":183},"Do not jump to horizontal before exhausting vertical (adds complexity for no gain)",{"type":53,"tag":79,"props":185,"children":186},{},[187,189,195],{"type":59,"value":188},"Do not set ",{"type":53,"tag":85,"props":190,"children":192},{"className":191},[],[193],{"type":59,"value":194},"shard_number",{"type":59,"value":196}," that isn't a multiple of node count (uneven distribution)",{"type":53,"tag":79,"props":198,"children":199},{},[200,202,207],{"type":59,"value":201},"Do not use ",{"type":53,"tag":85,"props":203,"children":205},{"className":204},[],[206],{"type":59,"value":103},{"type":59,"value":208}," in production if you need fault tolerance",{"type":53,"tag":79,"props":210,"children":211},{},[212],{"type":59,"value":213},"Do not add nodes without rebalancing shards (use shard move API to redistribute)",{"type":53,"tag":79,"props":215,"children":216},{},[217],{"type":59,"value":218},"Do not scale down RAM without load testing (cache eviction causes days-long latency incidents)",{"type":53,"tag":79,"props":220,"children":221},{},[222],{"type":59,"value":223},"Do not hit the collection limit by using one collection per tenant (use payload partitioning)",{"items":225,"total":324},[226,234,252,268,282,298,312],{"slug":4,"name":4,"fn":5,"description":6,"org":227,"tags":228,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[229,230,231,232,233],{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"slug":235,"name":235,"fn":236,"description":237,"org":238,"tags":239,"stars":28,"repoUrl":29,"updatedAt":251},"qdrant-indexing-performance-optimization","optimize Qdrant indexing performance","Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[240,243,244,247,250],{"name":241,"slug":242,"type":15},"Data Engineering","data-engineering",{"name":20,"slug":21,"type":15},{"name":245,"slug":246,"type":15},"ETL","etl",{"name":248,"slug":249,"type":15},"Performance","performance",{"name":17,"slug":18,"type":15},"2026-04-18T04:46:02.766357",{"slug":253,"name":253,"fn":254,"description":255,"org":256,"tags":257,"stars":28,"repoUrl":29,"updatedAt":267},"qdrant-memory-usage-optimization","optimize Qdrant memory usage","Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[258,261,262,265,266],{"name":259,"slug":260,"type":15},"Cost Optimization","cost-optimization",{"name":20,"slug":21,"type":15},{"name":263,"slug":264,"type":15},"Observability","observability",{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:01.525023",{"slug":269,"name":269,"fn":270,"description":271,"org":272,"tags":273,"stars":28,"repoUrl":29,"updatedAt":281},"qdrant-minimize-latency","minimize Qdrant query latency","Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[274,275,276,277,278],{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},"Search","search","2026-04-18T04:46:10.126667",{"slug":283,"name":283,"fn":284,"description":285,"org":286,"tags":287,"stars":28,"repoUrl":29,"updatedAt":297},"qdrant-monitoring-debugging","debug Qdrant production issues with metrics","Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[288,291,294,295,296],{"name":289,"slug":290,"type":15},"Debugging","debugging",{"name":292,"slug":293,"type":15},"Monitoring","monitoring",{"name":263,"slug":264,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:06.450784",{"slug":299,"name":299,"fn":300,"description":301,"org":302,"tags":303,"stars":28,"repoUrl":29,"updatedAt":311},"qdrant-monitoring-setup","set up Qdrant monitoring and alerting","Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus config', 'Grafana dashboard', 'health check endpoints', 'how to scrape Hybrid Cloud', 'what alerts to set', 'how to centralize logs', or 'audit logging'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[304,305,306,307,308],{"name":26,"slug":27,"type":15},{"name":292,"slug":293,"type":15},{"name":263,"slug":264,"type":15},{"name":17,"slug":18,"type":15},{"name":309,"slug":310,"type":15},"SRE","sre","2026-04-18T04:46:05.217192",{"slug":313,"name":313,"fn":314,"description":315,"org":316,"tags":317,"stars":28,"repoUrl":29,"updatedAt":323},"qdrant-scaling-data-volume","scale Qdrant data volume","Guides Qdrant data volume scaling decisions. Use when someone asks 'data doesn't fit on one node', 'too much data', 'need more storage', 'vertical or horizontal scaling', 'tenant scaling', 'time window rotation', or 'data growth exceeds capacity'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[318,319,320,321,322],{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:07.684464",15,{"items":326,"total":447},[327,335,343,351,359,367,375,383,395,407,423,435],{"slug":4,"name":4,"fn":5,"description":6,"org":328,"tags":329,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[330,331,332,333,334],{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"slug":235,"name":235,"fn":236,"description":237,"org":336,"tags":337,"stars":28,"repoUrl":29,"updatedAt":251},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[338,339,340,341,342],{"name":241,"slug":242,"type":15},{"name":20,"slug":21,"type":15},{"name":245,"slug":246,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"slug":253,"name":253,"fn":254,"description":255,"org":344,"tags":345,"stars":28,"repoUrl":29,"updatedAt":267},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[346,347,348,349,350],{"name":259,"slug":260,"type":15},{"name":20,"slug":21,"type":15},{"name":263,"slug":264,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"slug":269,"name":269,"fn":270,"description":271,"org":352,"tags":353,"stars":28,"repoUrl":29,"updatedAt":281},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[354,355,356,357,358],{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},{"slug":283,"name":283,"fn":284,"description":285,"org":360,"tags":361,"stars":28,"repoUrl":29,"updatedAt":297},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[362,363,364,365,366],{"name":289,"slug":290,"type":15},{"name":292,"slug":293,"type":15},{"name":263,"slug":264,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"slug":299,"name":299,"fn":300,"description":301,"org":368,"tags":369,"stars":28,"repoUrl":29,"updatedAt":311},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[370,371,372,373,374],{"name":26,"slug":27,"type":15},{"name":292,"slug":293,"type":15},{"name":263,"slug":264,"type":15},{"name":17,"slug":18,"type":15},{"name":309,"slug":310,"type":15},{"slug":313,"name":313,"fn":314,"description":315,"org":376,"tags":377,"stars":28,"repoUrl":29,"updatedAt":323},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[378,379,380,381,382],{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":23,"slug":24,"type":15},{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"slug":384,"name":384,"fn":385,"description":386,"org":387,"tags":388,"stars":28,"repoUrl":29,"updatedAt":394},"qdrant-scaling-qps","scale Qdrant query throughput","Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low', 'batch search', 'read replicas', or 'how to handle more concurrent queries'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[389,390,391,392,393],{"name":26,"slug":27,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},"2026-04-18T04:46:08.905219",{"slug":396,"name":396,"fn":397,"description":398,"org":399,"tags":400,"stars":28,"repoUrl":29,"updatedAt":406},"qdrant-scaling-query-volume","scale Qdrant query volume and pagination","Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[401,402,403,404,405],{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},"2026-04-18T04:46:11.371326",{"slug":408,"name":408,"fn":409,"description":410,"org":411,"tags":412,"stars":28,"repoUrl":29,"updatedAt":422},"qdrant-search-quality-diagnosis","diagnose Qdrant search quality issues","Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantization'. Also use when search quality degrades without obvious changes.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[413,416,419,420,421],{"name":414,"slug":415,"type":15},"Analytics","analytics",{"name":417,"slug":418,"type":15},"Data Quality","data-quality",{"name":289,"slug":290,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},"2026-04-18T04:46:17.579894",{"slug":424,"name":424,"fn":425,"description":426,"org":427,"tags":428,"stars":28,"repoUrl":29,"updatedAt":434},"qdrant-search-speed-optimization","optimize Qdrant search speed","Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[429,430,431,432,433],{"name":414,"slug":415,"type":15},{"name":20,"slug":21,"type":15},{"name":248,"slug":249,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},"2026-04-18T04:46:03.987332",{"slug":436,"name":436,"fn":437,"description":438,"org":439,"tags":440,"stars":28,"repoUrl":29,"updatedAt":446},"qdrant-search-strategies","select optimal Qdrant search strategies","Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', 'ColBERT reranking', or 'missing keyword matches'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[441,442,443,444,445],{"name":26,"slug":27,"type":15},{"name":414,"slug":415,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":279,"slug":280,"type":15},"2026-04-18T04:46:18.812306",45]