{
  "schema_version": 2,
  "id": "develop/data-types/json/performance",
  "title": "Performance",
  "url": "https://redis.io/docs/latest/develop/data-types/json/performance/",
  "summary": "Performance benchmarks",
  "tags": [
    "docs",
    "develop",
    "stack",
    "oss",
    "rs",
    "rc",
    "oss",
    "kubernetes",
    "clients"
  ],
  "last_updated": "2026-09-10T15:45:45+01:00",
  "children": [],
  "page_type": "content",
  "content_hash": "72601766a6922c0f268ba2c706e2cbfd69cb2df9da4ea1089a8c238f91f1df2c",
  "sections": [
    {
      "id": "overview",
      "title": "Overview",
      "role": "overview",
      "text": "To get an early sense of what Redis JSON is capable of, you can test it with `redis-benchmark` just like\nany other Redis command. However, in order to have more control over the tests, we'll use a \na tool written in Go called _ReJSONBenchmark_ that we expect to release in the near future.\n\nThe following figures were obtained from an AWS EC2 c4.8xlarge instance that ran both the Redis\nserver as well the as the benchmarking tool. Connections to the server are via the networking stack.\nAll tests are non-pipelined.\n\n> NOTE: The results below are measured using the preview version of Redis JSON, which is still very much unoptimized."
    },
    {
      "id": "redis-json-baseline",
      "title": "Redis JSON baseline",
      "role": "content",
      "text": ""
    },
    {
      "id": "a-smallish-object",
      "title": "A smallish object",
      "role": "content",
      "text": "We test a JSON value that, while purely synthetic, is interesting. The test subject is\n[/tests/files/pass-100.json](https://github.com/RedisLabsModules/redisjson/blob/master/tests/files/pass-100.json),\nwho weighs in at 380 bytes and is nested. We first test SETting it, then GETting it using several\ndifferent paths:\n\n![ReJSONBenchmark pass-100.json](images/bench_pass_100.png)\n\n![ReJSONBenchmark pass-100.json percentiles](images/bench_pass_100_p.png)"
    },
    {
      "id": "a-bigger-array",
      "title": "A bigger array",
      "role": "content",
      "text": "Moving on to bigger values, we use the 1.4 kB array in\n[/tests/files/pass-jsonsl-1.json](https://github.com/RedisLabsModules/redisjson/blob/master/tests/files/pass-jsonsl-1.json):\n\n\n![ReJSONBenchmark pass-jsonsl-1.json](images/bench_pass_jsonsl_1.png)\n\n![ReJSONBenchmark pass-jsonsl-1.json percentiles](images/bench_pass_jsonsl_1_p.png)"
    },
    {
      "id": "a-largish-object",
      "title": "A largish object",
      "role": "content",
      "text": "More of the same to wrap up, now we'll take on a behemoth of no less than 3.5 kB as given by\n[/tests/files/pass-json-parser-0000.json](https://github.com/RedisLabsModules/redisjson/blob/master/tests/files/pass-json-parser-0000.json):\n\n![ReJSONBenchmark pass-json-parser-0000.json](images/bench_pass_json_parser_0000.png)\n\n![ReJSONBenchmark pass-json-parser-0000.json percentiles](images/bench_pass_json_parser_0000_p.png)"
    },
    {
      "id": "number-operations",
      "title": "Number operations",
      "role": "content",
      "text": "Last but not least, some adding and multiplying:\n\n![ReJSONBenchmark number operations](images/bench_numbers.png)\n\n![ReJSONBenchmark number operations percentiles](images/bench_numbers_p.png)"
    },
    {
      "id": "baseline",
      "title": "Baseline",
      "role": "content",
      "text": "To establish a baseline, we'll use the Redis [`PING`](https://redis.io/docs/latest/commands/ping) command.\nFirst, lets see what `redis-benchmark` reports:\n\n[code example]\n\nReJSONBenchmark's concurrency is configurable, so we'll test a few settings to find a good one. Here\nare the results, which indicate that 16 workers yield the best throughput:\n\n![ReJSONBenchmark PING](images/bench_ping.png)\n\n![ReJSONBenchmark PING percentiles](images/bench_ping_p.png)\n\nNote how our benchmarking tool does slightly worse in PINGing - producing only 116K ops, compared to\n`redis-cli`'s 140K."
    },
    {
      "id": "the-empty-string",
      "title": "The empty string",
      "role": "content",
      "text": "Another JSON benchmark is that of setting and getting an empty string - a value that's only two\nbytes long (i.e. `\"\"`). Granted, that's not very useful, but it teaches us something about the basic\nperformance of the module:\n\n![ReJSONBenchmark empty string](images/bench_empty_string.png)\n\n![ReJSONBenchmark empty string percentiles](images/bench_empty_string_p.png)"
    },
    {
      "id": "comparison-vs-server-side-lua-scripting",
      "title": "Comparison vs. server-side Lua scripting",
      "role": "content",
      "text": "We compare the JSON performance of Redis Open Source with the Redis embedded Lua engine. For this purpose, we use the Lua\nscripts at [/benchmarks/lua](https://github.com/RedisLabsModules/redisjson/tree/master/benchmarks/lua).\nThese scripts provide JSON's GET and SET functionality on values stored in JSON or MessagePack\nformats. Each of the different operations (set root, get root, set path and get path) is executed\nwith each \"engine\" on objects of varying sizes."
    },
    {
      "id": "setting-and-getting-the-root",
      "title": "Setting and getting the root",
      "role": "configuration",
      "text": "Storing raw JSON performs best in this test, but that isn't really surprising as all it does is\nserve unprocessed strings. While you can and should use Redis for caching opaque data, and JSON\n\"blobs\" are just one example, this does not allow any updates other than these of the entire value.\n\nA more meaningful comparison therefore is between JSON and the MessagePack variant, since both\nprocess the incoming JSON value before actually storing it. While the rates and latencies of these \ntwo behave in a very similar way, the absolute measurements suggest that Redis JSON's performance may be\nfurther improved.\n\n![VS. Lua set root](images/bench_lua_set_root.png)\n\n![VS. Lua set root latency](images/bench_lua_set_root_l.png)\n\n![VS. Lua get root](images/bench_lua_get_root.png)\n\n![VS. Lua get root latency](images/bench_lua_get_root_l.png)"
    },
    {
      "id": "setting-and-getting-parts-of-objects",
      "title": "Setting and getting parts of objects",
      "role": "configuration",
      "text": "This test shows why Redis JSON exists. Not only does it outperform the Lua variants, it retains constant\nrates and latencies regardless the object's overall size. There's no magic here - JSON keeps the\nvalue deserialized so that accessing parts of it is a relatively inexpensive operation. In deep contrast\nare both raw JSON as well as MessagePack, which require decoding the entire object before anything can\nbe done with it (a process that becomes more expensive the larger the object is).\n\n![VS. Lua set path to scalar](images/bench_lua_set_path.png)\n\n![VS. Lua set path to scalar latency](images/bench_lua_set_path_l.png)\n\n![VS. Lua get scalar from path](images/bench_lua_get_path.png)\n\n![VS. Lua get scalar from path latency](images/bench_lua_get_path_l.png)"
    },
    {
      "id": "even-more-charts",
      "title": "Even more charts",
      "role": "content",
      "text": "These charts are more of the same but independent for each file (value):\n\n![VS. Lua pass-100.json rate](images/bench_lua_pass_100.png)\n\n![VS. Lua pass-100.json average latency](images/bench_lua_pass_100_l.png)\n\n![VS. Lua pass-jsonsl-1.json rate](images/bench_lua_pass_jsonsl_1.png)\n\n![VS. Lua pass-jsonsl-1.json average latency](images/bench_lua_pass_jsonsl_1_l.png)\n\n![VS. Lua pass-json-parser-0000.json rate](images/bench_lua_pass_json_parser_0000.png)\n\n![VS. Lua pass-json-parser-0000.json latency](images/bench_lua_pass_json_parser_0000_l.png)\n\n![VS. Lua pass-jsonsl-yahoo2.json rate](images/bench_lua_pass_jsonsl_yahoo2.png)\n\n![VS. Lua pass-jsonsl-yahoo2.json latency](images/bench_lua_pass_jsonsl_yahoo2_l.png)\n\n![VS. Lua pass-jsonsl-yelp.json rate](images/bench_lua_pass_jsonsl_yelp.png)\n\n![VS. Lua pass-jsonsl-yelp.json latency](images/bench_lua_pass_jsonsl_yelp_l.png)"
    },
    {
      "id": "raw-results",
      "title": "Raw results",
      "role": "content",
      "text": "The following are the raw results from the benchmark in CSV format."
    },
    {
      "id": "json-results",
      "title": "JSON results",
      "role": "content",
      "text": "title,concurrency,rate,average latency,50.00%-tile,90.00%-tile,95.00%-tile,99.00%-tile,99.50%-tile,100.00%-tile\n    [ping],1,22128.12,0.04,0.04,0.04,0.05,0.05,0.05,1.83\n    [ping],2,54641.13,0.04,0.03,0.05,0.05,0.06,0.07,2.14\n    [ping],4,76000.18,0.05,0.05,0.07,0.07,0.09,0.10,2.10\n    [ping],8,106750.99,0.07,0.07,0.10,0.11,0.14,0.16,2.99\n    [ping],12,111297.33,0.11,0.10,0.15,0.16,0.20,0.22,6.81\n    [ping],16,116292.19,0.14,0.13,0.19,0.21,0.27,0.33,7.50\n    [ping],20,110622.82,0.18,0.17,0.24,0.27,0.38,0.47,12.21\n    [ping],24,107468.51,0.22,0.20,0.31,0.38,0.58,0.71,13.86\n    [ping],28,102827.35,0.27,0.25,0.38,0.44,0.66,0.79,12.87\n    [ping],32,105733.51,0.30,0.28,0.42,0.50,0.79,0.97,10.56\n    [ping],36,102046.43,0.35,0.33,0.48,0.56,0.90,1.13,14.66\n    ... output truncated for AI-facing Markdown ...\n    JSON.GET {key} ResultSet.totalResultsAvailable,16,91202.84,0.17,0.16,0.24,0.28,0.35,0.38,5.30\n    JSON.SET {key} . {pass-jsonsl-yelp.json size: 40 kB},16,1624.86,9.84,9.67,9.86,9.94,15.86,19.36,31.94\n    JSON.GET {key} .,16,442.55,36.08,35.62,37.78,38.14,55.23,81.33,88.40\n    JSON.SET {key} message.code 1,16,77677.25,0.20,0.19,0.28,0.33,0.42,0.45,11.07\n    JSON.GET {key} message.code,16,89206.61,0.18,0.16,0.25,0.28,0.36,0.39,8.60\n    [JSON.SET num . 0],16,84498.21,0.19,0.17,0.26,0.30,0.39,0.43,8.08\n    [JSON.NUMINCRBY num . 1],16,78640.20,0.20,0.18,0.28,0.33,0.44,0.48,11.05\n    [JSON.NUMMULTBY num . 2],16,77170.85,0.21,0.19,0.28,0.33,0.43,0.47,6.85"
    },
    {
      "id": "lua-using-cjson",
      "title": "Lua using cjson",
      "role": "content",
      "text": "json-set-root.lua empty string,16,86817.84,0.18,0.17,0.26,0.31,0.39,0.42,9.36\n    json-get-root.lua,16,90795.08,0.17,0.16,0.25,0.28,0.36,0.39,8.75\n    json-set-root.lua pass-100.json,16,84190.26,0.19,0.17,0.27,0.30,0.38,0.41,12.00\n    json-get-root.lua,16,87170.45,0.18,0.17,0.26,0.29,0.38,0.45,9.81\n    json-get-path.lua sclr,16,54556.80,0.29,0.28,0.35,0.38,0.57,0.64,7.53\n    json-set-path.lua sclr 1,16,35907.30,0.44,0.42,0.53,0.67,0.93,1.00,8.57\n    json-get-path.lua sub_doc,16,51158.84,0.31,0.30,0.36,0.39,0.50,0.62,7.22\n    json-get-path.lua sub_doc sclr,16,51054.47,0.31,0.29,0.39,0.47,0.66,0.74,7.43\n    json-get-path.lua array_of_docs,16,39103.77,0.41,0.37,0.57,0.68,0.87,0.94,8.02\n    json-get-path.lua array_of_docs 1,16,45811.31,0.35,0.32,0.45,0.56,0.77,0.83,8.17\n    json-get-path.lua array_of_docs 1 sclr,16,47346.83,0.34,0.31,0.44,0.54,0.72,0.79,8.07\n    json-set-root.lua pass-jsonsl-1.json,16,82100.90,0.19,0.18,0.28,0.31,0.39,0.43,12.43\n    ... output truncated for AI-facing Markdown ...\n    json-set-root.lua pass-jsonsl-yahoo2.json,16,47544.65,0.33,0.31,0.41,0.47,0.59,0.64,10.52\n    json-get-root.lua,16,25369.92,0.63,0.57,0.91,1.05,1.37,1.56,9.95\n    json-set-path.lua ResultSet totalResultsAvailable 1,16,5077.32,3.15,3.09,3.20,3.24,5.12,6.26,14.98\n    json-get-path.lua ResultSet totalResultsAvailable,16,7652.56,2.09,2.05,2.13,2.17,3.23,3.95,9.65\n    json-set-root.lua pass-jsonsl-yelp.json,16,29575.20,0.54,0.52,0.64,0.75,0.94,1.00,12.66\n    json-get-root.lua,16,18424.29,0.87,0.84,1.25,1.40,1.82,1.95,7.35\n    json-set-path.lua message code 1,16,2251.07,7.10,6.98,7.14,7.22,11.00,12.79,21.14\n    json-get-path.lua message code,16,3380.72,4.73,4.44,5.03,6.82,10.28,11.06,14.93"
    },
    {
      "id": "lua-using-cmsgpack",
      "title": "Lua using cmsgpack",
      "role": "content",
      "text": "msgpack-set-root.lua empty string,16,82592.66,0.19,0.18,0.27,0.31,0.38,0.42,10.18\n    msgpack-get-root.lua,16,89561.41,0.18,0.16,0.25,0.29,0.37,0.40,9.52\n    msgpack-set-root.lua pass-100.json,16,44326.47,0.36,0.34,0.43,0.54,0.78,0.86,6.45\n    msgpack-get-root.lua,16,41036.58,0.39,0.36,0.51,0.62,0.84,0.91,7.21\n    msgpack-get-path.lua sclr,16,55845.56,0.28,0.26,0.36,0.44,0.64,0.70,11.29\n    msgpack-set-path.lua sclr 1,16,43608.26,0.37,0.34,0.47,0.58,0.78,0.85,10.27\n    msgpack-get-path.lua sub_doc,16,50153.07,0.32,0.29,0.41,0.50,0.69,0.75,8.56\n    msgpack-get-path.lua sub_doc sclr,16,54016.35,0.29,0.27,0.38,0.46,0.62,0.67,6.38\n    msgpack-get-path.lua array_of_docs,16,45394.79,0.35,0.32,0.45,0.56,0.78,0.85,11.88\n    msgpack-get-path.lua array_of_docs 1,16,48336.48,0.33,0.30,0.42,0.52,0.71,0.76,7.69\n    msgpack-get-path.lua array_of_docs 1 sclr,16,53689.41,0.30,0.27,0.38,0.46,0.64,0.69,11.16\n    msgpack-set-root.lua pass-jsonsl-1.json,16,28956.94,0.55,0.51,0.65,0.82,1.17,1.26,8.39\n    ... output truncated for AI-facing Markdown ...\n    msgpack-set-root.lua pass-jsonsl-yahoo2.json,16,5597.60,2.85,2.81,2.89,2.94,4.57,5.59,10.19\n    msgpack-get-root.lua,16,6585.01,2.43,2.39,2.52,2.66,3.76,4.80,10.59\n    msgpack-set-path.lua ResultSet totalResultsAvailable 1,16,6666.95,2.40,2.35,2.43,2.47,3.78,4.59,12.08\n    msgpack-get-path.lua ResultSet totalResultsAvailable,16,10733.03,1.49,1.45,1.60,1.66,2.36,2.93,13.15\n    msgpack-set-root-lua pass-jsonsl-yelp.json,16,2291.53,6.97,6.87,7.01,7.12,10.54,12.89,21.75\n    msgpack-get-root.lua,16,2889.59,5.53,5.45,5.71,5.86,8.80,10.48,25.55\n    msgpack-set-path.lua message code 1,16,2847.85,5.61,5.44,5.56,6.01,10.58,11.90,16.91\n    msgpack-get-path.lua message code,16,5030.95,3.18,3.07,3.24,3.57,6.08,6.92,12.44"
    }
  ],
  "examples": [
    {
      "id": "baseline-ex0",
      "language": "plaintext",
      "code": "~$ redis/src/redis-benchmark -n 1000000 ping\n====== ping ======\n  1000000 requests completed in 7.11 seconds\n  50 parallel clients\n  3 bytes payload\n  keep alive: 1\n\n99.99% <= 1 milliseconds\n100.00% <= 1 milliseconds\n140587.66 requests per second",
      "section_id": "baseline"
    }
  ]
}