AWS m6i : The why you should abandon your m5

Around 2 years after the last m5 and m5a, AWS renewed its Intel series with m6i. In short and avoiding to repeat their announce, they offer better CPU performance, a larger network bandwidth and for the same price than the m5 series. Yes, this is just a provider's annoucement, so let's dive together on these assertions with a Price/Performance benchmark.

From a pricing perspective, nothing changes

In the continiuty of the other general purpose VMs (M), we have a copy-paste of CPU/RAM specs, so nothing to reshape except if you take in account the performance.  If you use to pay $0.46 for a m5.2xlarge in Frankfurt, after a migration the bill at the end of the month will remain the same.

Instance type Hourly price
m5.2xlarge $0.460
m5a.2xlarge $0.416
m6i.2xlarge $0.460

Always the latest CPU

The CPU race is picking up again, there are mainly Intel, AMD and ARM through the custom Graviton 2. Facing this, AWS clarifies its gamification and m5 pass to m6i accompanied by the gain implied by this new version. And what it is this gain ?

    {
"configuration": {
"chart": {
"type": "bar",
"polar": false,
"zoomType": "",
"options3d": {},
"height": 350,
"width": null,
"margin": null,
"inverted": false
},
"credits": {
"enabled": false
},
"title": {
"text": ""
},
"colorAxis": null,
"subtitle": {
"text": ""
},
"xAxis": {
"title": {
"text": [
""
],
"useHTML": false,
"style": {
"color": "#666666"
}
},
"categories": [
"provider__short_name",
"flavor__name"
],
"lineWidth": 1,
"tickInterval": null,
"tickWidth": 0,
"tickLength": 10,
"tickPixelInterval": null,
"plotLines": null,
"labels": {
"enabled": false,
"formatter": "",
"style": {
"color": "#666666",
"cursor": "default",
"fontSize": "11px"
}
},
"plotBands": null,
"visible": true,
"floor": null,
"ceiling": null,
"type": "linear",
"min": null,
"gridLineWidth": null,
"gridLineColor": null,
"minorTickInterval": null,
"minorTickWidth": 0,
"minTickInterval": null,
"startOnTick": true,
"endOnTick": null,
"tickmarkPlacement": null
},
"yAxis": {
"title": {
"text": [
"Single and Multi Score (transparent)
Higher is better" ], "useHTML": false, "style": { "fontSize": "14px" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" } } }, "zAxis": { "title": { "text": "Single and Multi Score (transparent)
Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false } }, "rangeSelector": { "enabled": false }, "legend": { "enabled": true, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS m5.2xlarge", "data": [ { "x": 0, "y": 4034.318731574461, "single": 881.679974115011, "multi": 4034.318731574461, "scale": 457.5717777444044, "color": "rgba(247, 152, 29, 0.5)", "dataLabels": { "enabled": false } }, { "x": 0, "y": 881.679974115011, "single": 881.679974115011, "multi": 4034.318731574461, "scale": 457.5717777444044, "color": "#f7981d" } ], "color": "#f7981d", "grouping": false }, { "name": "AWS m5a.2xlarge", "data": [ { "x": 1, "y": 3252.3152845339296, "single": 719.3149992656543, "multi": 3252.3152845339296, "scale": 452.1406182067946, "color": "rgba(247, 152, 29, 0.5)", "dataLabels": { "enabled": false } }, { "x": 1, "y": 719.3149992656543, "single": 719.3149992656543, "multi": 3252.3152845339296, "scale": 452.1406182067946, "color": "#d7983d" } ], "color": "#d7a83d", "grouping": false }, { "name": "AWS m6i.2xlarge", "data": [ { "x": 2, "y": 5449.413265438406, "single": 1262.8190073158987, "multi": 5449.413265438406, "scale": 431.5276562886906, "color": "rgba(247, 152, 29, 0.5)", "dataLabels": { "enabled": false } }, { "x": 2, "y": 1262.8190073158987, "single": 1262.8190073158987, "multi": 5449.413265438406, "scale": 431.5276562886906, "color": "#a7985d" } ], "color": "#a7b85d", "grouping": false } ], "tooltip": { "enabled": true, "useHTML": true, "headerFormat": "", "pointFormat": "\n {series.name}:\n
\n\n\n\n
Single: {point.single:.0f}
Multi: {point.multi:.0f}
Scale: {point.scale:.0f}%
\n    ",
"footerFormat": "",
"shared": false,
"outside": false,
"valueDecimals": null,
"split": false
}
},
"hc_type": "chart",
"id": "139659200957184"
}
From our tests, there's no aspect where m5 or m5a can argue to have an advantage compared to m6i. On the left, you can see a comparison using Geekbench 5, it covers Integer, Floating Point and Cryptography domains.

It is the best bang for your buck

No need to have a PhD to guess that with the same price and higher performance, the ROI will be better for the latest series. This lets no doubt, you'll only have gains by changing the instance_type in your Terraform and update your infrastructure.
    {
"configuration": {
"chart": {
"type": "bar",
"polar": false,
"zoomType": "",
"options3d": {},
"height": 300,
"width": null,
"margin": null,
"inverted": false
},
"credits": {
"enabled": false
},
"title": {
"text": ""
},
"colorAxis": null,
"subtitle": {
"text": ""
},
"xAxis": {
"title": {
"text": [
""
],
"useHTML": false,
"style": {
"color": "#666666"
}
},
"categories": [
"provider__short_name"
],
"lineWidth": 1,
"tickInterval": null,
"tickWidth": 0,
"tickLength": 10,
"tickPixelInterval": null,
"plotLines": null,
"labels": {
"enabled": false,
"formatter": "",
"style": {
"color": "#666666",
"cursor": "default",
"fontSize": "11px"
}
},
"plotBands": null,
"visible": true,
"floor": null,
"ceiling": null,
"type": "linear",
"min": null,
"gridLineWidth": null,
"gridLineColor": null,
"minorTickInterval": null,
"minorTickWidth": 0,
"minTickInterval": null,
"startOnTick": true,
"endOnTick": null,
"tickmarkPlacement": null
},
"yAxis": {
"title": {
"text": [
"Higher is better"
],
"useHTML": false,
"style": {
"fontSize": "17px"
}
},
"categories": null,
"plotLines": null,
"plotBands": null,
"lineWidth": null,
"tickInterval": null,
"tickLength": 10,
"floor": null,
"ceiling": null,
"gridLineInterpolation": null,
"gridLineWidth": 1,
"gridLineColor": "#CCC",
"min": null,
"max": null,
"minorTickInterval": null,
"minorTickWidth": 0,
"minTickInterval": null,
"startOnTick": true,
"endOnTick": null,
"minRange": null,
"type": "linear",
"tickmarkPlacement": null,
"labels": {
"enabled": true,
"formatter": null,
"style": {
"fontSize": "14px"
}
}
},
"zAxis": {
"title": {
"text": "Higher is better"
}
},
"plotOptions": {
"series": {
"dataLabels": {
"enabled": true,
"format": "{series.name}",
"distance": 30,
"align": "left",
"inside": true,
"style": {
"fontSize": "17px"
}
},
"showInLegend": null,
"turboThreshold": 1000,
"stacking": "",
"groupPadding": 0,
"centerInCategory": false
}
},
"rangeSelector": {
"enabled": false
},
"legend": {
"enabled": true,
"align": "center",
"verticalAlign": "bottom",
"layout": "horizontal",
"width": null,
"margin": 12,
"reversed": false
},
"series": [
{
"name": "AWS EU (Frankfurt) m5.2xlarge",
"data": [
{
"x": 0,
"y": 8770258.112118391,
"perf": 4034.318731574461,
"price": 0.46,
"currency": "USD"
}
],
"color": "#f7981d",
"grouping": false
},
{
"name": "AWS EU (Frankfurt) m5a.2xlarge",
"data": [
{
"x": 1,
"y": 7818065.5878219465,
"perf": 3252.3152845339296,
"price": 0.416,
"currency": "USD"
}
],
"color": "#d7a83d",
"grouping": false
},
{
"name": "AWS EU (Frankfurt) m6i.2xlarge",
"data": [
{
"x": 2,
"y": 11846550.577040013,
"perf": 5449.413265438406,
"price": 0.46,
"currency": "USD"
}
],
"color": "#a7985d",
"grouping": false
}
],
"tooltip": {
"enabled": true,
"useHTML": false,
"headerFormat": "",
"pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>:<br><b>Price/Perf: {point.y:.2f}</b><br><b>Performance</b>: {point.perf:.2f}<br><b>Price</b>: {point.price:.4f} USD",
"footerFormat": "",
"shared": false,
"outside": false,
"valueDecimals": null,
"split": false
}
},
"hc_type": "chart",
"id": "140304345008896"
}
The m6i isn't generaly available yet and I guess in the next semesters we'll see c6i, r6i and why not i4i, that's make a while they didn't upgrade these VMs.

Of course we have more than just Geekbench 5 performance

We ran a full study comparing m5 vs m5a vs m6i. I didn't mentionned this here but there's also a visible plus in network performance.

Check out more: