From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ig0-f180.google.com ([209.85.213.180]:36106 "EHLO mail-ig0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752534AbbJEQAI (ORCPT ); Mon, 5 Oct 2015 12:00:08 -0400 Received: by igcrk20 with SMTP id rk20so64222545igc.1 for ; Mon, 05 Oct 2015 09:00:08 -0700 (PDT) Subject: Re: BTRFS as image store for KVM? To: Duncan <1i5t5.duncan@cox.net>, Lionel Bouton , linux-btrfs@vger.kernel.org References: <55F88ECC.1040604@menke.ac> <201510021421.09558.russell@coker.com.au> <560E737C.7050206@gmail.com> <201510031832.17802.russell@coker.com.au> <56111598.2080403@bouton.name> <20151005070455.104464fe@ws> From: Austin S Hemmelgarn Message-ID: <56129E77.7020806@gmail.com> Date: Mon, 5 Oct 2015 11:59:51 -0400 MIME-Version: 1.0 In-Reply-To: <20151005070455.104464fe@ws> Content-Type: multipart/signed; protocol="application/pkcs7-signature"; micalg=sha-512; boundary="------------ms010807070906010304070802" Sender: linux-btrfs-owner@vger.kernel.org List-ID: This is a cryptographically signed message in MIME format. --------------ms010807070906010304070802 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: quoted-printable On 2015-10-05 10:04, Duncan wrote: > On Mon, 5 Oct 2015 13:16:03 +0200 > Lionel Bouton wrote: > >> To better illustrate my point. >> >> According to Phoronix tests, BTRFS RAID-1 is even faster than md RAID1= >> most of the time. >> >> http://www.phoronix.com/scan.php?page=3Darticle&item=3Dbtrfs_raid_mdad= m&num=3D1 >> >> The only case where md RAID1 was noticeably faster is sequential reads= >> with FIO libaio. >> >> So if you base your analysis on Phoronix tests > [...snip...] > > Hmm... I think I've begun to see the kernel folks point about people > quoting Phoronix in support of their points, when it's really not > apropos at all. Yes, I do still consider Phoronix reports in context > to contain useful information, at some level. However, one really must= > be aware of what was actually tested in ordered to understand what the > results actually mean, and unfortunately, it seems most people quoting > it, including here, really can't properly do so in context, and thus > end up using it in support of points that simply are not supported by > the given evidence in the Phoronix articles people are attempting to > use. > Even aside from the obvious past issues with Phoronix reports, people=20 forget that they are news organization (regardless of what they claim,=20 they _are_ a news organization), and as such their employees are not=20 paid to verify existing results, they're paid to make impactful articles = that grab people's attention (I'd be willing to bet that this story=20 started in response to the people who pointed out correctly that XFS or=20 ext4 on top of mdraid beats the pants off of BTRFS performance wise, and = (incorrectly) assumed that this meant that mdraid was better than BTRFS=20 raid). This when combined with almost no evidence in many cases of=20 actual statistical analysis, really hurts their credibility (at least,=20 for me it does). The other issue is that so many people tout benchmarks as the pinnacle=20 of testing, when they really aren't. Benchmarks are by definition=20 synthetic workloads, and as such only the _really_ good ones (which=20 there aren't many of) give you more than a very basic idea what=20 performance differences you can expect with a given workload. On top of = that, people just accept results without trying to reproduce them=20 themselves (Kernel folks tend to be much better about this than many=20 other people though). A truly sane person, looking to determine the best configuration for a=20 given workload, will: 1. Look at a wide variety of sources to determine what configurations he = should even be testing. (The author of the linked article obviously=20 didn't do this, or just didn't care, the defaults on btrfs are=20 unsuitable for a significant number of cases, including usage on top of=20 mdraid). 2. Using this information, run established benchmarks similar to his=20 use-case to further narrow down the test candidates. 3. Write his own benchmark to simulate to the greatest degree possible=20 the actual workload he expects to run, and then use that for testing the = final candidates. 4. Gather some reasonable number of samples with the above mentioned=20 benchmark, and use _real_ statistical analysis to determine what he=20 should be using. To put this in further perspective, most people just do step one, assume = that other people know what they're talking about, and don't do any=20 further testing, and there are other people who just do step two, and=20 then claim their results are infallible. --------------ms010807070906010304070802 Content-Type: application/pkcs7-signature; name="smime.p7s" Content-Transfer-Encoding: base64 Content-Disposition: attachment; filename="smime.p7s" Content-Description: S/MIME Cryptographic Signature MIAGCSqGSIb3DQEHAqCAMIACAQExDzANBglghkgBZQMEAgMFADCABgkqhkiG9w0BBwEAAKCC Brgwgga0MIIEnKADAgECAgMRLfgwDQYJKoZIhvcNAQENBQAweTEQMA4GA1UEChMHUm9vdCBD QTEeMBwGA1UECxMVaHR0cDovL3d3dy5jYWNlcnQub3JnMSIwIAYDVQQDExlDQSBDZXJ0IFNp Z25pbmcgQXV0aG9yaXR5MSEwHwYJKoZIhvcNAQkBFhJzdXBwb3J0QGNhY2VydC5vcmcwHhcN MTUwOTIxMTEzNTEzWhcNMTYwMzE5MTEzNTEzWjBjMRgwFgYDVQQDEw9DQWNlcnQgV29UIFVz ZXIxIzAhBgkqhkiG9w0BCQEWFGFoZmVycm9pbjdAZ21haWwuY29tMSIwIAYJKoZIhvcNAQkB FhNhaGVtbWVsZ0BvaGlvZ3QuY29tMIICIjANBgkqhkiG9w0BAQEFAAOCAg8AMIICCgKCAgEA nQ/81tq0QBQi5w316VsVNfjg6kVVIMx760TuwA1MUaNQgQ3NyUl+UyFtjhpkNwwChjgAqfGd LIMTHAdObcwGfzO5uI2o1a8MHVQna8FRsU3QGouysIOGQlX8jFYXMKPEdnlt0GoQcd+BtESr pivbGWUEkPs1CwM6WOrs+09bAJP3qzKIr0VxervFrzrC5Dg9Rf18r9WXHElBuWHg4GYHNJ2V Ab8iKc10h44FnqxZK8RDN8ts/xX93i9bIBmHnFfyNRfiOUtNVeynJbf6kVtdHP+CRBkXCNRZ qyQT7gbTGD24P92PS2UTmDfplSBcWcTn65o3xWfesbf02jF6PL3BCrVnDRI4RgYxG3zFBJuG qvMoEODLhHKSXPAyQhwZINigZNdw5G1NqjXqUw+lIqdQvoPijK9J3eijiakh9u2bjWOMaleI SMRR6XsdM2O5qun1dqOrCgRkM0XSNtBQ2JjY7CycIx+qifJWsRaYWZz0aQU4ZrtAI7gVhO9h pyNaAGjvm7PdjEBiXq57e4QcgpwzvNlv8pG1c/hnt0msfDWNJtl3b6elhQ2Pz4w/QnWifZ8E BrFEmjeeJa2dqjE3giPVWrsH+lOvQQONsYJOuVb8b0zao4vrWeGmW2q2e3pdv0Axzm/60cJQ haZUv8+JdX9ZzqxOm5w5eUQSclt84u+D+hsCAwEAAaOCAVkwggFVMAwGA1UdEwEB/wQCMAAw VgYJYIZIAYb4QgENBEkWR1RvIGdldCB5b3VyIG93biBjZXJ0aWZpY2F0ZSBmb3IgRlJFRSBo ZWFkIG92ZXIgdG8gaHR0cDovL3d3dy5DQWNlcnQub3JnMA4GA1UdDwEB/wQEAwIDqDBABgNV HSUEOTA3BggrBgEFBQcDBAYIKwYBBQUHAwIGCisGAQQBgjcKAwQGCisGAQQBgjcKAwMGCWCG SAGG+EIEATAyBggrBgEFBQcBAQQmMCQwIgYIKwYBBQUHMAGGFmh0dHA6Ly9vY3NwLmNhY2Vy dC5vcmcwMQYDVR0fBCowKDAmoCSgIoYgaHR0cDovL2NybC5jYWNlcnQub3JnL3Jldm9rZS5j cmwwNAYDVR0RBC0wK4EUYWhmZXJyb2luN0BnbWFpbC5jb22BE2FoZW1tZWxnQG9oaW9ndC5j b20wDQYJKoZIhvcNAQENBQADggIBADMnxtSLiIunh/TQcjnRdf63yf2D8jMtYUm4yDoCF++J jCXbPQBGrpCEHztlNSGIkF3PH7ohKZvlqF4XePWxpY9dkr/pNyCF1PRkwxUURqvuHXbu8Lwn 8D3U2HeOEU3KmrfEo65DcbanJCMTTW7+mU9lZICPP7ZA9/zB+L0Gm1UNFZ6AU50N/86vjQfY WgkCd6dZD4rQ5y8L+d/lRbJW7ZGEQw1bSFVTRpkxxDTOwXH4/GpQfnfqTAtQuJ1CsKT12e+H NSD/RUWGTr289dA3P4nunBlz7qfvKamxPymHeBEUcuICKkL9/OZrnuYnGROFwcdvfjGE5iLB kjp/ttrY4aaVW5EsLASNgiRmA6mbgEAMlw3RwVx0sVelbiIAJg9Twzk4Ct6U9uBKiJ8S0sS2 8RCSyTmCRhJs0vvva5W9QUFGmp5kyFQEoSfBRJlbZfGX2ehI2Hi3U2/PMUm2ONuQG1E+a0AP u7I0NJc/Xil7rqR0gdbfkbWp0a+8dAvaM6J00aIcNo+HkcQkUgtfrw+C2Oyl3q8IjivGXZqT 5UdGUb2KujLjqjG91Dun3/RJ/qgQlotH7WkVBs7YJVTCxfkdN36rToPcnMYOI30FWa0Q06gn F6gUv9/mo6riv3A5bem/BdbgaJoPnWQD9D8wSyci9G4LKC+HQAMdLmGoeZfpJzKHMYIE0TCC BM0CAQEwgYAweTEQMA4GA1UEChMHUm9vdCBDQTEeMBwGA1UECxMVaHR0cDovL3d3dy5jYWNl cnQub3JnMSIwIAYDVQQDExlDQSBDZXJ0IFNpZ25pbmcgQXV0aG9yaXR5MSEwHwYJKoZIhvcN AQkBFhJzdXBwb3J0QGNhY2VydC5vcmcCAxEt+DANBglghkgBZQMEAgMFAKCCAiEwGAYJKoZI hvcNAQkDMQsGCSqGSIb3DQEHATAcBgkqhkiG9w0BCQUxDxcNMTUxMDA1MTU1OTUxWjBPBgkq hkiG9w0BCQQxQgRAtNMQIDsEcoWMGbbw/UPN0YqRNKDR6n6dvpt6eMLebruzmfte78pOWGlh AXu9FMjGNJ1XVUX3DviWUp0bpXGSfjBsBgkqhkiG9w0BCQ8xXzBdMAsGCWCGSAFlAwQBKjAL BglghkgBZQMEAQIwCgYIKoZIhvcNAwcwDgYIKoZIhvcNAwICAgCAMA0GCCqGSIb3DQMCAgFA MAcGBSsOAwIHMA0GCCqGSIb3DQMCAgEoMIGRBgkrBgEEAYI3EAQxgYMwgYAweTEQMA4GA1UE ChMHUm9vdCBDQTEeMBwGA1UECxMVaHR0cDovL3d3dy5jYWNlcnQub3JnMSIwIAYDVQQDExlD QSBDZXJ0IFNpZ25pbmcgQXV0aG9yaXR5MSEwHwYJKoZIhvcNAQkBFhJzdXBwb3J0QGNhY2Vy dC5vcmcCAxEt+DCBkwYLKoZIhvcNAQkQAgsxgYOggYAweTEQMA4GA1UEChMHUm9vdCBDQTEe MBwGA1UECxMVaHR0cDovL3d3dy5jYWNlcnQub3JnMSIwIAYDVQQDExlDQSBDZXJ0IFNpZ25p bmcgQXV0aG9yaXR5MSEwHwYJKoZIhvcNAQkBFhJzdXBwb3J0QGNhY2VydC5vcmcCAxEt+DAN BgkqhkiG9w0BAQEFAASCAgCAJ8MSF/JAQ2lfRV/b9vzckkuzgX6XDJUWxVqDv8U9O2b5O6Kl ReYLNl9U3Oqb4k7Td+qG5UpHgytaT39x8TKK0TGlBb6xU6ouL116N/A++VKDABDRT0FH952y k6IB8Dr83M4W3b9kiFYhLCNnV3O+ERfvBmKmLgrg3jyV14BE9ie0GK+7JLZt+d9NdZ+Qc4ko UlBrzRSeBD5CdYpa1FSt2p5wQqSXF/hpb6AiNKmsQN9W2UZma1OstiyetWbetyFfjlpLNm56 e+85zrSK6Vu5mUqNpCZZ81iwH75aXPJ/XzHsRifjw+Kzyanw9/PMORCMeTeVtIkPV6Lv3W60 0tfdYStjHrkSxP9wIBV2AOU9rBEYxsKS+eUJ2J5BDIFl0lcnXQtVf582dJXiGdjMjCLoFQOM UIgeD7ipp8LHM+yK+mtsiz4gT1v4IBb+4gFR7SnWdRLpVLWGSWCeVWPptZbm6CQq/G5TPfoA LQ/iEsb5IKfsvjbbTXu84A7J4sr1xArGkzrLnIxpfnJQZ6DNP4MUUv1+xRiM+BM8Jw79Dw89 f9UPYhNJ4+jOlNXgvGaok4jO92aF+Umb3tdlI6BF5C47P/E9aaRUYz3lZq/2+QWS+8exESYH egXZrb92eYjOL8MIQWmHTb9PLlm69rpzfudUhhm4pXLbGdH2N5xwfCbGlAAAAAAAAA== --------------ms010807070906010304070802--