Re: [CentOS] cyrus spool on btrfs?

On 9/9/2017 9:47 AM, hw wrote: Isn´t it easier for SSDs to write small chunks of data at a time? The small chunk might fit into some free space more easily than a large one which needs to be spread out all over the place. the SSD collects data blocks being written and when a full flash

Re: [CentOS] cyrus spool on btrfs?

Johnny Hughes wrote: On 09/07/2017 12:57 PM, hw wrote: Hi, is there anything that speaks against putting a cyrus mail spool onto a btrfs subvolume? This is what Red Hat says about btrfs: The Btrfs file system has been in Technology Preview state since the initial release of Red Hat

Re: [CentOS] cyrus spool on btrfs?

Gordon Messmer wrote: On 09/08/2017 11:06 AM, hw wrote: Make a test and replace a software RAID5 with a hardware RAID5. Even with only 4 disks, you will see an overall performance gain. I´m guessing that the SATA controllers they put onto the mainboards are not designed to handle all the data

Re: [CentOS] cyrus spool on btrfs?

> Am 09.09.2017 um 19:22 schrieb hw : > > Mark Haney wrote: >> On 09/08/2017 01:31 PM, hw wrote: >>> Mark Haney wrote: >>> >>> I/O is not heavy in that sense, that´s why I said that´s not the >>> application. >>> There is I/O which, as tests have shown, benefits greatly from low

Re: [CentOS] cyrus spool on btrfs?

Valeri Galtsev wrote: Thanks. That seems to clear fog a little bit. I still would like to hear manufacturers/models here. My choices would be: Areca or LSI (bought out by Intel, so former LSI chipset and microcode/firmware) and as SSD Samsung Evo SATA III. Does anyone who used these in hardware

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: On 09/08/2017 01:31 PM, hw wrote: Mark Haney wrote: I/O is not heavy in that sense, that´s why I said that´s not the application. There is I/O which, as tests have shown, benefits greatly from low latency, which is where the idea to use SSDs for the relevant data has arisen

Re: [CentOS] cyrus spool on btrfs?

> On Sep 9, 2017, at 12:47 PM, hw wrote: > > Isn´t it easier for SSDs to write small chunks of data at a time? SSDs read/write in large-ish (256k-4M) blocks/pages. Seems to me that drive blocks and hardware RAID strip size and file system block/cluster/extents sizes and etc

Re: [CentOS] cyrus spool on btrfs?

m.r...@5-cent.us wrote: hw wrote: Mark Haney wrote: On 09/08/2017 09:49 AM, hw wrote: Mark Haney wrote: Probably with the very expensive SSDs suited for this ... That´s because I do not store data on a single disk, without redundancy, and the SSDs I have are not suitable for hardware

Re: [CentOS] cyrus spool on btrfs?

John R Pierce wrote: And one may want to adjust stripe size to be resembling SSDs internals, as default is for hard drives, right? as the SSD physical data blocks have no visible relation to logical block numbers or CHS, its not practical to do this. I'd use a fairly large stripe size, like

Re: [CentOS] cyrus spool on btrfs?

On 9/8/2017 2:36 PM, Valeri Galtsev wrote: With all due respect, John, this is the same as hard drive cache is not backed up power wise for a case of power loss. And hard drives all lie about write operation completed before data actually are on the platters. So we can claim the same: hard

Re: [CentOS] cyrus spool on btrfs?

On Fri, September 8, 2017 3:06 pm, John R Pierce wrote: > On 9/8/2017 12:52 PM, Valeri Galtsev wrote: >> Thanks. That seems to clear fog a little bit. I still would like to hear >> manufacturers/models here. My choices would be: Areca or LSI (bought out >> by Intel, so former LSI chipset and

Re: [CentOS] cyrus spool on btrfs?

On 09/08/2017 11:06 AM, hw wrote: Make a test and replace a software RAID5 with a hardware RAID5.  Even with only 4 disks, you will see an overall performance gain.  I´m guessing that the SATA controllers they put onto the mainboards are not designed to handle all the data --- which gets

Re: [CentOS] cyrus spool on btrfs?

On Fri, Sep 8, 2017 at 2:52 PM, Valeri Galtsev wrote: > > manufacturers/models here. My choices would be: Areca or LSI (bought out > by Intel, so former LSI chipset and microcode/firmware) and as SSD Samsung > Intel only purchased the networking component of LSI,

Re: [CentOS] cyrus spool on btrfs?

On 9/8/2017 12:52 PM, Valeri Galtsev wrote: Thanks. That seems to clear fog a little bit. I still would like to hear manufacturers/models here. My choices would be: Areca or LSI (bought out by Intel, so former LSI chipset and microcode/firmware) and as SSD Samsung Evo SATA III. Does anyone who

Re: [CentOS] cyrus spool on btrfs?

On Fri, September 8, 2017 12:56 pm, hw wrote: > Valeri Galtsev wrote: >> >> On Fri, September 8, 2017 9:48 am, hw wrote: >>> m.r...@5-cent.us wrote: hw wrote: > Mark Haney wrote: >> BTRFS isn't going to impact I/O any more significantly than, say, >> XFS. > > But

Re: [CentOS] cyrus spool on btrfs?

On 09/07/2017 12:57 PM, hw wrote: > > Hi, > > is there anything that speaks against putting a cyrus mail spool onto a > btrfs subvolume? This is what Red Hat says about btrfs: The Btrfs file system has been in Technology Preview state since the initial release of Red Hat Enterprise Linux 6.

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: > On 09/08/2017 01:31 PM, hw wrote: >> Mark Haney wrote: >> >> Probably with the very expensive SSDs suited for this ... > Possibly, but that's somewhat irrelevant.  I've taken off the shelf SSDs > and hardware RAID'd them.  If they work for the hell I put them through >

Re: [CentOS] cyrus spool on btrfs?

On 09/08/2017 01:31 PM, hw wrote: Mark Haney wrote: I/O is not heavy in that sense, that´s why I said that´s not the application. There is I/O which, as tests have shown, benefits greatly from low latency, which is where the idea to use SSDs for the relevant data has arisen from.  This I/O

Re: [CentOS] cyrus spool on btrfs?

m.r...@5-cent.us wrote: Mark Haney wrote: On 09/08/2017 09:49 AM, hw wrote: Mark Haney wrote: It depends, i. e. I can´t tell how these SSDs would behave if large amounts of data would be written and/or read to/from them over extended periods of time because I haven´t tested that. That

Re: [CentOS] cyrus spool on btrfs?

hw wrote: > Mark Haney wrote: >> On 09/08/2017 09:49 AM, hw wrote: >>> Mark Haney wrote: > Probably with the very expensive SSDs suited for this ... >>> >>> That´s because I do not store data on a single disk, without >>> redundancy, and the SSDs I have are not suitable for hardware RAID.

Re: [CentOS] cyrus spool on btrfs?

Valeri Galtsev wrote: On Fri, September 8, 2017 9:48 am, hw wrote: m.r...@5-cent.us wrote: hw wrote: Mark Haney wrote: BTRFS isn't going to impact I/O any more significantly than, say, XFS. But mdadm does, the impact is severe. I know there are ppl saying otherwise, but I´ve seen the

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: > On 09/08/2017 09:49 AM, hw wrote: >> Mark Haney wrote: >> >> It depends, i. e. I can´t tell how these SSDs would behave if large >> amounts of data would be written and/or read to/from them over extended >> periods of time because I haven´t tested that.  That isn´t the >>

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: On 09/08/2017 09:49 AM, hw wrote: Mark Haney wrote: I hate top posting, but since you've got two items I want to comment on, I'll suck it up for now. I do, too, yet sometimes it´s reasonable. I also hate it when the lines are too long :) I'm afraid you'll have to live

Re: [CentOS] cyrus spool on btrfs?

On 8 September 2017 at 12:13, Valeri Galtsev wrote: > > On Fri, September 8, 2017 11:07 am, Stephen John Smoogen wrote: >> On 8 September 2017 at 11:00, Valeri Galtsev >> wrote: >>> >>> On Fri, September 8, 2017 9:48 am, hw wrote:

Re: [CentOS] cyrus spool on btrfs?

On Fri, September 8, 2017 11:07 am, Stephen John Smoogen wrote: > On 8 September 2017 at 11:00, Valeri Galtsev > wrote: >> >> On Fri, September 8, 2017 9:48 am, hw wrote: >>> m.r...@5-cent.us wrote: hw wrote: > Mark Haney wrote: >> BTRFS isn't going

Re: [CentOS] cyrus spool on btrfs?

On 8 September 2017 at 11:00, Valeri Galtsev wrote: > > On Fri, September 8, 2017 9:48 am, hw wrote: >> m.r...@5-cent.us wrote: >>> hw wrote: Mark Haney wrote: >>> > BTRFS isn't going to impact I/O any more significantly than, say, XFS. But mdadm

Re: [CentOS] cyrus spool on btrfs?

On Fri, September 8, 2017 9:48 am, hw wrote: > m.r...@5-cent.us wrote: >> hw wrote: >>> Mark Haney wrote: >> BTRFS isn't going to impact I/O any more significantly than, say, XFS. >>> >>> But mdadm does, the impact is severe. I know there are ppl saying >>> otherwise, but I´ve seen the

Re: [CentOS] cyrus spool on btrfs?

On 09/08/2017 09:49 AM, hw wrote: Mark Haney wrote: I hate top posting, but since you've got two items I want to comment on, I'll suck it up for now. I do, too, yet sometimes it´s reasonable.  I also hate it when the lines are too long :) I'm afraid you'll have to live with it a bit longer. 

Re: [CentOS] cyrus spool on btrfs?

m.r...@5-cent.us wrote: hw wrote: Mark Haney wrote: BTRFS isn't going to impact I/O any more significantly than, say, XFS. But mdadm does, the impact is severe. I know there are ppl saying otherwise, but I´ve seen the impact myself, and I definitely don´t want it on that particular server

Re: [CentOS] cyrus spool on btrfs?

hw wrote: > Mark Haney wrote: >> BTRFS isn't going to impact I/O any more significantly than, say, XFS. > > But mdadm does, the impact is severe. I know there are ppl saying > otherwise, but I´ve seen the impact myself, and I definitely don´t want > it on that particular server because it would

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: I hate top posting, but since you've got two items I want to comment on, I'll suck it up for now. I do, too, yet sometimes it´s reasonable. I also hate it when the lines are too long :) Having SSDs alone will give you great performance regardless of filesystem. It

Re: [CentOS] cyrus spool on btrfs?

Matty wrote: I think it depends on who you ask. Facebook and Netflix are using it extensively in production: https://www.linux.com/news/learn/intro-to-linux/how-facebook-uses-linux-and-btrfs-interview-chris-mason Though they have the in-house kernel engineering resources to troubleshoot

Re: [CentOS] cyrus spool on btrfs?

I hate top posting, but since you've got two items I want to comment on, I'll suck it up for now. Having SSDs alone will give you great performance regardless of filesystem.  BTRFS isn't going to impact I/O any more significantly than, say, XFS.  It does have serious stability/data integrity

Re: [CentOS] cyrus spool on btrfs?

I think it depends on who you ask. Facebook and Netflix are using it extensively in production: https://www.linux.com/news/learn/intro-to-linux/how-facebook-uses-linux-and-btrfs-interview-chris-mason Though they have the in-house kernel engineering resources to troubleshoot problems. When I see

Re: [CentOS] cyrus spool on btrfs?

PS: What kind of storage solutions do people use for cyrus mail spools? Apparently you can not use remote storage, at least not NFS. That even makes it difficult to use a VM due to limitations of available disk space. I´m reluctant to use btrfs, but there doesn´t seem to be any reasonable

Re: [CentOS] cyrus spool on btrfs?

Mark Haney wrote: On 09/07/2017 01:57 PM, hw wrote: Hi, is there anything that speaks against putting a cyrus mail spool onto a btrfs subvolume? I might be the lone voice on this, but I refuse to use btrfs for anything, much less a mail spool. I used it in production on DB and Web servers

Re: [CentOS] cyrus spool on btrfs?

On 09/07/2017 01:57 PM, hw wrote: Hi, is there anything that speaks against putting a cyrus mail spool onto a btrfs subvolume? I might be the lone voice on this, but I refuse to use btrfs for anything, much less a mail spool. I used it in production on DB and Web servers and fought

[CentOS] cyrus spool on btrfs?

Hi, is there anything that speaks against putting a cyrus mail spool onto a btrfs subvolume? ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos