Write cache (was: Re: [zfs-discuss] How to best layout our filesystems)
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Neil Perrin wrote: I suppose if you know the disk only contains zfs slices then write caching could be manually enabled using format -e - cache - write_cache - enable When will we have write cache control over ATA/SATA drives? :-). - -- Jesus Cea Avion _/_/ _/_/_/_/_/_/ [EMAIL PROTECTED] http://www.argo.es/~jcea/ _/_/_/_/ _/_/_/_/ _/_/ jabber / xmpp:[EMAIL PROTECTED] _/_/_/_/ _/_/_/_/_/ _/_/ _/_/_/_/ _/_/ _/_/ Things are not so easy _/_/ _/_/_/_/ _/_/_/_/ _/_/ My name is Dump, Core Dump _/_/_/_/_/_/ _/_/ _/_/ El amor es poner tu felicidad en la felicidad de otro - Leibniz -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.2.2 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iQCVAwUBRM+mzZlgi5GaxT1NAQL8oAP7BJEUzDlMhVGt5j3IKcNc2Q8TCyUwAn4k yWBCEmXdyBdpbRyoUnr6jlsn4QceC6/weYl/0H9df+eUibitu5QwWq4zRwFLUrqB BkgdIdgECmOt9u6Y6uAEFRGKlMQUU5ZVNuJKDgfIsJSlsvxD1f5ddKx74ZZpFqmx d9IVFK/KzQ0= =YqXY -END PGP SIGNATURE- ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
Robert, The patches will be available sometime late September. This may be a week or so before s10u3 actually releases. Thanks, George Robert Milkowski wrote: Hello eric, Thursday, July 27, 2006, 4:34:16 AM, you wrote: ek Robert Milkowski wrote: Hello George, Wednesday, July 26, 2006, 7:27:04 AM, you wrote: GW Additionally, I've just putback the latest feature set and bugfixes GW which will be part of s10u3_03. There were some additional performance GW fixes which may really benefit plus it will provide hot spares support. GW Once this build is available I would highly recommend that you guys take GW it for a spin (works great on Thumper). I guess patches will be released first (or later). Can you give actual BUG IDs especially those related to performance? ek For U3, these are the performance fixes: ek 6424554 full block re-writes need not read data in ek 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue ek parallelIOs when fsyncing ek 6447377 ZFS prefetch is inconsistant ek 6373978 want to take lots of snapshots quickly ('zfs snapshot -r') ek you could perhaps include these two as well: ek 4034947 anon_swap_adjust() should call kmem_reap() if availrmem is low. ek 6416482 filebench oltp workload hangs in zfs ok, thank you. Do you know if patches for S10 will be released before U3? ek There won't be anything in U3 that isn't already in nevada... I know that :) ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re[2]: [zfs-discuss] How to best layout our filesystems
Hello eric, Thursday, July 27, 2006, 4:34:16 AM, you wrote: ek Robert Milkowski wrote: Hello George, Wednesday, July 26, 2006, 7:27:04 AM, you wrote: GW Additionally, I've just putback the latest feature set and bugfixes GW which will be part of s10u3_03. There were some additional performance GW fixes which may really benefit plus it will provide hot spares support. GW Once this build is available I would highly recommend that you guys take GW it for a spin (works great on Thumper). I guess patches will be released first (or later). Can you give actual BUG IDs especially those related to performance? ek For U3, these are the performance fixes: ek 6424554 full block re-writes need not read data in ek 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue ek parallelIOs when fsyncing ek 6447377 ZFS prefetch is inconsistant ek 6373978 want to take lots of snapshots quickly ('zfs snapshot -r') ek you could perhaps include these two as well: ek 4034947 anon_swap_adjust() should call kmem_reap() if availrmem is low. ek 6416482 filebench oltp workload hangs in zfs ok, thank you. Do you know if patches for S10 will be released before U3? ek There won't be anything in U3 that isn't already in nevada... I know that :) -- Best regards, Robertmailto:[EMAIL PROTECTED] http://milek.blogspot.com ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
RE: [zfs-discuss] How to best layout our filesystems
Eric said: For U3, these are the performance fixes: 6424554 full block re-writes need not read data in 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue parallelIOs when fsyncing 6447377 ZFS prefetch is inconsistant 6373978 want to take lots of snapshots quickly ('zfs snapshot -r') you could perhaps include these two as well: 4034947 anon_swap_adjust() should call kmem_reap() if availrmem is low. 6416482 filebench oltp workload hangs in zfs There won't be anything in U3 that isn't already in nevada... Hi Eric, Do S10U2 users have to wait for U3 to get these fixes, or are they going to be released as patches before then? I'm presuming that U3 is scheduled for early 2007... Steve. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
For S10U3, RR is 11/13/06 and GA is 11/27/06. Gary Bennett, Steve wrote: Eric said: For U3, these are the performance fixes: 6424554 full block re-writes need not read data in 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue parallelIOs when fsyncing 6447377 ZFS prefetch is inconsistant 6373978 want to take lots of snapshots quickly ('zfs snapshot -r') you could perhaps include these two as well: 4034947 anon_swap_adjust() should call kmem_reap() if availrmem is low. 6416482 filebench oltp workload hangs in zfs There won't be anything in U3 that isn't already in nevada... Hi Eric, Do S10U2 users have to wait for U3 to get these fixes, or are they going to be released as patches before then? I'm presuming that U3 is scheduled for early 2007... Steve. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss -- Gary Combs Product Architect Sun Microsystems, Inc. 3295 NW 211th Terrace Hillsboro, OR 97124 US Phone x32604/+1 503 715 3517 Fax 503-715-3517 Email [EMAIL PROTECTED] "The box said 'Windows 2000 Server or better', so I installed Solaris" ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
On Tue, Jul 25, 2006 at 03:54:22PM -0700, Eric Schrock wrote: If you give zpool(1M) 'whole disks' (i.e. no 's0' slice number) and let it label and use the disks, it will automatically turn on the write cache for you. What if you can't give ZFS whole disks? I run snv_38 on the Optiplex GX620 on my desk at work and I run snv_40 on the Latitude D610 that I carry with me. In both cases the machines only have one disk, so I need to split it up for UFS for the OS and ZFS for my data. How do I turn on write cache for partial disks? -brian ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
Brian Hechinger wrote On 07/26/06 06:49,: On Tue, Jul 25, 2006 at 03:54:22PM -0700, Eric Schrock wrote: If you give zpool(1M) 'whole disks' (i.e. no 's0' slice number) and let it label and use the disks, it will automatically turn on the write cache for you. What if you can't give ZFS whole disks? I run snv_38 on the Optiplex GX620 on my desk at work and I run snv_40 on the Latitude D610 that I carry with me. In both cases the machines only have one disk, so I need to split it up for UFS for the OS and ZFS for my data. How do I turn on write cache for partial disks? -brian You can't enable write caching for just part of the disk. We don't enable it for slices because UFS (and other file systems) doesn't do write cache flushing and so could get corruption on power failure. I suppose if you know the disk only contains zfs slices then write caching could be manually enabled using format -e - cache - write_cache - enable Neil ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Write cache (was: Re: [zfs-discuss] How to best layout our filesystems)
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Neil Perrin wrote: I suppose if you know the disk only contains zfs slices then write caching could be manually enabled using format -e - cache - write_cache - enable When will we have write cache control over ATA/SATA drives? :-). - -- Jesus Cea Avion _/_/ _/_/_/_/_/_/ [EMAIL PROTECTED] http://www.argo.es/~jcea/ _/_/_/_/ _/_/_/_/ _/_/ jabber / xmpp:[EMAIL PROTECTED] _/_/_/_/ _/_/_/_/_/ _/_/ _/_/_/_/ _/_/ _/_/ Things are not so easy _/_/ _/_/_/_/ _/_/_/_/ _/_/ My name is Dump, Core Dump _/_/_/_/_/_/ _/_/ _/_/ El amor es poner tu felicidad en la felicidad de otro - Leibniz -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.2.2 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iQCVAwUBRMehLplgi5GaxT1NAQJKTwP/UmC3RIsOu+CygedrepaDqAXRyL4AzTpZ qpLR1XdS9Q01EuYx+SoPeFD//3QOUPAS+5gU1i7ZPBoLHx2ErkvcaxICYtecvoMD aIJW2vGvApEipLPLU6zlDjjhM3LlKb96x03ElpRvOmdM1FL0IV1RqGSzVJ+e2Uo7 fPKfpzhZESI= =5NBk -END PGP SIGNATURE- ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
On Wed, Jul 26, 2006 at 08:38:16AM -0600, Neil Perrin wrote: GX620 on my desk at work and I run snv_40 on the Latitude D610 that I carry with me. In both cases the machines only have one disk, so I need to split it up for UFS for the OS and ZFS for my data. How do I turn on write cache for partial disks? -brian You can't enable write caching for just part of the disk. We don't enable it for slices because UFS (and other file systems) doesn't do write cache flushing and so could get corruption on power failure. I suppose if you know the disk only contains zfs slices then write caching could be manually enabled using format -e - cache - write_cache - enable Eh, I guess I'll skip it then. ;) -brian ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
Robert Milkowski wrote: Hello George, Wednesday, July 26, 2006, 7:27:04 AM, you wrote: GW Additionally, I've just putback the latest feature set and bugfixes GW which will be part of s10u3_03. There were some additional performance GW fixes which may really benefit plus it will provide hot spares support. GW Once this build is available I would highly recommend that you guys take GW it for a spin (works great on Thumper). I guess patches will be released first (or later). Can you give actual BUG IDs especially those related to performance? For U3, these are the performance fixes: 6424554 full block re-writes need not read data in 6440499 zil should avoid txg_wait_synced() and use dmu_sync() to issue parallelIOs when fsyncing 6447377 ZFS prefetch is inconsistant 6373978 want to take lots of snapshots quickly ('zfs snapshot -r') you could perhaps include these two as well: 4034947 anon_swap_adjust() should call kmem_reap() if availrmem is low. 6416482 filebench oltp workload hangs in zfs There won't be anything in U3 that isn't already in nevada... happy performing, eric ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] How to best layout our filesystems
Our application Canary has approx 750 clients uploading to the server every 10 mins, that's approx 108,000 gzip tarballs per day writing to the /upload directory. The parser untars the tarball which consists of 8 ascii files into the /archives directory. /app is our application and tools (apache, tomcat, etc) directory. We also have batch jobs that run throughout the day, I would say we read 2 to 3 times more than we write. Since we have an alternate server, downtime or data lost is somewhat acceptable. How can we best layout our filesystems to get the most performance. directory info -- /app - 30G /upload - 10G /archives - 35G HW info --- System Configuration: Sun Microsystems sun4v Sun Fire T200 System clock frequency: 200 MHz Memory size: 8184 Megabytes CPU: 32 x 1000 MHz SUNW,UltraSPARC-T1 Disks: 4x68G Vendor: FUJITSU Product: MAV2073RCSUN72G Revision: 0301 We plan on using 1 disk for OS, the others 3 disks for canary filesystems, /app, /upload, and /archives. Should I create 3 pools, ie zpool create canary_app c1t1d0 zpool create canary_upload c1t2d0 zpool create canary_archives c1t3d0 --OR-- create 1 pool using dynamic stripe, ie zpool create canary c1t1d0 c1t2d0 c1t3d0 --OR-- create a single-parity raid-z pool, ie. zpool create canary raidz c1t1d0 c1t2d0 c1t3d0 Which option gives us the best performance? If there's another method that's not mentioned, please let me know. Also, should be enable read/write cache on the OS as well as the other disks? Is build 9 in S10U2 RR?? If not, please point me to the OS image on nana.eng. Thanks, karen -- NOTICE: This email message is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
Given the amount of I/O wouldn't it make sense to get more drives involved or something that has cache on the front end or both? If you're really pushing the amount of I/O you're alluding too - Hard to tell without all the details - then you're probably going to hit a limitation on the drive IOPS. (Even with the cache on.) Karen Chau wrote: Our application Canary has approx 750 clients uploading to the server every 10 mins, that's approx 108,000 gzip tarballs per day writing to the /upload directory. The parser untars the tarball which consists of 8 ascii files into the /archives directory. /app is our application and tools (apache, tomcat, etc) directory. We also have batch jobs that run throughout the day, I would say we read 2 to 3 times more than we write. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] How to best layout our filesystems
Hi Torrey; we are the cobblers kids. We borrowed this T2000 from Niagara engineering after we did some performance tests for them. I am trying to get a thumper to run this data set. This could take up to 3-4 months. Today we are watching 750 Sun Ray servers and 30,000 employees. Lets see 1) Solaris 10 2) ZFS version 6 3) T2000 32x1000 with the poorer performing drives that come with the Niagara We need a short term solution. Niagara engineering has given us two more of the internal drives so we can max out the Niagara with 4 internal drives. This is the hardware we need to use this week. . When we get a new box, more drives we will reconfigure. Our graphs have 5000 data points per month, 140 data points per day. we can stand to lose data. my suggestion was one drive as the system volume and the remaining three drives as one big zfs volume , probably raidz. thanks sean Torrey McMahon wrote: Given the amount of I/O wouldn't it make sense to get more drives involved or something that has cache on the front end or both? If you're really pushing the amount of I/O you're alluding too - Hard to tell without all the details - then you're probably going to hit a limitation on the drive IOPS. (Even with the cache on.) Karen Chau wrote: Our application Canary has approx 750 clients uploading to the server every 10 mins, that's approx 108,000 gzip tarballs per day writing to the /upload directory. The parser untars the tarball which consists of 8 ascii files into the /archives directory. /app is our application and tools (apache, tomcat, etc) directory. We also have batch jobs that run throughout the day, I would say we read 2 to 3 times more than we write. -- Sean Meighan Mgr ITSM Engineering Sun Microsystems, Inc. US Phone x32329 / +1 408 850-9537 Mobile 303-520-2024 Fax 408 850-9537 Email [EMAIL PROTECTED] NOTICE: This email message is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message. ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss