Hi, I am going to merge latest batch of the nullfs improvements into stable/9. This will bring up significant performance enchancements due to use of the shared locks for lookups if the lower layer supports it, much better caching on the nullfs layer, and proper handling of the text segments on the nullfs. Also, it should improve the error recovery and some corner cases with locking. Unfortunately, the merge would break KBI for VFS, since it needs 5 new VOP slots, and only three spares are left. We already are very liberal with the VFS KBI, so I do not feel that the merge is not acceptable, due to the benefits it brings to the nullfs. The merge is available at http://people.freebsd.org/~kib/misc/nullfs_9.1.patch -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 834 bytes Desc: not available URL: <http://lists.freebsd.org/pipermail/freebsd-stable/attachments/20121208/8192b3af/attachment.sig>
On Sat, Dec 08, 2012 at 03:01:09AM +0200, Konstantin Belousov wrote:> Hi, > I am going to merge latest batch of the nullfs improvements into > stable/9. This will bring up significant performance enchancements due > to use of the shared locks for lookups if the lower layer supports it, > much better caching on the nullfs layer, and proper handling of the text > segments on the nullfs. Also, it should improve the error recovery and > some corner cases with locking. > > Unfortunately, the merge would break KBI for VFS, since it needs 5 new > VOP slots, and only three spares are left. We already are very liberal > with the VFS KBI, so I do not feel that the merge is not acceptable, due > to the benefits it brings to the nullfs. > > The merge is available at > http://people.freebsd.org/~kib/misc/nullfs_9.1.patchSorry I haven't checked the latest zfs related MFC, but for some time there was an issue with nullfs improvements and zfs, will this mfc be synchronize with the mfc of the related zfs fixes? regards, Bapt -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 196 bytes Desc: not available URL: <http://lists.freebsd.org/pipermail/freebsd-stable/attachments/20121208/fffac1c8/attachment.sig>
By combining vop_settext/unset/get into a single call with parameters "op" and &out (for gettext) you can reduce 3 new vops into a single vop. The same can be done for write count vops. This will allow you to preserve kbi by reducing the vop additions to 2. Sent from my iPhone On Dec 7, 2012, at 5:01 PM, Konstantin Belousov <kostikbel at gmail.com> wrote:> Hi, > I am going to merge latest batch of the nullfs improvements into > stable/9. This will bring up significant performance enchancements due > to use of the shared locks for lookups if the lower layer supports it, > much better caching on the nullfs layer, and proper handling of the text > segments on the nullfs. Also, it should improve the error recovery and > some corner cases with locking. > > Unfortunately, the merge would break KBI for VFS, since it needs 5 new > VOP slots, and only three spares are left. We already are very liberal > with the VFS KBI, so I do not feel that the merge is not acceptable, due > to the benefits it brings to the nullfs. > > The merge is available at > http://people.freebsd.org/~kib/misc/nullfs_9.1.patch
> -----Original Message----- > From: owner-freebsd-stable at freebsd.org > [mailto:owner-freebsd-stable at freebsd.org] On Behalf Of > Konstantin Belousov > Sent: Saturday, 8 December 2012 12:01 PM > To: fs at freebsd.org > Cc: stable at freebsd.org > Subject: nullfs changes MFC > > Hi, > I am going to merge latest batch of the nullfs improvements > into stable/9. This will bring up significant performance > enchancements due to use of the shared locks for lookups if > the lower layer supports it, much better caching on the > nullfs layer, and proper handling of the text segments on the > nullfs. Also, it should improve the error recovery and some > corner cases with locking. > > Unfortunately, the merge would break KBI for VFS, since it > needs 5 new VOP slots, and only three spares are left. We > already are very liberal with the VFS KBI, so I do not feel > that the merge is not acceptable, due to the benefits it > brings to the nullfs. > > The merge is available at > http://people.freebsd.org/~kib/misc/nullfs_9.1.patch >Konstantin, Thank-you for these improvements. I've been running this patchset on test and build servers for a few weeks and the systems remained stable and reliable. On some fairly complex jail and nullfs environments there has been an improvement in the order of 3 to 8% for large sequential writes. Regards, Dewayne PS I've reversed out the patches now they've migrated to RELENG_9