From: Boaz Harrosh <boaz@plexistor.com> To: Dave Chinner <david@fromorbit.com>, Boaz Harrosh <boaz@plexistor.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>, Andrew Morton <akpm@linux-foundation.org>, "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, Jan Kara <jack@suse.cz>, Hugh Dickins <hughd@google.com>, Mel Gorman <mgorman@suse.de>, linux-mm@kvack.org, linux-nvdimm <linux-nvdimm@ml01.01.org>, linux-fsdevel <linux-fsdevel@vger.kernel.org>, Eryu Guan <eguan@redhat.com> Subject: Re: [PATCH 3/3] RFC: dax: dax_prepare_freeze Date: Wed, 25 Mar 2015 12:40:44 +0200 [thread overview] Message-ID: <551290AC.7080402@plexistor.com> (raw) In-Reply-To: <20150325094135.GI31342@dastard> On 03/25/2015 11:41 AM, Dave Chinner wrote: > On Wed, Mar 25, 2015 at 10:31:22AM +0200, Boaz Harrosh wrote: >> On 03/25/2015 04:26 AM, Dave Chinner wrote: <> >> sync and fsync should and will work correctly, but this does not >> solve our problem. because what turns pages to read-only is the >> writeback. And we do not have this in dax. Therefore we need to >> do this here as a special case. > > We can still use exactly the same dirty tracking as we use for data > writeback. The difference is that we don't need to go through all > teh page writeback; we can just flush the CPU caches and mark all > the mappings clean, then clear the I_DIRTY_PAGES flag and move on to > inode writeback.... > I see what you mean. the sb wide sync will not step into mmaped inodes and fsync them. If we go my way and write NT (None Temporal) style in Kernel. NT instructions exist since xeon and all the Intel iX core CPUs have them. In tests we conducted doing xeon NT-writes vs regular-writes-and-cl_flush at .fsync showed minimum of 20% improvement. That is on very large IOs. On 4k IOs it was even better. It looks like you have a much better picture in your mind how to fit this properly at the inode-dirty picture. Can you attempt a rough draft? If we are going the NT way. Then we can only I_DIRTY_ track the mmaped inodes. For me this is really scary because I do not want to trigger any writeback threads. If you could please draw me an outline (or write something up ;-)) it would be great. > Cheers, > Dave. Thanks Boaz
WARNING: multiple messages have this Message-ID (diff)
From: Boaz Harrosh <boaz@plexistor.com> To: Dave Chinner <david@fromorbit.com>, Boaz Harrosh <boaz@plexistor.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>, Andrew Morton <akpm@linux-foundation.org>, "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, Jan Kara <jack@suse.cz>, Hugh Dickins <hughd@google.com>, Mel Gorman <mgorman@suse.de>, linux-mm@kvack.org, linux-nvdimm <linux-nvdimm@ml01.01.org>, linux-fsdevel <linux-fsdevel@vger.kernel.org>, Eryu Guan <eguan@redhat.com> Subject: Re: [PATCH 3/3] RFC: dax: dax_prepare_freeze Date: Wed, 25 Mar 2015 12:40:44 +0200 [thread overview] Message-ID: <551290AC.7080402@plexistor.com> (raw) In-Reply-To: <20150325094135.GI31342@dastard> On 03/25/2015 11:41 AM, Dave Chinner wrote: > On Wed, Mar 25, 2015 at 10:31:22AM +0200, Boaz Harrosh wrote: >> On 03/25/2015 04:26 AM, Dave Chinner wrote: <> >> sync and fsync should and will work correctly, but this does not >> solve our problem. because what turns pages to read-only is the >> writeback. And we do not have this in dax. Therefore we need to >> do this here as a special case. > > We can still use exactly the same dirty tracking as we use for data > writeback. The difference is that we don't need to go through all > teh page writeback; we can just flush the CPU caches and mark all > the mappings clean, then clear the I_DIRTY_PAGES flag and move on to > inode writeback.... > I see what you mean. the sb wide sync will not step into mmaped inodes and fsync them. If we go my way and write NT (None Temporal) style in Kernel. NT instructions exist since xeon and all the Intel iX core CPUs have them. In tests we conducted doing xeon NT-writes vs regular-writes-and-cl_flush at .fsync showed minimum of 20% improvement. That is on very large IOs. On 4k IOs it was even better. It looks like you have a much better picture in your mind how to fit this properly at the inode-dirty picture. Can you attempt a rough draft? If we are going the NT way. Then we can only I_DIRTY_ track the mmaped inodes. For me this is really scary because I do not want to trigger any writeback threads. If you could please draw me an outline (or write something up ;-)) it would be great. > Cheers, > Dave. Thanks Boaz -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-03-25 10:40 UTC|newest] Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-03-23 12:47 [PATCH 0/3 v3] dax: Fix mmap-write not updating c/mtime Boaz Harrosh 2015-03-23 12:47 ` Boaz Harrosh 2015-03-23 12:49 ` [PATCH 1/3] mm: New pfn_mkwrite same as page_mkwrite for VM_PFNMAP Boaz Harrosh 2015-03-23 22:49 ` Andrew Morton 2015-03-23 22:49 ` Andrew Morton 2015-03-23 12:52 ` [PATCH 2/3] dax: use pfn_mkwrite to update c/mtime + freeze protection Boaz Harrosh 2015-03-23 12:54 ` [PATCH 3/3] RFC: dax: dax_prepare_freeze Boaz Harrosh 2015-03-23 22:40 ` Dave Chinner 2015-03-23 22:40 ` Dave Chinner 2015-03-24 6:14 ` Boaz Harrosh 2015-03-24 6:14 ` Boaz Harrosh 2015-03-25 2:22 ` Dave Chinner 2015-03-25 2:22 ` Dave Chinner 2015-03-25 8:10 ` Boaz Harrosh 2015-03-25 9:29 ` Dave Chinner 2015-03-25 9:29 ` Dave Chinner 2015-03-25 10:19 ` Boaz Harrosh 2015-03-25 10:19 ` Boaz Harrosh 2015-03-25 20:00 ` Dave Chinner 2015-03-25 20:00 ` Dave Chinner 2015-03-26 8:02 ` Boaz Harrosh 2015-03-26 20:58 ` Dave Chinner 2015-03-26 20:58 ` Dave Chinner 2015-03-24 12:37 ` Boaz Harrosh 2015-03-24 12:37 ` Boaz Harrosh 2015-03-25 2:26 ` Dave Chinner 2015-03-25 2:26 ` Dave Chinner 2015-03-25 8:31 ` Boaz Harrosh 2015-03-25 8:31 ` Boaz Harrosh 2015-03-25 9:41 ` Dave Chinner 2015-03-25 9:41 ` Dave Chinner 2015-03-25 10:40 ` Boaz Harrosh [this message] 2015-03-25 10:40 ` Boaz Harrosh 2015-03-25 20:05 ` Dave Chinner 2015-03-25 20:05 ` Dave Chinner 2015-03-23 12:56 ` [PATCH v4] xfstest: generic/080 test that mmap-write updates c/mtime Boaz Harrosh
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=551290AC.7080402@plexistor.com \ --to=boaz@plexistor.com \ --cc=akpm@linux-foundation.org \ --cc=david@fromorbit.com \ --cc=eguan@redhat.com \ --cc=hughd@google.com \ --cc=jack@suse.cz \ --cc=kirill.shutemov@linux.intel.com \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=linux-nvdimm@ml01.01.org \ --cc=matthew.r.wilcox@intel.com \ --cc=mgorman@suse.de \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.