From: Steve Dickson <SteveD@redhat.com> To: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: nfs@lists.sourceforge.net, linux-fsdevel@vger.kernel.org Subject: Re: [PATCH][RFC] NFS: Improving the access cache Date: Wed, 26 Apr 2006 11:03:17 -0400 [thread overview] Message-ID: <444F8BB5.2000700@RedHat.com> (raw) In-Reply-To: <1146056601.8177.34.camel@lade.trondhjem.org> Trond Myklebust wrote: > > > Instead of having the field 'id', why don't you let the nfs_inode keep a > small (hashed?) list of all the nfs_access_entry objects that refer to > it? That would speed up searches for cached entries. Actually I did look into having a pointer in the nfs_inode... but what do you do when the second hashed list is needed. Meaning P2(uid2) comes along and hashes to a different que. I guess I thought it was a bit messy to keep overwriting the point in the nfs_inode so I just kept everything in the hash table... > I agree with Neil's assessment that we need a bound on the size of the > cache. In fact, enforcing a bound is pretty much the raison d'être for a > global table (by which I mean that if we don't need a bound, then we > might as well cache everything in the nfs_inode). Ok.. > How about rather changing that hash table into an LRU list, then adding > a shrinker callback (using set_shrinker()) to allow the VM to free up > entries when memory pressure dictates that it must? Sounds interesting.. Just to be clear, by LRU list you mean use hlist correct? steved. - To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
WARNING: multiple messages have this Message-ID (diff)
From: Steve Dickson <SteveD@redhat.com> To: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: nfs@lists.sourceforge.net, linux-fsdevel@vger.kernel.org Subject: Re: [PATCH][RFC] NFS: Improving the access cache Date: Wed, 26 Apr 2006 11:03:17 -0400 [thread overview] Message-ID: <444F8BB5.2000700@RedHat.com> (raw) In-Reply-To: <1146056601.8177.34.camel@lade.trondhjem.org> Trond Myklebust wrote: >=20 >=20 > Instead of having the field 'id', why don't you let the nfs_inode kee= p a > small (hashed?) list of all the nfs_access_entry objects that refer t= o > it? That would speed up searches for cached entries. Actually I did look into having a pointer in the nfs_inode... but what do you do when the second hashed list is needed. Meaning P2(uid2) comes along and hashes to a different que. I guess I thought it was a bit messy to keep overwriting the point in the nfs_inode so I just kept everything in the hash table... > I agree with Neil's assessment that we need a bound on the size of th= e > cache. In fact, enforcing a bound is pretty much the raison d'=C3=AAt= re for a > global table (by which I mean that if we don't need a bound, then we > might as well cache everything in the nfs_inode). Ok.. > How about rather changing that hash table into an LRU list, then addi= ng > a shrinker callback (using set_shrinker()) to allow the VM to free up > entries when memory pressure dictates that it must? Sounds interesting.. Just to be clear, by LRU list you mean use hlist correct? steved. - To unsubscribe from this list: send the line "unsubscribe linux-fsdevel= " in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2006-04-26 15:03 UTC|newest] Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top 2006-04-26 1:14 [PATCH][RFC] NFS: Improving the access cache Steve Dickson 2006-04-26 1:31 ` Matthew Wilcox 2006-04-26 4:55 ` Neil Brown 2006-04-26 14:51 ` Steve Dickson 2006-04-26 22:32 ` Neil Brown 2006-05-02 9:49 ` Steve Dickson 2006-05-02 13:51 ` [NFS] " Peter Staubach 2006-05-02 14:38 ` Steve Dickson 2006-05-02 14:51 ` Peter Staubach 2006-05-02 15:26 ` [NFS] " Ian Kent 2006-05-03 4:42 ` Chuck Lever 2006-05-05 14:07 ` Steve Dickson 2006-05-05 14:53 ` Peter Staubach 2006-05-05 14:59 ` Peter Staubach 2006-05-06 14:35 ` [NFS] " Steve Dickson 2006-05-08 14:07 ` Peter Staubach 2006-05-08 17:09 ` Trond Myklebust 2006-05-08 17:20 ` Peter Staubach 2006-05-08 17:37 ` Steve Dickson 2006-05-08 2:44 ` [NFS] " Neil Brown 2006-05-08 3:23 ` Chuck Lever 2006-05-08 3:28 ` Neil Brown 2006-04-26 13:03 ` Trond Myklebust 2006-04-26 13:03 ` Trond Myklebust 2006-04-26 13:14 ` Peter Staubach 2006-04-26 13:14 ` Peter Staubach 2006-04-26 14:01 ` Trond Myklebust 2006-04-26 14:01 ` Trond Myklebust 2006-04-26 14:15 ` Peter Staubach 2006-04-26 14:15 ` Peter Staubach 2006-04-26 15:44 ` Trond Myklebust 2006-04-26 17:01 ` Peter Staubach 2006-04-26 15:03 ` Steve Dickson [this message] 2006-04-26 15:03 ` Steve Dickson 2006-04-26 13:17 ` [NFS] " Chuck Lever 2006-04-26 14:19 ` Steve Dickson
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=444F8BB5.2000700@RedHat.com \ --to=steved@redhat.com \ --cc=linux-fsdevel@vger.kernel.org \ --cc=nfs@lists.sourceforge.net \ --cc=trond.myklebust@fys.uio.no \ /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.