From: Trond Myklebust Subject: Re: [PATCH] [RESEND] Improve idmap parallelism Date: Mon, 12 Mar 2007 15:08:55 -0400 Message-ID: <1173726535.6436.58.camel@heimdal.trondhjem.org> References: <1173723596.19257.12.camel@dyn9047022153> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: NFS List To: Frank Filz Return-path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.91] helo=mail.sourceforge.net) by sc8-sf-list2-new.sourceforge.net with esmtp (Exim 4.43) id 1HQptL-0004fe-6C for nfs@lists.sourceforge.net; Mon, 12 Mar 2007 12:09:11 -0700 Received: from pat.uio.no ([129.240.10.15] ident=[U2FsdGVkX1/2E0zKoONRTU51z3lgGfthxReuejvjcIY=]) by mail.sourceforge.net with esmtp (Exim 4.44) id 1HQptK-00007L-Dw for nfs@lists.sourceforge.net; Mon, 12 Mar 2007 12:09:09 -0700 In-Reply-To: <1173723596.19257.12.camel@dyn9047022153> List-Id: "Discussion of NFS under Linux development, interoperability, and testing." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: nfs-bounces@lists.sourceforge.net Errors-To: nfs-bounces@lists.sourceforge.net On Mon, 2007-03-12 at 11:19 -0700, Frank Filz wrote: > Resend: I sent this awhile ago, but it may have been missed with the excitement of Connectathon, weddings, and honeymoons. I've verified it compiles against 2.6.21 (I originally tested it on 2.6.20). You forgot the Linux Storage and Filesystem Workshop and FAST. It has been an exciting life in the past 2 months. :-) At first glance it looks OK. I'll take it for a spin... Cheers, Trond > Frank > > This patch improves idmap parallelism by reducing the serialization of > idmap lookups. Currently, each client can only process one idmap lookup > at a time, potentially delaying other lookups that might be satisfied by > the in kernel cache while waiting for a user space lookup. > > The existing code uses two mutexes, but one of them is held the entire > time of the lookup. > > The biggest change this patch makes is to re-order lock use so that one > lock serializes multiple user space lookups (for the same nfs_client). > This lock is only held when the kernel cache lookup fails and a user > space lookup must occur. The other lock is used to protect the in kernel > cache (a pair of hash tables). This lock is only held when the internal > cache is being accessed. Further, since most accesses are lookups, this > second lock is changed to a read-write lock. > > After acquiring the mutex, a second cache lookup is made just in case a > user space lookup had been in progress for this id. > > I tested this using fsstress on an SMP machine. While testing, I put in > some metering code which showed as many as 1000 cache lookups satisfied > while an upcall was in progress, and noted occasional lookups for the id > that an upcall was in progress for. > > This patch was modified from an initial patch by Usha Ketineni. > > Signed-off-by: Frank Filz > > diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c > index 9d4a6b2..2877a02 100644 > --- a/fs/nfs/idmap.c > +++ b/fs/nfs/idmap.c > @@ -86,9 +86,9 @@ struct idmap_hashtable { > struct idmap { > struct dentry *idmap_dentry; > wait_queue_head_t idmap_wq; > - struct idmap_msg idmap_im; > + struct idmap_msg idmap_im; /* protected by mutex */ > struct mutex idmap_lock; /* Serializes upcalls */ > - struct mutex idmap_im_lock; /* Protects the hashtable */ > + rwlock_t idmap_im_lock; /* Protects the hashtable */ > struct idmap_hashtable idmap_user_hash; > struct idmap_hashtable idmap_group_hash; > }; > @@ -127,7 +127,7 @@ nfs_idmap_new(struct nfs_client *clp) > } > > mutex_init(&idmap->idmap_lock); > - mutex_init(&idmap->idmap_im_lock); > + rwlock_init(&idmap->idmap_im_lock); > init_waitqueue_head(&idmap->idmap_wq); > idmap->idmap_user_hash.h_type = IDMAP_TYPE_USER; > idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP; > @@ -243,14 +243,28 @@ nfs_idmap_id(struct idmap *idmap, struct > idmap_hashtable *h, > if (namelen >= IDMAP_NAMESZ) > return -EINVAL; > > + read_lock(&idmap->idmap_im_lock); > + he = idmap_lookup_name(h, name, namelen); > + if (he != NULL) { > + *id = he->ih_id; > + read_unlock(&idmap->idmap_im_lock); > + return 0; > + } > + read_unlock(&idmap->idmap_im_lock); > + > mutex_lock(&idmap->idmap_lock); > - mutex_lock(&idmap->idmap_im_lock); > > + /* Attempt lookup again in case we blocked > + * because another attempt on this name > + * was in progress. > + */ > + read_lock(&idmap->idmap_im_lock); > he = idmap_lookup_name(h, name, namelen); > if (he != NULL) { > *id = he->ih_id; > - ret = 0; > - goto out; > + read_unlock(&idmap->idmap_im_lock); > + mutex_unlock(&idmap->idmap_lock); > + return 0; > } > > memset(im, 0, sizeof(*im)); > @@ -270,11 +284,10 @@ nfs_idmap_id(struct idmap *idmap, struct > idmap_hashtable *h, > } > > set_current_state(TASK_UNINTERRUPTIBLE); > - mutex_unlock(&idmap->idmap_im_lock); > + read_unlock(&idmap->idmap_im_lock); > schedule(); > current->state = TASK_RUNNING; > remove_wait_queue(&idmap->idmap_wq, &wq); > - mutex_lock(&idmap->idmap_im_lock); > > if (im->im_status & IDMAP_STATUS_SUCCESS) { > *id = im->im_id; > @@ -283,7 +296,6 @@ nfs_idmap_id(struct idmap *idmap, struct > idmap_hashtable *h, > > out: > memset(im, 0, sizeof(*im)); > - mutex_unlock(&idmap->idmap_im_lock); > mutex_unlock(&idmap->idmap_lock); > return (ret); > } > @@ -304,14 +316,30 @@ nfs_idmap_name(struct idmap *idmap, struct > idmap_hashtable *h, > > im = &idmap->idmap_im; > > + read_lock(&idmap->idmap_im_lock); > + he = idmap_lookup_id(h, id); > + if (he != 0) { > + memcpy(name, he->ih_name, he->ih_namelen); > + ret = he->ih_namelen; > + read_unlock(&idmap->idmap_im_lock); > + return ret; > + } > + read_unlock(&idmap->idmap_im_lock); > + > mutex_lock(&idmap->idmap_lock); > - mutex_lock(&idmap->idmap_im_lock); > > + /* Attempt lookup again in case we blocked > + * because another attempt on this id > + * was in progress. > + */ > + read_lock(&idmap->idmap_im_lock); > he = idmap_lookup_id(h, id); > if (he != 0) { > memcpy(name, he->ih_name, he->ih_namelen); > ret = he->ih_namelen; > - goto out; > + read_unlock(&idmap->idmap_im_lock); > + mutex_unlock(&idmap->idmap_lock); > + return ret; > } > > memset(im, 0, sizeof(*im)); > @@ -331,11 +359,10 @@ nfs_idmap_name(struct idmap *idmap, struct > idmap_hashtable *h, > } > > set_current_state(TASK_UNINTERRUPTIBLE); > - mutex_unlock(&idmap->idmap_im_lock); > + read_unlock(&idmap->idmap_im_lock); > schedule(); > current->state = TASK_RUNNING; > remove_wait_queue(&idmap->idmap_wq, &wq); > - mutex_lock(&idmap->idmap_im_lock); > > if (im->im_status & IDMAP_STATUS_SUCCESS) { > if ((len = strnlen(im->im_name, IDMAP_NAMESZ)) == 0) > @@ -346,7 +373,6 @@ nfs_idmap_name(struct idmap *idmap, struct > idmap_hashtable *h, > > out: > memset(im, 0, sizeof(*im)); > - mutex_unlock(&idmap->idmap_im_lock); > mutex_unlock(&idmap->idmap_lock); > return ret; > } > @@ -391,7 +417,7 @@ idmap_pipe_downcall(struct file *filp, const char > __user *src, size_t mlen) > if (copy_from_user(&im_in, src, mlen) != 0) > return (-EFAULT); > > - mutex_lock(&idmap->idmap_im_lock); > + write_lock(&idmap->idmap_im_lock); > > ret = mlen; > im->im_status = im_in.im_status; > @@ -451,7 +477,7 @@ idmap_pipe_downcall(struct file *filp, const char > __user *src, size_t mlen) > idmap_update_entry(he, im_in.im_name, namelen_in, im_in.im_id); > ret = mlen; > out: > - mutex_unlock(&idmap->idmap_im_lock); > + write_unlock(&idmap->idmap_im_lock); > return ret; > } > > @@ -463,10 +489,10 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) > > if (msg->errno >= 0) > return; > - mutex_lock(&idmap->idmap_im_lock); > + write_lock(&idmap->idmap_im_lock); > im->im_status = IDMAP_STATUS_LOOKUPFAIL; > wake_up(&idmap->idmap_wq); > - mutex_unlock(&idmap->idmap_im_lock); > + write_unlock(&idmap->idmap_im_lock); > } > > /* > > > > ------------------------------------------------------------------------- > Take Surveys. Earn Cash. Influence the Future of IT > Join SourceForge.net's Techsay panel and you'll get the chance to share your > opinions on IT & business topics through brief surveys-and earn cash > http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV > _______________________________________________ > NFS maillist - NFS@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/nfs ------------------------------------------------------------------------- Take Surveys. Earn Cash. Influence the Future of IT Join SourceForge.net's Techsay panel and you'll get the chance to share your opinions on IT & business topics through brief surveys-and earn cash http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs