Re: [Libguestfs] [nbdkit PATCH v2] Introduce cacheextents filter

On 5/15/19 5:39 PM, Martin Kletzander wrote: > This filter caches the last result of the extents() call and offers a nice > speed-up for clients that only support req_on=1 in combination with plugins like > vddk, which has no overhead for returning information for multiple extents in > one call, but that call is very time-consuming. > > Quick test showed that on a fast connection and a sparsely allocated 16G disk > with a OS installed `qemu-img map` runs 16s instead of 33s (out of which it > takes 5s to the first extents request). For 100G disk with no data on it, that > is one hole extent spanning the whole disk (where there is no space for > improvement) this does not add any noticeable overhead. > > Signed-off-by: Martin Kletzander <mkletzan(a)redhat.com&gt; > --- > v2: > - Errors are set in _add and _fill functions > - Return values are checked for only -1 > - Added a test > - Indentation fixed > - Fixed access before lock > > + > +/* This lock protects the global state. */ > +static pthread_mutex_t lock = PTHREAD_MUTEX_INITIALIZER; > + > +/* The real size of the underlying plugin. */ > +static uint64_t size; > + We recently just fixed the truncate filter to NOT cache this globally (as doing so is too risky); instead, it needs to be cached per-connection. See commit b3a43ccd.

-- Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3226 Virtualization: qemu.org | libvirt.org