search for: lock1

...%1, i32 0, i32 0 %call = call ptx_device i32 @_Z12__iAtomicCASPiii(i32* %lock, i32 1, i32 0) br label %while.cond while.cond: ; preds = %while.body, %entry %2 = load i32** %callback.addr, align 8 %3 = bitcast i32* %2 to %struct.kernelgen_callback_t* %lock1 = getelementptr inbounds %struct.kernelgen_callback_t* %3, i32 0, i32 0 %call2 = call ptx_device i32 @_Z12__iAtomicCASPiii(i32* %lock1, i32 1, i32 1) %tobool = icmp ne i32 %call2, 0 %lnot = xor i1 %tobool, true br i1 %lnot, label %while.body, label %while.end while.body:...

On Wed, Apr 01, 2015 at 12:20:30PM -0400, Waiman Long wrote: > After more careful reading, I think the assumption that the presence of an > unused bucket means there is no match is not true. Consider the scenario: > > 1. cpu 0 puts lock1 into hb[0] > 2. cpu 1 puts lock2 into hb[1] > 3. cpu 2 clears hb[0] > 4. cpu 3 looks for lock2 and doesn't find it Hmm, yes. The only way I can see that being true is if we assume entries are never taken out again. The wikipedia page could use some clarification here, this is not cle...

On Wed, Apr 01, 2015 at 12:20:30PM -0400, Waiman Long wrote: > After more careful reading, I think the assumption that the presence of an > unused bucket means there is no match is not true. Consider the scenario: > > 1. cpu 0 puts lock1 into hb[0] > 2. cpu 1 puts lock2 into hb[1] > 3. cpu 2 clears hb[0] > 4. cpu 3 looks for lock2 and doesn't find it Hmm, yes. The only way I can see that being true is if we assume entries are never taken out again. The wikipedia page could use some clarification here, this is not cle...

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 If I use the smbtorture available at ftp://ftp.samba.org/pub/tridge/dbench, I get the following options: tests are: FDPASS LOCK1 LOCK2 LOCK3 UNLINK BROWSE ATTR TRANS2 MAXFID TORTURE RANDOMIPC NBW95 NBWNT default test is ALL But the smbtorture compiled with Gentoo's 3.0.2a gives me tests are: FDPASS LOCK1 LOCK2 LOCK3 LOCK4 LOCK5 LOCK6 LOCK7 UNLINK BROWSE ATTR TRANS2 MAXFID TORTURE RANDOMIPC NEGNOWAIT NBENCH OPLOCK1 OPLO...

...the second call overwrites the value saved by the first call. Indeed, the second call does not need to save the interrupt state, so it is changed to a simple spin_lock. The semantic match that finds this problem is as follows: (http://www.emn.fr/x-info/coccinelle/) // <smpl> @@ expression lock1,lock2; expression flags; @@ *spin_lock_irqsave(lock1,flags) ... when != flags *spin_lock_irqsave(lock2,flags) // </smpl> Signed-off-by: Julia Lawall <julia@diku.dk> --- fs/btrfs/async-thread.c | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs...

...l ptx_device i32 @_Z12__iAtomicCASPiii(i32* %lock, i32 1, i32 0) > br label %while.cond > > while.cond: ; preds = %while.body, %entry > %2 = load i32** %callback.addr, align 8 > %3 = bitcast i32* %2 to %struct.kernelgen_callback_t* > %lock1 = getelementptr inbounds %struct.kernelgen_callback_t* %3, i32 0, > i32 0 > %call2 = call ptx_device i32 @_Z12__iAtomicCASPiii(i32* %lock1, i32 1, i32 1) > %tobool = icmp ne i32 %call2, 0 > %lnot = xor i1 %tobool, true > br i1 %lnot, label %while.body, label %while.end >...

I have a data frame (morgan) of hourly river flow, river levels and wind direction and speed thus: Time hour lev.morgan lev.lock2 lev.lock1 flow direction velocity 1 2009-07-06 15:00:00 15 3.266 3.274 3.240 1710.6 180.282 4.352 2 2009-07-06 16:00:00 16 3.268 3.272 3.240 1441.8 192.338 5.496 3 2009-07-06 17:00:00 17 3.268 3.271 3.240 1300.1 202.294 2.695 4 2009-07-06 18:...

...ck); > + > + /* > + * If we hit an unused bucket, there is no match. > + */ > + if (!l) > + goto done; After more careful reading, I think the assumption that the presence of an unused bucket means there is no match is not true. Consider the scenario: 1. cpu 0 puts lock1 into hb[0] 2. cpu 1 puts lock2 into hb[1] 3. cpu 2 clears hb[0] 4. cpu 3 looks for lock2 and doesn't find it I was thinking about putting some USED flag in the buckets, but then we will eventually fill them all up as used. If we put the entries into a hashed linked list, we have to deal with...

...+0200, Peter Zijlstra wrote: > On Wed, Apr 01, 2015 at 12:20:30PM -0400, Waiman Long wrote: > > After more careful reading, I think the assumption that the presence of an > > unused bucket means there is no match is not true. Consider the scenario: > > > > 1. cpu 0 puts lock1 into hb[0] > > 2. cpu 1 puts lock2 into hb[1] > > 3. cpu 2 clears hb[0] > > 4. cpu 3 looks for lock2 and doesn't find it > > Hmm, yes. The only way I can see that being true is if we assume entries > are never taken out again. > > The wikipedia page could use...

On Thu, Mar 19, 2015 at 11:12:42AM +0100, Peter Zijlstra wrote: > So I was now thinking of hashing the lock pointer; let me go and quickly > put something together. A little something like so; ideally we'd allocate the hashtable since NR_CPUS is kinda bloated, but it shows the idea I think. And while this has loops in (the rehashing thing) their fwd progress does not depend on other

On Thu, Mar 19, 2015 at 11:12:42AM +0100, Peter Zijlstra wrote: > So I was now thinking of hashing the lock pointer; let me go and quickly > put something together. A little something like so; ideally we'd allocate the hashtable since NR_CPUS is kinda bloated, but it shows the idea I think. And while this has loops in (the rehashing thing) their fwd progress does not depend on other

Is smbtorture a simple SMB client that is completely separate from Samba server? (I.e., can I use it to test, e.g., a regular Windows SMB server?) Or is it something that only tests Samba server? Anyway, I haven't had any luck compiling it. Any hints? Here is a transcript (this is on SUSE Linux Enterprise 9): cwu@cham6:~/tmp/apps/samba-3.0.14a/source> ./configure

...Is there a workaround or solution? Please help. There are some issues with HP-UX being discussed on samba-technical. Looks like it could be a broken mmap() implementation in HP-UX. See this post from Don McCall @ HP. > Hello Claus, > We are seeing this as well. running the smbtorture test LOCK1 > will show this (and other issues as well). I'm not done with > my investigation, but at the moment, it APPEARS to be an issue > with the mmap implementation on HP-UX, and the fact that HP-UX > uses different caches for memory mapped file access as opposed > to filesystem (read...