On Tue, 16 Oct 2007 09:15:49 +0900 (JST)
[EMAIL PROTECTED] (YAMAMOTO Takashi) wrote:
> > Index: devel-2.6.23-rc8-mm2/mm/memcontrol.c
> > ===
> > --- devel-2.6.23-rc8-mm2.orig/mm/memcontrol.c
> > +++ devel-2.6.23-rc8-mm2/mm/memcontrol.
On Mon, 15 Oct 2007, Paul Jackson wrote:
> My solution may be worse than that. Because set_cpus_allowed() will
> fail if asked to set a non-overlapping cpumask, my solution could never
> terminate. If asked to set a cpusets cpus to something that went off
> line right then, this I'd guess this c
> > + if (cpus_equal(*cpus, t->cpus_allowed))
> > + continue;
> > ...
> > + for (q = tasks; q < p; q++) {
> > + set_cpus_allowed(*q, *cpus);
> > + put_task_struct(*q);
> > + }
> > + }
> > +}
>
> Y
> Will do - I justed wanted to get this quickly out to show the idea
> that I was working on.
Ok - good.
In the final analysis, I'll take whatever works ;).
I'll lobby for keeping the code "simple" (a subjective metric) and poke
what holes I can in things, and propose what alternatives I can mus
On 10/15/07, Paul Jackson <[EMAIL PROTECTED]> wrote:
> > currently against an older kernel
>
> ah .. which older kernel?
2.6.18, but I can do a version against 2.6.23-mm1.
> + if (!retval) {
> + cpus_allowed = cpuset_cpus_allowed(p);
> + if (!cpus_subset(new_mask
On Tue, 16 Oct 2007 09:25:43 +0530
Balbir Singh <[EMAIL PROTECTED]> wrote:
> How about we call it __mem_cgroup_add_stat() and add a comment stating
> that the routine should be called with pre-emption disabled?
>
> We can also add the VM_BUG_ON() suggested.
>
Ah, nice suggestion.
I'll think agai
KAMEZAWA Hiroyuki wrote:
> On Tue, 16 Oct 2007 07:38:23 +0900 (JST)
> [EMAIL PROTECTED] (YAMAMOTO Takashi) wrote:
>
> +/*
> + * For batchingmem_cgroup_charge_statistics()(see below).
> + */
> +static inline void mem_cgroup_stat_add(struct mem_cgroup_stat *stat,
> +
Quoting [EMAIL PROTECTED] ([EMAIL PROTECTED]):
>
>
> When a process in a container signals its container-init, we want
> to ensure that the signal does not terminate the container-init.
> i.e if the container-init has no handler for the signal, and the
> signal is fatal, we want to ignore the sig
Hi,
I have joint devel list recently. I want to contribute to OpenVZ. I have
read few papers on openVZ and one of the papers "Performance Evaluation of
Virtualization Technologies for Server Consolidation" ( HP Labs) - says
that , "For OpenVZ, there is no existing tool to directly measure the
On Tue, 16 Oct 2007 07:38:23 +0900 (JST)
[EMAIL PROTECTED] (YAMAMOTO Takashi) wrote:
> > > > +/*
> > > > + * For batchingmem_cgroup_charge_statistics()(see below).
> > > > + */
> > > > +static inline void mem_cgroup_stat_add(struct mem_cgroup_stat *stat,
> > > > +enum mem_cgrou
> currently against an older kernel
ah .. which older kernel?
I tried it against the broken out 2.6.23-rc8-mm2 patch set,
inserting it before the task-containersv11-* patches, but
that blew up on me - three rejected hunks.
Any chance of getting this against a current cgroup (aka
container) kern
> Yet by not doing any locking here to prevent a cpu from being
> hot-unplugged, you can race and allow the hot-unplug event to happen
> before calling set_cpus_allowed(). That makes this entire function a
> no-op with set_cpus_allowed() returning -EINVAL for every call, which
> isn't caught,
Paul Jackson wrote:
Paul M wrote:
Here's an alternative for consideration, below.
I don't see the alternative -- I just see my patch, with the added
blurbage:
#12 - /usr/local/google/home/menage/kernel9/linux/kernel/cpuset.c
# action=edit type=text
Should I be increasing my caffeine
Paul M wrote:
> Here's an alternative for consideration, below.
I don't see the alternative -- I just see my patch, with the added
blurbage:
#12 - /usr/local/google/home/menage/kernel9/linux/kernel/cpuset.c
# action=edit type=text
Should I be increasing my caffeine intake?
--
> Index: devel-2.6.23-rc8-mm2/mm/memcontrol.c
> ===
> --- devel-2.6.23-rc8-mm2.orig/mm/memcontrol.c
> +++ devel-2.6.23-rc8-mm2/mm/memcontrol.c
> @@ -469,6 +469,7 @@ void mem_cgroup_uncharge(struct page_cgr
> page = pc->pa
> > > +/*
> > > + * For batchingmem_cgroup_charge_statistics()(see below).
> > > + */
> > > +static inline void mem_cgroup_stat_add(struct mem_cgroup_stat *stat,
> > > +enum mem_cgroup_stat_index idx, int val)
> > > +{
> > > + int cpu = smp_processor_id();
> > > + stat->cpustat[
Paul Jackson wrote:
Paul M, David R, others -- how does this look?
Looks plausible, although as David comments I don't think it handles a
concurrent CPU hotplug/unplug. Also I don't like the idea of doing a
cgroup_lock() across sched_setaffinity() - cgroup_lock() can be held for
relatively
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Mon, 15 Oct 2007 15:55:21 +0400
> The difference in both functions is in the "id" passed to
> the rt6_select, so just pass it as an extra argument from
> two outer helpers.
>
> This is minus 60 lines of code and 360 bytes of .text
>
> Signed-off-by
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Mon, 15 Oct 2007 14:23:13 +0400
> When the loopback device is failed to initialize inside the new
> namespaces, panic() is called. Do not do it when the namespace
> in question is not the init_net.
>
> Plus cleanup the error path a bit.
>
> Signe
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Mon, 15 Oct 2007 17:38:57 +0400
> The pnigh_lookup is used to lookup proxy entries and to
> create them in case lookup failed.
>
> However, the "creation" code does not perform the re-lookup
> after GFP_KERNEL allocation. This is done because the
On Mon, 15 Oct 2007, Paul Jackson wrote:
> --- 2.6.23-mm1.orig/kernel/cpuset.c 2007-10-14 22:24:56.268309633 -0700
> +++ 2.6.23-mm1/kernel/cpuset.c2007-10-14 22:34:52.645364388 -0700
> @@ -677,6 +677,64 @@ done:
> }
>
> /*
> + * update_cgroup_cpus_allowed(cont, cpus)
> + *
> + * Keep
Daniel Lezcano <[EMAIL PROTECTED]> writes:
> Denis V. Lunev wrote:
>> Daniel Lezcano wrote:
>>> Eric W. Biederman wrote:
Daniel Lezcano <[EMAIL PROTECTED]> writes:
> The following patches activate the multicast sockets for
> the namespaces. The results is a traffic going through
Hugh Dickins wrote:
>
> --- 2.6.23-rc8-mm2/mm/swapfile.c 2007-09-27 12:03:36.0 +0100
> +++ linux/mm/swapfile.c 2007-10-07 14:33:05.0 +0100
> @@ -507,11 +507,23 @@ unsigned int count_swap_pages(int type,
> * just let do_wp_page work it out if a write is requested late
Denis V. Lunev wrote:
Daniel Lezcano wrote:
Eric W. Biederman wrote:
Daniel Lezcano <[EMAIL PROTECTED]> writes:
The following patches activate the multicast sockets for
the namespaces. The results is a traffic going through differents
namespaces. So if there are several applications
listenn
The pnigh_lookup is used to lookup proxy entries and to
create them in case lookup failed.
However, the "creation" code does not perform the re-lookup
after GFP_KERNEL allocation. This is done because the code
is expected to be protected with the RTNL lock, so add the
assertion (mainly to addre
The difference in both functions is in the "id" passed to
the rt6_select, so just pass it as an extra argument from
two outer helpers.
This is minus 60 lines of code and 360 bytes of .text
Signed-off-by: Pavel Emelyanov <[EMAIL PROTECTED]>
---
net/ipv6/route.c | 77 ++
When the loopback device is failed to initialize inside the new
namespaces, panic() is called. Do not do it when the namespace
in question is not the init_net.
Plus cleanup the error path a bit.
Signed-off-by: Pavel Emelyanov <[EMAIL PROTECTED]>
---
drivers/net/loopback.c | 11 +--
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 16:55:10 +0400
> Patrick recently pointed out, that there are three places that
> perform IP fragments management. In ipv4, ipv6 and in ip6
> conntracks. Looks like these places can be a bit consolidated.
>
> The proposal is to cr
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:29:01 +0400
> These ones use the generic data types too, so move
> them in one place.
>
> Signed-off-by: Pavel Emelyanov <[EMAIL PROTECTED]>
Also applied, thanks!
___
Devel mailing li
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:27:40 +0400
> After the evictor code is consolidated there is no need in
> passing the extra pointer to the xxx_put() functions.
>
> The only place when it made sense was the evictor code itself.
>
> Maybe this change must got
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:24:27 +0400
> The evictors collect some statistics for ipv4 and ipv6,
> so make it return the number of evicted queues and account
> them all at once in the caller.
>
> The XXX_ADD_STATS_BH() macros are just for this case,
> bu
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:21:06 +0400
> To make in possible we need to know the exact frag queue
> size for inet_frags->mem management and two callbacks:
>
> * to destoy the skb (optional, used in conntracks only)
> * to free the queue itself (mandatory
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:16:25 +0400
> This code works with the generic data types as well, so
> move this into inet_fragment.c
>
> This move makes it possible to hide the secret_timer
> management and the secret_rebuild routine completely in
> the inet_
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:12:43 +0400
> Since now all the xxx_frag_kill functions now work
> with the generic inet_frag_queue data type, this can
> be moved into a common place.
>
> The xxx_unlink() code is moved as well.
>
> Signed-off-by: Pavel Emelyan
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:10:05 +0400
> Some sysctl variables are used to tune the frag queues
> management and it will be useful to work with them in
> a common way in the future, so move them into one
> structure, moreover they are the same for all the f
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:06:13 +0400
> There are some objects that are common in all the places
> which are used to keep track of frag queues, they are:
>
> * hash table
> * LRU list
> * rw lock
> * rnd number for hash function
> * the number of que
From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 12 Oct 2007 17:00:06 +0400
> Introduce the struct inet_frag_queue in include/net/inet_frag.h
> file and place there all the common fields from three structs:
>
> * struct ipq in ipv4/ip_fragment.c
> * struct nf_ct_frag6_queue in nf_conntrack_
Daniel Lezcano wrote:
Eric W. Biederman wrote:
Daniel Lezcano <[EMAIL PROTECTED]> writes:
The following patches activate the multicast sockets for
the namespaces. The results is a traffic going through differents
namespaces. So if there are several applications
listenning to the same multica
Paul M, David R, others -- how does this look?
From: Paul Jackson <[EMAIL PROTECTED]>
Update the per-task cpus_allowed of each task in a cgroup
whenever it has a cpuset whose 'cpus' mask changes.
The change to basing cpusets on the cgroup (aka container)
infrastructure broke an essential cpuset
39 matches
Mail list logo
