Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1610843 > unrolled thread
| Started by | Zhou Chengming <zhouchengming1@huawei.com> |
|---|---|
| First post | 2017-03-28 15:20 +0200 |
| Last post | 2017-03-30 10:50 +0200 |
| Articles | 5 — 5 participants |
Back to article view | Back to linux.kernel
[PATCH v2] livepatch: Reduce the time of finding module symbols Zhou Chengming <zhouchengming1@huawei.com> - 2017-03-28 15:20 +0200
Re: [PATCH v2] livepatch: Reduce the time of finding module symbols Josh Poimboeuf <jpoimboe@redhat.com> - 2017-03-29 17:10 +0200
Re: [PATCH v2] livepatch: Reduce the time of finding module symbols Jessica Yu <jeyu@redhat.com> - 2017-03-29 21:50 +0200
Re: [PATCH v2] livepatch: Reduce the time of finding module symbols Miroslav Benes <mbenes@suse.cz> - 2017-03-30 10:10 +0200
Re: [PATCH v2] livepatch: Reduce the time of finding module symbols Jiri Kosina <jikos@kernel.org> - 2017-03-30 10:50 +0200
| From | Zhou Chengming <zhouchengming1@huawei.com> |
|---|---|
| Date | 2017-03-28 15:20 +0200 |
| Subject | [PATCH v2] livepatch: Reduce the time of finding module symbols |
| Message-ID | <tpZcu-88d-33@gated-at.bofh.it> |
It's reported that the time of insmoding a klp.ko for one of our out-tree modules is too long. ~ time sudo insmod klp.ko real 0m23.799s user 0m0.036s sys 0m21.256s Then we found the reason: our out-tree module used a lot of static local variables, so klp.ko has a lot of relocation records which reference the module. Then for each such entry klp_find_object_symbol() is called to resolve it, but this function uses the interface kallsyms_on_each_symbol() even for finding module symbols, so will waste a lot of time on walking through vmlinux kallsyms table many times. This patch changes it to use module_kallsyms_on_each_symbol() for modules symbols. After we apply this patch, the sys time reduced dramatically. ~ time sudo insmod klp.ko real 0m1.007s user 0m0.032s sys 0m0.924s Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com> --- kernel/livepatch/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index af46438..b4b8bb0 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -182,7 +182,10 @@ static int klp_find_object_symbol(const char *objname, const char *name, }; mutex_lock(&module_mutex); - kallsyms_on_each_symbol(klp_find_callback, &args); + if (objname) + module_kallsyms_on_each_symbol(klp_find_callback, &args); + else + kallsyms_on_each_symbol(klp_find_callback, &args); mutex_unlock(&module_mutex); /* -- 1.8.3.1
[toc] | [next] | [standalone]
| From | Josh Poimboeuf <jpoimboe@redhat.com> |
|---|---|
| Date | 2017-03-29 17:10 +0200 |
| Message-ID | <tqnou-9P-27@gated-at.bofh.it> |
| In reply to | #1610843 |
On Tue, Mar 28, 2017 at 09:10:35PM +0800, Zhou Chengming wrote: > It's reported that the time of insmoding a klp.ko for one of our > out-tree modules is too long. > > ~ time sudo insmod klp.ko > real 0m23.799s > user 0m0.036s > sys 0m21.256s > > Then we found the reason: our out-tree module used a lot of static local > variables, so klp.ko has a lot of relocation records which reference the > module. Then for each such entry klp_find_object_symbol() is called to > resolve it, but this function uses the interface kallsyms_on_each_symbol() > even for finding module symbols, so will waste a lot of time on walking > through vmlinux kallsyms table many times. > > This patch changes it to use module_kallsyms_on_each_symbol() for modules > symbols. After we apply this patch, the sys time reduced dramatically. > > ~ time sudo insmod klp.ko > real 0m1.007s > user 0m0.032s > sys 0m0.924s > > Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com> It would be good to make kallsyms faster, but either way this still a performance improvement for patching modules. Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> -- Josh
[toc] | [prev] | [next] | [standalone]
| From | Jessica Yu <jeyu@redhat.com> |
|---|---|
| Date | 2017-03-29 21:50 +0200 |
| Message-ID | <tqrLs-34R-19@gated-at.bofh.it> |
| In reply to | #1610843 |
+++ Zhou Chengming [28/03/17 21:10 +0800]: >It's reported that the time of insmoding a klp.ko for one of our >out-tree modules is too long. > >~ time sudo insmod klp.ko >real 0m23.799s >user 0m0.036s >sys 0m21.256s > >Then we found the reason: our out-tree module used a lot of static local >variables, so klp.ko has a lot of relocation records which reference the >module. Then for each such entry klp_find_object_symbol() is called to >resolve it, but this function uses the interface kallsyms_on_each_symbol() >even for finding module symbols, so will waste a lot of time on walking >through vmlinux kallsyms table many times. > >This patch changes it to use module_kallsyms_on_each_symbol() for modules >symbols. After we apply this patch, the sys time reduced dramatically. > >~ time sudo insmod klp.ko >real 0m1.007s >user 0m0.032s >sys 0m0.924s > >Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com> Limiting the search space for symbol lookups is a valid improvement, so: Acked-by: Jessica Yu <jeyu@redhat.com> >--- > kernel/livepatch/core.c | 5 ++++- > 1 file changed, 4 insertions(+), 1 deletion(-) > >diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c >index af46438..b4b8bb0 100644 >--- a/kernel/livepatch/core.c >+++ b/kernel/livepatch/core.c >@@ -182,7 +182,10 @@ static int klp_find_object_symbol(const char *objname, const char *name, > }; > > mutex_lock(&module_mutex); >- kallsyms_on_each_symbol(klp_find_callback, &args); >+ if (objname) >+ module_kallsyms_on_each_symbol(klp_find_callback, &args); >+ else >+ kallsyms_on_each_symbol(klp_find_callback, &args); > mutex_unlock(&module_mutex); > > /* >-- >1.8.3.1 > >-- >To unsubscribe from this list: send the line "unsubscribe live-patching" in >the body of a message to majordomo@vger.kernel.org >More majordomo info at http://vger.kernel.org/majordomo-info.html
[toc] | [prev] | [next] | [standalone]
| From | Miroslav Benes <mbenes@suse.cz> |
|---|---|
| Date | 2017-03-30 10:10 +0200 |
| Subject | Re: [PATCH v2] livepatch: Reduce the time of finding module symbols |
| Message-ID | <tqDjA-3gZ-17@gated-at.bofh.it> |
| In reply to | #1610843 |
On Tue, 28 Mar 2017, Zhou Chengming wrote: > It's reported that the time of insmoding a klp.ko for one of our > out-tree modules is too long. > > ~ time sudo insmod klp.ko > real 0m23.799s > user 0m0.036s > sys 0m21.256s > > Then we found the reason: our out-tree module used a lot of static local > variables, so klp.ko has a lot of relocation records which reference the > module. Then for each such entry klp_find_object_symbol() is called to > resolve it, but this function uses the interface kallsyms_on_each_symbol() > even for finding module symbols, so will waste a lot of time on walking > through vmlinux kallsyms table many times. > > This patch changes it to use module_kallsyms_on_each_symbol() for modules > symbols. After we apply this patch, the sys time reduced dramatically. > > ~ time sudo insmod klp.ko > real 0m1.007s > user 0m0.032s > sys 0m0.924s > > Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com> We are the only user of kallsyms_on_each_symbol() interface right now, so it is not that bad to optimize here. Temporarily :) Acked-by: Miroslav Benes <mbenes@suse.cz> Miroslav
[toc] | [prev] | [next] | [standalone]
| From | Jiri Kosina <jikos@kernel.org> |
|---|---|
| Date | 2017-03-30 10:50 +0200 |
| Subject | Re: [PATCH v2] livepatch: Reduce the time of finding module symbols |
| Message-ID | <tqDWj-3FT-39@gated-at.bofh.it> |
| In reply to | #1610843 |
On Tue, 28 Mar 2017, Zhou Chengming wrote: > It's reported that the time of insmoding a klp.ko for one of our > out-tree modules is too long. Applied to for-4.12/upstream. Thanks, -- Jiri Kosina SUSE Labs
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web