search for: swapout

...re in the core kernel to prevent concurrent pagein and truncate of the same file. This was to prevent a race wherein the paging-in task would wake up after the truncate and would instantiate a page in the process's page tables which had attached buffers. This leads to a BUG() if the swapout code tries to swap the page out. This semaphore has been removed. The swapout code has been altered to simply detect and ignore these pages. This is an incredibly obscure and hard-to-hit situation. The testcase which used to trigger it can no longer do so. So if anyone sees the messa...

...0 PM, Zi Yan wrote: > >>>>> On 22 Jun 2020, at 15:36, Ralph Campbell wrote: > >>>>>> On 6/21/20 4:20 PM, Zi Yan wrote: > >>>>>>> On 19 Jun 2020, at 17:56, Ralph Campbell wrote: > ... > >>> Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. > >>> I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference > >>> for swapping in device private pages, although s...

...dev/hda5 d: w95 fat 32 currently i can boot into the CentOS 4 install and it does not see the PATA drive by default unless i go into fdisk of course. it is not mounted. or i can switch them and boot into win98, whatever is best for this learning test. ive always tried to have 2 or more (hot/cold swapouts) of everything client and server hardwares so i never needed to dual boot. can someone show me what steps they would take using linux rescue to get this "test" situation to dual boot please? i did try with "linux rescue" and was rec'v grub not found errors when running gr...

...et a THP. IMHO, the former might be preferred, > > >> since the latter might cost a lot of CPU cycles but still gives no THP after all. > > > > > > Sounds reasonable. I'll work on adding the fallback path for v2. > > > > Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. > > I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference > > for swapping in device private pages, although swapping in pages...

...ages instead or reclaiming CPU memory until you get a THP. IMHO, the former might be preferred, >> since the latter might cost a lot of CPU cycles but still gives no THP after all. > > Sounds reasonable. I'll work on adding the fallback path for v2. Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference for swapping in device private pages, although swapping in pages from disk and from...

...t;>> On 6/22/20 1:10 PM, Zi Yan wrote: >>>>> On 22 Jun 2020, at 15:36, Ralph Campbell wrote: >>>>>> On 6/21/20 4:20 PM, Zi Yan wrote: >>>>>>> On 19 Jun 2020, at 17:56, Ralph Campbell wrote: ... >>> Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. >>> I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference >>> for swapping in device private pages, although swapping in...

...is problem, I'd like to get it into the archives. When copying large files (multigigabyte) on a CentOS 4.4 4GB Xeon (running 32 bit) server (2.6.9-42.0.3.ELsmp), I was getting: page allocation failure. order:0, mode:0x50 (snip lines and lines of debug output) This was accompanied by a huge swapout storm that brought the system to a near standstill. Also, it could trigger OOM-Killer activity. Setting /proc/sys/vm/lower_zone_protection to 150 seems to prevent the problem. (It's not been long enough that I'm *certain* that it's fixed but it seems to be.) The upstream bug report i...

A couple of days ago, I was given the task of replacing a mail server -- old hardware, network topology changes, and personnel changes led up to this. Now, the actual swapout of a mail server is relatively straightforward and (somewhat) easy to do. But this one had a wrench -- I had to authenticate off of an NT4 domain. There were some other, smaller, wrenches as well, but they have nothing to do with this story. Lost, I started out simple -- pam_smb_auth. I compile...

...date, Jeson can tell if I misread something there. For transient data passing through the ring, nobody should care if it's lost. It's not user-journaled anyway so it could hit the disk in any order. The only reason to flush it to do disk is if there's memory pressure (to pageout like a swapout) and in such case it's enough to mark it dirty only in the mmu notifier invalidate like you pointed out (and only if GUP was called with FOLL_WRITE). > O_DIRECT can suffer from the same issue but the race window for that > is small enough that it is unlikely it ever happened. But for dev...

...te: >>>>>>> On 22 Jun 2020, at 15:36, Ralph Campbell wrote: >>>>>>>> On 6/21/20 4:20 PM, Zi Yan wrote: >>>>>>>>> On 19 Jun 2020, at 17:56, Ralph Campbell wrote: >> ... >>>>> Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. >>>>> I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference >>>>> for swapping in device private pages, alth...

On Thu, Mar 07, 2019 at 02:38:38PM -0500, Andrea Arcangeli wrote: > On Thu, Mar 07, 2019 at 02:09:10PM -0500, Jerome Glisse wrote: > > I thought this patch was only for anonymous memory ie not file back ? > > Yes, the other common usages are on hugetlbfs/tmpfs that also don't > need to implement writeback and are obviously safe too. > > > If so then set dirty is

On Thu, Mar 07, 2019 at 02:38:38PM -0500, Andrea Arcangeli wrote: > On Thu, Mar 07, 2019 at 02:09:10PM -0500, Jerome Glisse wrote: > > I thought this patch was only for anonymous memory ie not file back ? > > Yes, the other common usages are on hugetlbfs/tmpfs that also don't > need to implement writeback and are obviously safe too. > > > If so then set dirty is

...ng CPU memory until you get a THP. IMHO, the former might be preferred, > >> since the latter might cost a lot of CPU cycles but still gives no THP after all. > > > > Sounds reasonable. I'll work on adding the fallback path for v2. > > Ying(cc?d) developed the code to swapout and swapin THP in one piece: https://lore.kernel.org/linux-mm/20181207054122.27822-1-ying.huang at intel.com/. > I am not sure whether the patchset makes into mainstream or not. It could be a good technical reference > for swapping in device private pages, although swapping in pages from disk...

...something there. Thanks > > For transient data passing through the ring, nobody should care if > it's lost. It's not user-journaled anyway so it could hit the disk in > any order. The only reason to flush it to do disk is if there's memory > pressure (to pageout like a swapout) and in such case it's enough to > mark it dirty only in the mmu notifier invalidate like you pointed out > (and only if GUP was called with FOLL_WRITE). > >> O_DIRECT can suffer from the same issue but the race window for that >> is small enough that it is unlikely it ever...

...something there. Thanks > > For transient data passing through the ring, nobody should care if > it's lost. It's not user-journaled anyway so it could hit the disk in > any order. The only reason to flush it to do disk is if there's memory > pressure (to pageout like a swapout) and in such case it's enough to > mark it dirty only in the mmu notifier invalidate like you pointed out > (and only if GUP was called with FOLL_WRITE). > >> O_DIRECT can suffer from the same issue but the race window for that >> is small enough that it is unlikely it ever...

...#39;s practically locked. The machine runs gnome-desktops for 40 users plus about a hundred sessions of a curses based point of sale software, plus a few other functions, so it's a busy machine. Dual Xeon 3.2GHz processors. 4096MB ram. 8192MB swap. During this period, I'm seeing lots of swapout. sar reports 266 pages per second averaged over that 10 minute period. I'm thinking that I have a runaway process, but have not been able to see one of these instances for myself at the time it is happening. I've set up a monitor to record the highest rss size process minute by minute, w...

Hello All, I could use a recommendation if anyone has a moment. I have the T100P but I have not gotten my service yet. I want to have at least 12 lines of digital voice with DID. Should I just seek out a PRI ISDN provider or is there something else I should look for? I want to keep cost as low as possible. Also, I want to own my own router for the phones since it is always a hassle to get

The patch deals with the situation which guest OS uses unused page table pages as data pages and write data to them. The pages will still be grabbed by Xen as page table pages, and lots of unnecessary page faults occur. The patch will check if the data guest writes to the page table contains valid mfn or not, if not, we believe it is a data page now and then unshadow the page. The patch

On 22 Jun 2020, at 15:36, Ralph Campbell wrote: > On 6/21/20 4:20 PM, Zi Yan wrote: >> On 19 Jun 2020, at 17:56, Ralph Campbell wrote: >> >>> Support transparent huge page migration to ZONE_DEVICE private memory. >>> A new flag (MIGRATE_PFN_COMPOUND) is added to the input PFN array to >>> indicate the huge page was fully mapped by the CPU. >>>

Now at 36 hours since zdb process start and: PID USERNAME SIZE RSS STATE PRI NICE TIME CPU PROCESS/NLWP 827 root 4936M 4931M sleep 59 0 0:50:47 0.2% zdb/209 Idling at 0.2% processor for nearly the past 24 hours... feels very stuck. Thoughts on how to determine where and why? -- This message posted from opensolaris.org