Top all-time · #13267
Sébastien Han
Personal blog · sebastien-han.fr/blogsystemsprogramming
Sébastien Han's personal blog at sebastien-han.fr covers systems and programming. Since 2013, 6 different Hacker News readers have linked it 8 times. The last post was in 2021, but the archive is still widely read.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN readers link Sébastien Han's blog for its Ceph and storage benchmarking posts, especially a 2014 post on testing SSD performance. Commenters cite it when discussing consumer SSD write speed and sync-write tests.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Senior Principal Software Engineer
What Hacker News says?
Basically on a PCIe 3.0 x4 maximum performance is 4000GB/s, in practice this is 3200-3500MB/s. With 4k random write, you will get maximum 800.000 to 875.000 iops per second. Consumer-grade SSD's barely manage to write 500-1000 iops when sending the ATA_CMD_FLUSH command unless they are lying which is really bad. Good read about consumer SSD performance: http://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test...
Comment linking /blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
on “Intel's roadmap for Optane SSDs with 1,000x performance”Submitted Bluestore, a new underlying filesystem for Ceph as a story · 2 points
HN discussionYou're reading the wrong numbers. Try benchmarking with PostgreSQL's pg_test_fsync or with fio with the following options: --direct=1 --sync=1 --rw=write --bs=4k Good random-write performance with 4k/8k blocks at QD1 is what matter for SSD's, not if they can write 2500MB/s to a volatile cache. Recommended read http://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test...
Comment linking /blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
on “Optane Memory – A bridge between DRAM and storage”Submitted Next Generation Servers With Containers as a story · 2 points
HN discussionThe latest OCZ Trion series at least honor O_DSYNC correctly. You get shitty write performance, but it is the same for Samsung 950 Pro. The read performance is another story for OCZ though :( Anyway enterprise SSD's have so much overall better performance that consumer grade SSD's is something I consider a joke. A joke even for consumer applications, web-surfing and email-clients. Remember that a lot of applications…
Comment linking /blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
on “How to move from Amazon RDS to a dedicated PostgreSQL server”See this blog post for some data at the end: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-tes... The post is from 2014, but the performance data was updated for many years after that. As you can see, there is not really 1 brand to single out. That Micron P400e was a pain to swap out in production, and if you use consumer drives there is even worse out there. Note: this post is on something very specific…
Comment linking /blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
on “LVM Cache Surprises”I'm interested in Ceph-in-production stories as well. I subscribe to this feed http://www.sebastien-han.fr/blog/ which follows Ceph development and have been toying with the idea of testing it when time permits. Currently we use local storage for VM hosts provided by LVM but something distributed and designed with HA in mind would be helpful.
Comment linking /blog/
on “DreamObjects is down”This is definitely possible, it is called block migration. Here is an example of someone showing usage (note the bug he mentioned has been fixed): http://www.sebastien-han.fr/blog/2012/07/12/openstack-block-... Note that there are some reliability issues using versions prior to qemu-1.4 and libvirt 1.0.2 To enable "true" block migration where the server remains live the whole time instead of being paused, you need t…
Comment linking /blog/2012/07/12/openstack-block-migration/
on “Why GlusterFS should not be integrated with OpenStack”
