Repository: incubator-crail-website Updated Branches: refs/heads/master af165cf7a -> 51c17fe1c
fix a doc typo: s/upcomding/upcoming Project: http://git-wip-us.apache.org/repos/asf/incubator-crail-website/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-crail-website/commit/51c17fe1 Tree: http://git-wip-us.apache.org/repos/asf/incubator-crail-website/tree/51c17fe1 Diff: http://git-wip-us.apache.org/repos/asf/incubator-crail-website/diff/51c17fe1 Branch: refs/heads/master Commit: 51c17fe1c3f0b1a99c16173349df9a57bc44cd8a Parents: af165cf Author: Yonglong Dai <y...@salesforce.com> Authored: Thu Mar 8 22:00:35 2018 -0800 Committer: Yonglong Dai <y...@salesforce.com> Committed: Thu Mar 8 22:00:35 2018 -0800 ---------------------------------------------------------------------- site/overview/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-crail-website/blob/51c17fe1/site/overview/index.md ---------------------------------------------------------------------- diff --git a/site/overview/index.md b/site/overview/index.md index 5db1e84..00ebdc8 100644 --- a/site/overview/index.md +++ b/site/overview/index.md @@ -62,7 +62,7 @@ backed with separate files inside the directory. Keyvalue nodes are similar to d <div style="text-align: justify"> <p> -Access to storage resources over the network -- as happening during file read/write operations -- are implemented using a variety of network and stoage APIs and protocols. Which API and protocol is uses to read/write a particular block depends to the type of storage that is accessed. For instance, accesses to blocks residing in the DRAM tier are implemented using one-sided read/write RDMA operations. Similarly, access to blocks residing in the NVMe tier of Crail are implemented using NVMe of fabrics (NVMf). In most of the cases, the network and storage devices are access directly from user-space via RDMA or other user-level APIs such as DPDK or SPDK. Crail is built in a way that new storage tiers can be added easily: storage tiers are actual plugins. With this, Crail can support new protocols and APIs and leverage upcomding storage and network technologies efficiently. +Access to storage resources over the network -- as happening during file read/write operations -- are implemented using a variety of network and stoage APIs and protocols. Which API and protocol is uses to read/write a particular block depends to the type of storage that is accessed. For instance, accesses to blocks residing in the DRAM tier are implemented using one-sided read/write RDMA operations. Similarly, access to blocks residing in the NVMe tier of Crail are implemented using NVMe of fabrics (NVMf). In most of the cases, the network and storage devices are access directly from user-space via RDMA or other user-level APIs such as DPDK or SPDK. Crail is built in a way that new storage tiers can be added easily: storage tiers are actual plugins. With this, Crail can support new protocols and APIs and leverage upcoming storage and network technologies efficiently. </p> </div> <br>
